2025-03-21T20:17:50.2490711Z Current runner version: '2.323.0'
2025-03-21T20:17:50.2497968Z Runner name: 'i-0c70e9b839f29d8f9'
2025-03-21T20:17:50.2499051Z Runner group name: 'Default'
2025-03-21T20:17:50.2499938Z Machine name: 'ip-10-0-52-230'
2025-03-21T20:17:50.2503046Z ##[group]GITHUB_TOKEN Permissions
2025-03-21T20:17:50.2505576Z Contents: read
2025-03-21T20:17:50.2506253Z Metadata: read
2025-03-21T20:17:50.2506879Z ##[endgroup]
2025-03-21T20:17:50.2509956Z Secret source: Actions
2025-03-21T20:17:50.2510818Z Prepare workflow directory
2025-03-21T20:17:50.3041626Z Prepare all required actions
2025-03-21T20:17:50.3086011Z Getting action download info
2025-03-21T20:17:50.5160556Z Download action repository 'actions/checkout@v4' (SHA:11bd71901bbe5b1630ceea73d27597364c9af683)
2025-03-21T20:17:50.7661074Z Download action repository 'pytorch/pytorch@main' (SHA:c5deacc27a4a29fa141e179535d56d21a0eb734f)
2025-03-21T20:18:03.1924290Z Download action repository 'actions/download-artifact@v4' (SHA:95815c38cf2ff2164869cbab79da8d1f422bc89e)
2025-03-21T20:18:03.5123176Z Download action repository 'pmeier/pytest-results-action@v0.3.0' (SHA:a2c1430e2bddadbad9f49a6f9b879f062c6b19b1)
2025-03-21T20:18:03.6072256Z Download action repository 'actions/upload-artifact@v4' (SHA:ea165f8d65b6e75b540449e92b4886f43607fa02)
2025-03-21T20:18:03.9789799Z Download action repository 'seemethere/upload-artifact-s3@v5' (SHA:baba72d0712b404f646cebe0730933554ebce96a)
2025-03-21T20:18:04.2436063Z Getting action download info
2025-03-21T20:18:04.4249583Z Uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@refs/heads/main (c1d92bc76c9d8ecf59b36ef10588c9605c8578d1)
2025-03-21T20:18:04.4251730Z ##[group] Inputs
2025-03-21T20:18:04.4254975Z   script: # The generic Linux job chooses to use base env, not the one setup by the image
CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
conda activate "${CONDA_ENV}"

DTYPE=fp32
BUILD_TOOL="cmake"
MODE=qnn
PT2E_QUANTIZE=qnn_16a16w

./install_requirements.sh --use-pt-pinned-commit
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh

# Setup executorch
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "${BUILD_TOOL}"
# Install requirements for export_llama
PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
# Test llama2
PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh -model stories110M -build_tool "${BUILD_TOOL}" -mode "${MODE}" -dtype "${DTYPE}" -pt2e_quantize "${PT2E_QUANTIZE}"

2025-03-21T20:18:04.4258713Z   timeout: 900
2025-03-21T20:18:04.4258989Z   runner: linux.2xlarge
2025-03-21T20:18:04.4259279Z   upload-artifact: 
2025-03-21T20:18:04.4259888Z   upload-artifact-to-s3: false
2025-03-21T20:18:04.4260204Z   download-artifact: 
2025-03-21T20:18:04.4260478Z   repository: 
2025-03-21T20:18:04.4260755Z   fetch-depth: 1
2025-03-21T20:18:04.4261017Z   submodules: true
2025-03-21T20:18:04.4261329Z   ref: be92d7d85cb7081ac0a544036da4096a4efa33a8
2025-03-21T20:18:04.4261734Z   test-infra-repository: pytorch/test-infra
2025-03-21T20:18:04.4262099Z   test-infra-ref: 
2025-03-21T20:18:04.4262407Z   docker-image: executorch-ubuntu-22.04-qnn-sdk
2025-03-21T20:18:04.4262795Z   docker-build-dir: .ci/docker
2025-03-21T20:18:04.4263099Z   gpu-arch-type: cpu
2025-03-21T20:18:04.4263362Z   gpu-arch-version: 
2025-03-21T20:18:04.4263643Z   job-name: linux-job
2025-03-21T20:18:04.4263924Z   continue-on-error: false
2025-03-21T20:18:04.4264218Z   binary-matrix: 
2025-03-21T20:18:04.4264482Z   run-with-docker: true
2025-03-21T20:18:04.4264739Z   secrets-env: 
2025-03-21T20:18:04.4264989Z   no-sudo: false
2025-03-21T20:18:04.4265275Z ##[endgroup]
2025-03-21T20:18:04.4265731Z Complete job name: test-llama-runner-qnn-linux (fp32, qnn_16a16w, qnn) / linux-job
2025-03-21T20:18:04.4704504Z A job started hook has been configured by the self-hosted runner administrator
2025-03-21T20:18:04.4812961Z ##[group]Run '/home/ec2-user/runner-scripts/before_job.sh'
2025-03-21T20:18:04.4822156Z shell: /usr/bin/bash --noprofile --norc -e -o pipefail {0}
2025-03-21T20:18:04.4823128Z ##[endgroup]
2025-03-21T20:18:05.6320624Z Runner Type: linux.2xlarge
2025-03-21T20:18:05.6321332Z Instance Type: c5.2xlarge
2025-03-21T20:18:05.6321784Z AMI Name: unknown
2025-03-21T20:18:05.6348857Z AMI ID: ami-08b5b3a93ed654d19
2025-03-21T20:18:10.8480847Z ##[group]Run set -euxo pipefail
2025-03-21T20:18:10.8481281Z set -euxo pipefail
2025-03-21T20:18:10.8481612Z if [[ "${NO_SUDO}" == "false" ]]; then
2025-03-21T20:18:10.8482023Z   echo "::group::Cleanup with-sudo debug output"
2025-03-21T20:18:10.8482430Z   sudo rm -rfv "${GITHUB_WORKSPACE}"
2025-03-21T20:18:10.8482765Z else
2025-03-21T20:18:10.8483055Z   echo "::group::Cleanup no-sudo debug output"
2025-03-21T20:18:10.8483427Z   rm -rfv "${GITHUB_WORKSPACE}"
2025-03-21T20:18:10.8483745Z fi
2025-03-21T20:18:10.8483971Z 
2025-03-21T20:18:10.8484242Z mkdir -p "${GITHUB_WORKSPACE}"
2025-03-21T20:18:10.8484579Z echo "::endgroup::"
2025-03-21T20:18:10.8493521Z shell: /usr/bin/bash -e {0}
2025-03-21T20:18:10.8493828Z env:
2025-03-21T20:18:10.8494109Z   DOCKER_IMAGE: executorch-ubuntu-22.04-qnn-sdk
2025-03-21T20:18:10.8494487Z   REPOSITORY: pytorch/executorch
2025-03-21T20:18:10.8494838Z   PR_NUMBER: 
2025-03-21T20:18:10.8497960Z   SCRIPT: # The generic Linux job chooses to use base env, not the one setup by the image
CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
conda activate "${CONDA_ENV}"

DTYPE=fp32
BUILD_TOOL="cmake"
MODE=qnn
PT2E_QUANTIZE=qnn_16a16w

./install_requirements.sh --use-pt-pinned-commit
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh

# Setup executorch
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "${BUILD_TOOL}"
# Install requirements for export_llama
PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
# Test llama2
PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh -model stories110M -build_tool "${BUILD_TOOL}" -mode "${MODE}" -dtype "${DTYPE}" -pt2e_quantize "${PT2E_QUANTIZE}"

2025-03-21T20:18:10.8501140Z   NO_SUDO: false
2025-03-21T20:18:10.8501383Z ##[endgroup]
2025-03-21T20:18:10.8528115Z + [[ false == \f\a\l\s\e ]]
2025-03-21T20:18:10.8541970Z ##[group]Cleanup with-sudo debug output
2025-03-21T20:18:10.8545096Z + echo '::group::Cleanup with-sudo debug output'
2025-03-21T20:18:10.8545610Z + sudo rm -rfv /home/ec2-user/actions-runner/_work/executorch/executorch
2025-03-21T20:18:10.9478985Z removed directory '/home/ec2-user/actions-runner/_work/executorch/executorch'
2025-03-21T20:18:10.9493137Z + mkdir -p /home/ec2-user/actions-runner/_work/executorch/executorch
2025-03-21T20:18:10.9503588Z + echo ::endgroup::
2025-03-21T20:18:10.9504480Z ##[endgroup]
2025-03-21T20:18:10.9614935Z ##[group]Run actions/checkout@v4
2025-03-21T20:18:10.9615292Z with:
2025-03-21T20:18:10.9615544Z   repository: pytorch/test-infra
2025-03-21T20:18:10.9615861Z   path: test-infra
2025-03-21T20:18:10.9616137Z   submodules: recursive
2025-03-21T20:18:10.9616707Z   token: ***
2025-03-21T20:18:10.9616973Z   ssh-strict: true
2025-03-21T20:18:10.9617224Z   ssh-user: git
2025-03-21T20:18:10.9617470Z   persist-credentials: true
2025-03-21T20:18:10.9617755Z   clean: true
2025-03-21T20:18:10.9618016Z   sparse-checkout-cone-mode: true
2025-03-21T20:18:10.9618332Z   fetch-depth: 1
2025-03-21T20:18:10.9618578Z   fetch-tags: false
2025-03-21T20:18:10.9618821Z   show-progress: true
2025-03-21T20:18:10.9619078Z   lfs: false
2025-03-21T20:18:10.9619323Z   set-safe-directory: true
2025-03-21T20:18:10.9619601Z env:
2025-03-21T20:18:10.9619862Z   DOCKER_IMAGE: executorch-ubuntu-22.04-qnn-sdk
2025-03-21T20:18:10.9620248Z   REPOSITORY: pytorch/executorch
2025-03-21T20:18:10.9620557Z   PR_NUMBER: 
2025-03-21T20:18:10.9623734Z   SCRIPT: # The generic Linux job chooses to use base env, not the one setup by the image
CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
conda activate "${CONDA_ENV}"

DTYPE=fp32
BUILD_TOOL="cmake"
MODE=qnn
PT2E_QUANTIZE=qnn_16a16w

./install_requirements.sh --use-pt-pinned-commit
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh

# Setup executorch
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "${BUILD_TOOL}"
# Install requirements for export_llama
PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
# Test llama2
PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh -model stories110M -build_tool "${BUILD_TOOL}" -mode "${MODE}" -dtype "${DTYPE}" -pt2e_quantize "${PT2E_QUANTIZE}"

2025-03-21T20:18:10.9627072Z ##[endgroup]
2025-03-21T20:18:11.0762356Z Syncing repository: pytorch/test-infra
2025-03-21T20:18:11.0763718Z ##[group]Getting Git version info
2025-03-21T20:18:11.0764845Z Working directory is '/home/ec2-user/actions-runner/_work/executorch/executorch/test-infra'
2025-03-21T20:18:11.0766514Z [command]/usr/bin/git version
2025-03-21T20:18:11.0767165Z git version 2.47.1
2025-03-21T20:18:11.0782746Z ##[endgroup]
2025-03-21T20:18:11.0796551Z Temporarily overriding HOME='/home/ec2-user/actions-runner/_work/_temp/d6b105d6-b27a-4760-bae5-755308475fa4' before making global git config changes
2025-03-21T20:18:11.0798419Z Adding repository directory to the temporary git global config as a safe directory
2025-03-21T20:18:11.0803061Z [command]/usr/bin/git config --global --add safe.directory /home/ec2-user/actions-runner/_work/executorch/executorch/test-infra
2025-03-21T20:18:11.0831336Z ##[group]Initializing the repository
2025-03-21T20:18:11.0836484Z [command]/usr/bin/git init /home/ec2-user/actions-runner/_work/executorch/executorch/test-infra
2025-03-21T20:18:11.0863782Z hint: Using 'master' as the name for the initial branch. This default branch name
2025-03-21T20:18:11.0864996Z hint: is subject to change. To configure the initial branch name to use in all
2025-03-21T20:18:11.0866233Z hint: of your new repositories, which will suppress this warning, call:
2025-03-21T20:18:11.0867240Z hint:
2025-03-21T20:18:11.0867922Z hint: 	git config --global init.defaultBranch <name>
2025-03-21T20:18:11.0868664Z hint:
2025-03-21T20:18:11.0869460Z hint: Names commonly chosen instead of 'master' are 'main', 'trunk' and
2025-03-21T20:18:11.0870584Z hint: 'development'. The just-created branch can be renamed via this command:
2025-03-21T20:18:11.0871489Z hint:
2025-03-21T20:18:11.0872163Z hint: 	git branch -m <name>
2025-03-21T20:18:11.0873305Z Initialized empty Git repository in /home/ec2-user/actions-runner/_work/executorch/executorch/test-infra/.git/
2025-03-21T20:18:11.0876075Z [command]/usr/bin/git remote add origin https://github.com/pytorch/test-infra
2025-03-21T20:18:11.0899592Z ##[endgroup]
2025-03-21T20:18:11.0900680Z ##[group]Disabling automatic garbage collection
2025-03-21T20:18:11.0904954Z [command]/usr/bin/git config --local gc.auto 0
2025-03-21T20:18:11.0929057Z ##[endgroup]
2025-03-21T20:18:11.0930067Z ##[group]Setting up auth
2025-03-21T20:18:11.0935650Z [command]/usr/bin/git config --local --name-only --get-regexp core\.sshCommand
2025-03-21T20:18:11.0959748Z [command]/usr/bin/git submodule foreach --recursive sh -c "git config --local --name-only --get-regexp 'core\.sshCommand' && git config --local --unset-all 'core.sshCommand' || :"
2025-03-21T20:18:11.1225237Z [command]/usr/bin/git config --local --name-only --get-regexp http\.https\:\/\/github\.com\/\.extraheader
2025-03-21T20:18:11.1250533Z [command]/usr/bin/git submodule foreach --recursive sh -c "git config --local --name-only --get-regexp 'http\.https\:\/\/github\.com\/\.extraheader' && git config --local --unset-all 'http.https://github.com/.extraheader' || :"
2025-03-21T20:18:11.1494409Z [command]/usr/bin/git config --local http.https://github.com/.extraheader AUTHORIZATION: basic ***
2025-03-21T20:18:11.1526717Z ##[endgroup]
2025-03-21T20:18:11.1527397Z ##[group]Determining the default branch
2025-03-21T20:18:11.1530147Z Retrieving the default branch name
2025-03-21T20:18:11.3287743Z Default branch 'main'
2025-03-21T20:18:11.3288851Z ##[endgroup]
2025-03-21T20:18:11.3289549Z ##[group]Fetching the repository
2025-03-21T20:18:11.3294663Z [command]/usr/bin/git -c protocol.version=2 fetch --no-tags --prune --no-recurse-submodules --depth=1 origin +refs/heads/main:refs/remotes/origin/main
2025-03-21T20:18:11.6873837Z From https://github.com/pytorch/test-infra
2025-03-21T20:18:11.6874310Z  * [new branch]      main       -> origin/main
2025-03-21T20:18:11.6894744Z ##[endgroup]
2025-03-21T20:18:11.6895180Z ##[group]Determining the checkout info
2025-03-21T20:18:11.6896640Z ##[endgroup]
2025-03-21T20:18:11.6901462Z [command]/usr/bin/git sparse-checkout disable
2025-03-21T20:18:11.6933474Z [command]/usr/bin/git config --local --unset-all extensions.worktreeConfig
2025-03-21T20:18:11.6957074Z ##[group]Checking out the ref
2025-03-21T20:18:11.6960645Z [command]/usr/bin/git checkout --progress --force -B main refs/remotes/origin/main
2025-03-21T20:18:11.7742223Z Switched to a new branch 'main'
2025-03-21T20:18:11.7743019Z branch 'main' set up to track 'origin/main'.
2025-03-21T20:18:11.7749336Z ##[endgroup]
2025-03-21T20:18:11.7749792Z ##[group]Setting up auth for fetching submodules
2025-03-21T20:18:11.7755004Z [command]/usr/bin/git config --global http.https://github.com/.extraheader AUTHORIZATION: basic ***
2025-03-21T20:18:11.7792124Z [command]/usr/bin/git config --global --unset-all url.https://github.com/.insteadOf
2025-03-21T20:18:11.7818443Z [command]/usr/bin/git config --global --add url.https://github.com/.insteadOf git@github.com:
2025-03-21T20:18:11.7843697Z [command]/usr/bin/git config --global --add url.https://github.com/.insteadOf org-21003710@github.com:
2025-03-21T20:18:11.7865543Z ##[endgroup]
2025-03-21T20:18:11.7865971Z ##[group]Fetching submodules
2025-03-21T20:18:11.7869278Z [command]/usr/bin/git submodule sync --recursive
2025-03-21T20:18:11.8117728Z [command]/usr/bin/git -c protocol.version=2 submodule update --init --force --depth=1 --recursive
2025-03-21T20:18:11.8363948Z [command]/usr/bin/git submodule foreach --recursive git config --local gc.auto 0
2025-03-21T20:18:11.8605059Z ##[endgroup]
2025-03-21T20:18:11.8605523Z ##[group]Persisting credentials for submodules
2025-03-21T20:18:11.8610496Z [command]/usr/bin/git submodule foreach --recursive sh -c "git config --local --name-only --get-regexp 'url\.https\:\/\/github\.com\/\.insteadOf' && git config --local --unset-all 'url.https://github.com/.insteadOf' || :"
2025-03-21T20:18:11.8858124Z [command]/usr/bin/git submodule foreach --recursive sh -c "git config --local 'http.https://github.com/.extraheader' 'AUTHORIZATION: basic ***' && git config --local --show-origin --name-only --get-regexp remote.origin.url"
2025-03-21T20:18:11.9105355Z [command]/usr/bin/git submodule foreach --recursive git config --local --add 'url.https://github.com/.insteadOf' 'git@github.com:'
2025-03-21T20:18:11.9347588Z [command]/usr/bin/git submodule foreach --recursive git config --local --add 'url.https://github.com/.insteadOf' 'org-21003710@github.com:'
2025-03-21T20:18:11.9587415Z ##[endgroup]
2025-03-21T20:18:11.9618709Z [command]/usr/bin/git log -1 --format=%H
2025-03-21T20:18:11.9639183Z c1d92bc76c9d8ecf59b36ef10588c9605c8578d1
2025-03-21T20:18:11.9804727Z Prepare all required actions
2025-03-21T20:18:11.9805246Z Getting action download info
2025-03-21T20:18:12.0842515Z Download action repository 'pytorch/test-infra@main' (SHA:c1d92bc76c9d8ecf59b36ef10588c9605c8578d1)
2025-03-21T20:18:13.0692816Z Getting action download info
2025-03-21T20:18:13.1630518Z Download action repository 'nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482' (SHA:3e91a01664abd3c5cd539100d10d33b9c5b68482)
2025-03-21T20:18:13.3173078Z ##[group]Run ./test-infra/.github/actions/setup-linux
2025-03-21T20:18:13.3173443Z env:
2025-03-21T20:18:13.3173725Z   DOCKER_IMAGE: executorch-ubuntu-22.04-qnn-sdk
2025-03-21T20:18:13.3174106Z   REPOSITORY: pytorch/executorch
2025-03-21T20:18:13.3174406Z   PR_NUMBER: 
2025-03-21T20:18:13.3177494Z   SCRIPT: # The generic Linux job chooses to use base env, not the one setup by the image
CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
conda activate "${CONDA_ENV}"

DTYPE=fp32
BUILD_TOOL="cmake"
MODE=qnn
PT2E_QUANTIZE=qnn_16a16w

./install_requirements.sh --use-pt-pinned-commit
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh

# Setup executorch
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "${BUILD_TOOL}"
# Install requirements for export_llama
PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
# Test llama2
PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh -model stories110M -build_tool "${BUILD_TOOL}" -mode "${MODE}" -dtype "${DTYPE}" -pt2e_quantize "${PT2E_QUANTIZE}"

2025-03-21T20:18:13.3180753Z ##[endgroup]
2025-03-21T20:18:13.3263089Z ##[group]Run set -euo pipefail
2025-03-21T20:18:13.3263438Z set -euo pipefail
2025-03-21T20:18:13.3263747Z function get_ec2_metadata() {
2025-03-21T20:18:13.3264131Z   # Pulled from instance metadata endpoint for EC2
2025-03-21T20:18:13.3264794Z   # see https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/instancedata-data-retrieval.html
2025-03-21T20:18:13.3265360Z   category=$1
2025-03-21T20:18:13.3266234Z   curl -H "X-aws-ec2-metadata-token: $(curl -s -X PUT "http://169.254.169.254/latest/api/token" -H "X-aws-ec2-metadata-token-ttl-seconds: 30")" -fsSL "http://169.254.169.254/latest/meta-data/${category}"
2025-03-21T20:18:13.3267129Z }
2025-03-21T20:18:13.3267402Z echo "ami-id: $(get_ec2_metadata ami-id)"
2025-03-21T20:18:13.3267833Z echo "instance-id: $(get_ec2_metadata instance-id)"
2025-03-21T20:18:13.3268300Z echo "instance-type: $(get_ec2_metadata instance-type)"
2025-03-21T20:18:13.3268726Z echo "system info $(uname -a)"
2025-03-21T20:18:13.3274406Z shell: /usr/bin/bash --noprofile --norc -e -o pipefail {0}
2025-03-21T20:18:13.3274794Z env:
2025-03-21T20:18:13.3275065Z   DOCKER_IMAGE: executorch-ubuntu-22.04-qnn-sdk
2025-03-21T20:18:13.3275448Z   REPOSITORY: pytorch/executorch
2025-03-21T20:18:13.3275738Z   PR_NUMBER: 
2025-03-21T20:18:13.3278768Z   SCRIPT: # The generic Linux job chooses to use base env, not the one setup by the image
CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
conda activate "${CONDA_ENV}"

DTYPE=fp32
BUILD_TOOL="cmake"
MODE=qnn
PT2E_QUANTIZE=qnn_16a16w

./install_requirements.sh --use-pt-pinned-commit
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh

# Setup executorch
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "${BUILD_TOOL}"
# Install requirements for export_llama
PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
# Test llama2
PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh -model stories110M -build_tool "${BUILD_TOOL}" -mode "${MODE}" -dtype "${DTYPE}" -pt2e_quantize "${PT2E_QUANTIZE}"

2025-03-21T20:18:13.3281842Z ##[endgroup]
2025-03-21T20:18:13.3403805Z ami-id: ami-08b5b3a93ed654d19
2025-03-21T20:18:13.3489019Z instance-id: i-0c70e9b839f29d8f9
2025-03-21T20:18:13.3572247Z instance-type: c5.2xlarge
2025-03-21T20:18:13.3581475Z system info Linux ip-10-0-52-230.ec2.internal 6.1.129-138.220.amzn2023.x86_64 #1 SMP PREEMPT_DYNAMIC Tue Feb 25 22:18:43 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
2025-03-21T20:18:13.3614321Z ##[group]Run echo "IN_CONTAINER_RUNNER=$(if [ -f /.inarc ] || [ -f /.incontainer ]; then echo true ; else echo false; fi)" >> "$GITHUB_OUTPUT"
2025-03-21T20:18:13.3615248Z echo "IN_CONTAINER_RUNNER=$(if [ -f /.inarc ] || [ -f /.incontainer ]; then echo true ; else echo false; fi)" >> "$GITHUB_OUTPUT"
2025-03-21T20:18:13.3621238Z shell: /usr/bin/bash --noprofile --norc -e -o pipefail {0}
2025-03-21T20:18:13.3621610Z env:
2025-03-21T20:18:13.3621885Z   DOCKER_IMAGE: executorch-ubuntu-22.04-qnn-sdk
2025-03-21T20:18:13.3622265Z   REPOSITORY: pytorch/executorch
2025-03-21T20:18:13.3622569Z   PR_NUMBER: 
2025-03-21T20:18:13.3625745Z   SCRIPT: # The generic Linux job chooses to use base env, not the one setup by the image
CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
conda activate "${CONDA_ENV}"

DTYPE=fp32
BUILD_TOOL="cmake"
MODE=qnn
PT2E_QUANTIZE=qnn_16a16w

./install_requirements.sh --use-pt-pinned-commit
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh

# Setup executorch
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "${BUILD_TOOL}"
# Install requirements for export_llama
PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
# Test llama2
PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh -model stories110M -build_tool "${BUILD_TOOL}" -mode "${MODE}" -dtype "${DTYPE}" -pt2e_quantize "${PT2E_QUANTIZE}"

2025-03-21T20:18:13.3628837Z ##[endgroup]
2025-03-21T20:18:13.3702782Z ##[group]Run if systemctl is-active --quiet docker; then
2025-03-21T20:18:13.3703237Z if systemctl is-active --quiet docker; then
2025-03-21T20:18:13.3703636Z     echo "Docker daemon is running...";
2025-03-21T20:18:13.3703977Z else
2025-03-21T20:18:13.3704338Z     echo "Starting docker deamon..." && sudo systemctl start docker;
2025-03-21T20:18:13.3704766Z fi
2025-03-21T20:18:13.3709739Z shell: /usr/bin/bash --noprofile --norc -e -o pipefail {0}
2025-03-21T20:18:13.3710124Z env:
2025-03-21T20:18:13.3710382Z   DOCKER_IMAGE: executorch-ubuntu-22.04-qnn-sdk
2025-03-21T20:18:13.3710754Z   REPOSITORY: pytorch/executorch
2025-03-21T20:18:13.3711058Z   PR_NUMBER: 
2025-03-21T20:18:13.3714090Z   SCRIPT: # The generic Linux job chooses to use base env, not the one setup by the image
CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
conda activate "${CONDA_ENV}"

DTYPE=fp32
BUILD_TOOL="cmake"
MODE=qnn
PT2E_QUANTIZE=qnn_16a16w

./install_requirements.sh --use-pt-pinned-commit
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh

# Setup executorch
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "${BUILD_TOOL}"
# Install requirements for export_llama
PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
# Test llama2
PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh -model stories110M -build_tool "${BUILD_TOOL}" -mode "${MODE}" -dtype "${DTYPE}" -pt2e_quantize "${PT2E_QUANTIZE}"

2025-03-21T20:18:13.3717188Z ##[endgroup]
2025-03-21T20:18:13.3783539Z Docker daemon is running...
2025-03-21T20:18:13.3811705Z ##[group]Run AWS_ACCOUNT_ID=$(aws sts get-caller-identity|grep Account|cut -f4 -d\")
2025-03-21T20:18:13.3812345Z AWS_ACCOUNT_ID=$(aws sts get-caller-identity|grep Account|cut -f4 -d\")
2025-03-21T20:18:13.3812872Z retry () { "$@"  || (sleep 1 && "$@") || (sleep 2 && "$@") }
2025-03-21T20:18:13.3813478Z retry aws ecr get-login-password --region "$AWS_DEFAULT_REGION" | docker login --username AWS \
2025-03-21T20:18:13.3814206Z     --password-stdin "$AWS_ACCOUNT_ID.dkr.ecr.$AWS_DEFAULT_REGION.amazonaws.com"
2025-03-21T20:18:13.3819517Z shell: /usr/bin/bash --noprofile --norc -e -o pipefail {0}
2025-03-21T20:18:13.3819906Z env:
2025-03-21T20:18:13.3820184Z   DOCKER_IMAGE: executorch-ubuntu-22.04-qnn-sdk
2025-03-21T20:18:13.3820558Z   REPOSITORY: pytorch/executorch
2025-03-21T20:18:13.3820841Z   PR_NUMBER: 
2025-03-21T20:18:13.3823883Z   SCRIPT: # The generic Linux job chooses to use base env, not the one setup by the image
CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
conda activate "${CONDA_ENV}"

DTYPE=fp32
BUILD_TOOL="cmake"
MODE=qnn
PT2E_QUANTIZE=qnn_16a16w

./install_requirements.sh --use-pt-pinned-commit
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh

# Setup executorch
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "${BUILD_TOOL}"
# Install requirements for export_llama
PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
# Test llama2
PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh -model stories110M -build_tool "${BUILD_TOOL}" -mode "${MODE}" -dtype "${DTYPE}" -pt2e_quantize "${PT2E_QUANTIZE}"

2025-03-21T20:18:13.3827070Z   AWS_RETRY_MODE: standard
2025-03-21T20:18:13.3827384Z   AWS_MAX_ATTEMPTS: 5
2025-03-21T20:18:13.3827655Z   AWS_DEFAULT_REGION: us-east-1
2025-03-21T20:18:13.3827926Z ##[endgroup]
2025-03-21T20:18:14.3677613Z WARNING! Your password will be stored unencrypted in /home/ec2-user/.docker/config.json.
2025-03-21T20:18:14.3678281Z Configure a credential helper to remove this warning. See
2025-03-21T20:18:14.3679253Z https://docs.docker.com/engine/reference/commandline/login/#credentials-store
2025-03-21T20:18:14.3679642Z 
2025-03-21T20:18:14.3679759Z Login Succeeded
2025-03-21T20:18:14.3721316Z ##[group]Run env | grep '^GITHUB' >> "${RUNNER_TEMP}/github_env_${GITHUB_RUN_ID}"
2025-03-21T20:18:14.3721915Z env | grep '^GITHUB' >> "${RUNNER_TEMP}/github_env_${GITHUB_RUN_ID}"
2025-03-21T20:18:14.3722452Z env | grep '^CI' >> "${RUNNER_TEMP}/github_env_${GITHUB_RUN_ID}"
2025-03-21T20:18:14.3728342Z shell: /usr/bin/bash --noprofile --norc -e -o pipefail {0}
2025-03-21T20:18:14.3728734Z env:
2025-03-21T20:18:14.3729011Z   DOCKER_IMAGE: executorch-ubuntu-22.04-qnn-sdk
2025-03-21T20:18:14.3729502Z   REPOSITORY: pytorch/executorch
2025-03-21T20:18:14.3729808Z   PR_NUMBER: 
2025-03-21T20:18:14.3733068Z   SCRIPT: # The generic Linux job chooses to use base env, not the one setup by the image
CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
conda activate "${CONDA_ENV}"

DTYPE=fp32
BUILD_TOOL="cmake"
MODE=qnn
PT2E_QUANTIZE=qnn_16a16w

./install_requirements.sh --use-pt-pinned-commit
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh

# Setup executorch
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "${BUILD_TOOL}"
# Install requirements for export_llama
PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
# Test llama2
PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh -model stories110M -build_tool "${BUILD_TOOL}" -mode "${MODE}" -dtype "${DTYPE}" -pt2e_quantize "${PT2E_QUANTIZE}"

2025-03-21T20:18:14.3736187Z ##[endgroup]
2025-03-21T20:18:14.3819750Z ##[group]Run RUNNER_ARTIFACT_DIR="${RUNNER_TEMP}/artifacts"
2025-03-21T20:18:14.3820242Z RUNNER_ARTIFACT_DIR="${RUNNER_TEMP}/artifacts"
2025-03-21T20:18:14.3820646Z sudo rm -rf "${RUNNER_ARTIFACT_DIR}"
2025-03-21T20:18:14.3821011Z mkdir -p "${RUNNER_ARTIFACT_DIR}"
2025-03-21T20:18:14.3821454Z echo "RUNNER_ARTIFACT_DIR=${RUNNER_ARTIFACT_DIR}" >> "${GITHUB_ENV}"
2025-03-21T20:18:14.3821894Z 
2025-03-21T20:18:14.3822209Z RUNNER_TEST_RESULTS_DIR="${RUNNER_TEMP}/test-results"
2025-03-21T20:18:14.3822648Z sudo rm -rf "${RUNNER_TEST_RESULTS_DIR}"
2025-03-21T20:18:14.3823030Z mkdir -p "${RUNNER_TEST_RESULTS_DIR}"
2025-03-21T20:18:14.3823529Z echo "RUNNER_TEST_RESULTS_DIR=${RUNNER_TEST_RESULTS_DIR}" >> "${GITHUB_ENV}"
2025-03-21T20:18:14.3824206Z 
2025-03-21T20:18:14.3824469Z RUNNER_DOCS_DIR="${RUNNER_TEMP}/docs"
2025-03-21T20:18:14.3824828Z sudo rm -rf "${RUNNER_DOCS_DIR}"
2025-03-21T20:18:14.3825170Z mkdir -p "${RUNNER_DOCS_DIR}"
2025-03-21T20:18:14.3825587Z echo "RUNNER_DOCS_DIR=${RUNNER_DOCS_DIR}" >> "${GITHUB_ENV}"
2025-03-21T20:18:14.3830844Z shell: /usr/bin/bash --noprofile --norc -e -o pipefail {0}
2025-03-21T20:18:14.3831218Z env:
2025-03-21T20:18:14.3831493Z   DOCKER_IMAGE: executorch-ubuntu-22.04-qnn-sdk
2025-03-21T20:18:14.3831864Z   REPOSITORY: pytorch/executorch
2025-03-21T20:18:14.3832161Z   PR_NUMBER: 
2025-03-21T20:18:14.3835436Z   SCRIPT: # The generic Linux job chooses to use base env, not the one setup by the image
CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
conda activate "${CONDA_ENV}"

DTYPE=fp32
BUILD_TOOL="cmake"
MODE=qnn
PT2E_QUANTIZE=qnn_16a16w

./install_requirements.sh --use-pt-pinned-commit
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh

# Setup executorch
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "${BUILD_TOOL}"
# Install requirements for export_llama
PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
# Test llama2
PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh -model stories110M -build_tool "${BUILD_TOOL}" -mode "${MODE}" -dtype "${DTYPE}" -pt2e_quantize "${PT2E_QUANTIZE}"

2025-03-21T20:18:14.3838662Z ##[endgroup]
2025-03-21T20:18:14.9635945Z ##[group]Run needs=0
2025-03-21T20:18:14.9636252Z needs=0
2025-03-21T20:18:14.9636643Z if lspci -v | grep -e 'controller.*NVIDIA' >/dev/null 2>/dev/null; then
2025-03-21T20:18:14.9637077Z   needs=1
2025-03-21T20:18:14.9637327Z fi
2025-03-21T20:18:14.9637596Z echo "does=${needs}" >> $GITHUB_OUTPUT
2025-03-21T20:18:14.9643475Z shell: /usr/bin/bash --noprofile --norc -e -o pipefail {0}
2025-03-21T20:18:14.9643865Z env:
2025-03-21T20:18:14.9644142Z   DOCKER_IMAGE: executorch-ubuntu-22.04-qnn-sdk
2025-03-21T20:18:14.9644526Z   REPOSITORY: pytorch/executorch
2025-03-21T20:18:14.9644829Z   PR_NUMBER: 
2025-03-21T20:18:14.9647866Z   SCRIPT: # The generic Linux job chooses to use base env, not the one setup by the image
CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
conda activate "${CONDA_ENV}"

DTYPE=fp32
BUILD_TOOL="cmake"
MODE=qnn
PT2E_QUANTIZE=qnn_16a16w

./install_requirements.sh --use-pt-pinned-commit
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh

# Setup executorch
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "${BUILD_TOOL}"
# Install requirements for export_llama
PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
# Test llama2
PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh -model stories110M -build_tool "${BUILD_TOOL}" -mode "${MODE}" -dtype "${DTYPE}" -pt2e_quantize "${PT2E_QUANTIZE}"

2025-03-21T20:18:14.9651192Z   RUNNER_ARTIFACT_DIR: /home/ec2-user/actions-runner/_work/_temp/artifacts
2025-03-21T20:18:14.9651787Z   RUNNER_TEST_RESULTS_DIR: /home/ec2-user/actions-runner/_work/_temp/test-results
2025-03-21T20:18:14.9652346Z   RUNNER_DOCS_DIR: /home/ec2-user/actions-runner/_work/_temp/docs
2025-03-21T20:18:14.9652746Z ##[endgroup]
2025-03-21T20:18:14.9909871Z ##[group]Run # ignore expansion of "docker ps -q" since it could be empty
2025-03-21T20:18:14.9910462Z # ignore expansion of "docker ps -q" since it could be empty
2025-03-21T20:18:14.9910899Z # shellcheck disable=SC2046
2025-03-21T20:18:14.9911231Z docker stop $(docker ps -q) || true
2025-03-21T20:18:14.9911591Z # Prune all of the docker images
2025-03-21T20:18:14.9911936Z docker system prune -af
2025-03-21T20:18:14.9917184Z shell: /usr/bin/bash --noprofile --norc -e -o pipefail {0}
2025-03-21T20:18:14.9917588Z env:
2025-03-21T20:18:14.9917996Z   DOCKER_IMAGE: executorch-ubuntu-22.04-qnn-sdk
2025-03-21T20:18:14.9918374Z   REPOSITORY: pytorch/executorch
2025-03-21T20:18:14.9918676Z   PR_NUMBER: 
2025-03-21T20:18:14.9921708Z   SCRIPT: # The generic Linux job chooses to use base env, not the one setup by the image
CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
conda activate "${CONDA_ENV}"

DTYPE=fp32
BUILD_TOOL="cmake"
MODE=qnn
PT2E_QUANTIZE=qnn_16a16w

./install_requirements.sh --use-pt-pinned-commit
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh

# Setup executorch
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "${BUILD_TOOL}"
# Install requirements for export_llama
PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
# Test llama2
PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh -model stories110M -build_tool "${BUILD_TOOL}" -mode "${MODE}" -dtype "${DTYPE}" -pt2e_quantize "${PT2E_QUANTIZE}"

2025-03-21T20:18:14.9925025Z   RUNNER_ARTIFACT_DIR: /home/ec2-user/actions-runner/_work/_temp/artifacts
2025-03-21T20:18:14.9925622Z   RUNNER_TEST_RESULTS_DIR: /home/ec2-user/actions-runner/_work/_temp/test-results
2025-03-21T20:18:14.9926184Z   RUNNER_DOCS_DIR: /home/ec2-user/actions-runner/_work/_temp/docs
2025-03-21T20:18:14.9926584Z ##[endgroup]
2025-03-21T20:18:15.0133127Z "docker stop" requires at least 1 argument.
2025-03-21T20:18:15.0133781Z See 'docker stop --help'.
2025-03-21T20:18:15.0134101Z 
2025-03-21T20:18:15.0134420Z Usage:  docker stop [OPTIONS] CONTAINER [CONTAINER...]
2025-03-21T20:18:15.0134941Z 
2025-03-21T20:18:15.0135139Z Stop one or more running containers
2025-03-21T20:18:15.0421482Z Total reclaimed space: 0B
2025-03-21T20:18:15.0493920Z ##[group]Run ./test-infra/.github/actions/setup-ssh
2025-03-21T20:18:15.0494307Z with:
2025-03-21T20:18:15.0494739Z   github-secret: ***
2025-03-21T20:18:15.0495440Z   instructions: All testing is done inside the container, to start an interactive session run:
   docker exec -it $(docker container ps --format '{{.ID}}') bash

2025-03-21T20:18:15.0496205Z   activate-with-label: false
2025-03-21T20:18:15.0496492Z   label: with-ssh
2025-03-21T20:18:15.0496762Z   remove-existing-keys: true
2025-03-21T20:18:15.0497050Z   fail-silently: true
2025-03-21T20:18:15.0497288Z env:
2025-03-21T20:18:15.0497560Z   DOCKER_IMAGE: executorch-ubuntu-22.04-qnn-sdk
2025-03-21T20:18:15.0497933Z   REPOSITORY: pytorch/executorch
2025-03-21T20:18:15.0498230Z   PR_NUMBER: 
2025-03-21T20:18:15.0501293Z   SCRIPT: # The generic Linux job chooses to use base env, not the one setup by the image
CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
conda activate "${CONDA_ENV}"

DTYPE=fp32
BUILD_TOOL="cmake"
MODE=qnn
PT2E_QUANTIZE=qnn_16a16w

./install_requirements.sh --use-pt-pinned-commit
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh

# Setup executorch
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "${BUILD_TOOL}"
# Install requirements for export_llama
PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
# Test llama2
PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh -model stories110M -build_tool "${BUILD_TOOL}" -mode "${MODE}" -dtype "${DTYPE}" -pt2e_quantize "${PT2E_QUANTIZE}"

2025-03-21T20:18:15.0504532Z   RUNNER_ARTIFACT_DIR: /home/ec2-user/actions-runner/_work/_temp/artifacts
2025-03-21T20:18:15.0505126Z   RUNNER_TEST_RESULTS_DIR: /home/ec2-user/actions-runner/_work/_temp/test-results
2025-03-21T20:18:15.0505683Z   RUNNER_DOCS_DIR: /home/ec2-user/actions-runner/_work/_temp/docs
2025-03-21T20:18:15.0506069Z ##[endgroup]
2025-03-21T20:18:15.1524218Z Please see https://github.com/pytorch/pytorch/wiki/Debugging-using-with-ssh-for-Github-Actions for more info.
2025-03-21T20:18:15.1526019Z Not on pull request and ciflow reference could not be extracted, skipping adding ssh keys
2025-03-21T20:18:15.1655841Z ##[group]Run actions/checkout@v4
2025-03-21T20:18:15.1656154Z with:
2025-03-21T20:18:15.1656408Z   repository: pytorch/executorch
2025-03-21T20:18:15.1656731Z   ref: be92d7d85cb7081ac0a544036da4096a4efa33a8
2025-03-21T20:18:15.1657090Z   path: pytorch/executorch
2025-03-21T20:18:15.1657375Z   fetch-depth: 1
2025-03-21T20:18:15.1657612Z   submodules: true
2025-03-21T20:18:15.1658014Z   token: ***
2025-03-21T20:18:15.1658237Z   ssh-strict: true
2025-03-21T20:18:15.1658480Z   ssh-user: git
2025-03-21T20:18:15.1658735Z   persist-credentials: true
2025-03-21T20:18:15.1659020Z   clean: true
2025-03-21T20:18:15.1659275Z   sparse-checkout-cone-mode: true
2025-03-21T20:18:15.1659573Z   fetch-tags: false
2025-03-21T20:18:15.1659825Z   show-progress: true
2025-03-21T20:18:15.1660079Z   lfs: false
2025-03-21T20:18:15.1660321Z   set-safe-directory: true
2025-03-21T20:18:15.1660592Z env:
2025-03-21T20:18:15.1660843Z   DOCKER_IMAGE: executorch-ubuntu-22.04-qnn-sdk
2025-03-21T20:18:15.1661269Z   REPOSITORY: pytorch/executorch
2025-03-21T20:18:15.1661703Z   PR_NUMBER: 
2025-03-21T20:18:15.1664741Z   SCRIPT: # The generic Linux job chooses to use base env, not the one setup by the image
CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
conda activate "${CONDA_ENV}"

DTYPE=fp32
BUILD_TOOL="cmake"
MODE=qnn
PT2E_QUANTIZE=qnn_16a16w

./install_requirements.sh --use-pt-pinned-commit
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh

# Setup executorch
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "${BUILD_TOOL}"
# Install requirements for export_llama
PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
# Test llama2
PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh -model stories110M -build_tool "${BUILD_TOOL}" -mode "${MODE}" -dtype "${DTYPE}" -pt2e_quantize "${PT2E_QUANTIZE}"

2025-03-21T20:18:15.1667977Z   RUNNER_ARTIFACT_DIR: /home/ec2-user/actions-runner/_work/_temp/artifacts
2025-03-21T20:18:15.1668577Z   RUNNER_TEST_RESULTS_DIR: /home/ec2-user/actions-runner/_work/_temp/test-results
2025-03-21T20:18:15.1669134Z   RUNNER_DOCS_DIR: /home/ec2-user/actions-runner/_work/_temp/docs
2025-03-21T20:18:15.1669513Z ##[endgroup]
2025-03-21T20:18:15.2592493Z Syncing repository: pytorch/executorch
2025-03-21T20:18:15.2599604Z ##[group]Getting Git version info
2025-03-21T20:18:15.2600633Z Working directory is '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch'
2025-03-21T20:18:15.2627126Z [command]/usr/bin/git version
2025-03-21T20:18:15.2661366Z git version 2.47.1
2025-03-21T20:18:15.2685888Z ##[endgroup]
2025-03-21T20:18:15.2698794Z Temporarily overriding HOME='/home/ec2-user/actions-runner/_work/_temp/bdd8626b-8def-4a24-be1a-7b4b0499e713' before making global git config changes
2025-03-21T20:18:15.2700503Z Adding repository directory to the temporary git global config as a safe directory
2025-03-21T20:18:15.2705257Z [command]/usr/bin/git config --global --add safe.directory /home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch
2025-03-21T20:18:15.2737921Z ##[group]Initializing the repository
2025-03-21T20:18:15.2743119Z [command]/usr/bin/git init /home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch
2025-03-21T20:18:15.2770431Z hint: Using 'master' as the name for the initial branch. This default branch name
2025-03-21T20:18:15.2771525Z hint: is subject to change. To configure the initial branch name to use in all
2025-03-21T20:18:15.2772519Z hint: of your new repositories, which will suppress this warning, call:
2025-03-21T20:18:15.2773221Z hint:
2025-03-21T20:18:15.2773712Z hint: 	git config --global init.defaultBranch <name>
2025-03-21T20:18:15.2774328Z hint:
2025-03-21T20:18:15.2774914Z hint: Names commonly chosen instead of 'master' are 'main', 'trunk' and
2025-03-21T20:18:15.2775889Z hint: 'development'. The just-created branch can be renamed via this command:
2025-03-21T20:18:15.2776646Z hint:
2025-03-21T20:18:15.2777357Z hint: 	git branch -m <name>
2025-03-21T20:18:15.2778479Z Initialized empty Git repository in /home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/.git/
2025-03-21T20:18:15.2783103Z [command]/usr/bin/git remote add origin https://github.com/pytorch/executorch
2025-03-21T20:18:15.2806915Z ##[endgroup]
2025-03-21T20:18:15.2807735Z ##[group]Disabling automatic garbage collection
2025-03-21T20:18:15.2812173Z [command]/usr/bin/git config --local gc.auto 0
2025-03-21T20:18:15.2836398Z ##[endgroup]
2025-03-21T20:18:15.2837126Z ##[group]Setting up auth
2025-03-21T20:18:15.2842794Z [command]/usr/bin/git config --local --name-only --get-regexp core\.sshCommand
2025-03-21T20:18:15.2866794Z [command]/usr/bin/git submodule foreach --recursive sh -c "git config --local --name-only --get-regexp 'core\.sshCommand' && git config --local --unset-all 'core.sshCommand' || :"
2025-03-21T20:18:15.3111907Z [command]/usr/bin/git config --local --name-only --get-regexp http\.https\:\/\/github\.com\/\.extraheader
2025-03-21T20:18:15.3134848Z [command]/usr/bin/git submodule foreach --recursive sh -c "git config --local --name-only --get-regexp 'http\.https\:\/\/github\.com\/\.extraheader' && git config --local --unset-all 'http.https://github.com/.extraheader' || :"
2025-03-21T20:18:15.3379237Z [command]/usr/bin/git config --local http.https://github.com/.extraheader AUTHORIZATION: basic ***
2025-03-21T20:18:15.3416375Z ##[endgroup]
2025-03-21T20:18:15.3416832Z ##[group]Fetching the repository
2025-03-21T20:18:15.3423405Z [command]/usr/bin/git -c protocol.version=2 fetch --no-tags --prune --no-recurse-submodules --depth=1 origin be92d7d85cb7081ac0a544036da4096a4efa33a8
2025-03-21T20:18:16.8880559Z From https://github.com/pytorch/executorch
2025-03-21T20:18:16.8881100Z  * branch            be92d7d85cb7081ac0a544036da4096a4efa33a8 -> FETCH_HEAD
2025-03-21T20:18:16.8899492Z ##[endgroup]
2025-03-21T20:18:16.8900014Z ##[group]Determining the checkout info
2025-03-21T20:18:16.8901755Z ##[endgroup]
2025-03-21T20:18:16.8906065Z [command]/usr/bin/git sparse-checkout disable
2025-03-21T20:18:16.8935494Z [command]/usr/bin/git config --local --unset-all extensions.worktreeConfig
2025-03-21T20:18:16.8956857Z ##[group]Checking out the ref
2025-03-21T20:18:16.8960383Z [command]/usr/bin/git checkout --progress --force be92d7d85cb7081ac0a544036da4096a4efa33a8
2025-03-21T20:18:17.3472990Z Note: switching to 'be92d7d85cb7081ac0a544036da4096a4efa33a8'.
2025-03-21T20:18:17.3473497Z 
2025-03-21T20:18:17.3473727Z You are in 'detached HEAD' state. You can look around, make experimental
2025-03-21T20:18:17.3474292Z changes and commit them, and you can discard any commits you make in this
2025-03-21T20:18:17.3474851Z state without impacting any branches by switching back to a branch.
2025-03-21T20:18:17.3475171Z 
2025-03-21T20:18:17.3475397Z If you want to create a new branch to retain commits you create, you may
2025-03-21T20:18:17.3475910Z do so (now or later) by using -c with the switch command. Example:
2025-03-21T20:18:17.3476252Z 
2025-03-21T20:18:17.3476385Z   git switch -c <new-branch-name>
2025-03-21T20:18:17.3476586Z 
2025-03-21T20:18:17.3476702Z Or undo this operation with:
2025-03-21T20:18:17.3476899Z 
2025-03-21T20:18:17.3476998Z   git switch -
2025-03-21T20:18:17.3477148Z 
2025-03-21T20:18:17.3477387Z Turn off this advice by setting config variable advice.detachedHead to false
2025-03-21T20:18:17.3477745Z 
2025-03-21T20:18:17.3477908Z HEAD is now at be92d7d [Android] Use new Llm package API
2025-03-21T20:18:17.3496549Z ##[endgroup]
2025-03-21T20:18:17.3496998Z ##[group]Setting up auth for fetching submodules
2025-03-21T20:18:17.3502101Z [command]/usr/bin/git config --global http.https://github.com/.extraheader AUTHORIZATION: basic ***
2025-03-21T20:18:17.3539936Z [command]/usr/bin/git config --global --unset-all url.https://github.com/.insteadOf
2025-03-21T20:18:17.3562108Z [command]/usr/bin/git config --global --add url.https://github.com/.insteadOf git@github.com:
2025-03-21T20:18:17.3586287Z [command]/usr/bin/git config --global --add url.https://github.com/.insteadOf org-21003710@github.com:
2025-03-21T20:18:17.3606106Z ##[endgroup]
2025-03-21T20:18:17.3606529Z ##[group]Fetching submodules
2025-03-21T20:18:17.3609719Z [command]/usr/bin/git submodule sync
2025-03-21T20:18:17.3862955Z [command]/usr/bin/git -c protocol.version=2 submodule update --init --force --depth=1
2025-03-21T20:18:17.4106824Z Submodule 'backends/arm/third-party/ethos-u-core-driver' (https://github.com/pytorch-labs/ethos-u-core-driver-mirror) registered for path 'backends/arm/third-party/ethos-u-core-driver'
2025-03-21T20:18:17.4108850Z Submodule 'backends/arm/third-party/serialization_lib' (https://github.com/pytorch-labs/tosa_serialization_lib-mirror) registered for path 'backends/arm/third-party/serialization_lib'
2025-03-21T20:18:17.4110551Z Submodule 'backends/cadence/utils/FACTO' (https://github.com/pytorch-labs/FACTO.git) registered for path 'backends/cadence/utils/FACTO'
2025-03-21T20:18:17.4113130Z Submodule 'backends/vulkan/third-party/Vulkan-Headers' (https://github.com/KhronosGroup/Vulkan-Headers) registered for path 'backends/vulkan/third-party/Vulkan-Headers'
2025-03-21T20:18:17.4115868Z Submodule 'backends/vulkan/third-party/VulkanMemoryAllocator' (https://github.com/GPUOpen-LibrariesAndSDKs/VulkanMemoryAllocator.git) registered for path 'backends/vulkan/third-party/VulkanMemoryAllocator'
2025-03-21T20:18:17.4118009Z Submodule 'backends/vulkan/third-party/volk' (https://github.com/zeux/volk) registered for path 'backends/vulkan/third-party/volk'
2025-03-21T20:18:17.4120709Z Submodule 'backends/xnnpack/third-party/FP16' (https://github.com/Maratyszcza/FP16.git) registered for path 'backends/xnnpack/third-party/FP16'
2025-03-21T20:18:17.4123472Z Submodule 'backends/xnnpack/third-party/FXdiv' (https://github.com/Maratyszcza/FXdiv.git) registered for path 'backends/xnnpack/third-party/FXdiv'
2025-03-21T20:18:17.4126361Z Submodule 'backends/xnnpack/third-party/XNNPACK' (https://github.com/google/XNNPACK.git) registered for path 'backends/xnnpack/third-party/XNNPACK'
2025-03-21T20:18:17.4129227Z Submodule 'backends/xnnpack/third-party/cpuinfo' (https://github.com/pytorch/cpuinfo.git) registered for path 'backends/xnnpack/third-party/cpuinfo'
2025-03-21T20:18:17.4132549Z Submodule 'backends/xnnpack/third-party/pthreadpool' (https://github.com/Maratyszcza/pthreadpool.git) registered for path 'backends/xnnpack/third-party/pthreadpool'
2025-03-21T20:18:17.4137395Z Submodule 'extension/llm/tokenizers' (https://github.com/pytorch-labs/tokenizers.git) registered for path 'extension/llm/tokenizers'
2025-03-21T20:18:17.4140602Z Submodule 'kernels/optimized/third-party/eigen' (https://gitlab.com/libeigen/eigen.git) registered for path 'kernels/optimized/third-party/eigen'
2025-03-21T20:18:17.4143638Z Submodule 'shim' (https://github.com/facebook/buck2-shims-meta) registered for path 'shim'
2025-03-21T20:18:17.4147145Z Submodule 'third-party/ao' (https://github.com/pytorch/ao.git) registered for path 'third-party/ao'
2025-03-21T20:18:17.4150728Z Submodule 'third-party/flatbuffers' (https://github.com/google/flatbuffers.git) registered for path 'third-party/flatbuffers'
2025-03-21T20:18:17.4155573Z Submodule 'third-party/flatcc' (https://github.com/dvidelabs/flatcc.git) registered for path 'third-party/flatcc'
2025-03-21T20:18:17.4159237Z Submodule 'third-party/gflags' (https://github.com/gflags/gflags.git) registered for path 'third-party/gflags'
2025-03-21T20:18:17.4163028Z Submodule 'third-party/googletest' (https://github.com/google/googletest.git) registered for path 'third-party/googletest'
2025-03-21T20:18:17.4166718Z Submodule 'third-party/ios-cmake' (https://github.com/leetal/ios-cmake) registered for path 'third-party/ios-cmake'
2025-03-21T20:18:17.4170846Z Submodule 'third-party/pocketfft' (https://github.com/mreineck/pocketfft) registered for path 'third-party/pocketfft'
2025-03-21T20:18:17.4174749Z Submodule 'third-party/prelude' (https://github.com/facebook/buck2-prelude.git) registered for path 'third-party/prelude'
2025-03-21T20:18:17.4178923Z Submodule 'third-party/pybind11' (https://github.com/pybind/pybind11.git) registered for path 'third-party/pybind11'
2025-03-21T20:18:17.4203298Z Cloning into '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/backends/arm/third-party/ethos-u-core-driver'...
2025-03-21T20:18:17.6419371Z Cloning into '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/backends/arm/third-party/serialization_lib'...
2025-03-21T20:18:17.8544334Z Cloning into '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/backends/cadence/utils/FACTO'...
2025-03-21T20:18:18.1017137Z Cloning into '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/backends/vulkan/third-party/Vulkan-Headers'...
2025-03-21T20:18:18.4841907Z Cloning into '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/backends/vulkan/third-party/VulkanMemoryAllocator'...
2025-03-21T20:18:18.7270700Z Cloning into '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/backends/vulkan/third-party/volk'...
2025-03-21T20:18:19.2301598Z Cloning into '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/backends/xnnpack/third-party/FP16'...
2025-03-21T20:18:19.4016131Z Cloning into '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/backends/xnnpack/third-party/FXdiv'...
2025-03-21T20:18:19.5745680Z Cloning into '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/backends/xnnpack/third-party/XNNPACK'...
2025-03-21T20:18:20.2741546Z Cloning into '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/backends/xnnpack/third-party/cpuinfo'...
2025-03-21T20:18:20.6075590Z Cloning into '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/backends/xnnpack/third-party/pthreadpool'...
2025-03-21T20:18:20.7736644Z Cloning into '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/extension/llm/tokenizers'...
2025-03-21T20:18:21.0411557Z Cloning into '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/kernels/optimized/third-party/eigen'...
2025-03-21T20:18:21.7193017Z Cloning into '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/shim'...
2025-03-21T20:18:21.9171621Z Cloning into '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/third-party/ao'...
2025-03-21T20:18:22.2307669Z Cloning into '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/third-party/flatbuffers'...
2025-03-21T20:18:22.5340770Z Cloning into '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/third-party/flatcc'...
2025-03-21T20:18:22.7771502Z Cloning into '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/third-party/gflags'...
2025-03-21T20:18:22.9540609Z Cloning into '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/third-party/googletest'...
2025-03-21T20:18:23.1808747Z Cloning into '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/third-party/ios-cmake'...
2025-03-21T20:18:23.3539945Z Cloning into '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/third-party/pocketfft'...
2025-03-21T20:18:23.5246544Z Cloning into '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/third-party/prelude'...
2025-03-21T20:18:23.8877856Z Cloning into '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/third-party/pybind11'...
2025-03-21T20:18:24.5930429Z From https://github.com/pytorch-labs/ethos-u-core-driver-mirror
2025-03-21T20:18:24.5931016Z  * branch            78df0006c5fa667150d3ee35db7bde1d3f6f58c7 -> FETCH_HEAD
2025-03-21T20:18:24.6038330Z Submodule path 'backends/arm/third-party/ethos-u-core-driver': checked out '78df0006c5fa667150d3ee35db7bde1d3f6f58c7'
2025-03-21T20:18:25.0989123Z From https://github.com/pytorch-labs/tosa_serialization_lib-mirror
2025-03-21T20:18:25.0989985Z  * branch            187af0d41fe75d08d2a7ec84c1b4d24b9b641ed2 -> FETCH_HEAD
2025-03-21T20:18:25.1094204Z Submodule path 'backends/arm/third-party/serialization_lib': checked out '187af0d41fe75d08d2a7ec84c1b4d24b9b641ed2'
2025-03-21T20:18:25.1182215Z Submodule path 'backends/cadence/utils/FACTO': checked out '1db37fc79d0d59638cbb794fa49d878aafc24461'
2025-03-21T20:18:25.8307628Z From https://github.com/KhronosGroup/Vulkan-Headers
2025-03-21T20:18:25.8308395Z  * branch            0c5928795a66e93f65e5e68a36d8daa79a209dc2 -> FETCH_HEAD
2025-03-21T20:18:25.8794205Z Submodule path 'backends/vulkan/third-party/Vulkan-Headers': checked out '0c5928795a66e93f65e5e68a36d8daa79a209dc2'
2025-03-21T20:18:26.4390598Z From https://github.com/GPUOpen-LibrariesAndSDKs/VulkanMemoryAllocator
2025-03-21T20:18:26.4391224Z  * branch            a6bfc237255a6bac1513f7c1ebde6d8aed6b5191 -> FETCH_HEAD
2025-03-21T20:18:26.4698085Z Submodule path 'backends/vulkan/third-party/VulkanMemoryAllocator': checked out 'a6bfc237255a6bac1513f7c1ebde6d8aed6b5191'
2025-03-21T20:18:26.8836587Z From https://github.com/zeux/volk
2025-03-21T20:18:26.8837087Z  * branch            b3bc21e584f97400b6884cb2a541a56c6a5ddba3 -> FETCH_HEAD
2025-03-21T20:18:26.8905785Z Submodule path 'backends/vulkan/third-party/volk': checked out 'b3bc21e584f97400b6884cb2a541a56c6a5ddba3'
2025-03-21T20:18:27.3481392Z From https://github.com/Maratyszcza/FP16
2025-03-21T20:18:27.3481911Z  * branch            4dfe081cf6bcd15db339cf2680b9281b8451eeb3 -> FETCH_HEAD
2025-03-21T20:18:27.3566341Z Submodule path 'backends/xnnpack/third-party/FP16': checked out '4dfe081cf6bcd15db339cf2680b9281b8451eeb3'
2025-03-21T20:18:27.6953606Z From https://github.com/Maratyszcza/FXdiv
2025-03-21T20:18:27.6954113Z  * branch            b408327ac2a15ec3e43352421954f5b1967701d1 -> FETCH_HEAD
2025-03-21T20:18:27.7008596Z Submodule path 'backends/xnnpack/third-party/FXdiv': checked out 'b408327ac2a15ec3e43352421954f5b1967701d1'
2025-03-21T20:18:29.2224711Z From https://github.com/google/XNNPACK
2025-03-21T20:18:29.2225273Z  * branch              4ea82e595b36106653175dcb04b2aa532660d0d8 -> FETCH_HEAD
2025-03-21T20:18:29.8055503Z Submodule path 'backends/xnnpack/third-party/XNNPACK': checked out '4ea82e595b36106653175dcb04b2aa532660d0d8'
2025-03-21T20:18:30.3516629Z From https://github.com/pytorch/cpuinfo
2025-03-21T20:18:30.3517131Z  * branch            1e83a2fdd3102f65c6f1fb602c1b320486218a99 -> FETCH_HEAD
2025-03-21T20:18:30.4338568Z Submodule path 'backends/xnnpack/third-party/cpuinfo': checked out '1e83a2fdd3102f65c6f1fb602c1b320486218a99'
2025-03-21T20:18:30.8201202Z From https://github.com/Maratyszcza/pthreadpool
2025-03-21T20:18:30.8201734Z  * branch            4fe0e1e183925bf8cfa6aae24237e724a96479b8 -> FETCH_HEAD
2025-03-21T20:18:30.8281871Z Submodule path 'backends/xnnpack/third-party/pthreadpool': checked out '4fe0e1e183925bf8cfa6aae24237e724a96479b8'
2025-03-21T20:18:31.2598735Z From https://github.com/pytorch-labs/tokenizers
2025-03-21T20:18:31.2599318Z  * branch            d70f5a760552d8d3bb288cdd93eebde477bb6eb0 -> FETCH_HEAD
2025-03-21T20:18:31.3077446Z Submodule path 'extension/llm/tokenizers': checked out 'd70f5a760552d8d3bb288cdd93eebde477bb6eb0'
2025-03-21T20:18:32.9823278Z From https://gitlab.com/libeigen/eigen
2025-03-21T20:18:32.9823816Z  * branch            a39ade4ccf99df845ec85c580fbbb324f71952fa -> FETCH_HEAD
2025-03-21T20:18:33.1051796Z Submodule path 'kernels/optimized/third-party/eigen': checked out 'a39ade4ccf99df845ec85c580fbbb324f71952fa'
2025-03-21T20:18:33.1287065Z Submodule path 'shim': checked out 'cf6a954aae4bee7b4515e13475878460115027d1'
2025-03-21T20:18:33.6251011Z From https://github.com/pytorch/ao
2025-03-21T20:18:33.6251540Z  * branch            64bcf4c25755a783685ba7383000b3bf722523c1 -> FETCH_HEAD
2025-03-21T20:18:33.6906628Z Submodule path 'third-party/ao': checked out '64bcf4c25755a783685ba7383000b3bf722523c1'
2025-03-21T20:18:34.2934072Z From https://github.com/google/flatbuffers
2025-03-21T20:18:34.2934814Z  * branch            595bf0007ab1929570c7671f091313c8fc20644e -> FETCH_HEAD
2025-03-21T20:18:34.3935437Z Submodule path 'third-party/flatbuffers': checked out '595bf0007ab1929570c7671f091313c8fc20644e'
2025-03-21T20:18:34.9022832Z From https://github.com/dvidelabs/flatcc
2025-03-21T20:18:34.9023424Z  * branch            896db54787e8b730a6be482c69324751f3f5f117 -> FETCH_HEAD
2025-03-21T20:18:34.9265002Z Submodule path 'third-party/flatcc': checked out '896db54787e8b730a6be482c69324751f3f5f117'
2025-03-21T20:18:35.4525159Z From https://github.com/gflags/gflags
2025-03-21T20:18:35.4525701Z  * branch            a738fdf9338412f83ab3f26f31ac11ed3f3ec4bd -> FETCH_HEAD
2025-03-21T20:18:35.4611837Z Submodule path 'third-party/gflags': checked out 'a738fdf9338412f83ab3f26f31ac11ed3f3ec4bd'
2025-03-21T20:18:36.0662270Z From https://github.com/google/googletest
2025-03-21T20:18:36.0662792Z  * branch            e2239ee6043f73722e7aa812a459f54a28552929 -> FETCH_HEAD
2025-03-21T20:18:36.1000774Z Submodule path 'third-party/googletest': checked out 'e2239ee6043f73722e7aa812a459f54a28552929'
2025-03-21T20:18:36.4625693Z From https://github.com/leetal/ios-cmake
2025-03-21T20:18:36.4626290Z  * branch            06465b27698424cf4a04a5ca4904d50a3c966c45 -> FETCH_HEAD
2025-03-21T20:18:36.4697119Z Submodule path 'third-party/ios-cmake': checked out '06465b27698424cf4a04a5ca4904d50a3c966c45'
2025-03-21T20:18:36.4780236Z Submodule path 'third-party/pocketfft': checked out '0fa0ef591e38c2758e3184c6c23e497b9f732ffa'
2025-03-21T20:18:38.3441394Z From https://github.com/facebook/buck2-prelude
2025-03-21T20:18:38.3441935Z  * branch            851d3f09c452937fc5adef27e2c50f7f304f1646 -> FETCH_HEAD
2025-03-21T20:18:38.4178739Z Submodule path 'third-party/prelude': checked out '851d3f09c452937fc5adef27e2c50f7f304f1646'
2025-03-21T20:18:38.9466361Z From https://github.com/pybind/pybind11
2025-03-21T20:18:38.9466875Z  * branch            a2e59f0e7065404b44dfe92a28aca47ba1378dc4 -> FETCH_HEAD
2025-03-21T20:18:38.9727204Z Submodule path 'third-party/pybind11': checked out 'a2e59f0e7065404b44dfe92a28aca47ba1378dc4'
2025-03-21T20:18:38.9742175Z [command]/usr/bin/git submodule foreach git config --local gc.auto 0
2025-03-21T20:18:38.9988207Z Entering 'backends/arm/third-party/ethos-u-core-driver'
2025-03-21T20:18:39.0012536Z Entering 'backends/arm/third-party/serialization_lib'
2025-03-21T20:18:39.0036676Z Entering 'backends/cadence/utils/FACTO'
2025-03-21T20:18:39.0061262Z Entering 'backends/vulkan/third-party/Vulkan-Headers'
2025-03-21T20:18:39.0085868Z Entering 'backends/vulkan/third-party/VulkanMemoryAllocator'
2025-03-21T20:18:39.0111215Z Entering 'backends/vulkan/third-party/volk'
2025-03-21T20:18:39.0136024Z Entering 'backends/xnnpack/third-party/FP16'
2025-03-21T20:18:39.0159513Z Entering 'backends/xnnpack/third-party/FXdiv'
2025-03-21T20:18:39.0183108Z Entering 'backends/xnnpack/third-party/XNNPACK'
2025-03-21T20:18:39.0206768Z Entering 'backends/xnnpack/third-party/cpuinfo'
2025-03-21T20:18:39.0230048Z Entering 'backends/xnnpack/third-party/pthreadpool'
2025-03-21T20:18:39.0253849Z Entering 'extension/llm/tokenizers'
2025-03-21T20:18:39.0277169Z Entering 'kernels/optimized/third-party/eigen'
2025-03-21T20:18:39.0300930Z Entering 'shim'
2025-03-21T20:18:39.0324857Z Entering 'third-party/ao'
2025-03-21T20:18:39.0348539Z Entering 'third-party/flatbuffers'
2025-03-21T20:18:39.0371861Z Entering 'third-party/flatcc'
2025-03-21T20:18:39.0395099Z Entering 'third-party/gflags'
2025-03-21T20:18:39.0418814Z Entering 'third-party/googletest'
2025-03-21T20:18:39.0442627Z Entering 'third-party/ios-cmake'
2025-03-21T20:18:39.0465941Z Entering 'third-party/pocketfft'
2025-03-21T20:18:39.0490093Z Entering 'third-party/prelude'
2025-03-21T20:18:39.0515425Z Entering 'third-party/pybind11'
2025-03-21T20:18:39.0548203Z ##[endgroup]
2025-03-21T20:18:39.0548711Z ##[group]Persisting credentials for submodules
2025-03-21T20:18:39.0555660Z [command]/usr/bin/git submodule foreach --recursive sh -c "git config --local --name-only --get-regexp 'url\.https\:\/\/github\.com\/\.insteadOf' && git config --local --unset-all 'url.https://github.com/.insteadOf' || :"
2025-03-21T20:18:39.0800468Z Entering 'backends/arm/third-party/ethos-u-core-driver'
2025-03-21T20:18:39.0849524Z Entering 'backends/arm/third-party/serialization_lib'
2025-03-21T20:18:39.0897517Z Entering 'backends/cadence/utils/FACTO'
2025-03-21T20:18:39.0946675Z Entering 'backends/vulkan/third-party/Vulkan-Headers'
2025-03-21T20:18:39.0995104Z Entering 'backends/vulkan/third-party/VulkanMemoryAllocator'
2025-03-21T20:18:39.1043671Z Entering 'backends/vulkan/third-party/volk'
2025-03-21T20:18:39.1091937Z Entering 'backends/xnnpack/third-party/FP16'
2025-03-21T20:18:39.1140825Z Entering 'backends/xnnpack/third-party/FXdiv'
2025-03-21T20:18:39.1189496Z Entering 'backends/xnnpack/third-party/XNNPACK'
2025-03-21T20:18:39.1254208Z Entering 'backends/xnnpack/third-party/cpuinfo'
2025-03-21T20:18:39.1303373Z Entering 'backends/xnnpack/third-party/pthreadpool'
2025-03-21T20:18:39.1352578Z Entering 'extension/llm/tokenizers'
2025-03-21T20:18:39.1401240Z Entering 'kernels/optimized/third-party/eigen'
2025-03-21T20:18:39.1452194Z Entering 'shim'
2025-03-21T20:18:39.1500701Z Entering 'third-party/ao'
2025-03-21T20:18:39.1550106Z Entering 'third-party/flatbuffers'
2025-03-21T20:18:39.1600572Z Entering 'third-party/flatcc'
2025-03-21T20:18:39.1648989Z Entering 'third-party/gflags'
2025-03-21T20:18:39.1697171Z Entering 'third-party/googletest'
2025-03-21T20:18:39.1749447Z Entering 'third-party/ios-cmake'
2025-03-21T20:18:39.1797115Z Entering 'third-party/pocketfft'
2025-03-21T20:18:39.1846273Z Entering 'third-party/prelude'
2025-03-21T20:18:39.1895973Z Entering 'third-party/pybind11'
2025-03-21T20:18:39.1956733Z [command]/usr/bin/git submodule foreach sh -c "git config --local 'http.https://github.com/.extraheader' 'AUTHORIZATION: basic ***' && git config --local --show-origin --name-only --get-regexp remote.origin.url"
2025-03-21T20:18:39.2201208Z Entering 'backends/arm/third-party/ethos-u-core-driver'
2025-03-21T20:18:39.2247465Z file:/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/.git/modules/backends/arm/third-party/ethos-u-core-driver/config	remote.origin.url
2025-03-21T20:18:39.2248574Z Entering 'backends/arm/third-party/serialization_lib'
2025-03-21T20:18:39.2294213Z file:/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/.git/modules/backends/arm/third-party/serialization_lib/config	remote.origin.url
2025-03-21T20:18:39.2295411Z Entering 'backends/cadence/utils/FACTO'
2025-03-21T20:18:39.2341190Z file:/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/.git/modules/backends/cadence/utils/FACTO/config	remote.origin.url
2025-03-21T20:18:39.2342481Z Entering 'backends/vulkan/third-party/Vulkan-Headers'
2025-03-21T20:18:39.2387665Z file:/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/.git/modules/backends/vulkan/third-party/Vulkan-Headers/config	remote.origin.url
2025-03-21T20:18:39.2388905Z Entering 'backends/vulkan/third-party/VulkanMemoryAllocator'
2025-03-21T20:18:39.2434960Z file:/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/.git/modules/backends/vulkan/third-party/VulkanMemoryAllocator/config	remote.origin.url
2025-03-21T20:18:39.2436067Z Entering 'backends/vulkan/third-party/volk'
2025-03-21T20:18:39.2481829Z file:/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/.git/modules/backends/vulkan/third-party/volk/config	remote.origin.url
2025-03-21T20:18:39.2483055Z Entering 'backends/xnnpack/third-party/FP16'
2025-03-21T20:18:39.2527910Z file:/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/.git/modules/backends/xnnpack/third-party/FP16/config	remote.origin.url
2025-03-21T20:18:39.2529224Z Entering 'backends/xnnpack/third-party/FXdiv'
2025-03-21T20:18:39.2575485Z file:/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/.git/modules/backends/xnnpack/third-party/FXdiv/config	remote.origin.url
2025-03-21T20:18:39.2576596Z Entering 'backends/xnnpack/third-party/XNNPACK'
2025-03-21T20:18:39.2621626Z file:/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/.git/modules/backends/xnnpack/third-party/XNNPACK/config	remote.origin.url
2025-03-21T20:18:39.2622688Z Entering 'backends/xnnpack/third-party/cpuinfo'
2025-03-21T20:18:39.2669360Z file:/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/.git/modules/backends/xnnpack/third-party/cpuinfo/config	remote.origin.url
2025-03-21T20:18:39.2670585Z Entering 'backends/xnnpack/third-party/pthreadpool'
2025-03-21T20:18:39.2716540Z file:/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/.git/modules/backends/xnnpack/third-party/pthreadpool/config	remote.origin.url
2025-03-21T20:18:39.2717543Z Entering 'extension/llm/tokenizers'
2025-03-21T20:18:39.2762577Z file:/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/.git/modules/extension/llm/tokenizers/config	remote.origin.url
2025-03-21T20:18:39.2763761Z Entering 'kernels/optimized/third-party/eigen'
2025-03-21T20:18:39.2808744Z file:/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/.git/modules/kernels/optimized/third-party/eigen/config	remote.origin.url
2025-03-21T20:18:39.2809658Z Entering 'shim'
2025-03-21T20:18:39.2854446Z file:/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/.git/modules/shim/config	remote.origin.url
2025-03-21T20:18:39.2855545Z Entering 'third-party/ao'
2025-03-21T20:18:39.2900374Z file:/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/.git/modules/third-party/ao/config	remote.origin.url
2025-03-21T20:18:39.2901423Z Entering 'third-party/flatbuffers'
2025-03-21T20:18:39.2947811Z file:/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/.git/modules/third-party/flatbuffers/config	remote.origin.url
2025-03-21T20:18:39.2948909Z Entering 'third-party/flatcc'
2025-03-21T20:18:39.2994053Z file:/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/.git/modules/third-party/flatcc/config	remote.origin.url
2025-03-21T20:18:39.2995182Z Entering 'third-party/gflags'
2025-03-21T20:18:39.3040492Z file:/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/.git/modules/third-party/gflags/config	remote.origin.url
2025-03-21T20:18:39.3041658Z Entering 'third-party/googletest'
2025-03-21T20:18:39.3087085Z file:/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/.git/modules/third-party/googletest/config	remote.origin.url
2025-03-21T20:18:39.3088116Z Entering 'third-party/ios-cmake'
2025-03-21T20:18:39.3135495Z file:/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/.git/modules/third-party/ios-cmake/config	remote.origin.url
2025-03-21T20:18:39.3136300Z Entering 'third-party/pocketfft'
2025-03-21T20:18:39.3181670Z file:/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/.git/modules/third-party/pocketfft/config	remote.origin.url
2025-03-21T20:18:39.3182894Z Entering 'third-party/prelude'
2025-03-21T20:18:39.3227676Z file:/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/.git/modules/third-party/prelude/config	remote.origin.url
2025-03-21T20:18:39.3228858Z Entering 'third-party/pybind11'
2025-03-21T20:18:39.3275280Z file:/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/.git/modules/third-party/pybind11/config	remote.origin.url
2025-03-21T20:18:39.3440212Z [command]/usr/bin/git submodule foreach git config --local --add 'url.https://github.com/.insteadOf' 'git@github.com:'
2025-03-21T20:18:39.3684344Z Entering 'backends/arm/third-party/ethos-u-core-driver'
2025-03-21T20:18:39.3708217Z Entering 'backends/arm/third-party/serialization_lib'
2025-03-21T20:18:39.3731439Z Entering 'backends/cadence/utils/FACTO'
2025-03-21T20:18:39.3755439Z Entering 'backends/vulkan/third-party/Vulkan-Headers'
2025-03-21T20:18:39.3779101Z Entering 'backends/vulkan/third-party/VulkanMemoryAllocator'
2025-03-21T20:18:39.3802659Z Entering 'backends/vulkan/third-party/volk'
2025-03-21T20:18:39.3825844Z Entering 'backends/xnnpack/third-party/FP16'
2025-03-21T20:18:39.3849408Z Entering 'backends/xnnpack/third-party/FXdiv'
2025-03-21T20:18:39.3873027Z Entering 'backends/xnnpack/third-party/XNNPACK'
2025-03-21T20:18:39.3896416Z Entering 'backends/xnnpack/third-party/cpuinfo'
2025-03-21T20:18:39.3919640Z Entering 'backends/xnnpack/third-party/pthreadpool'
2025-03-21T20:18:39.3943032Z Entering 'extension/llm/tokenizers'
2025-03-21T20:18:39.3966925Z Entering 'kernels/optimized/third-party/eigen'
2025-03-21T20:18:39.3990210Z Entering 'shim'
2025-03-21T20:18:39.4013448Z Entering 'third-party/ao'
2025-03-21T20:18:39.4036687Z Entering 'third-party/flatbuffers'
2025-03-21T20:18:39.4059813Z Entering 'third-party/flatcc'
2025-03-21T20:18:39.4083035Z Entering 'third-party/gflags'
2025-03-21T20:18:39.4105960Z Entering 'third-party/googletest'
2025-03-21T20:18:39.4128824Z Entering 'third-party/ios-cmake'
2025-03-21T20:18:39.4152065Z Entering 'third-party/pocketfft'
2025-03-21T20:18:39.4175892Z Entering 'third-party/prelude'
2025-03-21T20:18:39.4198744Z Entering 'third-party/pybind11'
2025-03-21T20:18:39.4233729Z [command]/usr/bin/git submodule foreach git config --local --add 'url.https://github.com/.insteadOf' 'org-21003710@github.com:'
2025-03-21T20:18:39.4477601Z Entering 'backends/arm/third-party/ethos-u-core-driver'
2025-03-21T20:18:39.4502063Z Entering 'backends/arm/third-party/serialization_lib'
2025-03-21T20:18:39.4526023Z Entering 'backends/cadence/utils/FACTO'
2025-03-21T20:18:39.4551157Z Entering 'backends/vulkan/third-party/Vulkan-Headers'
2025-03-21T20:18:39.4576278Z Entering 'backends/vulkan/third-party/VulkanMemoryAllocator'
2025-03-21T20:18:39.4601188Z Entering 'backends/vulkan/third-party/volk'
2025-03-21T20:18:39.4625252Z Entering 'backends/xnnpack/third-party/FP16'
2025-03-21T20:18:39.4649498Z Entering 'backends/xnnpack/third-party/FXdiv'
2025-03-21T20:18:39.4673506Z Entering 'backends/xnnpack/third-party/XNNPACK'
2025-03-21T20:18:39.4697951Z Entering 'backends/xnnpack/third-party/cpuinfo'
2025-03-21T20:18:39.4722002Z Entering 'backends/xnnpack/third-party/pthreadpool'
2025-03-21T20:18:39.4746544Z Entering 'extension/llm/tokenizers'
2025-03-21T20:18:39.4770399Z Entering 'kernels/optimized/third-party/eigen'
2025-03-21T20:18:39.4794117Z Entering 'shim'
2025-03-21T20:18:39.4817814Z Entering 'third-party/ao'
2025-03-21T20:18:39.4841521Z Entering 'third-party/flatbuffers'
2025-03-21T20:18:39.4865208Z Entering 'third-party/flatcc'
2025-03-21T20:18:39.4889124Z Entering 'third-party/gflags'
2025-03-21T20:18:39.4912585Z Entering 'third-party/googletest'
2025-03-21T20:18:39.4936380Z Entering 'third-party/ios-cmake'
2025-03-21T20:18:39.4959877Z Entering 'third-party/pocketfft'
2025-03-21T20:18:39.4984039Z Entering 'third-party/prelude'
2025-03-21T20:18:39.5007472Z Entering 'third-party/pybind11'
2025-03-21T20:18:39.5038412Z ##[endgroup]
2025-03-21T20:18:39.5069794Z [command]/usr/bin/git log -1 --format=%H
2025-03-21T20:18:39.5088966Z be92d7d85cb7081ac0a544036da4096a4efa33a8
2025-03-21T20:18:39.5271570Z Prepare all required actions
2025-03-21T20:18:39.5272083Z Getting action download info
2025-03-21T20:18:39.6224601Z Download action repository 'nick-fields/retry@v3.0.0' (SHA:7152eba30c6575329ac0576536151aca5a72780e)
2025-03-21T20:18:39.7841195Z ##[group]Run ./test-infra/.github/actions/calculate-docker-image
2025-03-21T20:18:39.7841595Z with:
2025-03-21T20:18:39.7841867Z   docker-image-name: executorch-ubuntu-22.04-qnn-sdk
2025-03-21T20:18:39.7842242Z   docker-build-dir: .ci/docker
2025-03-21T20:18:39.7842544Z   working-directory: pytorch/executorch
2025-03-21T20:18:39.7842952Z   docker-registry: 308535385114.dkr.ecr.us-east-1.amazonaws.com
2025-03-21T20:18:39.7843373Z   force-push: false
2025-03-21T20:18:39.7843619Z env:
2025-03-21T20:18:39.7843874Z   DOCKER_IMAGE: executorch-ubuntu-22.04-qnn-sdk
2025-03-21T20:18:39.7844239Z   REPOSITORY: pytorch/executorch
2025-03-21T20:18:39.7844533Z   PR_NUMBER: 
2025-03-21T20:18:39.7847596Z   SCRIPT: # The generic Linux job chooses to use base env, not the one setup by the image
CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
conda activate "${CONDA_ENV}"

DTYPE=fp32
BUILD_TOOL="cmake"
MODE=qnn
PT2E_QUANTIZE=qnn_16a16w

./install_requirements.sh --use-pt-pinned-commit
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh

# Setup executorch
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "${BUILD_TOOL}"
# Install requirements for export_llama
PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
# Test llama2
PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh -model stories110M -build_tool "${BUILD_TOOL}" -mode "${MODE}" -dtype "${DTYPE}" -pt2e_quantize "${PT2E_QUANTIZE}"

2025-03-21T20:18:39.7850949Z   RUNNER_ARTIFACT_DIR: /home/ec2-user/actions-runner/_work/_temp/artifacts
2025-03-21T20:18:39.7851533Z   RUNNER_TEST_RESULTS_DIR: /home/ec2-user/actions-runner/_work/_temp/test-results
2025-03-21T20:18:39.7852083Z   RUNNER_DOCS_DIR: /home/ec2-user/actions-runner/_work/_temp/docs
2025-03-21T20:18:39.7852589Z ##[endgroup]
2025-03-21T20:18:39.7875184Z ##[group]Run set -ex
2025-03-21T20:18:39.7875511Z set -ex
2025-03-21T20:18:39.7875735Z 
2025-03-21T20:18:39.7876135Z # If the docker build directory or the build script doesn't exist, the action will
2025-03-21T20:18:39.7876803Z # gracefully return the docker image name as it is.  Pulling docker image in Linux
2025-03-21T20:18:39.7877377Z # job could then download the pre-built image as usual
2025-03-21T20:18:39.7877898Z if [[ ! -d "${DOCKER_BUILD_DIR}" ]] || [[ ! -f "${DOCKER_BUILD_DIR}/build.sh" ]]; then
2025-03-21T20:18:39.7878372Z   echo "skip=true" >> "${GITHUB_OUTPUT}"
2025-03-21T20:18:39.7878814Z   echo "docker-image=${DOCKER_IMAGE_NAME}" >> "${GITHUB_OUTPUT}"
2025-03-21T20:18:39.7879231Z 
2025-03-21T20:18:39.7879601Z   echo "There is no Docker build script in ${REPO_NAME} repo, skipping..."
2025-03-21T20:18:39.7880060Z   exit 0
2025-03-21T20:18:39.7880300Z else
2025-03-21T20:18:39.7880559Z   echo "skip=false" >> "${GITHUB_OUTPUT}"
2025-03-21T20:18:39.7880895Z fi
2025-03-21T20:18:39.7881115Z 
2025-03-21T20:18:39.7881460Z if [[ "${DOCKER_IMAGE_NAME}" == *"${DOCKER_REGISTRY}/${REPO_NAME}"* ]]; then
2025-03-21T20:18:39.7882058Z   # The docker image name already includes the ECR prefix and tag, so we can just
2025-03-21T20:18:39.7882595Z   # use it as it is, but first let's extract the tag
2025-03-21T20:18:39.7883069Z   DOCKER_TAG=$(echo "${DOCKER_IMAGE_NAME}" | awk -F '[:,]' '{print $2}')
2025-03-21T20:18:39.7883578Z   echo "docker-tag=${DOCKER_TAG}" >> "${GITHUB_OUTPUT}"
2025-03-21T20:18:39.7884072Z   echo "docker-image=${DOCKER_IMAGE_NAME}" >> "${GITHUB_OUTPUT}"
2025-03-21T20:18:39.7884482Z else
2025-03-21T20:18:39.7884958Z   DOCKER_TAG=$(git rev-parse HEAD:"${DOCKER_BUILD_DIR}")
2025-03-21T20:18:39.7885436Z   echo "docker-tag=${DOCKER_TAG}" >> "${GITHUB_OUTPUT}"
2025-03-21T20:18:39.7886062Z   echo "docker-image=${DOCKER_REGISTRY}/${REPO_NAME}/${DOCKER_IMAGE_NAME}:${DOCKER_TAG}" >> "${GITHUB_OUTPUT}"
2025-03-21T20:18:39.7886633Z fi
2025-03-21T20:18:39.7892244Z shell: /usr/bin/bash --noprofile --norc -e -o pipefail {0}
2025-03-21T20:18:39.7892627Z env:
2025-03-21T20:18:39.7892898Z   DOCKER_IMAGE: executorch-ubuntu-22.04-qnn-sdk
2025-03-21T20:18:39.7893268Z   REPOSITORY: pytorch/executorch
2025-03-21T20:18:39.7893553Z   PR_NUMBER: 
2025-03-21T20:18:39.7896604Z   SCRIPT: # The generic Linux job chooses to use base env, not the one setup by the image
CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
conda activate "${CONDA_ENV}"

DTYPE=fp32
BUILD_TOOL="cmake"
MODE=qnn
PT2E_QUANTIZE=qnn_16a16w

./install_requirements.sh --use-pt-pinned-commit
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh

# Setup executorch
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "${BUILD_TOOL}"
# Install requirements for export_llama
PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
# Test llama2
PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh -model stories110M -build_tool "${BUILD_TOOL}" -mode "${MODE}" -dtype "${DTYPE}" -pt2e_quantize "${PT2E_QUANTIZE}"

2025-03-21T20:18:39.7899830Z   RUNNER_ARTIFACT_DIR: /home/ec2-user/actions-runner/_work/_temp/artifacts
2025-03-21T20:18:39.7900420Z   RUNNER_TEST_RESULTS_DIR: /home/ec2-user/actions-runner/_work/_temp/test-results
2025-03-21T20:18:39.7900963Z   RUNNER_DOCS_DIR: /home/ec2-user/actions-runner/_work/_temp/docs
2025-03-21T20:18:39.7901372Z   REPO_NAME: executorch
2025-03-21T20:18:39.7901695Z   DOCKER_IMAGE_NAME: executorch-ubuntu-22.04-qnn-sdk
2025-03-21T20:18:39.7902074Z   DOCKER_BUILD_DIR: .ci/docker
2025-03-21T20:18:39.7902461Z   DOCKER_REGISTRY: 308535385114.dkr.ecr.us-east-1.amazonaws.com
2025-03-21T20:18:39.7902920Z ##[endgroup]
2025-03-21T20:18:39.7926408Z + [[ ! -d .ci/docker ]]
2025-03-21T20:18:39.7926717Z + [[ ! -f .ci/docker/build.sh ]]
2025-03-21T20:18:39.7927011Z + echo skip=false
2025-03-21T20:18:39.7927549Z + [[ executorch-ubuntu-22.04-qnn-sdk == *\3\0\8\5\3\5\3\8\5\1\1\4\.\d\k\r\.\e\c\r\.\u\s\-\e\a\s\t\-\1\.\a\m\a\z\o\n\a\w\s\.\c\o\m\/\e\x\e\c\u\t\o\r\c\h* ]]
2025-03-21T20:18:39.7933458Z ++ git rev-parse HEAD:.ci/docker
2025-03-21T20:18:39.7947217Z + DOCKER_TAG=2abd9b1bd42f655b7d130222db4a0cdbc04da8a4
2025-03-21T20:18:39.7947693Z + echo docker-tag=2abd9b1bd42f655b7d130222db4a0cdbc04da8a4
2025-03-21T20:18:39.7948528Z + echo docker-image=308535385114.dkr.ecr.us-east-1.amazonaws.com/executorch/executorch-ubuntu-22.04-qnn-sdk:2abd9b1bd42f655b7d130222db4a0cdbc04da8a4
2025-03-21T20:18:39.7977894Z ##[group]Run set +e
2025-03-21T20:18:39.7978236Z set +e
2025-03-21T20:18:39.7978476Z set -x
2025-03-21T20:18:39.7978722Z 
2025-03-21T20:18:39.7978945Z login() {
2025-03-21T20:18:39.7979427Z   aws ecr get-login-password --region us-east-1 | docker login -u AWS --password-stdin "$1"
2025-03-21T20:18:39.7979950Z }
2025-03-21T20:18:39.7980167Z 
2025-03-21T20:18:39.7980390Z retry () {
2025-03-21T20:18:39.7980666Z   $*  || (sleep 1 && $*) || (sleep 2 && $*)
2025-03-21T20:18:39.7980977Z }
2025-03-21T20:18:39.7981197Z 
2025-03-21T20:18:39.7981439Z retry login "${DOCKER_REGISTRY}"
2025-03-21T20:18:39.7981754Z 
2025-03-21T20:18:39.7981972Z START_TIME=$(date +%s)
2025-03-21T20:18:39.7982273Z # Wait up to 120 minutes
2025-03-21T20:18:39.7982644Z while [[ $(( $(date +%s) - 7200 )) -lt $START_TIME ]]; do
2025-03-21T20:18:39.7983141Z   # Check if image already exists, if it does then skip building it
2025-03-21T20:18:39.7983763Z   if docker manifest inspect "${DOCKER_IMAGE}"; then
2025-03-21T20:18:39.7984146Z     exit 0
2025-03-21T20:18:39.7984381Z   fi
2025-03-21T20:18:39.7984607Z 
2025-03-21T20:18:39.7984996Z   # NB: This flag is used by Docker build workflow to push the image to ECR, so we can
2025-03-21T20:18:39.7985660Z   # use this to differentiate between the Docker build and regular build jobs. For the
2025-03-21T20:18:39.7986324Z   # latter, it will wait for the Docker images to become available before continuing
2025-03-21T20:18:39.7986853Z   if [ "${DOCKER_PUSH:-false}" == "true" ]; then
2025-03-21T20:18:39.7987248Z     # It's a Docker build job, let's build the image
2025-03-21T20:18:39.7987611Z     break
2025-03-21T20:18:39.7987856Z   else
2025-03-21T20:18:39.7988205Z     # It's a regular build job, wait for the image to become available
2025-03-21T20:18:39.7988625Z     sleep 300
2025-03-21T20:18:39.7988870Z   fi
2025-03-21T20:18:39.7989109Z done
2025-03-21T20:18:39.7989334Z 
2025-03-21T20:18:39.7989696Z # NB: This part requires a full checkout. Otherwise, the merge base will
2025-03-21T20:18:39.7990268Z # be empty.  The default action would be to continue rebuild the image
2025-03-21T20:18:39.7990789Z if [[ "$BASE_REVISION" = "$(git rev-parse HEAD)" ]]; then
2025-03-21T20:18:39.7991236Z   # if we're on the base branch then use the parent commit
2025-03-21T20:18:39.7991645Z   MERGE_BASE=$(git rev-parse HEAD~)
2025-03-21T20:18:39.7991969Z else
2025-03-21T20:18:39.7992303Z   # otherwise we're on a PR, so use the most recent base commit
2025-03-21T20:18:39.7992781Z   MERGE_BASE=$(git merge-base HEAD "$BASE_REVISION")
2025-03-21T20:18:39.7993143Z fi
2025-03-21T20:18:39.7993372Z 
2025-03-21T20:18:39.7993615Z if [[ -z "${MERGE_BASE}" ]]; then
2025-03-21T20:18:39.7993984Z   echo "rebuild=true" >> "${GITHUB_OUTPUT}"
2025-03-21T20:18:39.7994416Z 
2025-03-21T20:18:39.7994885Z   echo "Finding merge base only works with full checkout, please set fetch-depth to 0, continuing ..."
2025-03-21T20:18:39.7995425Z   exit 0
2025-03-21T20:18:39.7995663Z fi
2025-03-21T20:18:39.7995883Z 
2025-03-21T20:18:39.7996198Z if ! git rev-parse "${MERGE_BASE}:${DOCKER_BUILD_DIR}"; then
2025-03-21T20:18:39.7996876Z   echo "Directory '${DOCKER_BUILD_DIR}' not found in commit $MERGE_BASE, you should rebase onto a more recent commit"
2025-03-21T20:18:39.7997445Z   exit 1
2025-03-21T20:18:39.7997677Z fi
2025-03-21T20:18:39.7997897Z 
2025-03-21T20:18:39.7998262Z PREVIOUS_DOCKER_TAG=$(git rev-parse "${MERGE_BASE}:${DOCKER_BUILD_DIR}")
2025-03-21T20:18:39.7998913Z # If no image exists but the hash is the same as the previous hash then we should error out here
2025-03-21T20:18:39.7999509Z if [[ "${PREVIOUS_DOCKER_TAG}" == "${DOCKER_TAG}" ]]; then
2025-03-21T20:18:39.8000176Z   echo "WARNING: Something has gone wrong and the previous image isn't available for the merge-base of your branch"
2025-03-21T20:18:39.8000933Z   echo "         Will re-build docker image to store in local cache, TTS may be longer"
2025-03-21T20:18:39.8001391Z fi
2025-03-21T20:18:39.8001615Z 
2025-03-21T20:18:39.8001883Z echo "rebuild=true" >> "${GITHUB_OUTPUT}"
2025-03-21T20:18:39.8007143Z shell: /usr/bin/bash --noprofile --norc -e -o pipefail {0}
2025-03-21T20:18:39.8007535Z env:
2025-03-21T20:18:39.8008180Z   DOCKER_IMAGE: 308535385114.dkr.ecr.us-east-1.amazonaws.com/executorch/executorch-ubuntu-22.04-qnn-sdk:2abd9b1bd42f655b7d130222db4a0cdbc04da8a4
2025-03-21T20:18:39.8008934Z   REPOSITORY: pytorch/executorch
2025-03-21T20:18:39.8009331Z   PR_NUMBER: 
2025-03-21T20:18:39.8012458Z   SCRIPT: # The generic Linux job chooses to use base env, not the one setup by the image
CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
conda activate "${CONDA_ENV}"

DTYPE=fp32
BUILD_TOOL="cmake"
MODE=qnn
PT2E_QUANTIZE=qnn_16a16w

./install_requirements.sh --use-pt-pinned-commit
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh

# Setup executorch
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "${BUILD_TOOL}"
# Install requirements for export_llama
PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
# Test llama2
PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh -model stories110M -build_tool "${BUILD_TOOL}" -mode "${MODE}" -dtype "${DTYPE}" -pt2e_quantize "${PT2E_QUANTIZE}"

2025-03-21T20:18:39.8015679Z   RUNNER_ARTIFACT_DIR: /home/ec2-user/actions-runner/_work/_temp/artifacts
2025-03-21T20:18:39.8016265Z   RUNNER_TEST_RESULTS_DIR: /home/ec2-user/actions-runner/_work/_temp/test-results
2025-03-21T20:18:39.8016828Z   RUNNER_DOCS_DIR: /home/ec2-user/actions-runner/_work/_temp/docs
2025-03-21T20:18:39.8017228Z   DOCKER_BUILD_DIR: .ci/docker
2025-03-21T20:18:39.8017568Z   BASE_REVISION: be92d7d85cb7081ac0a544036da4096a4efa33a8
2025-03-21T20:18:39.8017984Z   DOCKER_TAG: 2abd9b1bd42f655b7d130222db4a0cdbc04da8a4
2025-03-21T20:18:39.8018430Z   DOCKER_REGISTRY: 308535385114.dkr.ecr.us-east-1.amazonaws.com
2025-03-21T20:18:39.8018826Z   DOCKER_PUSH: 
2025-03-21T20:18:39.8019051Z ##[endgroup]
2025-03-21T20:18:39.8041307Z + retry login 308535385114.dkr.ecr.us-east-1.amazonaws.com
2025-03-21T20:18:39.8041791Z + login 308535385114.dkr.ecr.us-east-1.amazonaws.com
2025-03-21T20:18:39.8044277Z + aws ecr get-login-password --region us-east-1
2025-03-21T20:18:39.8045113Z + docker login -u AWS --password-stdin 308535385114.dkr.ecr.us-east-1.amazonaws.com
2025-03-21T20:18:40.3054611Z WARNING! Your password will be stored unencrypted in /home/ec2-user/.docker/config.json.
2025-03-21T20:18:40.3055443Z Configure a credential helper to remove this warning. See
2025-03-21T20:18:40.3056327Z https://docs.docker.com/engine/reference/commandline/login/#credentials-store
2025-03-21T20:18:40.3057163Z 
2025-03-21T20:18:40.3057318Z Login Succeeded
2025-03-21T20:18:40.3069139Z ++ date +%s
2025-03-21T20:18:40.3077307Z + START_TIME=1742588320
2025-03-21T20:18:40.3080229Z ++ date +%s
2025-03-21T20:18:40.3089627Z + [[ 1742581120 -lt 1742588320 ]]
2025-03-21T20:18:40.3090737Z + docker manifest inspect 308535385114.dkr.ecr.us-east-1.amazonaws.com/executorch/executorch-ubuntu-22.04-qnn-sdk:2abd9b1bd42f655b7d130222db4a0cdbc04da8a4
2025-03-21T20:18:40.5131435Z {
2025-03-21T20:18:40.5131893Z 	"schemaVersion": 2,
2025-03-21T20:18:40.5132684Z 	"mediaType": "application/vnd.docker.distribution.manifest.v2+json",
2025-03-21T20:18:40.5133371Z 	"config": {
2025-03-21T20:18:40.5133899Z 		"mediaType": "application/vnd.docker.container.image.v1+json",
2025-03-21T20:18:40.5134588Z 		"size": 15116,
2025-03-21T20:18:40.5135324Z 		"digest": "sha256:a30343f4b72f0dce49d6d4823ed055cd99145a3bc06228740f811eb1decc1863"
2025-03-21T20:18:40.5136189Z 	},
2025-03-21T20:18:40.5136528Z 	"layers": [
2025-03-21T20:18:40.5136839Z 		{
2025-03-21T20:18:40.5137334Z 			"mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
2025-03-21T20:18:40.5138080Z 			"size": 30440118,
2025-03-21T20:18:40.5138775Z 			"digest": "sha256:8f84a9f2102e97a4a6bf673b150fc9894df5acc9618ad3484c6c36f768c1caa0"
2025-03-21T20:18:40.5139516Z 		},
2025-03-21T20:18:40.5139840Z 		{
2025-03-21T20:18:40.5140327Z 			"mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
2025-03-21T20:18:40.5141019Z 			"size": 632,
2025-03-21T20:18:40.5141757Z 			"digest": "sha256:86e413e13063e43e9840dda1e93f5db4a40e184a756693799c0369fd9d008e6e"
2025-03-21T20:18:40.5142545Z 		},
2025-03-21T20:18:40.5142854Z 		{
2025-03-21T20:18:40.5143334Z 			"mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
2025-03-21T20:18:40.5144027Z 			"size": 157526659,
2025-03-21T20:18:40.5144759Z 			"digest": "sha256:56848936f031f07230bafdc656bc2496665574dc8b02b43ffee6c54b53cf514b"
2025-03-21T20:18:40.5145854Z 		},
2025-03-21T20:18:40.5146228Z 		{
2025-03-21T20:18:40.5146759Z 			"mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
2025-03-21T20:18:40.5147353Z 			"size": 623,
2025-03-21T20:18:40.5147927Z 			"digest": "sha256:261c0f487ad07815c767b360dc3f2b7876eec9795ea5a311db7499b7ca2f1e38"
2025-03-21T20:18:40.5148619Z 		},
2025-03-21T20:18:40.5148925Z 		{
2025-03-21T20:18:40.5149355Z 			"mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
2025-03-21T20:18:40.5149851Z 			"size": 19308800,
2025-03-21T20:18:40.5150290Z 			"digest": "sha256:a3f0567f83ae99b86c52170d45ec5d261f30cf897dba2100e348a19ba11e81b6"
2025-03-21T20:18:40.5150776Z 		},
2025-03-21T20:18:40.5150983Z 		{
2025-03-21T20:18:40.5151309Z 			"mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
2025-03-21T20:18:40.5151730Z 			"size": 737,
2025-03-21T20:18:40.5152162Z 			"digest": "sha256:a0c2fdb93deca15e6e50f0cc2f2b253f65c424a5ba7146fa214b3dabf949e47d"
2025-03-21T20:18:40.5152658Z 		},
2025-03-21T20:18:40.5152880Z 		{
2025-03-21T20:18:40.5153202Z 			"mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
2025-03-21T20:18:40.5153624Z 			"size": 131418191,
2025-03-21T20:18:40.5154047Z 			"digest": "sha256:4e0f8d4747dac663f43c5d2b26132555949337e7cd648644b12ff05b7fdbe750"
2025-03-21T20:18:40.5154519Z 		},
2025-03-21T20:18:40.5154725Z 		{
2025-03-21T20:18:40.5155045Z 			"mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
2025-03-21T20:18:40.5155469Z 			"size": 447,
2025-03-21T20:18:40.5155878Z 			"digest": "sha256:5a102502de33c5d0391cba90688a95c6d138caa80472d8586f51fe199d15e056"
2025-03-21T20:18:40.5156350Z 		},
2025-03-21T20:18:40.5156557Z 		{
2025-03-21T20:18:40.5156880Z 			"mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
2025-03-21T20:18:40.5157300Z 			"size": 104,
2025-03-21T20:18:40.5157708Z 			"digest": "sha256:5d24dc753f042bf098877a7e9c814f22d72e16bf8f4d731e11d707f626d3a716"
2025-03-21T20:18:40.5158178Z 		},
2025-03-21T20:18:40.5158383Z 		{
2025-03-21T20:18:40.5158859Z 			"mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
2025-03-21T20:18:40.5159281Z 			"size": 637,
2025-03-21T20:18:40.5159691Z 			"digest": "sha256:85f4a172d5b6549c71f192713230a09e559248bc692b3c7880a7aeb8cbc8063d"
2025-03-21T20:18:40.5160158Z 		},
2025-03-21T20:18:40.5160363Z 		{
2025-03-21T20:18:40.5160683Z 			"mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
2025-03-21T20:18:40.5161106Z 			"size": 33695150,
2025-03-21T20:18:40.5161537Z 			"digest": "sha256:bb9ad7d84f6e851744d415663cd550e7fffcad904d896f5e5f0c0700cbff5249"
2025-03-21T20:18:40.5162019Z 		},
2025-03-21T20:18:40.5162221Z 		{
2025-03-21T20:18:40.5162543Z 			"mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
2025-03-21T20:18:40.5162977Z 			"size": 319,
2025-03-21T20:18:40.5163387Z 			"digest": "sha256:5120711d46e36360293dc8943ca1ad1310579dc5a9970d1ec6f4f3b3a408ccac"
2025-03-21T20:18:40.5163863Z 		},
2025-03-21T20:18:40.5164068Z 		{
2025-03-21T20:18:40.5164398Z 			"mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
2025-03-21T20:18:40.5164826Z 			"size": 249990691,
2025-03-21T20:18:40.5165252Z 			"digest": "sha256:2d4cecada8b45d3248f175d740425816048bb20527e7369fdaa7250146b3b173"
2025-03-21T20:18:40.5165726Z 		},
2025-03-21T20:18:40.5165936Z 		{
2025-03-21T20:18:40.5166259Z 			"mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
2025-03-21T20:18:40.5166677Z 			"size": 475,
2025-03-21T20:18:40.5167100Z 			"digest": "sha256:e1fd02ccae095d8166d03a3f7af0d5ea3fcc2cb9514e293d10ac0025e3ef3211"
2025-03-21T20:18:40.5167588Z 		},
2025-03-21T20:18:40.5167796Z 		{
2025-03-21T20:18:40.5168121Z 			"mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
2025-03-21T20:18:40.5168545Z 			"size": 1043,
2025-03-21T20:18:40.5168965Z 			"digest": "sha256:508bc8ee650d1222c97006db6a268d90fb07ac31c4c3b84c99c7fc760b02b365"
2025-03-21T20:18:40.5169563Z 		},
2025-03-21T20:18:40.5169772Z 		{
2025-03-21T20:18:40.5170194Z 			"mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
2025-03-21T20:18:40.5170632Z 			"size": 613,
2025-03-21T20:18:40.5171065Z 			"digest": "sha256:6ff1ffcc6d8434dbeeeffcbf49238e47562a299ebd97987c8fb752e47aad7dc0"
2025-03-21T20:18:40.5171561Z 		},
2025-03-21T20:18:40.5171771Z 		{
2025-03-21T20:18:40.5172095Z 			"mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
2025-03-21T20:18:40.5172526Z 			"size": 77562541,
2025-03-21T20:18:40.5172957Z 			"digest": "sha256:6a063300ab4b844689b6c0ae46ce80e0423bae164b62e75ae970c77d4abf0d00"
2025-03-21T20:18:40.5173432Z 		},
2025-03-21T20:18:40.5173641Z 		{
2025-03-21T20:18:40.5173960Z 			"mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
2025-03-21T20:18:40.5174386Z 			"size": 562,
2025-03-21T20:18:40.5174808Z 			"digest": "sha256:fb7c06bc00e5da7a1402ca2017266d38dfbd2144ae151a8f2c9c205c543d5b0a"
2025-03-21T20:18:40.5175286Z 		},
2025-03-21T20:18:40.5175489Z 		{
2025-03-21T20:18:40.5175811Z 			"mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
2025-03-21T20:18:40.5176235Z 			"size": 208,
2025-03-21T20:18:40.5176661Z 			"digest": "sha256:eda4db11af8ffbdc56d01d522c9d47a2ae3730b850b74f7517e30049eb73637e"
2025-03-21T20:18:40.5177153Z 		},
2025-03-21T20:18:40.5177357Z 		{
2025-03-21T20:18:40.5177677Z 			"mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
2025-03-21T20:18:40.5178097Z 			"size": 1189,
2025-03-21T20:18:40.5178524Z 			"digest": "sha256:3cfbc5ff2ac06cf9bffc37a8a7a1578bd7264def9f15522294ac0f325930481b"
2025-03-21T20:18:40.5179015Z 		},
2025-03-21T20:18:40.5179209Z 		{
2025-03-21T20:18:40.5179546Z 			"mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
2025-03-21T20:18:40.5179975Z 			"size": 679,
2025-03-21T20:18:40.5180381Z 			"digest": "sha256:59fe3e9404630f57be5670798e4d94c7767c07a9ca79487e335054f938daf0ba"
2025-03-21T20:18:40.5180854Z 		},
2025-03-21T20:18:40.5181049Z 		{
2025-03-21T20:18:40.5181385Z 			"mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
2025-03-21T20:18:40.5181810Z 			"size": 6839266947,
2025-03-21T20:18:40.5182245Z 			"digest": "sha256:50754bc025fc1de200f32bd74019f345ec85c136d6a09b915c482c98fb5bd8af"
2025-03-21T20:18:40.5182788Z 		},
2025-03-21T20:18:40.5182980Z 		{
2025-03-21T20:18:40.5183318Z 			"mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
2025-03-21T20:18:40.5183738Z 			"size": 1383,
2025-03-21T20:18:40.5184159Z 			"digest": "sha256:db5c552aa08bc175670ba61c1394e4eb8f14e880b54bc9117e45d201a78983d1"
2025-03-21T20:18:40.5184643Z 		},
2025-03-21T20:18:40.5184834Z 		{
2025-03-21T20:18:40.5185173Z 			"mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
2025-03-21T20:18:40.5185592Z 			"size": 679,
2025-03-21T20:18:40.5185999Z 			"digest": "sha256:59fe3e9404630f57be5670798e4d94c7767c07a9ca79487e335054f938daf0ba"
2025-03-21T20:18:40.5186470Z 		},
2025-03-21T20:18:40.5186661Z 		{
2025-03-21T20:18:40.5186993Z 			"mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
2025-03-21T20:18:40.5187419Z 			"size": 230829648,
2025-03-21T20:18:40.5187848Z 			"digest": "sha256:706d7d7c1227085c0cac3515a61ff3c6b82a74c3731770098e9c7daf32e2184e"
2025-03-21T20:18:40.5188327Z 		},
2025-03-21T20:18:40.5188515Z 		{
2025-03-21T20:18:40.5188846Z 			"mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
2025-03-21T20:18:40.5189262Z 			"size": 828,
2025-03-21T20:18:40.5189690Z 			"digest": "sha256:32a4dbb2ef2f3551374be7a84cb414cd30b101c4d3cdfe7c4ddebfe78ea1d939"
2025-03-21T20:18:40.5190174Z 		},
2025-03-21T20:18:40.5190365Z 		{
2025-03-21T20:18:40.5190702Z 			"mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
2025-03-21T20:18:40.5191122Z 			"size": 679,
2025-03-21T20:18:40.5191387Z + exit 0
2025-03-21T20:18:40.5191774Z 			"digest": "sha256:59fe3e9404630f57be5670798e4d94c7767c07a9ca79487e335054f938daf0ba"
2025-03-21T20:18:40.5192241Z 		},
2025-03-21T20:18:40.5192434Z 		{
2025-03-21T20:18:40.5192766Z 			"mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
2025-03-21T20:18:40.5193189Z 			"size": 178598108,
2025-03-21T20:18:40.5193688Z 			"digest": "sha256:242848c50d1a4198b82dd1283e85e8cd8581d6fbccfe9015dc50de6e0340dec9"
2025-03-21T20:18:40.5194169Z 		},
2025-03-21T20:18:40.5194361Z 		{
2025-03-21T20:18:40.5194695Z 			"mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
2025-03-21T20:18:40.5195117Z 			"size": 530,
2025-03-21T20:18:40.5195532Z 			"digest": "sha256:77ba92adb1392840c455cc217ac4fee89f4452db783ce2b4948dc40025a0840a"
2025-03-21T20:18:40.5196008Z 		},
2025-03-21T20:18:40.5196200Z 		{
2025-03-21T20:18:40.5196537Z 			"mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
2025-03-21T20:18:40.5196963Z 			"size": 679,
2025-03-21T20:18:40.5197375Z 			"digest": "sha256:59fe3e9404630f57be5670798e4d94c7767c07a9ca79487e335054f938daf0ba"
2025-03-21T20:18:40.5197845Z 		},
2025-03-21T20:18:40.5198039Z 		{
2025-03-21T20:18:40.5198375Z 			"mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
2025-03-21T20:18:40.5198797Z 			"size": 356,
2025-03-21T20:18:40.5199204Z 			"digest": "sha256:3c65b9b0c07752feb5370318714bc114b717fb4cc8978ee39180b73cb1a03666"
2025-03-21T20:18:40.5199685Z 		},
2025-03-21T20:18:40.5199876Z 		{
2025-03-21T20:18:40.5200209Z 			"mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
2025-03-21T20:18:40.5200629Z 			"size": 32,
2025-03-21T20:18:40.5201048Z 			"digest": "sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1"
2025-03-21T20:18:40.5201546Z 		},
2025-03-21T20:18:40.5201740Z 		{
2025-03-21T20:18:40.5202078Z 			"mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
2025-03-21T20:18:40.5202506Z 			"size": 165,
2025-03-21T20:18:40.5202919Z 			"digest": "sha256:3d39d3c3833d0b35f99be7ef483e33856321f4f469a7fe9d58612f96caf7ab8c"
2025-03-21T20:18:40.5203399Z 		},
2025-03-21T20:18:40.5203593Z 		{
2025-03-21T20:18:40.5203931Z 			"mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
2025-03-21T20:18:40.5204365Z 			"size": 1111,
2025-03-21T20:18:40.5204790Z 			"digest": "sha256:040f4b25fe47bc8918c851025cce90e70d8c7182f8e6bbc984aee16c30b5bd3a"
2025-03-21T20:18:40.5205273Z 		},
2025-03-21T20:18:40.5205537Z 		{
2025-03-21T20:18:40.5205876Z 			"mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
2025-03-21T20:18:40.5206304Z 			"size": 32,
2025-03-21T20:18:40.5206727Z 			"digest": "sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1"
2025-03-21T20:18:40.5207213Z 		},
2025-03-21T20:18:40.5207412Z 		{
2025-03-21T20:18:40.5207751Z 			"mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
2025-03-21T20:18:40.5208173Z 			"size": 108,
2025-03-21T20:18:40.5208586Z 			"digest": "sha256:2ce202d93f2e5871bc44522f1b7c6aab9bf20560c95bd2e9482dbde946b83ff7"
2025-03-21T20:18:40.5209153Z 		}
2025-03-21T20:18:40.5209350Z 	]
2025-03-21T20:18:40.5209556Z }
2025-03-21T20:18:40.5241225Z ##[group]Run set -eux
2025-03-21T20:18:40.5241532Z set -eux
2025-03-21T20:18:40.5242421Z aws secretsmanager get-secret-value --secret-id docker_hub_readonly_token | jq --raw-output '.SecretString' | jq -r .docker_hub_readonly_token | docker login --username pytorchbot --password-stdin
2025-03-21T20:18:40.5248889Z shell: /usr/bin/bash --noprofile --norc -e -o pipefail {0}
2025-03-21T20:18:40.5249368Z env:
2025-03-21T20:18:40.5249652Z   DOCKER_IMAGE: executorch-ubuntu-22.04-qnn-sdk
2025-03-21T20:18:40.5250032Z   REPOSITORY: pytorch/executorch
2025-03-21T20:18:40.5250334Z   PR_NUMBER: 
2025-03-21T20:18:40.5253511Z   SCRIPT: # The generic Linux job chooses to use base env, not the one setup by the image
CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
conda activate "${CONDA_ENV}"

DTYPE=fp32
BUILD_TOOL="cmake"
MODE=qnn
PT2E_QUANTIZE=qnn_16a16w

./install_requirements.sh --use-pt-pinned-commit
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh

# Setup executorch
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "${BUILD_TOOL}"
# Install requirements for export_llama
PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
# Test llama2
PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh -model stories110M -build_tool "${BUILD_TOOL}" -mode "${MODE}" -dtype "${DTYPE}" -pt2e_quantize "${PT2E_QUANTIZE}"

2025-03-21T20:18:40.5256763Z   RUNNER_ARTIFACT_DIR: /home/ec2-user/actions-runner/_work/_temp/artifacts
2025-03-21T20:18:40.5257358Z   RUNNER_TEST_RESULTS_DIR: /home/ec2-user/actions-runner/_work/_temp/test-results
2025-03-21T20:18:40.5257923Z   RUNNER_DOCS_DIR: /home/ec2-user/actions-runner/_work/_temp/docs
2025-03-21T20:18:40.5258328Z ##[endgroup]
2025-03-21T20:18:40.5284806Z + aws secretsmanager get-secret-value --secret-id docker_hub_readonly_token
2025-03-21T20:18:40.5285639Z + jq --raw-output .SecretString
2025-03-21T20:18:40.5287030Z + jq -r .docker_hub_readonly_token
2025-03-21T20:18:40.5288139Z + docker login --username pytorchbot --password-stdin
2025-03-21T20:18:41.0840150Z WARNING! Your password will be stored unencrypted in /home/ec2-user/.docker/config.json.
2025-03-21T20:18:41.0840771Z Configure a credential helper to remove this warning. See
2025-03-21T20:18:41.0841621Z https://docs.docker.com/engine/reference/commandline/login/#credentials-store
2025-03-21T20:18:41.0842346Z 
2025-03-21T20:18:41.0842526Z Login Succeeded
2025-03-21T20:18:41.0923362Z Prepare all required actions
2025-03-21T20:18:41.0960536Z ##[group]Run ./test-infra/.github/actions/pull-docker-image
2025-03-21T20:18:41.0961022Z with:
2025-03-21T20:18:41.0961804Z   docker-image: 308535385114.dkr.ecr.us-east-1.amazonaws.com/executorch/executorch-ubuntu-22.04-qnn-sdk:2abd9b1bd42f655b7d130222db4a0cdbc04da8a4
2025-03-21T20:18:41.0962743Z   docker-registry: 308535385114.dkr.ecr.us-east-1.amazonaws.com
2025-03-21T20:18:41.0963215Z env:
2025-03-21T20:18:41.0963582Z   DOCKER_IMAGE: executorch-ubuntu-22.04-qnn-sdk
2025-03-21T20:18:41.0964048Z   REPOSITORY: pytorch/executorch
2025-03-21T20:18:41.0964414Z   PR_NUMBER: 
2025-03-21T20:18:41.0967694Z   SCRIPT: # The generic Linux job chooses to use base env, not the one setup by the image
CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
conda activate "${CONDA_ENV}"

DTYPE=fp32
BUILD_TOOL="cmake"
MODE=qnn
PT2E_QUANTIZE=qnn_16a16w

./install_requirements.sh --use-pt-pinned-commit
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh

# Setup executorch
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "${BUILD_TOOL}"
# Install requirements for export_llama
PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
# Test llama2
PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh -model stories110M -build_tool "${BUILD_TOOL}" -mode "${MODE}" -dtype "${DTYPE}" -pt2e_quantize "${PT2E_QUANTIZE}"

2025-03-21T20:18:41.0971303Z   RUNNER_ARTIFACT_DIR: /home/ec2-user/actions-runner/_work/_temp/artifacts
2025-03-21T20:18:41.0971969Z   RUNNER_TEST_RESULTS_DIR: /home/ec2-user/actions-runner/_work/_temp/test-results
2025-03-21T20:18:41.0972613Z   RUNNER_DOCS_DIR: /home/ec2-user/actions-runner/_work/_temp/docs
2025-03-21T20:18:41.0973126Z ##[endgroup]
2025-03-21T20:18:41.1004965Z ##[group]Run set -x
2025-03-21T20:18:41.1005255Z set -x
2025-03-21T20:18:41.1005496Z set +e
2025-03-21T20:18:41.1005749Z 
2025-03-21T20:18:41.1005977Z login() {
2025-03-21T20:18:41.1006451Z   aws ecr get-login-password --region us-east-1 | docker login -u AWS --password-stdin "$1"
2025-03-21T20:18:41.1006978Z }
2025-03-21T20:18:41.1007203Z 
2025-03-21T20:18:41.1007427Z retry () {
2025-03-21T20:18:41.1007715Z   $*  || (sleep 1 && $*) || (sleep 2 && $*)
2025-03-21T20:18:41.1008030Z }
2025-03-21T20:18:41.1008247Z 
2025-03-21T20:18:41.1008489Z retry login "${DOCKER_REGISTRY}"
2025-03-21T20:18:41.1008808Z 
2025-03-21T20:18:41.1009026Z set -e
2025-03-21T20:18:41.1009488Z # ignore output since only exit code is used for conditional
2025-03-21T20:18:41.1009984Z # only pull docker image if it's not available locally
2025-03-21T20:18:41.1010539Z if ! docker inspect --type=image "${DOCKER_IMAGE}" >/dev/null 2>/dev/null; then
2025-03-21T20:18:41.1011058Z   retry docker pull "${DOCKER_IMAGE}"
2025-03-21T20:18:41.1011389Z fi
2025-03-21T20:18:41.1017231Z shell: /usr/bin/bash --noprofile --norc -e -o pipefail {0}
2025-03-21T20:18:41.1017604Z env:
2025-03-21T20:18:41.1018259Z   DOCKER_IMAGE: 308535385114.dkr.ecr.us-east-1.amazonaws.com/executorch/executorch-ubuntu-22.04-qnn-sdk:2abd9b1bd42f655b7d130222db4a0cdbc04da8a4
2025-03-21T20:18:41.1019018Z   REPOSITORY: pytorch/executorch
2025-03-21T20:18:41.1019317Z   PR_NUMBER: 
2025-03-21T20:18:41.1022492Z   SCRIPT: # The generic Linux job chooses to use base env, not the one setup by the image
CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
conda activate "${CONDA_ENV}"

DTYPE=fp32
BUILD_TOOL="cmake"
MODE=qnn
PT2E_QUANTIZE=qnn_16a16w

./install_requirements.sh --use-pt-pinned-commit
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh

# Setup executorch
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "${BUILD_TOOL}"
# Install requirements for export_llama
PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
# Test llama2
PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh -model stories110M -build_tool "${BUILD_TOOL}" -mode "${MODE}" -dtype "${DTYPE}" -pt2e_quantize "${PT2E_QUANTIZE}"

2025-03-21T20:18:41.1025721Z   RUNNER_ARTIFACT_DIR: /home/ec2-user/actions-runner/_work/_temp/artifacts
2025-03-21T20:18:41.1026318Z   RUNNER_TEST_RESULTS_DIR: /home/ec2-user/actions-runner/_work/_temp/test-results
2025-03-21T20:18:41.1026880Z   RUNNER_DOCS_DIR: /home/ec2-user/actions-runner/_work/_temp/docs
2025-03-21T20:18:41.1027374Z   DOCKER_REGISTRY: 308535385114.dkr.ecr.us-east-1.amazonaws.com
2025-03-21T20:18:41.1027769Z ##[endgroup]
2025-03-21T20:18:41.1050614Z + set +e
2025-03-21T20:18:41.1050969Z + retry login 308535385114.dkr.ecr.us-east-1.amazonaws.com
2025-03-21T20:18:41.1051607Z + login 308535385114.dkr.ecr.us-east-1.amazonaws.com
2025-03-21T20:18:41.1054011Z + aws ecr get-login-password --region us-east-1
2025-03-21T20:18:41.1055371Z + docker login -u AWS --password-stdin 308535385114.dkr.ecr.us-east-1.amazonaws.com
2025-03-21T20:18:41.5912771Z WARNING! Your password will be stored unencrypted in /home/ec2-user/.docker/config.json.
2025-03-21T20:18:41.5913725Z Configure a credential helper to remove this warning. See
2025-03-21T20:18:41.5914516Z https://docs.docker.com/engine/reference/commandline/login/#credentials-store
2025-03-21T20:18:41.5914905Z 
2025-03-21T20:18:41.5915031Z Login Succeeded
2025-03-21T20:18:41.5924663Z + set -e
2025-03-21T20:18:41.5925450Z + docker inspect --type=image 308535385114.dkr.ecr.us-east-1.amazonaws.com/executorch/executorch-ubuntu-22.04-qnn-sdk:2abd9b1bd42f655b7d130222db4a0cdbc04da8a4
2025-03-21T20:18:41.6028572Z + retry docker pull 308535385114.dkr.ecr.us-east-1.amazonaws.com/executorch/executorch-ubuntu-22.04-qnn-sdk:2abd9b1bd42f655b7d130222db4a0cdbc04da8a4
2025-03-21T20:18:41.6029832Z + docker pull 308535385114.dkr.ecr.us-east-1.amazonaws.com/executorch/executorch-ubuntu-22.04-qnn-sdk:2abd9b1bd42f655b7d130222db4a0cdbc04da8a4
2025-03-21T20:18:41.8138246Z 2abd9b1bd42f655b7d130222db4a0cdbc04da8a4: Pulling from executorch/executorch-ubuntu-22.04-qnn-sdk
2025-03-21T20:18:41.8139898Z 8f84a9f2102e: Pulling fs layer
2025-03-21T20:18:41.8140613Z 86e413e13063: Pulling fs layer
2025-03-21T20:18:41.8141281Z 56848936f031: Pulling fs layer
2025-03-21T20:18:41.8142116Z 261c0f487ad0: Pulling fs layer
2025-03-21T20:18:41.8142507Z a3f0567f83ae: Pulling fs layer
2025-03-21T20:18:41.8142862Z a0c2fdb93dec: Pulling fs layer
2025-03-21T20:18:41.8143172Z 4e0f8d4747da: Pulling fs layer
2025-03-21T20:18:41.8143457Z 261c0f487ad0: Waiting
2025-03-21T20:18:41.8143719Z 5a102502de33: Pulling fs layer
2025-03-21T20:18:41.8143992Z a3f0567f83ae: Waiting
2025-03-21T20:18:41.8144246Z a0c2fdb93dec: Waiting
2025-03-21T20:18:41.8144525Z 4e0f8d4747da: Waiting
2025-03-21T20:18:41.8144812Z 5d24dc753f04: Pulling fs layer
2025-03-21T20:18:41.8145103Z 85f4a172d5b6: Pulling fs layer
2025-03-21T20:18:41.8145412Z bb9ad7d84f6e: Pulling fs layer
2025-03-21T20:18:41.8145690Z 5120711d46e3: Pulling fs layer
2025-03-21T20:18:41.8145967Z 5a102502de33: Waiting
2025-03-21T20:18:41.8146235Z 2d4cecada8b4: Pulling fs layer
2025-03-21T20:18:41.8146529Z e1fd02ccae09: Pulling fs layer
2025-03-21T20:18:41.8146797Z 5d24dc753f04: Waiting
2025-03-21T20:18:41.8147059Z 508bc8ee650d: Pulling fs layer
2025-03-21T20:18:41.8147359Z 6ff1ffcc6d84: Pulling fs layer
2025-03-21T20:18:41.8147647Z 2d4cecada8b4: Waiting
2025-03-21T20:18:41.8147945Z 85f4a172d5b6: Waiting
2025-03-21T20:18:41.8148199Z 6a063300ab4b: Pulling fs layer
2025-03-21T20:18:41.8148513Z bb9ad7d84f6e: Waiting
2025-03-21T20:18:41.8148839Z fb7c06bc00e5: Pulling fs layer
2025-03-21T20:18:41.8149135Z eda4db11af8f: Pulling fs layer
2025-03-21T20:18:41.8149468Z e1fd02ccae09: Waiting
2025-03-21T20:18:41.8149724Z 3cfbc5ff2ac0: Pulling fs layer
2025-03-21T20:18:41.8150014Z fb7c06bc00e5: Waiting
2025-03-21T20:18:41.8150266Z 508bc8ee650d: Waiting
2025-03-21T20:18:41.8150517Z eda4db11af8f: Waiting
2025-03-21T20:18:41.8150986Z 59fe3e940463: Pulling fs layer
2025-03-21T20:18:41.8151264Z 6a063300ab4b: Waiting
2025-03-21T20:18:41.8151517Z 5120711d46e3: Waiting
2025-03-21T20:18:41.8151768Z 6ff1ffcc6d84: Waiting
2025-03-21T20:18:41.8152030Z 3cfbc5ff2ac0: Waiting
2025-03-21T20:18:41.8152295Z 50754bc025fc: Pulling fs layer
2025-03-21T20:18:41.8152579Z db5c552aa08b: Pulling fs layer
2025-03-21T20:18:41.8152867Z 706d7d7c1227: Pulling fs layer
2025-03-21T20:18:41.8153156Z 32a4dbb2ef2f: Pulling fs layer
2025-03-21T20:18:41.8153468Z db5c552aa08b: Waiting
2025-03-21T20:18:41.8153780Z 706d7d7c1227: Waiting
2025-03-21T20:18:41.8154040Z 242848c50d1a: Pulling fs layer
2025-03-21T20:18:41.8154372Z 59fe3e940463: Waiting
2025-03-21T20:18:41.8154833Z 77ba92adb139: Pulling fs layer
2025-03-21T20:18:41.8155196Z 32a4dbb2ef2f: Waiting
2025-03-21T20:18:41.8155441Z 50754bc025fc: Waiting
2025-03-21T20:18:41.8155875Z 3c65b9b0c077: Pulling fs layer
2025-03-21T20:18:41.8156227Z 4f4fb700ef54: Pulling fs layer
2025-03-21T20:18:41.8156524Z 77ba92adb139: Waiting
2025-03-21T20:18:41.8156789Z 3d39d3c3833d: Pulling fs layer
2025-03-21T20:18:41.8157061Z 3c65b9b0c077: Waiting
2025-03-21T20:18:41.8157343Z 242848c50d1a: Waiting
2025-03-21T20:18:41.8157733Z 4f4fb700ef54: Waiting
2025-03-21T20:18:41.8158169Z 040f4b25fe47: Pulling fs layer
2025-03-21T20:18:41.8158687Z 2ce202d93f2e: Pulling fs layer
2025-03-21T20:18:41.8159119Z 3d39d3c3833d: Waiting
2025-03-21T20:18:41.8159403Z 2ce202d93f2e: Waiting
2025-03-21T20:18:41.8994165Z 86e413e13063: Verifying Checksum
2025-03-21T20:18:41.8994548Z 86e413e13063: Download complete
2025-03-21T20:18:41.9665408Z 261c0f487ad0: Verifying Checksum
2025-03-21T20:18:41.9665986Z 261c0f487ad0: Download complete
2025-03-21T20:18:42.1699969Z 8f84a9f2102e: Verifying Checksum
2025-03-21T20:18:42.1700416Z 8f84a9f2102e: Download complete
2025-03-21T20:18:42.2021703Z a3f0567f83ae: Verifying Checksum
2025-03-21T20:18:42.2022390Z a3f0567f83ae: Download complete
2025-03-21T20:18:42.2350402Z a0c2fdb93dec: Verifying Checksum
2025-03-21T20:18:42.2351036Z a0c2fdb93dec: Download complete
2025-03-21T20:18:42.3155314Z 5a102502de33: Verifying Checksum
2025-03-21T20:18:42.3155863Z 5a102502de33: Download complete
2025-03-21T20:18:42.3841313Z 5d24dc753f04: Download complete
2025-03-21T20:18:42.4544367Z 85f4a172d5b6: Download complete
2025-03-21T20:18:42.8861647Z bb9ad7d84f6e: Verifying Checksum
2025-03-21T20:18:42.8862272Z bb9ad7d84f6e: Download complete
2025-03-21T20:18:42.9402142Z 5120711d46e3: Verifying Checksum
2025-03-21T20:18:42.9402595Z 5120711d46e3: Download complete
2025-03-21T20:18:43.0943167Z 8f84a9f2102e: Pull complete
2025-03-21T20:18:43.1074657Z 86e413e13063: Pull complete
2025-03-21T20:18:43.4370171Z 56848936f031: Verifying Checksum
2025-03-21T20:18:43.4370606Z 56848936f031: Download complete
2025-03-21T20:18:43.5080574Z e1fd02ccae09: Verifying Checksum
2025-03-21T20:18:43.5081192Z e1fd02ccae09: Download complete
2025-03-21T20:18:43.5755094Z 508bc8ee650d: Verifying Checksum
2025-03-21T20:18:43.5755688Z 508bc8ee650d: Download complete
2025-03-21T20:18:43.5756584Z 4e0f8d4747da: Verifying Checksum
2025-03-21T20:18:43.5757463Z 4e0f8d4747da: Download complete
2025-03-21T20:18:43.6589667Z 6ff1ffcc6d84: Download complete
2025-03-21T20:18:43.7330501Z fb7c06bc00e5: Verifying Checksum
2025-03-21T20:18:43.7331111Z fb7c06bc00e5: Download complete
2025-03-21T20:18:43.8124119Z eda4db11af8f: Verifying Checksum
2025-03-21T20:18:43.8124644Z eda4db11af8f: Download complete
2025-03-21T20:18:43.8773047Z 3cfbc5ff2ac0: Verifying Checksum
2025-03-21T20:18:43.8773432Z 3cfbc5ff2ac0: Download complete
2025-03-21T20:18:43.9542669Z 59fe3e940463: Verifying Checksum
2025-03-21T20:18:43.9543052Z 59fe3e940463: Download complete
2025-03-21T20:18:44.3972254Z 6a063300ab4b: Verifying Checksum
2025-03-21T20:18:44.3972785Z 6a063300ab4b: Download complete
2025-03-21T20:18:44.4751358Z db5c552aa08b: Verifying Checksum
2025-03-21T20:18:44.4751864Z db5c552aa08b: Download complete
2025-03-21T20:18:45.4911806Z 2d4cecada8b4: Verifying Checksum
2025-03-21T20:18:45.4912462Z 2d4cecada8b4: Download complete
2025-03-21T20:18:45.5644593Z 32a4dbb2ef2f: Download complete
2025-03-21T20:18:46.8363781Z 706d7d7c1227: Verifying Checksum
2025-03-21T20:18:46.8364336Z 706d7d7c1227: Download complete
2025-03-21T20:18:46.9205767Z 77ba92adb139: Download complete
2025-03-21T20:18:46.9986014Z 4f4fb700ef54: Verifying Checksum
2025-03-21T20:18:46.9986571Z 4f4fb700ef54: Download complete
2025-03-21T20:18:47.0699907Z 3d39d3c3833d: Verifying Checksum
2025-03-21T20:18:47.0700505Z 3d39d3c3833d: Download complete
2025-03-21T20:18:47.1318816Z 040f4b25fe47: Verifying Checksum
2025-03-21T20:18:47.1319398Z 040f4b25fe47: Download complete
2025-03-21T20:18:47.2143368Z 2ce202d93f2e: Verifying Checksum
2025-03-21T20:18:47.2143969Z 2ce202d93f2e: Download complete
2025-03-21T20:18:47.3991807Z 242848c50d1a: Verifying Checksum
2025-03-21T20:18:47.3992188Z 242848c50d1a: Download complete
2025-03-21T20:18:47.6127821Z 56848936f031: Pull complete
2025-03-21T20:18:47.7308265Z 261c0f487ad0: Pull complete
2025-03-21T20:18:48.1069919Z a3f0567f83ae: Pull complete
2025-03-21T20:18:48.3001777Z a0c2fdb93dec: Pull complete
2025-03-21T20:18:50.8457428Z 4e0f8d4747da: Pull complete
2025-03-21T20:18:50.9822416Z 5a102502de33: Pull complete
2025-03-21T20:18:51.1121485Z 5d24dc753f04: Pull complete
2025-03-21T20:18:51.2517607Z 85f4a172d5b6: Pull complete
2025-03-21T20:18:51.9211290Z bb9ad7d84f6e: Pull complete
2025-03-21T20:18:52.0505584Z 5120711d46e3: Pull complete
2025-03-21T20:18:58.2587742Z 2d4cecada8b4: Pull complete
2025-03-21T20:18:58.3809492Z e1fd02ccae09: Pull complete
2025-03-21T20:18:58.4828615Z 508bc8ee650d: Pull complete
2025-03-21T20:18:58.5822219Z 6ff1ffcc6d84: Pull complete
2025-03-21T20:19:02.6839247Z 6a063300ab4b: Pull complete
2025-03-21T20:19:02.8899203Z fb7c06bc00e5: Pull complete
2025-03-21T20:19:03.1094108Z eda4db11af8f: Pull complete
2025-03-21T20:19:03.3166169Z 3cfbc5ff2ac0: Pull complete
2025-03-21T20:19:03.5251864Z 59fe3e940463: Pull complete
2025-03-21T20:19:52.3900943Z 50754bc025fc: Verifying Checksum
2025-03-21T20:19:52.3901363Z 50754bc025fc: Download complete
2025-03-21T20:21:04.4048625Z 50754bc025fc: Pull complete
2025-03-21T20:21:04.5788786Z db5c552aa08b: Pull complete
2025-03-21T20:21:11.9562522Z 706d7d7c1227: Pull complete
2025-03-21T20:21:12.1440054Z 32a4dbb2ef2f: Pull complete
2025-03-21T20:21:19.4127116Z 242848c50d1a: Pull complete
2025-03-21T20:21:19.5660160Z 77ba92adb139: Pull complete
2025-03-21T20:21:19.7720839Z 3c65b9b0c077: Pull complete
2025-03-21T20:21:19.8404325Z 4f4fb700ef54: Pull complete
2025-03-21T20:21:19.8748524Z 3d39d3c3833d: Pull complete
2025-03-21T20:21:19.9053011Z 040f4b25fe47: Pull complete
2025-03-21T20:21:19.9742721Z 2ce202d93f2e: Pull complete
2025-03-21T20:21:20.0423160Z Digest: sha256:d38559c98aeb82552e009bbb7b17d76adfa19c8f3fb874ea99a5e76d87757f76
2025-03-21T20:21:20.0749745Z Status: Downloaded newer image for 308535385114.dkr.ecr.us-east-1.amazonaws.com/executorch/executorch-ubuntu-22.04-qnn-sdk:2abd9b1bd42f655b7d130222db4a0cdbc04da8a4
2025-03-21T20:21:20.0915339Z 308535385114.dkr.ecr.us-east-1.amazonaws.com/executorch/executorch-ubuntu-22.04-qnn-sdk:2abd9b1bd42f655b7d130222db4a0cdbc04da8a4
2025-03-21T20:21:20.0957222Z ##[group]Run echo "IN_CONTAINER_RUNNER=$(if [ -f /.inarc ] || [ -f /.incontainer ]; then echo true ; else echo false; fi)" >> "$GITHUB_OUTPUT"
2025-03-21T20:21:20.0958189Z echo "IN_CONTAINER_RUNNER=$(if [ -f /.inarc ] || [ -f /.incontainer ]; then echo true ; else echo false; fi)" >> "$GITHUB_OUTPUT"
2025-03-21T20:21:20.0965194Z shell: /usr/bin/bash --noprofile --norc -e -o pipefail {0}
2025-03-21T20:21:20.0965586Z env:
2025-03-21T20:21:20.0965868Z   DOCKER_IMAGE: executorch-ubuntu-22.04-qnn-sdk
2025-03-21T20:21:20.0966244Z   REPOSITORY: pytorch/executorch
2025-03-21T20:21:20.0966546Z   PR_NUMBER: 
2025-03-21T20:21:20.0969725Z   SCRIPT: # The generic Linux job chooses to use base env, not the one setup by the image
CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
conda activate "${CONDA_ENV}"

DTYPE=fp32
BUILD_TOOL="cmake"
MODE=qnn
PT2E_QUANTIZE=qnn_16a16w

./install_requirements.sh --use-pt-pinned-commit
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh

# Setup executorch
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "${BUILD_TOOL}"
# Install requirements for export_llama
PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
# Test llama2
PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh -model stories110M -build_tool "${BUILD_TOOL}" -mode "${MODE}" -dtype "${DTYPE}" -pt2e_quantize "${PT2E_QUANTIZE}"

2025-03-21T20:21:20.0972972Z   RUNNER_ARTIFACT_DIR: /home/ec2-user/actions-runner/_work/_temp/artifacts
2025-03-21T20:21:20.0973571Z   RUNNER_TEST_RESULTS_DIR: /home/ec2-user/actions-runner/_work/_temp/test-results
2025-03-21T20:21:20.0974127Z   RUNNER_DOCS_DIR: /home/ec2-user/actions-runner/_work/_temp/docs
2025-03-21T20:21:20.0974687Z ##[endgroup]
2025-03-21T20:21:20.1174884Z ##[group]Run set -ex
2025-03-21T20:21:20.1175191Z set -ex
2025-03-21T20:21:20.1175435Z {
2025-03-21T20:21:20.1175669Z   echo "#!/usr/bin/env bash";
2025-03-21T20:21:20.1176008Z   echo "set -eou pipefail";
2025-03-21T20:21:20.1176341Z   # shellcheck disable=SC2016
2025-03-21T20:21:20.1176695Z   echo 'eval "$(conda shell.bash hook)"';
2025-03-21T20:21:20.1177044Z   echo "set -x";
2025-03-21T20:21:20.1177330Z   echo "${SCRIPT}";
2025-03-21T20:21:20.1177628Z } > "${RUNNER_TEMP}/exec_script"
2025-03-21T20:21:20.1177984Z chmod +x "${RUNNER_TEMP}/exec_script"
2025-03-21T20:21:20.1178708Z python3 "/home/ec2-user/actions-runner/_work/executorch/executorch/test-infra/.github/scripts/run_with_env_secrets.py" ""
2025-03-21T20:21:20.1184323Z shell: /usr/bin/bash -e {0}
2025-03-21T20:21:20.1184615Z env:
2025-03-21T20:21:20.1185313Z   DOCKER_IMAGE: 308535385114.dkr.ecr.us-east-1.amazonaws.com/executorch/executorch-ubuntu-22.04-qnn-sdk:2abd9b1bd42f655b7d130222db4a0cdbc04da8a4
2025-03-21T20:21:20.1186072Z   REPOSITORY: pytorch/executorch
2025-03-21T20:21:20.1186376Z   PR_NUMBER: 
2025-03-21T20:21:20.1189404Z   SCRIPT: # The generic Linux job chooses to use base env, not the one setup by the image
CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
conda activate "${CONDA_ENV}"

DTYPE=fp32
BUILD_TOOL="cmake"
MODE=qnn
PT2E_QUANTIZE=qnn_16a16w

./install_requirements.sh --use-pt-pinned-commit
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh

# Setup executorch
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "${BUILD_TOOL}"
# Install requirements for export_llama
PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
# Test llama2
PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh -model stories110M -build_tool "${BUILD_TOOL}" -mode "${MODE}" -dtype "${DTYPE}" -pt2e_quantize "${PT2E_QUANTIZE}"

2025-03-21T20:21:20.1192623Z   RUNNER_ARTIFACT_DIR: /home/ec2-user/actions-runner/_work/_temp/artifacts
2025-03-21T20:21:20.1193218Z   RUNNER_TEST_RESULTS_DIR: /home/ec2-user/actions-runner/_work/_temp/test-results
2025-03-21T20:21:20.1193772Z   RUNNER_DOCS_DIR: /home/ec2-user/actions-runner/_work/_temp/docs
2025-03-21T20:21:20.1194445Z   ALL_SECRETS: {
  "github_token": "***"
}
2025-03-21T20:21:20.1194760Z ##[endgroup]
2025-03-21T20:21:20.1217880Z + echo '#!/usr/bin/env bash'
2025-03-21T20:21:20.1218206Z + echo 'set -eou pipefail'
2025-03-21T20:21:20.1218510Z + echo 'eval "$(conda shell.bash hook)"'
2025-03-21T20:21:20.1218845Z + echo 'set -x'
2025-03-21T20:21:20.1219364Z + echo '# The generic Linux job chooses to use base env, not the one setup by the image
2025-03-21T20:21:20.1219916Z CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
2025-03-21T20:21:20.1220314Z conda activate "${CONDA_ENV}"
2025-03-21T20:21:20.1220514Z 
2025-03-21T20:21:20.1220638Z DTYPE=fp32
2025-03-21T20:21:20.1220871Z BUILD_TOOL="cmake"
2025-03-21T20:21:20.1221118Z MODE=qnn
2025-03-21T20:21:20.1221364Z PT2E_QUANTIZE=qnn_16a16w
2025-03-21T20:21:20.1221532Z 
2025-03-21T20:21:20.1221706Z ./install_requirements.sh --use-pt-pinned-commit
2025-03-21T20:21:20.1222169Z PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
2025-03-21T20:21:20.1222652Z PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh
2025-03-21T20:21:20.1222953Z 
2025-03-21T20:21:20.1223057Z # Setup executorch
2025-03-21T20:21:20.1223498Z PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "${BUILD_TOOL}"
2025-03-21T20:21:20.1224331Z # Install requirements for export_llama
2025-03-21T20:21:20.1224817Z PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
2025-03-21T20:21:20.1225268Z # Test llama2
2025-03-21T20:21:20.1226118Z PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh -model stories110M -build_tool "${BUILD_TOOL}" -mode "${MODE}" -dtype "${DTYPE}" -pt2e_quantize "${PT2E_QUANTIZE}"
2025-03-21T20:21:20.1227005Z '
2025-03-21T20:21:20.1227321Z + chmod +x /home/ec2-user/actions-runner/_work/_temp/exec_script
2025-03-21T20:21:20.1229298Z + python3 /home/ec2-user/actions-runner/_work/executorch/executorch/test-infra/.github/scripts/run_with_env_secrets.py ''
2025-03-21T20:21:40.9897863Z Running command: 
2025-03-21T20:21:40.9904685Z         docker run             -e PR_NUMBER             -e RUNNER_ARTIFACT_DIR=/artifacts             -e RUNNER_DOCS_DIR=/docs             -e RUNNER_TEST_RESULTS_DIR=/test-results             --env-file="/home/ec2-user/actions-runner/_work/_temp/github_env_14000170672"             `# It is unknown why the container sees a different value for this.`             -e GITHUB_STEP_SUMMARY             -e SECRET_GITHUB_TOKEN             --cap-add=SYS_PTRACE             --detach             --ipc=host             --security-opt seccomp=unconfined             --shm-size=2g             --tty             --ulimit stack=10485760:83886080             --ulimit core=0                          -v "/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch:/pytorch/executorch"             -v "/home/ec2-user/actions-runner/_work/executorch/executorch/test-infra:/test-infra"             -v "/home/ec2-user/actions-runner/_work/_temp/artifacts:/artifacts"             -v "/home/ec2-user/actions-runner/_work/_temp/docs:/docs"             -v "/home/ec2-user/actions-runner/_work/_temp/test-results:/test-results"             -v "/home/ec2-user/actions-runner/_work/_temp/exec_script:/exec"             -v "/home/ec2-user/actions-runner/_work/_temp/_runner_file_commands/step_summary_c86338e7-620a-4c41-bc12-8bbc68be3451":"/home/ec2-user/actions-runner/_work/_temp/_runner_file_commands/step_summary_c86338e7-620a-4c41-bc12-8bbc68be3451"             -w /pytorch/executorch             "308535385114.dkr.ecr.us-east-1.amazonaws.com/executorch/executorch-ubuntu-22.04-qnn-sdk:2abd9b1bd42f655b7d130222db4a0cdbc04da8a4"
2025-03-21T20:21:40.9910223Z         
2025-03-21T20:21:40.9910595Z e4535af01bcec20a70eace7fee6b4cd457f84d9eb152ff3bc4c2d5a7ab85cc60
2025-03-21T20:21:40.9911327Z Running command: docker exec -t e4535af01bcec20a70eace7fee6b4cd457f84d9eb152ff3bc4c2d5a7ab85cc60 /exec
2025-03-21T20:21:40.9911932Z ++ conda env list --json
2025-03-21T20:21:40.9912192Z ++ local cmd=env
2025-03-21T20:21:40.9912432Z ++ case "$cmd" in
2025-03-21T20:21:40.9912689Z ++ __conda_exe env list --json
2025-03-21T20:21:40.9912988Z ++ jq -r '.envs | .[-1]'
2025-03-21T20:21:40.9913270Z ++ /opt/conda/bin/conda env list --json
2025-03-21T20:21:40.9913614Z + CONDA_ENV=/opt/conda/envs/py_3.10
2025-03-21T20:21:40.9913941Z + conda activate /opt/conda/envs/py_3.10
2025-03-21T20:21:40.9914262Z + local cmd=activate
2025-03-21T20:21:40.9914511Z + case "$cmd" in
2025-03-21T20:21:40.9914784Z + __conda_activate activate /opt/conda/envs/py_3.10
2025-03-21T20:21:40.9915134Z + '[' -n '' ']'
2025-03-21T20:21:40.9915368Z + local ask_conda
2025-03-21T20:21:40.9915613Z ++ PS1='(base) '
2025-03-21T20:21:40.9915939Z ++ __conda_exe shell.posix activate /opt/conda/envs/py_3.10
2025-03-21T20:21:40.9916424Z ++ /opt/conda/bin/conda shell.posix activate /opt/conda/envs/py_3.10
2025-03-21T20:21:40.9916860Z + ask_conda='PS1='\''(py_3.10) '\''
2025-03-21T20:21:40.9917728Z export PATH='\''/opt/conda/envs/py_3.10/bin:/opt/conda/condabin:/opt/cache/bin:/opt/conda/envs/py_3.10/bin:/opt/conda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin'\''
2025-03-21T20:21:40.9918637Z export CONDA_PREFIX='\''/opt/conda/envs/py_3.10'\''
2025-03-21T20:21:40.9919002Z export CONDA_SHLVL='\''2'\''
2025-03-21T20:21:40.9919305Z export CONDA_DEFAULT_ENV='\''py_3.10'\''
2025-03-21T20:21:40.9919654Z export CONDA_PROMPT_MODIFIER='\''(py_3.10) '\''
2025-03-21T20:21:40.9920021Z export CONDA_PREFIX_1='\''/opt/conda'\''
2025-03-21T20:21:40.9920370Z export CONDA_EXE='\''/opt/conda/bin/conda'\''
2025-03-21T20:21:40.9920704Z export _CE_M='\'''\''
2025-03-21T20:21:40.9920969Z export _CE_CONDA='\'''\''
2025-03-21T20:21:40.9921747Z export CONDA_PYTHON_EXE='\''/opt/conda/bin/python'\'''
2025-03-21T20:21:40.9922128Z + eval 'PS1='\''(py_3.10) '\''
2025-03-21T20:21:40.9922972Z export PATH='\''/opt/conda/envs/py_3.10/bin:/opt/conda/condabin:/opt/cache/bin:/opt/conda/envs/py_3.10/bin:/opt/conda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin'\''
2025-03-21T20:21:40.9923875Z export CONDA_PREFIX='\''/opt/conda/envs/py_3.10'\''
2025-03-21T20:21:40.9924242Z export CONDA_SHLVL='\''2'\''
2025-03-21T20:21:40.9924538Z export CONDA_DEFAULT_ENV='\''py_3.10'\''
2025-03-21T20:21:40.9924903Z export CONDA_PROMPT_MODIFIER='\''(py_3.10) '\''
2025-03-21T20:21:40.9925268Z export CONDA_PREFIX_1='\''/opt/conda'\''
2025-03-21T20:21:40.9925629Z export CONDA_EXE='\''/opt/conda/bin/conda'\''
2025-03-21T20:21:40.9925965Z export _CE_M='\'''\''
2025-03-21T20:21:40.9926215Z export _CE_CONDA='\'''\''
2025-03-21T20:21:40.9926547Z export CONDA_PYTHON_EXE='\''/opt/conda/bin/python'\'''
2025-03-21T20:21:40.9926916Z ++ PS1='(py_3.10) '
2025-03-21T20:21:40.9927709Z ++ export PATH=/opt/conda/envs/py_3.10/bin:/opt/conda/condabin:/opt/cache/bin:/opt/conda/envs/py_3.10/bin:/opt/conda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
2025-03-21T20:21:40.9929048Z ++ PATH=/opt/conda/envs/py_3.10/bin:/opt/conda/condabin:/opt/cache/bin:/opt/conda/envs/py_3.10/bin:/opt/conda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
2025-03-21T20:21:40.9930157Z ++ export CONDA_PREFIX=/opt/conda/envs/py_3.10
2025-03-21T20:21:40.9930512Z ++ CONDA_PREFIX=/opt/conda/envs/py_3.10
2025-03-21T20:21:40.9930842Z ++ export CONDA_SHLVL=2
2025-03-21T20:21:40.9931107Z ++ CONDA_SHLVL=2
2025-03-21T20:21:40.9931377Z ++ export CONDA_DEFAULT_ENV=py_3.10
2025-03-21T20:21:40.9931701Z ++ CONDA_DEFAULT_ENV=py_3.10
2025-03-21T20:21:40.9932041Z ++ export 'CONDA_PROMPT_MODIFIER=(py_3.10) '
2025-03-21T20:21:40.9932592Z ++ CONDA_PROMPT_MODIFIER='(py_3.10) '
2025-03-21T20:21:40.9932925Z ++ export CONDA_PREFIX_1=/opt/conda
2025-03-21T20:21:40.9933247Z ++ CONDA_PREFIX_1=/opt/conda
2025-03-21T20:21:40.9933565Z ++ export CONDA_EXE=/opt/conda/bin/conda
2025-03-21T20:21:40.9933897Z ++ CONDA_EXE=/opt/conda/bin/conda
2025-03-21T20:21:40.9934178Z ++ export _CE_M=
2025-03-21T20:21:40.9934417Z ++ _CE_M=
2025-03-21T20:21:40.9934642Z ++ export _CE_CONDA=
2025-03-21T20:21:40.9934887Z ++ _CE_CONDA=
2025-03-21T20:21:40.9935148Z ++ export CONDA_PYTHON_EXE=/opt/conda/bin/python
2025-03-21T20:21:40.9935521Z ++ CONDA_PYTHON_EXE=/opt/conda/bin/python
2025-03-21T20:21:40.9935844Z + __conda_hashr
2025-03-21T20:21:40.9936080Z + '[' -n '' ']'
2025-03-21T20:21:40.9936310Z + '[' -n '' ']'
2025-03-21T20:21:40.9936527Z + hash -r
2025-03-21T20:21:40.9936746Z + DTYPE=fp32
2025-03-21T20:21:40.9936976Z + BUILD_TOOL=cmake
2025-03-21T20:21:40.9937213Z + MODE=qnn
2025-03-21T20:21:40.9937445Z + PT2E_QUANTIZE=qnn_16a16w
2025-03-21T20:21:40.9937767Z + ./install_requirements.sh --use-pt-pinned-commit
2025-03-21T20:21:40.9938361Z Looking in indexes: https://pypi.org/simple, https://download.pytorch.org/whl/nightly/cpu
2025-03-21T20:21:40.9939183Z Requirement already satisfied: torch in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (2.7.0a0+git295f2ed)
2025-03-21T20:21:40.9940089Z Requirement already satisfied: torchvision in /var/lib/ci-user/.local/lib/python3.10/site-packages (0.19.0a0+d23a6e1)
2025-03-21T20:21:40.9940999Z Requirement already satisfied: torchaudio in /var/lib/ci-user/.local/lib/python3.10/site-packages (2.6.0a0+c670ad8)
2025-03-21T20:21:40.9941721Z Collecting timm==1.0.7 (from -r requirements-examples.txt (line 3))
2025-03-21T20:21:40.9942224Z   Downloading timm-1.0.7-py3-none-any.whl.metadata (47 kB)
2025-03-21T20:21:40.9943067Z Requirement already satisfied: torchsr==1.0.4 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from -r requirements-examples.txt (line 4)) (1.0.4)
2025-03-21T20:21:40.9944288Z Requirement already satisfied: transformers==4.47.1 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from -r requirements-examples.txt (line 5)) (4.47.1)
2025-03-21T20:21:40.9945406Z Collecting cmake>=3.19 (from -r requirements-dev.txt (line 1))
2025-03-21T20:21:40.9946046Z   Downloading cmake-3.31.6-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (6.3 kB)
2025-03-21T20:21:40.9946987Z Requirement already satisfied: pip>=23 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from -r requirements-dev.txt (line 2)) (25.0)
2025-03-21T20:21:40.9948100Z Requirement already satisfied: pyyaml in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from -r requirements-dev.txt (line 3)) (6.0.1)
2025-03-21T20:21:40.9949253Z Requirement already satisfied: setuptools>=63 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from -r requirements-dev.txt (line 4)) (75.8.0)
2025-03-21T20:21:40.9950388Z Requirement already satisfied: tomli in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from -r requirements-dev.txt (line 5)) (2.0.1)
2025-03-21T20:21:40.9951502Z Requirement already satisfied: wheel in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from -r requirements-dev.txt (line 6)) (0.45.1)
2025-03-21T20:21:40.9952620Z Requirement already satisfied: zstd in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from -r requirements-dev.txt (line 7)) (1.5.5.1)
2025-03-21T20:21:40.9953844Z Requirement already satisfied: huggingface_hub in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from timm==1.0.7->-r requirements-examples.txt (line 3)) (0.29.3)
2025-03-21T20:21:40.9955144Z Requirement already satisfied: safetensors in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from timm==1.0.7->-r requirements-examples.txt (line 3)) (0.5.3)
2025-03-21T20:21:40.9956457Z Requirement already satisfied: filelock in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from transformers==4.47.1->-r requirements-examples.txt (line 5)) (3.18.0)
2025-03-21T20:21:40.9957795Z Requirement already satisfied: numpy>=1.17 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from transformers==4.47.1->-r requirements-examples.txt (line 5)) (2.2.4)
2025-03-21T20:21:40.9959125Z Requirement already satisfied: packaging>=20.0 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from transformers==4.47.1->-r requirements-examples.txt (line 5)) (24.2)
2025-03-21T20:21:40.9960497Z Requirement already satisfied: regex!=2019.12.17 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from transformers==4.47.1->-r requirements-examples.txt (line 5)) (2024.11.6)
2025-03-21T20:21:40.9961855Z Requirement already satisfied: requests in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from transformers==4.47.1->-r requirements-examples.txt (line 5)) (2.32.3)
2025-03-21T20:21:40.9963229Z Requirement already satisfied: tokenizers<0.22,>=0.21 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from transformers==4.47.1->-r requirements-examples.txt (line 5)) (0.21.1)
2025-03-21T20:21:40.9964686Z Requirement already satisfied: tqdm>=4.27 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from transformers==4.47.1->-r requirements-examples.txt (line 5)) (4.67.1)
2025-03-21T20:21:53.7110067Z Requirement already satisfied: typing-extensions>=4.10.0 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from torch) (4.12.2)
2025-03-21T20:21:53.7111594Z Requirement already satisfied: sympy>=1.13.3 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from torch) (1.13.3)
2025-03-21T20:21:53.7112766Z Requirement already satisfied: networkx in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from torch) (3.4.2)
2025-03-21T20:21:53.7113723Z Requirement already satisfied: jinja2 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from torch) (3.1.6)
2025-03-21T20:21:53.7114622Z Requirement already satisfied: fsspec in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from torch) (2025.3.0)
2025-03-21T20:21:53.7115589Z Requirement already satisfied: pillow!=8.3.*,>=5.3.0 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from torchvision) (11.1.0)
2025-03-21T20:21:53.7116794Z Requirement already satisfied: mpmath<1.4,>=1.1.0 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from sympy>=1.13.3->torch) (1.3.0)
2025-03-21T20:21:53.7117927Z Requirement already satisfied: MarkupSafe>=2.0 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from jinja2->torch) (3.0.2)
2025-03-21T20:21:53.7119192Z Requirement already satisfied: charset-normalizer<4,>=2 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from requests->transformers==4.47.1->-r requirements-examples.txt (line 5)) (3.4.1)
2025-03-21T20:21:53.7120657Z Requirement already satisfied: idna<4,>=2.5 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from requests->transformers==4.47.1->-r requirements-examples.txt (line 5)) (3.10)
2025-03-21T20:21:53.7122068Z Requirement already satisfied: urllib3<3,>=1.21.1 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from requests->transformers==4.47.1->-r requirements-examples.txt (line 5)) (2.3.0)
2025-03-21T20:21:53.7123520Z Requirement already satisfied: certifi>=2017.4.17 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from requests->transformers==4.47.1->-r requirements-examples.txt (line 5)) (2025.1.31)
2025-03-21T20:21:53.7124463Z Downloading timm-1.0.7-py3-none-any.whl (2.3 MB)
2025-03-21T20:21:53.7125570Z [?25l   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 0.0/2.3 MB ? eta -:--:--
2025-03-21T20:21:53.7126287Z    ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 2.3/2.3 MB 70.9 MB/s eta 0:00:00
2025-03-21T20:21:53.7127041Z [?25hDownloading cmake-3.31.6-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (27.8 MB)
2025-03-21T20:21:53.7127797Z [?25l   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 0.0/27.8 MB ? eta -:--:--
2025-03-21T20:21:53.7128487Z    ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 27.8/27.8 MB 234.1 MB/s eta 0:00:00
2025-03-21T20:21:53.7129029Z [?25hInstalling collected packages: cmake, timm
2025-03-21T20:21:53.7129487Z   Attempting uninstall: timm
2025-03-21T20:21:53.7129827Z     Found existing installation: timm 0.6.13
2025-03-21T20:21:53.7130190Z     Uninstalling timm-0.6.13:
2025-03-21T20:21:53.7130495Z       Successfully uninstalled timm-0.6.13
2025-03-21T20:21:53.7130865Z Successfully installed cmake-3.31.6 timm-1.0.7
2025-03-21T20:21:53.7131228Z Processing ./third-party/ao
2025-03-21T20:21:53.7131641Z   Preparing metadata (setup.py) ... [?25l- \ done
2025-03-21T20:21:53.7132113Z [?25hBuilding wheels for collected packages: torchao
2025-03-21T20:21:53.7132825Z   Building wheel for torchao (setup.py) ... [?25l- \ | done
2025-03-21T20:21:53.7133883Z [?25h  Created wheel for torchao: filename=torchao-0.10.0+git64bcf4c-py3-none-any.whl size=758276 sha256=1791321060faa0586203126a9186a84742a86b239492671e5431d0dbe17128f5
2025-03-21T20:21:53.7135059Z   Stored in directory: /tmp/pip-ephem-wheel-cache-18y4fsx1/wheels/0b/23/ff/2261dc1c4a27252503fe159d9fc88676b133e0e8d621abf36f
2025-03-21T20:21:53.7135749Z Successfully built torchao
2025-03-21T20:21:53.7136058Z Installing collected packages: torchao
2025-03-21T20:21:53.7136449Z Successfully installed torchao-0.10.0+git64bcf4c
2025-03-21T20:21:53.7136807Z + PYTHON_EXECUTABLE=python
2025-03-21T20:21:53.7137107Z + bash .ci/scripts/setup-qnn-deps.sh
2025-03-21T20:21:53.7137419Z + setup_libc++ 12
2025-03-21T20:21:53.7137666Z + clang_version=12
2025-03-21T20:21:53.7137904Z + sudo apt-get update
2025-03-21T20:21:53.7138075Z 
2025-03-21T20:21:53.7138167Z 0% [Working]
2025-03-21T20:21:53.7138390Z             
2025-03-21T20:21:53.7138695Z Hit:1 https://dl.yarnpkg.com/debian stable InRelease
2025-03-21T20:21:53.7138962Z 
2025-03-21T20:21:53.7139218Z 0% [Connecting to archive.ubuntu.com (185.125.190.81)] [Connecting to security.
2025-03-21T20:21:53.7139694Z                                                                                
2025-03-21T20:21:53.7140111Z Hit:2 https://deb.nodesource.com/node_16.x nodistro InRelease
2025-03-21T20:21:53.7140417Z 
2025-03-21T20:21:53.7140539Z                                                                                
2025-03-21T20:21:53.7141142Z 0% [Waiting for headers] [Waiting for headers]
2025-03-21T20:21:53.7141491Z                                               
2025-03-21T20:21:53.7141946Z Get:3 http://security.ubuntu.com/ubuntu jammy-security InRelease [129 kB]
2025-03-21T20:21:53.7142293Z 
2025-03-21T20:21:53.7142460Z 0% [Waiting for headers] [3 InRelease 5484 B/129 kB 4%]
2025-03-21T20:21:53.7142819Z                                                        
2025-03-21T20:21:53.7143214Z Hit:4 http://archive.ubuntu.com/ubuntu jammy InRelease
2025-03-21T20:21:53.7143495Z 
2025-03-21T20:21:53.7143604Z                                                        
2025-03-21T20:21:53.7143927Z 0% [3 InRelease 14.2 kB/129 kB 11%]
2025-03-21T20:21:53.7144285Z 0% [Waiting for headers] [3 InRelease 14.2 kB/129 kB 11%]
2025-03-21T20:21:53.7144649Z                                                          
2025-03-21T20:21:53.7145100Z Get:5 http://archive.ubuntu.com/ubuntu jammy-updates InRelease [128 kB]
2025-03-21T20:21:53.7145449Z 
2025-03-21T20:21:53.7145630Z 0% [5 InRelease 2588 B/128 kB 2%] [3 InRelease 17.1 kB/129 kB 13%]
2025-03-21T20:21:53.7146097Z 0% [5 InRelease 15.6 kB/128 kB 12%] [3 InRelease 22.9 kB/129 kB 18%]
2025-03-21T20:21:53.7146570Z 0% [5 InRelease 18.5 kB/128 kB 14%] [3 InRelease 48.9 kB/129 kB 38%]
2025-03-21T20:21:53.7146975Z                                                                     
2025-03-21T20:21:53.7147297Z 0% [5 InRelease 72.1 kB/128 kB 56%]
2025-03-21T20:21:53.7147597Z                                    
2025-03-21T20:21:53.7159446Z 0% [5 InRelease 124 kB/128 kB 97%]
2025-03-21T20:21:53.7160016Z                                   
2025-03-21T20:21:53.7160317Z 0% [Working]
2025-03-21T20:21:53.7160565Z 0% [Waiting for headers]
2025-03-21T20:21:53.7160835Z                         
2025-03-21T20:21:53.7161257Z Get:6 http://archive.ubuntu.com/ubuntu jammy-backports InRelease [127 kB]
2025-03-21T20:21:53.7161623Z 
2025-03-21T20:21:53.7161729Z 0% [6 InRelease 2588 B/127 kB 2%]
2025-03-21T20:21:53.7162054Z                                  
2025-03-21T20:21:53.7162338Z 0% [Working]
2025-03-21T20:21:53.7162579Z 27% [Waiting for headers]
2025-03-21T20:21:53.7162847Z                          
2025-03-21T20:21:53.7163271Z Get:7 http://archive.ubuntu.com/ubuntu jammy-updates/main amd64 Packages [3003 kB]
2025-03-21T20:21:53.7163666Z 
2025-03-21T20:21:53.7163774Z 27% [7 Packages 2655 B/3003 kB 0%]
2025-03-21T20:21:53.7164076Z                                   
2025-03-21T20:21:53.7164357Z 95% [Working]
2025-03-21T20:21:53.7164635Z 95% [7 Packages store 0 B] [Waiting for headers]
2025-03-21T20:21:53.7164988Z                                                 
2025-03-21T20:21:53.7165467Z Get:8 http://archive.ubuntu.com/ubuntu jammy-backports/main amd64 Packages [112 kB]
2025-03-21T20:21:53.7165864Z 
2025-03-21T20:21:53.7166026Z 96% [7 Packages store 0 B] [8 Packages 17.0 kB/112 kB 15%]
2025-03-21T20:21:53.7166409Z                                                           
2025-03-21T20:21:53.7166745Z 98% [7 Packages store 0 B]
2025-03-21T20:21:53.7167023Z                           
2025-03-21T20:21:53.7167468Z Get:9 http://archive.ubuntu.com/ubuntu jammy-backports/universe amd64 Packages [38.5 kB]
2025-03-21T20:21:53.7167881Z 
2025-03-21T20:21:53.7168033Z 98% [7 Packages store 0 B] [9 Packages 7003 B/38.5 kB 18%]
2025-03-21T20:21:53.7168404Z                                                           
2025-03-21T20:21:53.7168738Z 99% [7 Packages store 0 B]
2025-03-21T20:21:53.7169008Z                           
2025-03-21T20:21:53.7169254Z 99% [Working]
2025-03-21T20:21:53.7169572Z 99% [8 Packages store 0 B]
2025-03-21T20:21:53.7169840Z                           
2025-03-21T20:21:53.7170095Z 100% [Working]
2025-03-21T20:21:53.7170337Z 100% [9 Packages store 0 B]
2025-03-21T20:21:53.7170595Z                            
2025-03-21T20:21:53.7170860Z 100% [Working]
2025-03-21T20:21:53.7171088Z               
2025-03-21T20:21:53.7171333Z Fetched 3538 kB in 1s (3037 kB/s)
2025-03-21T20:21:53.7171527Z 
2025-03-21T20:21:53.7171837Z Reading package lists... 0%
2025-03-21T20:21:53.7172017Z 
2025-03-21T20:21:53.7172125Z Reading package lists... 0%
2025-03-21T20:21:53.7172314Z 
2025-03-21T20:21:53.7172419Z Reading package lists... 0%
2025-03-21T20:21:53.7172607Z 
2025-03-21T20:21:53.7172713Z Reading package lists... 4%
2025-03-21T20:21:53.7172901Z 
2025-03-21T20:21:53.7173007Z Reading package lists... 4%
2025-03-21T20:21:53.7173180Z 
2025-03-21T20:21:53.7173300Z Reading package lists... 5%
2025-03-21T20:21:53.7173478Z 
2025-03-21T20:21:53.7173598Z Reading package lists... 5%
2025-03-21T20:21:53.7173774Z 
2025-03-21T20:21:53.7173884Z Reading package lists... 48%
2025-03-21T20:21:53.7174077Z 
2025-03-21T20:21:53.7174185Z Reading package lists... 48%
2025-03-21T20:21:53.7174382Z 
2025-03-21T20:21:53.7174487Z Reading package lists... 48%
2025-03-21T20:21:53.7174677Z 
2025-03-21T20:21:53.7174783Z Reading package lists... 48%
2025-03-21T20:21:53.7174960Z 
2025-03-21T20:21:53.7175081Z Reading package lists... 57%
2025-03-21T20:21:53.7175265Z 
2025-03-21T20:21:53.7175391Z Reading package lists... 57%
2025-03-21T20:21:53.7175568Z 
2025-03-21T20:21:53.7175674Z Reading package lists... 70%
2025-03-21T20:21:53.7175868Z 
2025-03-21T20:21:53.7175976Z Reading package lists... 70%
2025-03-21T20:21:53.7176166Z 
2025-03-21T20:21:53.7176273Z Reading package lists... 74%
2025-03-21T20:21:53.7176457Z 
2025-03-21T20:21:53.7176562Z Reading package lists... 74%
2025-03-21T20:21:53.7176740Z 
2025-03-21T20:21:53.7176858Z Reading package lists... 75%
2025-03-21T20:21:53.7177035Z 
2025-03-21T20:21:53.7177154Z Reading package lists... 75%
2025-03-21T20:21:53.7177331Z 
2025-03-21T20:21:53.7177437Z Reading package lists... 75%
2025-03-21T20:21:53.7177631Z 
2025-03-21T20:21:53.7177740Z Reading package lists... 75%
2025-03-21T20:21:53.7177931Z 
2025-03-21T20:21:53.7178036Z Reading package lists... 75%
2025-03-21T20:21:53.7178225Z 
2025-03-21T20:21:53.7178333Z Reading package lists... 75%
2025-03-21T20:21:53.7178510Z 
2025-03-21T20:21:53.7178629Z Reading package lists... 83%
2025-03-21T20:21:53.7178815Z 
2025-03-21T20:21:53.7178933Z Reading package lists... 83%
2025-03-21T20:21:53.7179110Z 
2025-03-21T20:21:53.7179219Z Reading package lists... 85%
2025-03-21T20:21:53.7179409Z 
2025-03-21T20:21:53.7179514Z Reading package lists... 95%
2025-03-21T20:21:53.7179705Z 
2025-03-21T20:21:53.7179812Z Reading package lists... 95%
2025-03-21T20:21:53.7180004Z 
2025-03-21T20:21:53.7180111Z Reading package lists... 99%
2025-03-21T20:21:53.7180289Z 
2025-03-21T20:21:53.7180410Z Reading package lists... 99%
2025-03-21T20:21:53.7180586Z 
2025-03-21T20:21:53.7180707Z Reading package lists... 99%
2025-03-21T20:21:53.7180885Z 
2025-03-21T20:21:53.7180990Z Reading package lists... 99%
2025-03-21T20:21:53.7181181Z 
2025-03-21T20:21:53.7181286Z Reading package lists... 99%
2025-03-21T20:21:53.7181476Z 
2025-03-21T20:21:53.7181582Z Reading package lists... 99%
2025-03-21T20:21:53.7181771Z 
2025-03-21T20:21:53.7181875Z Reading package lists... 99%
2025-03-21T20:21:53.7182054Z 
2025-03-21T20:21:53.7182185Z Reading package lists... 99%
2025-03-21T20:21:53.7182361Z 
2025-03-21T20:21:53.7182480Z Reading package lists... 99%
2025-03-21T20:21:53.7182661Z 
2025-03-21T20:21:53.7182765Z Reading package lists... 99%
2025-03-21T20:21:53.7182957Z 
2025-03-21T20:21:53.7183065Z Reading package lists... Done
2025-03-21T20:21:53.7183260Z 
2025-03-21T20:21:53.7183930Z W: https://dl.yarnpkg.com/debian/dists/stable/InRelease: Key is stored in legacy trusted.gpg keyring (/etc/apt/trusted.gpg), see the DEPRECATION section in apt-key(8) for details.
2025-03-21T20:21:53.7184843Z + pkgs_to_check=("libc++-${clang_version}-dev")
2025-03-21T20:21:53.7185176Z + j=0
2025-03-21T20:21:53.7185404Z + '[' 0 -lt 1 ']'
2025-03-21T20:21:53.7185660Z ++ verify_pkg_installed libc++-12-dev
2025-03-21T20:21:53.7186049Z +++ dpkg-query -W '--showformat=${Status}\n' libc++-12-dev
2025-03-21T20:21:53.7186441Z +++ grep 'install ok installed'
2025-03-21T20:21:53.7186743Z ++ echo install ok installed
2025-03-21T20:21:53.7187047Z + install_status='install ok installed'
2025-03-21T20:21:53.7187509Z + '[' 'install ok installed' == '' ']'
2025-03-21T20:21:53.7187815Z + j=1
2025-03-21T20:21:53.7188034Z + '[' 1 -lt 1 ']'
2025-03-21T20:21:53.7188277Z + install_qnn
2025-03-21T20:21:53.7188525Z + echo 'Start installing qnn.'
2025-03-21T20:21:53.7188805Z Start installing qnn.
2025-03-21T20:21:53.7189088Z + QNN_INSTALLATION_DIR=/tmp/qnn
2025-03-21T20:21:53.7189386Z + mkdir -p /tmp/qnn
2025-03-21T20:22:35.4136711Z + curl -Lo /tmp/v2.28.0.24.10.29.zip https://softwarecenter.qualcomm.com/api/download/software/qualcomm_neural_processing_sdk/v2.28.0.241029.zip
2025-03-21T20:22:35.4137874Z   % Total    % Received % Xferd  Average Speed   Time    Time     Time  Current
2025-03-21T20:22:35.4138378Z                                  Dload  Upload   Total   Spent    Left  Speed
2025-03-21T20:22:35.4138642Z 
2025-03-21T20:22:35.4138804Z   0     0    0     0    0     0      0      0 --:--:-- --:--:-- --:--:--     0
2025-03-21T20:22:35.4139244Z 100   134  100   134    0     0    413      0 --:--:-- --:--:-- --:--:--   414
2025-03-21T20:22:35.4139544Z 
2025-03-21T20:22:35.4139707Z   0  954M    0 34353    0     0  44620      0  6:13:57 --:--:--  6:13:57 44620
2025-03-21T20:22:35.4140152Z   2  954M    2 28.5M    0     0  17.7M      0  0:00:53  0:00:01  0:00:52 34.0M
2025-03-21T20:22:35.4140577Z  10  954M   10 97.9M    0     0  37.3M      0  0:00:25  0:00:02  0:00:23 52.7M
2025-03-21T20:22:35.4141007Z  17  954M   17  168M    0     0  46.7M      0  0:00:20  0:00:03  0:00:17 59.3M
2025-03-21T20:22:35.4141437Z  25  954M   25  241M    0     0  51.9M      0  0:00:18  0:00:04  0:00:14 62.2M
2025-03-21T20:22:35.4141852Z  32  954M   32  308M    0     0  54.8M      0  0:00:17  0:00:05  0:00:12 63.5M
2025-03-21T20:22:35.4142282Z  39  954M   39  376M    0     0  56.9M      0  0:00:16  0:00:06  0:00:10 69.5M
2025-03-21T20:22:35.4142713Z  46  954M   46  445M    0     0  58.5M      0  0:00:16  0:00:07  0:00:09 69.7M
2025-03-21T20:22:35.4143140Z  53  954M   53  506M    0     0  58.7M      0  0:00:16  0:00:08  0:00:08 67.5M
2025-03-21T20:22:35.4143580Z  60  954M   60  576M    0     0  59.9M      0  0:00:15  0:00:09  0:00:06 67.4M
2025-03-21T20:22:35.4144010Z  68  954M   68  652M    0     0  61.4M      0  0:00:15  0:00:10  0:00:05 68.8M
2025-03-21T20:22:35.4144425Z  74  954M   74  712M    0     0  61.3M      0  0:00:15  0:00:11  0:00:04 67.3M
2025-03-21T20:22:35.4144854Z  81  954M   81  780M    0     0  61.7M      0  0:00:15  0:00:12  0:00:03 66.5M
2025-03-21T20:22:35.4145283Z  88  954M   88  845M    0     0  62.1M      0  0:00:15  0:00:13  0:00:02 67.8M
2025-03-21T20:22:35.4145712Z  95  954M   95  910M    0     0  62.2M      0  0:00:15  0:00:14  0:00:01 66.7M
2025-03-21T20:22:35.4146154Z 100  954M  100  954M    0     0  62.4M      0  0:00:15  0:00:15 --:--:-- 64.5M
2025-03-21T20:22:35.4146562Z + echo 'Finishing downloading qnn sdk.'
2025-03-21T20:22:35.4146893Z Finishing downloading qnn sdk.
2025-03-21T20:22:35.4147222Z + unzip -qo /tmp/v2.28.0.24.10.29.zip -d /tmp
2025-03-21T20:22:35.4147575Z + echo 'Finishing unzip qnn sdk.'
2025-03-21T20:22:35.4147893Z Finishing unzip qnn sdk.
2025-03-21T20:22:35.4148172Z + ls -lah /tmp/qairt
2025-03-21T20:22:35.4148408Z total 16K
2025-03-21T20:22:35.4148679Z drwxrwxrwx. 3 ci-user ci-user  27 Oct 30 05:44 .
2025-03-21T20:22:35.4149069Z drwxrwxrwt. 1 root    root     58 Mar 21 20:22 ..
2025-03-21T20:22:35.4149494Z drwxrwxrwx. 9 ci-user ci-user 16K Oct 30 05:45 2.28.0.241029
2025-03-21T20:22:35.4149891Z + mv /tmp/qairt/2.28.0.241029 /tmp/qnn
2025-03-21T20:22:35.4150235Z + echo 'Finishing installing qnn '\''/tmp/qnn'\'' .'
2025-03-21T20:22:35.4150613Z Finishing installing qnn '/tmp/qnn' .
2025-03-21T20:22:35.4150931Z + ls -lah /tmp/qnn
2025-03-21T20:22:35.4151173Z total 16K
2025-03-21T20:22:35.4151427Z drwxr-xr-x. 3 ci-user ci-user  27 Mar 21 20:22 .
2025-03-21T20:22:35.4151816Z drwxrwxrwt. 1 root    root     58 Mar 21 20:22 ..
2025-03-21T20:22:35.4152237Z drwxrwxrwx. 9 ci-user ci-user 16K Oct 30 05:45 2.28.0.241029
2025-03-21T20:22:35.4152638Z + PYTHON_EXECUTABLE=python
2025-03-21T20:22:35.4153301Z + bash .ci/scripts/build-qnn-sdk.sh
2025-03-21T20:22:35.4153613Z + set -o xtrace
2025-03-21T20:22:35.4153841Z + build_qnn_backend
2025-03-21T20:22:35.4154109Z + echo 'Start building qnn backend.'
2025-03-21T20:22:35.4154433Z Start building qnn backend.
2025-03-21T20:22:35.4154733Z + export ANDROID_NDK_ROOT=/opt/ndk
2025-03-21T20:22:35.4155036Z + ANDROID_NDK_ROOT=/opt/ndk
2025-03-21T20:22:35.4155346Z + export QNN_SDK_ROOT=/tmp/qnn/2.28.0.241029
2025-03-21T20:22:35.4155689Z + QNN_SDK_ROOT=/tmp/qnn/2.28.0.241029
2025-03-21T20:22:35.4156025Z +++ dirname -- .ci/scripts/build-qnn-sdk.sh
2025-03-21T20:22:35.4156360Z ++ cd -- .ci/scripts/../..
2025-03-21T20:22:35.4156617Z ++ pwd
2025-03-21T20:22:35.4156874Z + export EXECUTORCH_ROOT=/pytorch/executorch
2025-03-21T20:22:35.4157233Z + EXECUTORCH_ROOT=/pytorch/executorch
2025-03-21T20:22:35.4157726Z + bash backends/qualcomm/scripts/build.sh --skip_aarch64 --job_number 2 --release
2025-03-21T20:22:35.4158275Z + [[ -z /tmp/qnn/2.28.0.241029 ]]
2025-03-21T20:22:35.4158596Z + '[' --skip_aarch64 = -h ']'
2025-03-21T20:22:35.4158885Z + BUILD_X86_64=true
2025-03-21T20:22:35.4159127Z + CMAKE_X86_64=build-x86
2025-03-21T20:22:35.4159401Z + BUILD_AARCH64=true
2025-03-21T20:22:35.4159674Z + CMAKE_AARCH64=build-android
2025-03-21T20:22:35.4159957Z + CLEAN=true
2025-03-21T20:22:35.4160178Z + BUILD_TYPE=Debug
2025-03-21T20:22:35.4160437Z + BUILD_JOB_NUMBER=16
2025-03-21T20:22:35.4160710Z + '[' -z PYTHON_EXECUTABLE ']'
2025-03-21T20:22:35.4161007Z + '[' -z BUCK2 ']'
2025-03-21T20:22:35.4161356Z + long_options=skip_x86_64,skip_aarch64,no_clean,release,job_number:
2025-03-21T20:22:35.4162284Z ++ getopt -a --options '' --longoptions skip_x86_64,skip_aarch64,no_clean,release,job_number: --name backends/qualcomm/scripts/build.sh -- --skip_aarch64 --job_number 2 --release
2025-03-21T20:22:35.4163178Z + parsed_args=' --skip_aarch64 --job_number '\''2'\'' --release --'
2025-03-21T20:22:35.4163677Z + eval set -- ' --skip_aarch64 --job_number '\''2'\'' --release --'
2025-03-21T20:22:35.4164122Z ++ set -- --skip_aarch64 --job_number 2 --release --
2025-03-21T20:22:35.4164468Z + true
2025-03-21T20:22:35.4164675Z + case "$1" in
2025-03-21T20:22:35.4164919Z + BUILD_AARCH64=false
2025-03-21T20:22:35.4165177Z + shift
2025-03-21T20:22:35.4165389Z + true
2025-03-21T20:22:35.4165596Z + case "$1" in
2025-03-21T20:22:35.4165839Z + BUILD_JOB_NUMBER=2
2025-03-21T20:22:35.4166089Z + shift 2
2025-03-21T20:22:35.4166312Z + true
2025-03-21T20:22:35.4166535Z + case "$1" in
2025-03-21T20:22:35.4166760Z + BUILD_TYPE=Release
2025-03-21T20:22:35.4167012Z + shift
2025-03-21T20:22:35.4167225Z + true
2025-03-21T20:22:35.4167440Z + case "$1" in
2025-03-21T20:22:35.4167672Z + shift
2025-03-21T20:22:35.4167872Z + break
2025-03-21T20:22:35.4168126Z +++ dirname backends/qualcomm/scripts/build.sh
2025-03-21T20:22:35.4168490Z ++ cd backends/qualcomm/scripts/../../..
2025-03-21T20:22:35.4168809Z ++ pwd -P
2025-03-21T20:22:35.4169037Z + PRJ_ROOT=/pytorch/executorch
2025-03-21T20:22:35.4169466Z + '[' false = true ']'
2025-03-21T20:22:35.4169733Z + '[' true = true ']'
2025-03-21T20:22:35.4170015Z + BUILD_ROOT=/pytorch/executorch/build-x86
2025-03-21T20:22:35.4170345Z + '[' true = true ']'
2025-03-21T20:22:35.4170606Z + rm -rf /pytorch/executorch/build-x86
2025-03-21T20:22:35.4170942Z + mkdir /pytorch/executorch/build-x86
2025-03-21T20:22:35.4171273Z + cd /pytorch/executorch/build-x86
2025-03-21T20:22:35.4173025Z + cmake -DCMAKE_BUILD_TYPE=Release -DCMAKE_INSTALL_PREFIX=/pytorch/executorch/build-x86 -DQNN_SDK_ROOT=/tmp/qnn/2.28.0.241029 -DEXECUTORCH_BUILD_QNN=ON -DEXECUTORCH_BUILD_DEVTOOLS=ON -DEXECUTORCH_BUILD_EXTENSION_MODULE=ON -DEXECUTORCH_BUILD_KERNELS_QUANTIZED=ON -DEXECUTORCH_BUILD_EXTENSION_TENSOR=ON -DEXECUTORCH_ENABLE_EVENT_TRACER=ON -DPYTHON_EXECUTABLE=python -S /pytorch/executorch -B /pytorch/executorch/build-x86
2025-03-21T20:22:35.4174830Z -- The C compiler identification is Clang 12.0.1
2025-03-21T20:22:35.4175229Z -- The CXX compiler identification is Clang 12.0.1
2025-03-21T20:22:35.4175704Z -- Detecting C compiler ABI info
2025-03-21T20:22:35.4176094Z -- Detecting C compiler ABI info - done
2025-03-21T20:22:35.4176502Z -- Check for working C compiler: /opt/cache/bin/cc - skipped
2025-03-21T20:22:35.4176906Z -- Detecting C compile features
2025-03-21T20:22:35.4177223Z -- Detecting C compile features - done
2025-03-21T20:22:35.4177558Z -- Detecting CXX compiler ABI info
2025-03-21T20:22:35.4177873Z -- Detecting CXX compiler ABI info - done
2025-03-21T20:22:35.4178285Z -- Check for working CXX compiler: /opt/cache/bin/c++ - skipped
2025-03-21T20:22:35.4178696Z -- Detecting CXX compile features
2025-03-21T20:22:35.4179023Z -- Detecting CXX compile features - done
2025-03-21T20:22:35.4179922Z CMake Deprecation Warning at backends/xnnpack/third-party/FXdiv/CMakeLists.txt:1 (CMAKE_MINIMUM_REQUIRED):
2025-03-21T20:22:35.4180659Z   Compatibility with CMake < 3.10 will be removed from a future version of
2025-03-21T20:22:35.4181078Z   CMake.
2025-03-21T20:22:35.4181213Z 
2025-03-21T20:22:35.4181452Z   Update the VERSION argument <min> value.  Or, use the <min>...<max> syntax
2025-03-21T20:22:35.4182020Z   to tell CMake that the project requires at least <min> but has been updated
2025-03-21T20:22:35.4182517Z   to work with policies introduced by <max> or earlier.
2025-03-21T20:22:35.4182775Z 
2025-03-21T20:22:35.4182899Z 
2025-03-21T20:22:35.4183504Z CMake Deprecation Warning at backends/xnnpack/third-party/cpuinfo/CMakeLists.txt:1 (CMAKE_MINIMUM_REQUIRED):
2025-03-21T20:22:35.4184251Z   Compatibility with CMake < 3.10 will be removed from a future version of
2025-03-21T20:22:35.4184679Z   CMake.
2025-03-21T20:22:35.4184810Z 
2025-03-21T20:22:35.4185036Z   Update the VERSION argument <min> value.  Or, use the <min>...<max> syntax
2025-03-21T20:22:35.4185597Z   to tell CMake that the project requires at least <min> but has been updated
2025-03-21T20:22:35.4186091Z   to work with policies introduced by <max> or earlier.
2025-03-21T20:22:35.4186347Z 
2025-03-21T20:22:35.4186455Z 
2025-03-21T20:22:35.4186712Z -- Performing Test CMAKE_HAVE_LIBC_PTHREAD
2025-03-21T20:22:35.4187125Z -- Performing Test CMAKE_HAVE_LIBC_PTHREAD - Success
2025-03-21T20:22:35.4187488Z -- Found Threads: TRUE
2025-03-21T20:22:35.4188172Z CMake Deprecation Warning at backends/xnnpack/third-party/pthreadpool/CMakeLists.txt:1 (CMAKE_MINIMUM_REQUIRED):
2025-03-21T20:22:35.4188933Z   Compatibility with CMake < 3.10 will be removed from a future version of
2025-03-21T20:22:35.4189350Z   CMake.
2025-03-21T20:22:35.4189483Z 
2025-03-21T20:22:35.4189708Z   Update the VERSION argument <min> value.  Or, use the <min>...<max> syntax
2025-03-21T20:22:35.4190275Z   to tell CMake that the project requires at least <min> but has been updated
2025-03-21T20:22:35.4190769Z   to work with policies introduced by <max> or earlier.
2025-03-21T20:22:35.4191023Z 
2025-03-21T20:22:35.4191141Z 
2025-03-21T20:22:35.4191366Z -- Using python executable 'python'
2025-03-21T20:22:35.4191685Z -- Resolved buck2 as buck2.
2025-03-21T20:22:35.4191973Z -- Killing buck2 daemon
2025-03-21T20:22:35.4192232Z 'buck2 killall'
2025-03-21T20:22:35.4192492Z -- executorch: Generating source lists
2025-03-21T20:22:35.4193011Z -- executorch: Generating source file list /pytorch/executorch/build-x86/executorch_srcs.cmake
2025-03-21T20:22:35.4193701Z -- executorch: Using sources file /pytorch/executorch/build-x86/executorch_srcs.cmake
2025-03-21T20:22:35.4194212Z -- executorch: Using PAL default 'posix'
2025-03-21T20:22:35.4194548Z -- Generating operator lib:
2025-03-21T20:22:35.4194845Z --   LIB_NAME: portable_ops_lib
2025-03-21T20:22:35.4195248Z --   OPS_SCHEMA_YAML: /pytorch/executorch/kernels/portable/functions.yaml
2025-03-21T20:22:35.4195679Z --   ROOT_OPS: 
2025-03-21T20:22:35.4195930Z --   INCLUDE_ALL_OPS: 
2025-03-21T20:22:35.4197190Z Command - python;-m;codegen.tools.gen_oplist;--output_path=/pytorch/executorch/build-x86/kernels/portable/portable_ops_lib/selected_operators.yaml;--ops_schema_yaml_path="/pytorch/executorch/kernels/portable/functions.yaml"
2025-03-21T20:22:35.4198449Z -- Generating kernel bindings:
2025-03-21T20:22:35.4198764Z --   LIB_NAME: portable_ops_lib
2025-03-21T20:22:35.4199170Z --   FUNCTIONS_YAML: /pytorch/executorch/kernels/portable/functions.yaml
2025-03-21T20:22:35.4199607Z --   CUSTOM_OPS_YAML: 
2025-03-21T20:22:35.4199883Z --   ADD_EXCEPTION_BOUNDARY: FALSE
2025-03-21T20:22:35.4201566Z Generated files /pytorch/executorch/build-x86/kernels/portable/portable_ops_lib/RegisterCodegenUnboxedKernelsEverything.cpp;/pytorch/executorch/build-x86/kernels/portable/portable_ops_lib/Functions.h;/pytorch/executorch/build-x86/kernels/portable/portable_ops_lib/NativeFunctions.h
2025-03-21T20:22:35.4203028Z -- Generating operator lib:
2025-03-21T20:22:35.4203322Z --   LIB_NAME: portable_ops_lib
2025-03-21T20:22:35.4203616Z --   KERNEL_LIBS: portable_kernels
2025-03-21T20:22:35.4203923Z --   DEPS: executorch
2025-03-21T20:22:35.4204503Z CMake Deprecation Warning at third-party/gflags/CMakeLists.txt:73 (cmake_minimum_required):
2025-03-21T20:22:35.4205176Z   Compatibility with CMake < 3.10 will be removed from a future version of
2025-03-21T20:22:35.4205608Z   CMake.
2025-03-21T20:22:35.4205729Z 
2025-03-21T20:22:35.4205957Z   Update the VERSION argument <min> value.  Or, use the <min>...<max> syntax
2025-03-21T20:22:39.8270282Z   to tell CMake that the project requires at least <min> but has been updated
2025-03-21T20:22:39.8271218Z   to work with policies introduced by <max> or earlier.
2025-03-21T20:22:39.8271530Z 
2025-03-21T20:22:39.8271898Z 
2025-03-21T20:22:39.8272216Z -- Looking for C++ include unistd.h
2025-03-21T20:22:39.8272736Z -- Looking for C++ include unistd.h - found
2025-03-21T20:22:39.8273379Z -- Looking for C++ include stdint.h
2025-03-21T20:22:39.8273779Z -- Looking for C++ include stdint.h - found
2025-03-21T20:22:39.8274112Z -- Looking for C++ include inttypes.h
2025-03-21T20:22:39.8274513Z -- Looking for C++ include inttypes.h - found
2025-03-21T20:22:39.8274872Z -- Looking for C++ include sys/types.h
2025-03-21T20:22:39.8275311Z -- Looking for C++ include sys/types.h - found
2025-03-21T20:22:39.8275897Z -- Looking for C++ include sys/stat.h
2025-03-21T20:22:39.8276487Z -- Looking for C++ include sys/stat.h - found
2025-03-21T20:22:39.8276826Z -- Looking for C++ include fnmatch.h
2025-03-21T20:22:39.8277163Z -- Looking for C++ include fnmatch.h - found
2025-03-21T20:22:39.8277506Z -- Looking for C++ include stddef.h
2025-03-21T20:22:39.8277838Z -- Looking for C++ include stddef.h - found
2025-03-21T20:22:39.8278173Z -- Check size of uint32_t
2025-03-21T20:22:39.8278449Z -- Check size of uint32_t - done
2025-03-21T20:22:39.8278747Z -- Looking for strtoll
2025-03-21T20:22:39.8279021Z -- Looking for strtoll - found
2025-03-21T20:22:39.8279332Z -- Using qnn sdk root /tmp/qnn/2.28.0.241029
2025-03-21T20:22:39.8279703Z -- Using EXECUTORCH_SOURCE_DIR /pytorch/executorch
2025-03-21T20:22:39.8280452Z CMake Deprecation Warning at third-party/pybind11/CMakeLists.txt:13 (cmake_minimum_required):
2025-03-21T20:22:39.8281157Z   Compatibility with CMake < 3.10 will be removed from a future version of
2025-03-21T20:22:39.8281591Z   CMake.
2025-03-21T20:22:39.8281713Z 
2025-03-21T20:22:39.8281953Z   Update the VERSION argument <min> value.  Or, use the <min>...<max> syntax
2025-03-21T20:22:39.8282518Z   to tell CMake that the project requires at least <min> but has been updated
2025-03-21T20:22:39.8283001Z   to work with policies introduced by <max> or earlier.
2025-03-21T20:22:39.8283274Z 
2025-03-21T20:22:39.8283381Z 
2025-03-21T20:22:39.8283602Z -- pybind11 v2.13.6 
2025-03-21T20:22:39.8284059Z -- Found PythonInterp: python (found suitable version "3.10.16", minimum required is "3.7")
2025-03-21T20:22:39.8284669Z -- Found PythonLibs: /opt/conda/envs/py_3.10/lib/libpython3.10.so
2025-03-21T20:22:39.8285094Z -- Performing Test HAS_FLTO_THIN
2025-03-21T20:22:39.8285406Z -- Performing Test HAS_FLTO_THIN - Success
2025-03-21T20:22:39.8286042Z CMake Deprecation Warning at third-party/flatcc/CMakeLists.txt:2 (cmake_minimum_required):
2025-03-21T20:22:39.8287562Z   Compatibility with CMake < 3.10 will be removed from a future version of
2025-03-21T20:22:39.8287998Z   CMake.
2025-03-21T20:22:39.8288120Z 
2025-03-21T20:22:39.8288362Z   Update the VERSION argument <min> value.  Or, use the <min>...<max> syntax
2025-03-21T20:22:39.8288920Z   to tell CMake that the project requires at least <min> but has been updated
2025-03-21T20:22:39.8289521Z   to work with policies introduced by <max> or earlier.
2025-03-21T20:22:39.8289809Z 
2025-03-21T20:22:39.8289986Z 
2025-03-21T20:22:39.8290409Z -- dist install dir /pytorch/executorch/third-party/flatcc
2025-03-21T20:22:39.8290930Z -- lib install dir /pytorch/executorch/third-party/flatcc/lib
2025-03-21T20:22:39.8291341Z -- Setting Clang compiler options
2025-03-21T20:22:39.8292040Z -- Configured C_FLAGS:  -DFLATCC_REFLECTION=0 -Wstrict-prototypes -Wsign-conversion -Wconversion -std=c11 -pedantic -Wall -Wextra -Werror
2025-03-21T20:22:39.8292879Z CMake Deprecation Warning at CMakeLists.txt:2 (cmake_minimum_required):
2025-03-21T20:22:39.8293468Z   Compatibility with CMake < 3.10 will be removed from a future version of
2025-03-21T20:22:39.8293895Z   CMake.
2025-03-21T20:22:39.8294014Z 
2025-03-21T20:22:39.8294252Z   Update the VERSION argument <min> value.  Or, use the <min>...<max> syntax
2025-03-21T20:22:39.8294816Z   to tell CMake that the project requires at least <min> but has been updated
2025-03-21T20:22:39.8295294Z   to work with policies introduced by <max> or earlier.
2025-03-21T20:22:39.8295564Z 
2025-03-21T20:22:39.8295568Z 
2025-03-21T20:22:39.8295707Z -- The C compiler identification is Clang 12.0.1
2025-03-21T20:22:39.8296075Z -- Detecting C compiler ABI info
2025-03-21T20:22:39.8296397Z -- Detecting C compiler ABI info - done
2025-03-21T20:22:39.8296800Z -- Check for working C compiler: /opt/cache/bin/cc - skipped
2025-03-21T20:22:39.8297192Z -- Detecting C compile features
2025-03-21T20:22:39.8297508Z -- Detecting C compile features - done
2025-03-21T20:22:39.8297901Z -- dist install dir /pytorch/executorch/third-party/flatcc
2025-03-21T20:22:39.8298373Z -- lib install dir /pytorch/executorch/third-party/flatcc/lib
2025-03-21T20:22:39.8298780Z -- Setting Clang compiler options
2025-03-21T20:22:39.8299468Z -- Configured C_FLAGS:  -DFLATCC_REFLECTION=0 -Wstrict-prototypes -Wsign-conversion -Wconversion -std=c11 -pedantic -Wall -Wextra -Werror
2025-03-21T20:22:39.8300186Z -- Configuring done (0.2s)
2025-03-21T20:22:39.8300478Z -- Generating done (0.0s)
2025-03-21T20:22:39.8300899Z -- Build files have been written to: /pytorch/executorch/build-x86/_host_build
2025-03-21T20:22:39.8301466Z [  3%] Building C object src/runtime/CMakeFiles/flatccrt.dir/builder.c.o
2025-03-21T20:22:39.8302004Z [  6%] Building C object src/runtime/CMakeFiles/flatccrt.dir/emitter.c.o
2025-03-21T20:22:39.8302517Z [  9%] Building C object src/runtime/CMakeFiles/flatccrt.dir/refmap.c.o
2025-03-21T20:22:39.8303052Z [ 12%] Building C object src/runtime/CMakeFiles/flatccrt.dir/verifier.c.o
2025-03-21T20:22:39.8303620Z [ 15%] Building C object src/runtime/CMakeFiles/flatccrt.dir/json_parser.c.o
2025-03-21T20:22:39.8304195Z [ 18%] Building C object src/runtime/CMakeFiles/flatccrt.dir/json_printer.c.o
2025-03-21T20:22:39.8304813Z [ 21%] Linking C static library /pytorch/executorch/third-party/flatcc/lib/libflatccrt.a
2025-03-21T20:22:39.8305311Z [ 21%] Built target flatccrt
2025-03-21T20:22:39.8305767Z [ 24%] Building C object src/compiler/CMakeFiles/flatcc.dir/__/__/external/hash/str_set.c.o
2025-03-21T20:22:39.8306459Z [ 27%] Building C object src/compiler/CMakeFiles/flatcc.dir/__/__/external/hash/ptr_set.c.o
2025-03-21T20:22:39.8307137Z [ 30%] Building C object src/compiler/CMakeFiles/flatcc.dir/hash_tables/symbol_table.c.o
2025-03-21T20:22:39.8307795Z [ 33%] Building C object src/compiler/CMakeFiles/flatcc.dir/hash_tables/scope_table.c.o
2025-03-21T20:22:39.8308449Z [ 36%] Building C object src/compiler/CMakeFiles/flatcc.dir/hash_tables/name_table.c.o
2025-03-21T20:22:39.8309104Z [ 39%] Building C object src/compiler/CMakeFiles/flatcc.dir/hash_tables/schema_table.c.o
2025-03-21T20:22:39.8309943Z [ 42%] Building C object src/compiler/CMakeFiles/flatcc.dir/hash_tables/value_set.c.o
2025-03-21T20:22:39.8310552Z [ 45%] Building C object src/compiler/CMakeFiles/flatcc.dir/fileio.c.o
2025-03-21T20:22:39.8311079Z [ 48%] Building C object src/compiler/CMakeFiles/flatcc.dir/parser.c.o
2025-03-21T20:22:39.8311619Z [ 51%] Building C object src/compiler/CMakeFiles/flatcc.dir/semantics.c.o
2025-03-21T20:22:39.8312156Z [ 54%] Building C object src/compiler/CMakeFiles/flatcc.dir/coerce.c.o
2025-03-21T20:22:39.8312677Z [ 57%] Building C object src/compiler/CMakeFiles/flatcc.dir/flatcc.c.o
2025-03-21T20:22:39.8313195Z [ 60%] Building C object src/compiler/CMakeFiles/flatcc.dir/codegen_c.c.o
2025-03-21T20:22:39.8313765Z [ 63%] Building C object src/compiler/CMakeFiles/flatcc.dir/codegen_c_reader.c.o
2025-03-21T20:22:39.8314359Z [ 66%] Building C object src/compiler/CMakeFiles/flatcc.dir/codegen_c_sort.c.o
2025-03-21T20:22:39.8314962Z [ 69%] Building C object src/compiler/CMakeFiles/flatcc.dir/codegen_c_builder.c.o
2025-03-21T20:22:39.8315586Z [ 72%] Building C object src/compiler/CMakeFiles/flatcc.dir/codegen_c_verifier.c.o
2025-03-21T20:22:39.8316199Z [ 75%] Building C object src/compiler/CMakeFiles/flatcc.dir/codegen_c_sorter.c.o
2025-03-21T20:22:39.8316809Z [ 78%] Building C object src/compiler/CMakeFiles/flatcc.dir/codegen_c_json_parser.c.o
2025-03-21T20:22:39.8317466Z [ 81%] Building C object src/compiler/CMakeFiles/flatcc.dir/codegen_c_json_printer.c.o
2025-03-21T20:22:39.8318108Z [ 84%] Building C object src/compiler/CMakeFiles/flatcc.dir/__/runtime/builder.c.o
2025-03-21T20:22:39.8318723Z [ 87%] Building C object src/compiler/CMakeFiles/flatcc.dir/__/runtime/emitter.c.o
2025-03-21T20:22:39.8319332Z [ 90%] Building C object src/compiler/CMakeFiles/flatcc.dir/__/runtime/refmap.c.o
2025-03-21T20:22:39.8319954Z [ 93%] Linking C static library /pytorch/executorch/third-party/flatcc/lib/libflatcc.a
2025-03-21T20:22:39.8320429Z [ 93%] Built target flatcc
2025-03-21T20:22:39.8320822Z [ 96%] Building C object src/cli/CMakeFiles/flatcc_cli.dir/flatcc_cli.c.o
2025-03-21T20:22:39.8321389Z [100%] Linking C executable /pytorch/executorch/third-party/flatcc/bin/flatcc
2025-03-21T20:22:39.8321846Z [100%] Built target flatcc_cli
2025-03-21T20:22:39.8322153Z -- Generating operator lib:
2025-03-21T20:22:39.8322437Z --   LIB_NAME: quantized_ops_lib
2025-03-21T20:22:39.8322860Z --   OPS_SCHEMA_YAML: /pytorch/executorch/kernels/quantized/quantized.yaml
2025-03-21T20:22:39.8323290Z --   ROOT_OPS: 
2025-03-21T20:22:39.8323535Z --   INCLUDE_ALL_OPS: 
2025-03-21T20:22:39.8324843Z Command - python;-m;codegen.tools.gen_oplist;--output_path=/pytorch/executorch/build-x86/kernels/quantized/quantized_ops_lib/selected_operators.yaml;--ops_schema_yaml_path="/pytorch/executorch/kernels/quantized/quantized.yaml"
2025-03-21T20:22:39.8326056Z -- Generating kernel bindings:
2025-03-21T20:22:39.8326359Z --   LIB_NAME: quantized_ops_lib
2025-03-21T20:22:39.8326646Z --   FUNCTIONS_YAML: 
2025-03-21T20:22:39.8327044Z --   CUSTOM_OPS_YAML: /pytorch/executorch/kernels/quantized/quantized.yaml
2025-03-21T20:22:39.8327500Z --   ADD_EXCEPTION_BOUNDARY: FALSE
2025-03-21T20:22:39.8330738Z Generated files /pytorch/executorch/build-x86/kernels/quantized/quantized_ops_lib/RegisterCodegenUnboxedKernelsEverything.cpp;/pytorch/executorch/build-x86/kernels/quantized/quantized_ops_lib/Functions.h;/pytorch/executorch/build-x86/kernels/quantized/quantized_ops_lib/NativeFunctions.h;/pytorch/executorch/build-x86/kernels/quantized/quantized_ops_lib/RegisterCPUCustomOps.cpp;/pytorch/executorch/build-x86/kernels/quantized/quantized_ops_lib/RegisterSchema.cpp;/pytorch/executorch/build-x86/kernels/quantized/quantized_ops_lib/CustomOpsNativeFunctions.h
2025-03-21T20:22:39.8333696Z -- Generating operator lib:
2025-03-21T20:22:39.8334004Z --   LIB_NAME: quantized_ops_lib
2025-03-21T20:22:39.8334319Z --   KERNEL_LIBS: quantized_kernels
2025-03-21T20:22:39.8334628Z --   DEPS: executorch
2025-03-21T20:22:39.8335009Z -- 
2025-03-21T20:22:39.8335316Z -- ******** Summary ********
2025-03-21T20:22:39.8335616Z --   CMAKE_BUILD_TYPE              : Release
2025-03-21T20:22:39.8335953Z --   CMAKE_CXX_STANDARD            : 17
2025-03-21T20:22:39.8336289Z --   CMAKE_CXX_COMPILER_ID         : Clang
2025-03-21T20:22:39.8336613Z --   CMAKE_TOOLCHAIN_FILE          : 
2025-03-21T20:22:39.8336936Z --   BUCK2                         : buck2
2025-03-21T20:22:39.8337270Z --   PYTHON_EXECUTABLE             : python
2025-03-21T20:22:39.8337768Z --   FLATC_EXECUTABLE              : /pytorch/executorch/build-x86/third-party/flatbuffers/flatc
2025-03-21T20:22:39.8338382Z --   EXECUTORCH_ENABLE_LOGGING              : OFF
2025-03-21T20:22:39.8338756Z --   EXECUTORCH_ENABLE_PROGRAM_VERIFICATION : OFF
2025-03-21T20:22:39.8339198Z --   EXECUTORCH_LOG_LEVEL                   : Info
2025-03-21T20:22:39.8339572Z --   EXECUTORCH_BUILD_ANDROID_JNI           : OFF
2025-03-21T20:22:39.8339944Z --   EXECUTORCH_BUILD_ARM_BAREMETAL         : OFF
2025-03-21T20:22:39.8340322Z --   EXECUTORCH_BUILD_CADENCE               : OFF
2025-03-21T20:22:39.8340678Z --   EXECUTORCH_BUILD_COREML                : OFF
2025-03-21T20:22:39.8341043Z --   EXECUTORCH_BUILD_CPUINFO               : ON
2025-03-21T20:22:39.8341407Z --   EXECUTORCH_BUILD_DEVTOOLS              : ON
2025-03-21T20:22:42.7124110Z --   EXECUTORCH_BUILD_EXECUTOR_RUNNER       : ON
2025-03-21T20:22:42.7124847Z --   EXECUTORCH_BUILD_EXTENSION_DATA_LOADER : ON
2025-03-21T20:22:42.7125238Z --   EXECUTORCH_BUILD_EXTENSION_FLAT_TENSOR : ON
2025-03-21T20:22:42.7125616Z --   EXECUTORCH_BUILD_EXTENSION_LLM : OFF
2025-03-21T20:22:42.7125981Z --   EXECUTORCH_BUILD_EXTENSION_MODULE      : ON
2025-03-21T20:22:42.7126360Z --   EXECUTORCH_BUILD_EXTENSION_RUNNER_UTIL : OFF
2025-03-21T20:22:42.7126725Z --   EXECUTORCH_BUILD_EXTENSION_TENSOR      : ON
2025-03-21T20:22:42.7127103Z --   EXECUTORCH_BUILD_EXTENSION_TRAINING    : OFF
2025-03-21T20:22:42.7127475Z --   EXECUTORCH_BUILD_FLATC                 : ON
2025-03-21T20:22:42.7127871Z --   EXECUTORCH_BUILD_GFLAGS                : ON
2025-03-21T20:22:42.7128230Z --   EXECUTORCH_BUILD_HOST_TARGETS          : ON
2025-03-21T20:22:42.7128589Z --   EXECUTORCH_BUILD_KERNELS_CUSTOM        : OFF
2025-03-21T20:22:42.7129014Z --   EXECUTORCH_BUILD_KERNELS_CUSTOM_AOT    : OFF
2025-03-21T20:22:42.7129462Z --   EXECUTORCH_BUILD_KERNELS_OPTIMIZED     : OFF
2025-03-21T20:22:42.7129844Z --   EXECUTORCH_BUILD_KERNELS_QUANTIZED     : ON
2025-03-21T20:22:42.7130212Z --   EXECUTORCH_BUILD_MPS                   : OFF
2025-03-21T20:22:42.7130577Z --   EXECUTORCH_BUILD_NEURON                : OFF
2025-03-21T20:22:42.7130996Z --   EXECUTORCH_BUILD_PTHREADPOOL           : ON
2025-03-21T20:22:42.7131352Z --   EXECUTORCH_BUILD_PYBIND                : OFF
2025-03-21T20:22:42.7131762Z --   EXECUTORCH_BUILD_QNN                   : ON
2025-03-21T20:22:42.7132126Z --   EXECUTORCH_BUILD_SIZE_TEST             : OFF
2025-03-21T20:22:42.7132928Z --   EXECUTORCH_BUILD_TESTS                 : OFF
2025-03-21T20:22:42.7133413Z --   EXECUTORCH_BUILD_VULKAN                : OFF
2025-03-21T20:22:42.7133767Z --   EXECUTORCH_BUILD_XNNPACK               : OFF
2025-03-21T20:22:42.7134175Z -- Configuring done (12.9s)
2025-03-21T20:22:42.7134466Z -- Generating done (0.2s)
2025-03-21T20:22:42.7134901Z -- Build files have been written to: /pytorch/executorch/build-x86
2025-03-21T20:22:42.7135476Z + cmake --build /pytorch/executorch/build-x86 -j2 --target install
2025-03-21T20:22:42.7136211Z [  0%] Creating directories for 'flatbuffers'
2025-03-21T20:22:42.7137016Z [  0%] Building CXX object third-party/gflags/CMakeFiles/gflags_nothreads_static.dir/src/gflags.cc.o
2025-03-21T20:22:42.7137749Z [  0%] No download step for 'flatbuffers'
2025-03-21T20:22:42.7138201Z [  1%] No update step for 'flatbuffers'
2025-03-21T20:22:42.7138683Z [  1%] No patch step for 'flatbuffers'
2025-03-21T20:22:42.7139167Z [  1%] Performing configure step for 'flatbuffers'
2025-03-21T20:22:42.7139839Z CMake Warning:
2025-03-21T20:22:42.7140334Z   Ignoring empty string ("") provided on the command line.
2025-03-21T20:22:42.7140631Z 
2025-03-21T20:22:42.7140764Z 
2025-03-21T20:22:42.7141066Z fatal: No names found, cannot describe anything.
2025-03-21T20:22:42.7141578Z CMake Warning at CMake/Version.cmake:32 (message):
2025-03-21T20:22:42.7141976Z   git describe failed with exit code: 128
2025-03-21T20:22:42.7142210Z 
2025-03-21T20:22:42.7142439Z   Make sure you cloned with tags or run 'git fetch --tags'.
2025-03-21T20:22:42.7142838Z Call Stack (most recent call first):
2025-03-21T20:22:42.7143210Z   CMakeLists.txt:5 (include)
2025-03-21T20:22:42.7143390Z 
2025-03-21T20:22:42.7143513Z 
2025-03-21T20:22:42.7143741Z -- Proceeding with version: 24.3.25.0
2025-03-21T20:22:42.7144169Z -- The CXX compiler identification is Clang 12.0.1
2025-03-21T20:22:42.7144541Z -- Detecting CXX compiler ABI info
2025-03-21T20:22:42.7145351Z [  2%] Building CXX object third-party/gflags/CMakeFiles/gflags_nothreads_static.dir/src/gflags_reporting.cc.o
2025-03-21T20:22:42.7146500Z [  2%] Building CXX object third-party/gflags/CMakeFiles/gflags_nothreads_static.dir/src/gflags_completions.cc.o
2025-03-21T20:22:42.7147220Z -- Detecting CXX compiler ABI info - done
2025-03-21T20:22:42.7147744Z [  2%] Linking CXX static library libgflags_nothreads.a
2025-03-21T20:22:42.7148235Z -- Check for working CXX compiler: /opt/cache/bin/c++ - skipped
2025-03-21T20:22:42.7148704Z -- Detecting CXX compile features
2025-03-21T20:22:42.7149033Z -- Detecting CXX compile features - done
2025-03-21T20:22:42.7149446Z [  2%] Built target gflags_nothreads_static
2025-03-21T20:22:42.7149759Z -- Looking for strtof_l
2025-03-21T20:22:42.7150153Z [  2%] Generating etdump headers
2025-03-21T20:22:42.7150490Z [  2%] Built target etdump_schema
2025-03-21T20:22:42.7151173Z [  2%] Building C object third-party/flatcc/src/runtime/CMakeFiles/flatccrt.dir/builder.c.o
2025-03-21T20:22:42.7152105Z [  2%] Building C object third-party/flatcc/src/runtime/CMakeFiles/flatccrt.dir/emitter.c.o
2025-03-21T20:22:42.7153044Z [  3%] Building C object third-party/flatcc/src/runtime/CMakeFiles/flatccrt.dir/refmap.c.o
2025-03-21T20:22:42.7153601Z -- Looking for strtof_l - found
2025-03-21T20:22:42.7153948Z -- Looking for strtoull_l
2025-03-21T20:22:42.7154580Z [  3%] Building C object third-party/flatcc/src/runtime/CMakeFiles/flatccrt.dir/verifier.c.o
2025-03-21T20:22:42.7155535Z [  3%] Building C object third-party/flatcc/src/runtime/CMakeFiles/flatccrt.dir/json_parser.c.o
2025-03-21T20:22:42.7156150Z -- Looking for strtoull_l - found
2025-03-21T20:22:42.7156449Z -- Looking for realpath
2025-03-21T20:22:42.7157121Z [  3%] Building C object third-party/flatcc/src/runtime/CMakeFiles/flatccrt.dir/json_printer.c.o
2025-03-21T20:22:42.7158045Z [  3%] Linking C static library /pytorch/executorch/third-party/flatcc/lib/libflatccrt.a
2025-03-21T20:22:42.7158637Z [  3%] Built target flatccrt
2025-03-21T20:22:42.7159324Z [  3%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/api.c.o
2025-03-21T20:22:42.7159929Z -- Looking for realpath - found
2025-03-21T20:22:42.7160288Z -- CMAKE_CXX_FLAGS: "-DFLATBUFFERS_MAX_ALIGNMENT=1024"
2025-03-21T20:22:42.7160662Z -- Configuring done (0.9s)
2025-03-21T20:22:42.7160995Z -- Generating done (0.0s)
2025-03-21T20:22:42.7161457Z -- Build files have been written to: /pytorch/executorch/build-x86/third-party/flatbuffers
2025-03-21T20:22:42.7162076Z [  4%] Performing build step for 'flatbuffers'
2025-03-21T20:22:42.7162695Z [  2%] Building CXX object CMakeFiles/flatc.dir/src/idl_parser.cpp.o
2025-03-21T20:22:42.7163482Z [  4%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/cache.c.o
2025-03-21T20:22:42.7164407Z [  5%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/init.c.o
2025-03-21T20:22:42.7165495Z [  5%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/log.c.o
2025-03-21T20:22:42.7166425Z [  5%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/init.c.o
2025-03-21T20:22:42.7167212Z [  5%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_text.cpp.o
2025-03-21T20:22:42.7168004Z [  5%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/info.c.o
2025-03-21T20:22:42.7169020Z [  5%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/vendor.c.o
2025-03-21T20:22:42.7169891Z [  7%] Building CXX object CMakeFiles/flatc.dir/src/reflection.cpp.o
2025-03-21T20:22:42.7170700Z [  5%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/uarch.c.o
2025-03-21T20:22:42.7171643Z [  6%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/name.c.o
2025-03-21T20:22:42.7172401Z [ 10%] Building CXX object CMakeFiles/flatc.dir/src/util.cpp.o
2025-03-21T20:22:42.7173202Z [  6%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/topology.c.o
2025-03-21T20:22:42.7174145Z [  6%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/isa.c.o
2025-03-21T20:22:42.7174931Z [ 13%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_binary.cpp.o
2025-03-21T20:22:42.7175846Z [  6%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/cache/init.c.o
2025-03-21T20:22:42.7176884Z [  6%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/cache/descriptor.c.o
2025-03-21T20:22:42.7177968Z [  6%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/cache/deterministic.c.o
2025-03-21T20:22:42.7178828Z [ 15%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_cpp.cpp.o
2025-03-21T20:22:42.7179724Z [  7%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/linux/init.c.o
2025-03-21T20:22:42.7180729Z [  7%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/linux/cpuinfo.c.o
2025-03-21T20:22:42.7181563Z [ 18%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_csharp.cpp.o
2025-03-21T20:22:42.7182420Z [  7%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/linux/smallfile.c.o
2025-03-21T20:22:42.7183431Z [  7%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/linux/multiline.c.o
2025-03-21T20:22:42.7184245Z [ 21%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_dart.cpp.o
2025-03-21T20:22:42.7185074Z [  7%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/linux/cpulist.c.o
2025-03-21T20:22:42.7186127Z [  7%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/linux/processors.c.o
2025-03-21T20:22:42.7186861Z [  8%] Linking C static library libcpuinfo.a
2025-03-21T20:22:42.7187434Z [ 23%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_kotlin.cpp.o
2025-03-21T20:22:42.7187893Z [  8%] Built target cpuinfo
2025-03-21T20:22:42.7188626Z [  8%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/api.c.o
2025-03-21T20:22:42.7189638Z [  8%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/cache.c.o
2025-03-21T20:22:42.7190627Z [  8%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/init.c.o
2025-03-21T20:22:42.7191465Z [ 26%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_kotlin_kmp.cpp.o
2025-03-21T20:22:42.7192413Z [  8%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/log.c.o
2025-03-21T20:22:42.7193495Z [  8%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/x86/init.c.o
2025-03-21T20:22:42.7194318Z [ 28%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_go.cpp.o
2025-03-21T20:22:42.7195171Z [  9%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/x86/info.c.o
2025-03-21T20:22:42.7196222Z [  9%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/x86/vendor.c.o
2025-03-21T20:22:46.8121795Z [  9%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/x86/uarch.c.o
2025-03-21T20:22:46.8122735Z [ 31%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_java.cpp.o
2025-03-21T20:22:46.8123708Z [  9%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/x86/name.c.o
2025-03-21T20:22:46.8124826Z [  9%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/x86/topology.c.o
2025-03-21T20:22:46.8125680Z [ 34%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_ts.cpp.o
2025-03-21T20:22:46.8126522Z [  9%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/x86/isa.c.o
2025-03-21T20:22:46.8127605Z [ 10%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/x86/cache/init.c.o
2025-03-21T20:22:46.8128757Z [ 10%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/x86/cache/descriptor.c.o
2025-03-21T20:22:46.8129723Z [ 36%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_php.cpp.o
2025-03-21T20:22:46.8130681Z [ 10%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/x86/cache/deterministic.c.o
2025-03-21T20:22:46.8131847Z [ 10%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/x86/linux/init.c.o
2025-03-21T20:22:46.8132906Z [ 39%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_python.cpp.o
2025-03-21T20:22:46.8133822Z [ 10%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/x86/linux/cpuinfo.c.o
2025-03-21T20:22:46.8134948Z [ 10%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/linux/smallfile.c.o
2025-03-21T20:22:46.8135828Z [ 42%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_lobster.cpp.o
2025-03-21T20:22:46.8136776Z [ 11%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/linux/multiline.c.o
2025-03-21T20:22:46.8137882Z [ 11%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/linux/cpulist.c.o
2025-03-21T20:22:46.8139003Z [ 11%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/linux/processors.c.o
2025-03-21T20:22:46.8139880Z [ 44%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_rust.cpp.o
2025-03-21T20:22:46.8140475Z [ 11%] Linking C static library libcpuinfo_internals.a
2025-03-21T20:22:46.8140871Z [ 11%] Built target cpuinfo_internals
2025-03-21T20:22:46.8141620Z [ 11%] Building C object backends/xnnpack/third-party/pthreadpool/CMakeFiles/pthreadpool.dir/src/legacy-api.c.o
2025-03-21T20:22:46.8142481Z [ 47%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_fbs.cpp.o
2025-03-21T20:22:46.8143548Z [ 11%] Building C object backends/xnnpack/third-party/pthreadpool/CMakeFiles/pthreadpool.dir/src/portable-api.c.o
2025-03-21T20:22:46.8144611Z [ 12%] Building C object backends/xnnpack/third-party/pthreadpool/CMakeFiles/pthreadpool.dir/src/memory.c.o
2025-03-21T20:22:46.8145430Z [ 50%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_grpc.cpp.o
2025-03-21T20:22:46.8147498Z [ 12%] Building C object backends/xnnpack/third-party/pthreadpool/CMakeFiles/pthreadpool.dir/src/pthreads.c.o
2025-03-21T20:22:46.8148718Z [ 12%] Building C object backends/xnnpack/third-party/pthreadpool/CMakeFiles/pthreadpool.dir/src/fastpath.c.o
2025-03-21T20:22:46.8149595Z [ 52%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_json_schema.cpp.o
2025-03-21T20:22:46.8150235Z [ 12%] Linking C static library libpthreadpool.a
2025-03-21T20:22:46.8150624Z [ 12%] Built target pthreadpool
2025-03-21T20:22:46.8151338Z [ 12%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/__/__/external/hash/str_set.c.o
2025-03-21T20:22:46.8152382Z [ 12%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/__/__/external/hash/ptr_set.c.o
2025-03-21T20:22:46.8153203Z [ 55%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_swift.cpp.o
2025-03-21T20:22:46.8154062Z [ 12%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/hash_tables/symbol_table.c.o
2025-03-21T20:22:46.8155065Z [ 12%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/hash_tables/scope_table.c.o
2025-03-21T20:22:46.8155961Z [ 57%] Building CXX object CMakeFiles/flatc.dir/src/file_name_saving_file_manager.cpp.o
2025-03-21T20:22:46.8156865Z [ 12%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/hash_tables/name_table.c.o
2025-03-21T20:22:46.8157867Z [ 13%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/hash_tables/schema_table.c.o
2025-03-21T20:22:46.8158708Z [ 60%] Building CXX object CMakeFiles/flatc.dir/src/file_binary_writer.cpp.o
2025-03-21T20:22:46.8159550Z [ 13%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/hash_tables/value_set.c.o
2025-03-21T20:22:46.8160348Z [ 63%] Building CXX object CMakeFiles/flatc.dir/src/file_writer.cpp.o
2025-03-21T20:22:46.8161108Z [ 13%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/fileio.c.o
2025-03-21T20:22:46.8161944Z [ 13%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/parser.c.o
2025-03-21T20:22:46.8162653Z [ 65%] Building CXX object CMakeFiles/flatc.dir/src/flatc.cpp.o
2025-03-21T20:22:46.8163393Z [ 13%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/semantics.c.o
2025-03-21T20:22:46.8164235Z [ 13%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/coerce.c.o
2025-03-21T20:22:46.8165068Z [ 14%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/flatcc.c.o
2025-03-21T20:22:46.8165793Z [ 68%] Building CXX object CMakeFiles/flatc.dir/src/flatc_main.cpp.o
2025-03-21T20:22:46.8166550Z [ 14%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/codegen_c.c.o
2025-03-21T20:22:46.8167463Z [ 14%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/codegen_c_reader.c.o
2025-03-21T20:22:46.8168265Z [ 71%] Building CXX object CMakeFiles/flatc.dir/src/binary_annotator.cpp.o
2025-03-21T20:22:46.8169064Z [ 14%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/codegen_c_sort.c.o
2025-03-21T20:22:46.8170096Z [ 14%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/codegen_c_builder.c.o
2025-03-21T20:22:46.8170950Z [ 73%] Building CXX object CMakeFiles/flatc.dir/src/annotated_binary_text_gen.cpp.o
2025-03-21T20:22:46.8171816Z [ 14%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/codegen_c_verifier.c.o
2025-03-21T20:22:46.8172762Z [ 15%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/codegen_c_sorter.c.o
2025-03-21T20:22:46.8173724Z [ 15%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/codegen_c_json_parser.c.o
2025-03-21T20:22:46.8174680Z [ 76%] Building CXX object CMakeFiles/flatc.dir/src/bfbs_gen_lua.cpp.o
2025-03-21T20:22:46.8175503Z [ 15%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/codegen_c_json_printer.c.o
2025-03-21T20:22:46.8176478Z [ 15%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/__/runtime/builder.c.o
2025-03-21T20:22:46.8177267Z [ 78%] Building CXX object CMakeFiles/flatc.dir/src/bfbs_gen_nim.cpp.o
2025-03-21T20:22:46.8178071Z [ 15%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/__/runtime/emitter.c.o
2025-03-21T20:22:46.8179016Z [ 15%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/__/runtime/refmap.c.o
2025-03-21T20:22:46.8179888Z [ 16%] Linking C static library /pytorch/executorch/third-party/flatcc/lib/libflatcc.a
2025-03-21T20:22:46.8180398Z [ 16%] Built target flatcc
2025-03-21T20:22:46.8180900Z [ 81%] Building CXX object CMakeFiles/flatc.dir/src/code_generators.cpp.o
2025-03-21T20:22:46.8181677Z [ 16%] Building C object third-party/flatcc/src/cli/CMakeFiles/flatcc_cli.dir/flatcc_cli.c.o
2025-03-21T20:22:46.8182492Z [ 16%] Linking C executable /pytorch/executorch/third-party/flatcc/bin/flatcc
2025-03-21T20:22:46.8183286Z [ 16%] Built target flatcc_cli
2025-03-21T20:22:46.8183869Z [ 84%] Building CXX object CMakeFiles/flatc.dir/grpc/src/compiler/cpp_generator.cc.o
2025-03-21T20:22:46.8184722Z [ 86%] Building CXX object CMakeFiles/flatc.dir/grpc/src/compiler/go_generator.cc.o
2025-03-21T20:22:46.8185502Z [ 89%] Building CXX object CMakeFiles/flatc.dir/grpc/src/compiler/java_generator.cc.o
2025-03-21T20:22:46.8186296Z [ 92%] Building CXX object CMakeFiles/flatc.dir/grpc/src/compiler/python_generator.cc.o
2025-03-21T20:22:46.8187099Z [ 94%] Building CXX object CMakeFiles/flatc.dir/grpc/src/compiler/swift_generator.cc.o
2025-03-21T20:22:46.8187889Z [ 97%] Building CXX object CMakeFiles/flatc.dir/grpc/src/compiler/ts_generator.cc.o
2025-03-21T20:22:46.8188475Z [100%] Linking CXX executable flatc
2025-03-21T20:22:46.8188805Z [100%] Built target flatc
2025-03-21T20:22:46.8189172Z [ 16%] No install step for 'flatbuffers'
2025-03-21T20:22:46.8189592Z [ 16%] Completed 'flatbuffers'
2025-03-21T20:22:46.8189929Z [ 16%] Built target flatbuffers
2025-03-21T20:22:46.8190309Z [ 16%] Generating common_schema headers
2025-03-21T20:22:46.8190748Z [ 16%] Generating qualcomm ir schema headers
2025-03-21T20:22:46.8191114Z [ 16%] Built target common_schema
2025-03-21T20:22:46.8191416Z [ 16%] Built target qcir
2025-03-21T20:22:46.8191769Z [ 16%] Generating qnn_schema headers
2025-03-21T20:22:46.8192207Z [ 16%] Generating bundled_program headers
2025-03-21T20:22:46.8192551Z [ 16%] Built target qnn_schema
2025-03-21T20:22:46.8192866Z [ 16%] Built target bundled_program_schema
2025-03-21T20:22:46.8193308Z [ 16%] Generating scalar_type_schema headers
2025-03-21T20:22:51.1582077Z [ 16%] Generating program_schema headers
2025-03-21T20:22:51.1582746Z [ 16%] Built target scalar_type_schema
2025-03-21T20:22:51.1583426Z [ 16%] Building CXX object backends/qualcomm/CMakeFiles/qcir_utils.dir/aot/ir/qcir_utils.cpp.o
2025-03-21T20:22:51.1584000Z [ 16%] Built target program_schema
2025-03-21T20:22:51.1584688Z [ 16%] Building CXX object backends/qualcomm/CMakeFiles/qnn_executorch_logging.dir/runtime/Logging.cpp.o
2025-03-21T20:22:51.1585411Z [ 17%] Linking CXX static library libqcir_utils.a
2025-03-21T20:22:51.1585962Z [ 17%] Linking CXX static library libqnn_executorch_logging.a
2025-03-21T20:22:51.1586390Z [ 17%] Built target qcir_utils
2025-03-21T20:22:51.1586703Z [ 17%] Built target qnn_executorch_logging
2025-03-21T20:22:51.1587134Z [ 17%] Generating flat_tensor_schema headers
2025-03-21T20:22:51.1588161Z [ 17%] Building CXX object CMakeFiles/executorch_core.dir/runtime/backend/interface.cpp.o
2025-03-21T20:22:51.1588714Z [ 17%] Built target flat_tensor_schema
2025-03-21T20:22:51.1589289Z [ 17%] Building CXX object CMakeFiles/executorch_core.dir/runtime/core/evalue.cpp.o
2025-03-21T20:22:51.1590225Z [ 17%] Building CXX object CMakeFiles/executorch_core.dir/runtime/core/exec_aten/util/tensor_shape_to_c_string.cpp.o
2025-03-21T20:22:51.1591333Z [ 17%] Building CXX object backends/qualcomm/CMakeFiles/qnn_implementation.dir/runtime/backends/QnnImplementation.cpp.o
2025-03-21T20:22:51.1592423Z [ 18%] Building CXX object CMakeFiles/executorch_core.dir/runtime/core/exec_aten/util/tensor_util_portable.cpp.o
2025-03-21T20:22:51.1593203Z [ 18%] Linking CXX static library libqnn_implementation.a
2025-03-21T20:22:51.1593627Z [ 18%] Built target qnn_implementation
2025-03-21T20:22:51.1594613Z [ 18%] Building CXX object backends/qualcomm/CMakeFiles/qnn_sys_implementation.dir/runtime/backends/QnnSysImplementation.cpp.o
2025-03-21T20:22:51.1595685Z [ 18%] Building CXX object CMakeFiles/executorch_core.dir/runtime/core/portable_type/tensor_impl.cpp.o
2025-03-21T20:22:51.1596450Z [ 18%] Linking CXX static library libqnn_sys_implementation.a
2025-03-21T20:22:51.1596897Z [ 18%] Built target qnn_sys_implementation
2025-03-21T20:22:51.1597688Z [ 18%] Building CXX object backends/qualcomm/CMakeFiles/qnn_custom_protocol.dir/runtime/backends/QnnCustomProtocol.cpp.o
2025-03-21T20:22:51.1598675Z [ 18%] Building CXX object CMakeFiles/executorch_core.dir/runtime/core/tag.cpp.o
2025-03-21T20:22:51.1599474Z [ 18%] Building CXX object CMakeFiles/executorch_core.dir/runtime/core/tensor_layout.cpp.o
2025-03-21T20:22:51.1600218Z [ 18%] Linking CXX static library libqnn_custom_protocol.a
2025-03-21T20:22:51.1600643Z [ 18%] Built target qnn_custom_protocol
2025-03-21T20:22:51.1601355Z [ 18%] Building CXX object backends/qualcomm/CMakeFiles/qnn_profiler.dir/runtime/backends/QnnProfiler.cpp.o
2025-03-21T20:22:51.1602254Z [ 18%] Building CXX object CMakeFiles/executorch_core.dir/runtime/executor/method.cpp.o
2025-03-21T20:22:51.1602938Z [ 18%] Linking CXX static library libqnn_profiler.a
2025-03-21T20:22:51.1603329Z [ 18%] Built target qnn_profiler
2025-03-21T20:22:51.1603911Z [ 19%] Building CXX object backends/qualcomm/CMakeFiles/utils.dir/runtime/Utils.cpp.o
2025-03-21T20:22:51.1604736Z [ 19%] Building CXX object CMakeFiles/executorch_core.dir/runtime/executor/method_meta.cpp.o
2025-03-21T20:22:51.1605366Z [ 19%] Linking CXX static library libutils.a
2025-03-21T20:22:51.1605726Z [ 19%] Built target utils
2025-03-21T20:22:51.1606349Z [ 20%] Building CXX object CMakeFiles/executorch_core.dir/runtime/executor/program.cpp.o
2025-03-21T20:22:51.1607238Z [ 20%] Building CXX object backends/qualcomm/CMakeFiles/shared_buffer.dir/runtime/SharedBuffer.cpp.o
2025-03-21T20:22:51.1608146Z [ 20%] Building CXX object CMakeFiles/executorch_core.dir/runtime/executor/pte_data_map.cpp.o
2025-03-21T20:22:51.1608824Z [ 20%] Linking CXX static library libshared_buffer.a
2025-03-21T20:22:51.1609203Z [ 20%] Built target shared_buffer
2025-03-21T20:22:51.1609959Z [ 20%] Building CXX object backends/qualcomm/CMakeFiles/wrappers.dir/aot/wrappers/TensorWrapper.cpp.o
2025-03-21T20:22:51.1610928Z [ 20%] Building CXX object CMakeFiles/executorch_core.dir/runtime/executor/tensor_parser_exec_aten.cpp.o
2025-03-21T20:22:51.1611941Z [ 20%] Building CXX object backends/qualcomm/CMakeFiles/wrappers.dir/aot/wrappers/QuantizeParamsWrapper.cpp.o
2025-03-21T20:22:51.1613068Z [ 20%] Building CXX object CMakeFiles/executorch_core.dir/runtime/executor/tensor_parser_portable.cpp.o
2025-03-21T20:22:51.1614010Z [ 20%] Building CXX object backends/qualcomm/CMakeFiles/wrappers.dir/aot/wrappers/OpWrapper.cpp.o
2025-03-21T20:22:51.1614872Z [ 21%] Linking CXX static library libwrappers.a
2025-03-21T20:22:51.1615686Z [ 21%] Building CXX object CMakeFiles/executorch_core.dir/runtime/kernel/operator_registry.cpp.o
2025-03-21T20:22:51.1616252Z [ 21%] Built target wrappers
2025-03-21T20:22:51.1616821Z [ 21%] Building CXX object CMakeFiles/executorch_core.dir/runtime/platform/abort.cpp.o
2025-03-21T20:22:51.1617708Z [ 22%] Building CXX object backends/qualcomm/CMakeFiles/qnn_logger.dir/runtime/backends/QnnLogger.cpp.o
2025-03-21T20:22:51.1618567Z [ 23%] Building CXX object CMakeFiles/executorch_core.dir/runtime/platform/log.cpp.o
2025-03-21T20:22:51.1619362Z [ 23%] Building CXX object CMakeFiles/executorch_core.dir/runtime/platform/profiler.cpp.o
2025-03-21T20:22:51.1620019Z [ 23%] Linking CXX static library libqnn_logger.a
2025-03-21T20:22:51.1620398Z [ 23%] Built target qnn_logger
2025-03-21T20:22:51.1620982Z [ 23%] Building CXX object CMakeFiles/executorch_core.dir/runtime/platform/runtime.cpp.o
2025-03-21T20:22:51.1621794Z [ 23%] Building CXX object CMakeFiles/executorch_core.dir/schema/extended_header.cpp.o
2025-03-21T20:22:51.1622839Z [ 23%] Building CXX object backends/qualcomm/CMakeFiles/qnn_backend_cache.dir/runtime/backends/QnnBackendCache.cpp.o
2025-03-21T20:22:51.1623809Z [ 23%] Building CXX object CMakeFiles/executorch_core.dir/runtime/platform/default/posix.cpp.o
2025-03-21T20:22:51.1624503Z [ 23%] Linking CXX static library libexecutorch_core.a
2025-03-21T20:22:51.1625401Z [ 23%] Building CXX object backends/qualcomm/CMakeFiles/qnn_backend_cache.dir/runtime/backends/htpbackend/HtpBackendCache.cpp.o
2025-03-21T20:22:51.1626126Z [ 23%] Built target executorch_core
2025-03-21T20:22:51.1626935Z [ 24%] Building CXX object backends/qualcomm/CMakeFiles/qnn_device.dir/runtime/backends/QnnDeviceCommon.cpp.o
2025-03-21T20:22:51.1627992Z [ 24%] Building CXX object backends/qualcomm/CMakeFiles/qnn_device.dir/runtime/backends/htpbackend/HtpDevice.cpp.o
2025-03-21T20:22:51.1628871Z [ 24%] Linking CXX static library libqnn_backend_cache.a
2025-03-21T20:22:51.1629285Z [ 24%] Built target qnn_backend_cache
2025-03-21T20:22:51.1629919Z [ 24%] Building CXX object extension/tensor/CMakeFiles/extension_tensor.dir/tensor_ptr.cpp.o
2025-03-21T20:22:51.1631056Z [ 24%] Building CXX object backends/qualcomm/CMakeFiles/qnn_device.dir/runtime/backends/htpbackend/x86_64/HtpDevicePlatformInfoConfig.cpp.o
2025-03-21T20:22:51.1632183Z [ 24%] Building CXX object extension/tensor/CMakeFiles/extension_tensor.dir/tensor_ptr_maker.cpp.o
2025-03-21T20:22:51.1633487Z [ 24%] Building CXX object backends/qualcomm/CMakeFiles/qnn_device.dir/runtime/backends/htpbackend/x86_64/HtpDeviceCustomConfig.cpp.o
2025-03-21T20:22:51.1634376Z [ 24%] Linking CXX static library libextension_tensor.a
2025-03-21T20:22:51.1634777Z [ 24%] Built target extension_tensor
2025-03-21T20:22:51.1635682Z [ 24%] Building CXX object backends/qualcomm/CMakeFiles/PyQnnWrapperAdaptor.dir/aot/python/PyQnnWrapperAdaptor.cpp.o
2025-03-21T20:22:51.1636499Z [ 24%] Linking CXX static library libqnn_device.a
2025-03-21T20:22:51.1636885Z [ 24%] Built target qnn_device
2025-03-21T20:22:51.1637626Z [ 24%] Building CXX object backends/qualcomm/CMakeFiles/PyQnnWrapperAdaptor.dir/aot/wrappers/TensorWrapper.cpp.o
2025-03-21T20:22:51.1638588Z [ 24%] Building CXX object CMakeFiles/executorch.dir/kernels/prim_ops/et_copy_index.cpp.o
2025-03-21T20:22:51.1639397Z [ 24%] Linking CXX shared module PyQnnWrapperAdaptor.cpython-310-x86_64-linux-gnu.so
2025-03-21T20:22:51.1640281Z [ 25%] Building CXX object CMakeFiles/executorch.dir/kernels/prim_ops/et_view.cpp.o
2025-03-21T20:22:51.1641112Z [ 25%] Building CXX object CMakeFiles/executorch.dir/kernels/prim_ops/register_prim_ops.cpp.o
2025-03-21T20:22:51.1641789Z [ 25%] Linking CXX static library libexecutorch.a
2025-03-21T20:22:51.1642412Z [ 25%] Built target executorch
2025-03-21T20:22:51.1643092Z [ 25%] Building CXX object extension/threadpool/CMakeFiles/extension_threadpool.dir/threadpool.cpp.o
2025-03-21T20:22:51.1644089Z [ 26%] Building CXX object extension/threadpool/CMakeFiles/extension_threadpool.dir/threadpool_guard.cpp.o
2025-03-21T20:22:51.1645201Z [ 26%] Building CXX object extension/threadpool/CMakeFiles/extension_threadpool.dir/thread_parallel.cpp.o
2025-03-21T20:22:51.1646179Z [ 26%] Building CXX object extension/threadpool/CMakeFiles/extension_threadpool.dir/cpuinfo_utils.cpp.o
2025-03-21T20:22:51.1646955Z [ 26%] Linking CXX static library libextension_threadpool.a
2025-03-21T20:22:51.1647395Z [ 26%] Built target extension_threadpool
2025-03-21T20:22:51.1648143Z [ 26%] Building CXX object backends/qualcomm/CMakeFiles/qnn_backend.dir/runtime/backends/QnnBackendCommon.cpp.o
2025-03-21T20:22:51.1648914Z [ 26%] Linking CXX static library libqnn_backend.a
2025-03-21T20:22:51.1649372Z [ 26%] Built target qnn_backend
2025-03-21T20:22:51.1650035Z [ 27%] Building CXX object devtools/CMakeFiles/bundled_program.dir/bundled_program/bundled_program.cpp.o
2025-03-21T20:22:51.1650779Z [ 27%] Linking CXX static library libbundled_program.a
2025-03-21T20:22:51.1651186Z [ 27%] Built target bundled_program
2025-03-21T20:22:51.1651891Z [ 28%] Building CXX object extension/data_loader/CMakeFiles/extension_data_loader.dir/file_data_loader.cpp.o
2025-03-21T20:22:51.1653017Z [ 28%] Building CXX object extension/data_loader/CMakeFiles/extension_data_loader.dir/mmap_data_loader.cpp.o
2025-03-21T20:22:51.1654127Z [ 28%] Linking CXX static library libextension_data_loader.a
2025-03-21T20:22:58.4575675Z [ 28%] Built target extension_data_loader
2025-03-21T20:22:58.4577005Z [ 29%] Building CXX object kernels/quantized/CMakeFiles/quantized_kernels.dir/cpu/embeddingxb.cpp.o
2025-03-21T20:22:58.4578284Z [ 29%] Building CXX object kernels/quantized/CMakeFiles/quantized_kernels.dir/cpu/op_add.cpp.o
2025-03-21T20:22:58.4579228Z [ 29%] Building CXX object kernels/quantized/CMakeFiles/quantized_kernels.dir/cpu/op_choose_qparams.cpp.o
2025-03-21T20:22:58.4580254Z [ 29%] Building CXX object kernels/quantized/CMakeFiles/quantized_kernels.dir/cpu/op_dequantize.cpp.o
2025-03-21T20:22:58.4581193Z [ 29%] Building CXX object kernels/quantized/CMakeFiles/quantized_kernels.dir/cpu/op_embedding.cpp.o
2025-03-21T20:22:58.4582149Z [ 29%] Building CXX object kernels/quantized/CMakeFiles/quantized_kernels.dir/cpu/op_embedding2b.cpp.o
2025-03-21T20:22:58.4583118Z [ 30%] Building CXX object kernels/quantized/CMakeFiles/quantized_kernels.dir/cpu/op_embedding4b.cpp.o
2025-03-21T20:22:58.4584083Z [ 30%] Building CXX object kernels/quantized/CMakeFiles/quantized_kernels.dir/cpu/op_mixed_linear.cpp.o
2025-03-21T20:22:58.4585031Z [ 30%] Building CXX object kernels/quantized/CMakeFiles/quantized_kernels.dir/cpu/op_mixed_mm.cpp.o
2025-03-21T20:22:58.4585970Z [ 30%] Building CXX object kernels/quantized/CMakeFiles/quantized_kernels.dir/cpu/op_quantize.cpp.o
2025-03-21T20:22:58.4586705Z [ 30%] Linking CXX static library libquantized_kernels.a
2025-03-21T20:22:58.4587111Z [ 30%] Built target quantized_kernels
2025-03-21T20:22:58.4587815Z [ 30%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op__empty_dim_order.cpp.o
2025-03-21T20:22:58.4588816Z [ 30%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op__to_dim_order_copy.cpp.o
2025-03-21T20:22:58.4589757Z [ 31%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_abs.cpp.o
2025-03-21T20:22:58.4590633Z [ 31%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_acos.cpp.o
2025-03-21T20:22:58.4591729Z [ 31%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_acosh.cpp.o
2025-03-21T20:22:58.4592708Z [ 31%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_add.cpp.o
2025-03-21T20:22:58.4593582Z [ 31%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_addmm.cpp.o
2025-03-21T20:22:58.4594495Z [ 31%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_alias_copy.cpp.o
2025-03-21T20:22:58.4595422Z [ 32%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_allclose.cpp.o
2025-03-21T20:22:58.4596316Z [ 32%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_amax.cpp.o
2025-03-21T20:22:58.4597186Z [ 32%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_amin.cpp.o
2025-03-21T20:22:58.4598053Z [ 32%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_any.cpp.o
2025-03-21T20:22:58.4598930Z [ 32%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_arange.cpp.o
2025-03-21T20:22:58.4599514Z [ 32%] Built target PyQnnWrapperAdaptor
2025-03-21T20:22:58.4600116Z [ 32%] Building CXX object devtools/CMakeFiles/etdump.dir/etdump/etdump_flatcc.cpp.o
2025-03-21T20:22:58.4600961Z [ 32%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_argmax.cpp.o
2025-03-21T20:22:58.4601765Z [ 32%] Building CXX object devtools/CMakeFiles/etdump.dir/etdump/emitter.cpp.o
2025-03-21T20:22:58.4602584Z [ 33%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_argmin.cpp.o
2025-03-21T20:22:58.4603476Z [ 34%] Building CXX object devtools/CMakeFiles/etdump.dir/etdump/data_sinks/buffer_data_sink.cpp.o
2025-03-21T20:22:58.4604421Z [ 34%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_as_strided_copy.cpp.o
2025-03-21T20:22:58.4605355Z [ 34%] Building CXX object devtools/CMakeFiles/etdump.dir/etdump/data_sinks/file_data_sink.cpp.o
2025-03-21T20:22:58.4606242Z [ 34%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_asin.cpp.o
2025-03-21T20:22:58.4606910Z [ 34%] Linking CXX static library libetdump.a
2025-03-21T20:22:58.4607279Z [ 34%] Built target etdump
2025-03-21T20:22:58.4607990Z [ 34%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op__empty_dim_order.cpp.o
2025-03-21T20:22:58.4608968Z [ 34%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_asinh.cpp.o
2025-03-21T20:22:58.4610081Z [ 34%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op__to_dim_order_copy.cpp.o
2025-03-21T20:22:58.4611060Z [ 34%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_atan.cpp.o
2025-03-21T20:22:58.4611980Z [ 34%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_abs.cpp.o
2025-03-21T20:22:58.4612907Z [ 34%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_atan2.cpp.o
2025-03-21T20:22:58.4613840Z [ 35%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_acos.cpp.o
2025-03-21T20:22:58.4614753Z [ 36%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_atanh.cpp.o
2025-03-21T20:22:58.4615690Z [ 36%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_acosh.cpp.o
2025-03-21T20:22:58.4616648Z [ 36%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_avg_pool2d.cpp.o
2025-03-21T20:22:58.4617593Z [ 36%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_add.cpp.o
2025-03-21T20:22:58.4618545Z [ 36%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_bitwise_and.cpp.o
2025-03-21T20:22:58.4620115Z [ 36%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_addmm.cpp.o
2025-03-21T20:22:58.4621065Z [ 36%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_bitwise_not.cpp.o
2025-03-21T20:22:58.4622058Z [ 36%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_alias_copy.cpp.o
2025-03-21T20:22:58.4623038Z [ 36%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_bitwise_or.cpp.o
2025-03-21T20:22:58.4624019Z [ 36%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_allclose.cpp.o
2025-03-21T20:22:58.4624998Z [ 36%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_bitwise_xor.cpp.o
2025-03-21T20:22:58.4625954Z [ 37%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_amax.cpp.o
2025-03-21T20:22:58.4626870Z [ 38%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_bmm.cpp.o
2025-03-21T20:22:58.4627779Z [ 38%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_amin.cpp.o
2025-03-21T20:22:58.4628695Z [ 38%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_cat.cpp.o
2025-03-21T20:22:58.4629608Z [ 38%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_any.cpp.o
2025-03-21T20:22:58.4630567Z [ 38%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_cdist_forward.cpp.o
2025-03-21T20:22:58.4631538Z [ 38%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_arange.cpp.o
2025-03-21T20:22:58.4643321Z [ 38%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_ceil.cpp.o
2025-03-21T20:22:58.4645105Z [ 38%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_argmax.cpp.o
2025-03-21T20:22:58.4646575Z [ 38%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_clamp.cpp.o
2025-03-21T20:22:58.4648089Z [ 38%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_argmin.cpp.o
2025-03-21T20:22:58.4649650Z [ 38%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_clone.cpp.o
2025-03-21T20:22:58.4650661Z [ 39%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_as_strided_copy.cpp.o
2025-03-21T20:22:58.4651675Z [ 40%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_constant_pad_nd.cpp.o
2025-03-21T20:22:58.4652649Z [ 40%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_asin.cpp.o
2025-03-21T20:22:58.4653614Z [ 40%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_convolution.cpp.o
2025-03-21T20:22:58.4654602Z [ 40%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_asinh.cpp.o
2025-03-21T20:22:58.4655573Z [ 40%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_atan.cpp.o
2025-03-21T20:22:58.4656576Z [ 40%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_convolution_backward.cpp.o
2025-03-21T20:22:58.4657582Z [ 40%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_atan2.cpp.o
2025-03-21T20:22:58.4659034Z [ 40%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_copy.cpp.o
2025-03-21T20:22:58.4659985Z [ 40%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_atanh.cpp.o
2025-03-21T20:22:58.4660905Z [ 40%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_cos.cpp.o
2025-03-21T20:23:03.7552905Z [ 41%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_avg_pool2d.cpp.o
2025-03-21T20:23:03.7554187Z [ 41%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_cosh.cpp.o
2025-03-21T20:23:03.7555272Z [ 41%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_bitwise_and.cpp.o
2025-03-21T20:23:03.7556308Z [ 42%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_cumsum.cpp.o
2025-03-21T20:23:03.7557405Z [ 42%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_bitwise_not.cpp.o
2025-03-21T20:23:03.7558448Z [ 42%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_detach_copy.cpp.o
2025-03-21T20:23:03.7559532Z [ 42%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_bitwise_or.cpp.o
2025-03-21T20:23:03.7560590Z [ 42%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_diagonal_copy.cpp.o
2025-03-21T20:23:03.7561662Z [ 42%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_bitwise_xor.cpp.o
2025-03-21T20:23:03.7562728Z [ 42%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_div.cpp.o
2025-03-21T20:23:03.7563700Z [ 42%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_bmm.cpp.o
2025-03-21T20:23:03.7564713Z [ 42%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_embedding.cpp.o
2025-03-21T20:23:03.7565741Z [ 42%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_empty.cpp.o
2025-03-21T20:23:03.7566718Z [ 43%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_cat.cpp.o
2025-03-21T20:23:03.7567690Z [ 44%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_eq.cpp.o
2025-03-21T20:23:03.7568784Z [ 44%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_cdist_forward.cpp.o
2025-03-21T20:23:03.7569880Z [ 44%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_erf.cpp.o
2025-03-21T20:23:03.7570866Z [ 44%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_ceil.cpp.o
2025-03-21T20:23:03.7571904Z [ 44%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_exp.cpp.o
2025-03-21T20:23:03.7572898Z [ 44%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_clamp.cpp.o
2025-03-21T20:23:03.7573912Z [ 44%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_expand_copy.cpp.o
2025-03-21T20:23:03.7575004Z [ 44%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_clone.cpp.o
2025-03-21T20:23:03.7576007Z [ 44%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_expm1.cpp.o
2025-03-21T20:23:03.7577088Z [ 44%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_constant_pad_nd.cpp.o
2025-03-21T20:23:03.7578141Z [ 44%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_fill.cpp.o
2025-03-21T20:23:03.7579173Z [ 45%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_convolution.cpp.o
2025-03-21T20:23:03.7580372Z [ 45%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_convolution_backward.cpp.o
2025-03-21T20:23:03.7581430Z [ 46%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_flip.cpp.o
2025-03-21T20:23:03.7582458Z [ 46%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_copy.cpp.o
2025-03-21T20:23:03.7583556Z [ 46%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_floor.cpp.o
2025-03-21T20:23:03.7584626Z [ 46%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_cos.cpp.o
2025-03-21T20:23:03.7585706Z [ 46%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_floor_divide.cpp.o
2025-03-21T20:23:03.7586738Z [ 46%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_cosh.cpp.o
2025-03-21T20:23:03.7587707Z [ 46%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_fmod.cpp.o
2025-03-21T20:23:03.7588710Z [ 46%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_cumsum.cpp.o
2025-03-21T20:23:03.7589697Z [ 46%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_full.cpp.o
2025-03-21T20:23:03.7590672Z [ 47%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_detach_copy.cpp.o
2025-03-21T20:23:03.7591714Z [ 47%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_full_like.cpp.o
2025-03-21T20:23:03.7592710Z [ 47%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_diagonal_copy.cpp.o
2025-03-21T20:23:03.7593682Z [ 48%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_gather.cpp.o
2025-03-21T20:23:03.7594602Z [ 48%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_div.cpp.o
2025-03-21T20:23:03.7595562Z [ 48%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_ge.cpp.o
2025-03-21T20:23:03.7596520Z [ 48%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_embedding.cpp.o
2025-03-21T20:23:03.7597465Z [ 48%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_gelu.cpp.o
2025-03-21T20:23:03.7598407Z [ 48%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_empty.cpp.o
2025-03-21T20:23:03.7599323Z [ 48%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_glu.cpp.o
2025-03-21T20:23:03.7600234Z [ 48%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_eq.cpp.o
2025-03-21T20:23:03.7601124Z [ 48%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_gt.cpp.o
2025-03-21T20:23:03.7602118Z [ 49%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_erf.cpp.o
2025-03-21T20:23:03.7603120Z [ 49%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_hardtanh.cpp.o
2025-03-21T20:23:03.7604063Z [ 49%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_exp.cpp.o
2025-03-21T20:23:03.7604990Z [ 50%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_index.cpp.o
2025-03-21T20:23:03.7605961Z [ 50%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_expand_copy.cpp.o
2025-03-21T20:23:03.7606994Z [ 50%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_index_put.cpp.o
2025-03-21T20:23:03.7608257Z [ 50%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_expm1.cpp.o
2025-03-21T20:23:03.7609481Z [ 50%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_index_select.cpp.o
2025-03-21T20:23:03.7610450Z [ 50%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_fill.cpp.o
2025-03-21T20:23:03.7611382Z [ 50%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_isinf.cpp.o
2025-03-21T20:23:03.7612361Z [ 50%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_isnan.cpp.o
2025-03-21T20:23:03.7613506Z [ 50%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_flip.cpp.o
2025-03-21T20:23:03.7614410Z [ 50%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_le.cpp.o
2025-03-21T20:23:03.7615337Z [ 51%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_floor.cpp.o
2025-03-21T20:23:03.7616299Z [ 52%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_leaky_relu.cpp.o
2025-03-21T20:23:03.7617293Z [ 52%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_floor_divide.cpp.o
2025-03-21T20:23:03.7618305Z [ 52%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_lift_fresh_copy.cpp.o
2025-03-21T20:23:03.7619295Z [ 52%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_fmod.cpp.o
2025-03-21T20:23:03.7620313Z [ 52%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_linear_scratch_example.cpp.o
2025-03-21T20:23:03.7621308Z [ 52%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_full.cpp.o
2025-03-21T20:23:03.7622223Z [ 52%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_log.cpp.o
2025-03-21T20:23:03.7623170Z [ 52%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_full_like.cpp.o
2025-03-21T20:23:03.7624117Z [ 52%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_log10.cpp.o
2025-03-21T20:23:03.7625053Z [ 52%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_gather.cpp.o
2025-03-21T20:23:03.7625985Z [ 52%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_log1p.cpp.o
2025-03-21T20:23:09.1621152Z [ 53%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_ge.cpp.o
2025-03-21T20:23:09.1622556Z [ 54%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_log2.cpp.o
2025-03-21T20:23:09.1623559Z [ 54%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_gelu.cpp.o
2025-03-21T20:23:09.1624560Z [ 54%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_log_softmax.cpp.o
2025-03-21T20:23:09.1625522Z [ 54%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_glu.cpp.o
2025-03-21T20:23:09.1626476Z [ 54%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_logical_and.cpp.o
2025-03-21T20:23:09.1627423Z [ 54%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_gt.cpp.o
2025-03-21T20:23:09.1628429Z [ 54%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_logical_not.cpp.o
2025-03-21T20:23:09.1629467Z [ 54%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_hardtanh.cpp.o
2025-03-21T20:23:09.1630598Z [ 54%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_logical_or.cpp.o
2025-03-21T20:23:09.1631690Z [ 54%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_index.cpp.o
2025-03-21T20:23:09.1633286Z [ 54%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_logical_xor.cpp.o
2025-03-21T20:23:09.1634302Z [ 55%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_index_put.cpp.o
2025-03-21T20:23:09.1635256Z [ 56%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_logit.cpp.o
2025-03-21T20:23:09.1636235Z [ 56%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_index_select.cpp.o
2025-03-21T20:23:09.1637539Z [ 56%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_lt.cpp.o
2025-03-21T20:23:09.1638467Z [ 56%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_isinf.cpp.o
2025-03-21T20:23:09.1639435Z [ 56%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_masked_fill.cpp.o
2025-03-21T20:23:09.1640395Z [ 56%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_isnan.cpp.o
2025-03-21T20:23:09.1641367Z [ 56%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_masked_scatter.cpp.o
2025-03-21T20:23:09.1642329Z [ 56%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_le.cpp.o
2025-03-21T20:23:09.1643287Z [ 56%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_masked_select.cpp.o
2025-03-21T20:23:09.1644271Z [ 56%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_leaky_relu.cpp.o
2025-03-21T20:23:09.1645218Z [ 56%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_max.cpp.o
2025-03-21T20:23:09.1646193Z [ 57%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_lift_fresh_copy.cpp.o
2025-03-21T20:23:09.1647250Z [ 58%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_max_pool2d_with_indices.cpp.o
2025-03-21T20:23:09.1648351Z [ 58%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_linear_scratch_example.cpp.o
2025-03-21T20:23:09.1649578Z [ 58%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_max_pool2d_with_indices_backward.cpp.o
2025-03-21T20:23:09.1650625Z [ 58%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_log.cpp.o
2025-03-21T20:23:09.1651587Z [ 58%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_maximum.cpp.o
2025-03-21T20:23:09.1652524Z [ 58%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_log10.cpp.o
2025-03-21T20:23:09.1653443Z [ 58%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_mean.cpp.o
2025-03-21T20:23:09.1654376Z [ 58%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_log1p.cpp.o
2025-03-21T20:23:09.1655291Z [ 58%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_min.cpp.o
2025-03-21T20:23:09.1656213Z [ 58%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_log2.cpp.o
2025-03-21T20:23:09.1657149Z [ 58%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_minimum.cpp.o
2025-03-21T20:23:09.1658137Z [ 59%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_log_softmax.cpp.o
2025-03-21T20:23:09.1659074Z [ 60%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_mm.cpp.o
2025-03-21T20:23:09.1660028Z [ 60%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_logical_and.cpp.o
2025-03-21T20:23:09.1660973Z [ 60%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_mul.cpp.o
2025-03-21T20:23:09.1661930Z [ 60%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_logical_not.cpp.o
2025-03-21T20:23:09.1663127Z [ 60%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_narrow_copy.cpp.o
2025-03-21T20:23:09.1664202Z [ 60%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_logical_or.cpp.o
2025-03-21T20:23:09.1665251Z [ 60%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_native_batch_norm.cpp.o
2025-03-21T20:23:09.1666448Z [ 60%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_logical_xor.cpp.o
2025-03-21T20:23:09.1667467Z [ 60%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_native_group_norm.cpp.o
2025-03-21T20:23:09.1668454Z [ 60%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_logit.cpp.o
2025-03-21T20:23:09.1669440Z [ 60%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_native_layer_norm.cpp.o
2025-03-21T20:23:09.1670422Z [ 61%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_lt.cpp.o
2025-03-21T20:23:09.1671327Z [ 62%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_ne.cpp.o
2025-03-21T20:23:09.1672267Z [ 62%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_masked_fill.cpp.o
2025-03-21T20:23:09.1673322Z [ 62%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_masked_scatter.cpp.o
2025-03-21T20:23:09.1674281Z [ 62%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_neg.cpp.o
2025-03-21T20:23:09.1675248Z [ 62%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_masked_select.cpp.o
2025-03-21T20:23:09.1676222Z [ 62%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_nonzero.cpp.o
2025-03-21T20:23:09.1677158Z [ 62%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_max.cpp.o
2025-03-21T20:23:09.1678079Z [ 62%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_ones.cpp.o
2025-03-21T20:23:09.1679091Z [ 62%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_max_pool2d_with_indices.cpp.o
2025-03-21T20:23:09.1680150Z [ 62%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_pdist_forward.cpp.o
2025-03-21T20:23:09.1681108Z [ 62%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_permute_copy.cpp.o
2025-03-21T20:23:09.1682216Z [ 63%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_max_pool2d_with_indices_backward.cpp.o
2025-03-21T20:23:09.1683302Z [ 64%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_pixel_shuffle.cpp.o
2025-03-21T20:23:09.1684290Z [ 64%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_maximum.cpp.o
2025-03-21T20:23:09.1685283Z [ 64%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_pixel_unshuffle.cpp.o
2025-03-21T20:23:09.1686192Z [ 64%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_pow.cpp.o
2025-03-21T20:23:09.1687118Z [ 64%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_mean.cpp.o
2025-03-21T20:23:09.1688043Z [ 64%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_prod.cpp.o
2025-03-21T20:23:09.1688970Z [ 64%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_min.cpp.o
2025-03-21T20:23:09.1690037Z [ 64%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_minimum.cpp.o
2025-03-21T20:23:09.1691008Z [ 64%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_reciprocal.cpp.o
2025-03-21T20:23:09.1691958Z [ 64%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_mm.cpp.o
2025-03-21T20:23:09.1692924Z [ 65%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_reflection_pad1d.cpp.o
2025-03-21T20:23:14.4237189Z [ 65%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_reflection_pad2d.cpp.o
2025-03-21T20:23:14.4238390Z [ 66%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_mul.cpp.o
2025-03-21T20:23:14.4239384Z [ 66%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_reflection_pad3d.cpp.o
2025-03-21T20:23:14.4240406Z [ 66%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_narrow_copy.cpp.o
2025-03-21T20:23:14.4241349Z [ 66%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_relu.cpp.o
2025-03-21T20:23:14.4242347Z [ 66%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_native_batch_norm.cpp.o
2025-03-21T20:23:14.4243358Z [ 66%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_remainder.cpp.o
2025-03-21T20:23:14.4244387Z [ 66%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_native_group_norm.cpp.o
2025-03-21T20:23:14.4245386Z [ 66%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_repeat.cpp.o
2025-03-21T20:23:14.4246396Z [ 66%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_native_layer_norm.cpp.o
2025-03-21T20:23:14.4247407Z [ 66%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_ne.cpp.o
2025-03-21T20:23:14.4248376Z [ 67%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_repeat_interleave.cpp.o
2025-03-21T20:23:14.4249484Z [ 67%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_replication_pad1d.cpp.o
2025-03-21T20:23:14.4250476Z [ 68%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_neg.cpp.o
2025-03-21T20:23:14.4251462Z [ 68%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_replication_pad2d.cpp.o
2025-03-21T20:23:14.4252477Z [ 68%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_nonzero.cpp.o
2025-03-21T20:23:14.4253476Z [ 68%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_replication_pad3d.cpp.o
2025-03-21T20:23:14.4254456Z [ 68%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_ones.cpp.o
2025-03-21T20:23:14.4255367Z [ 68%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_roll.cpp.o
2025-03-21T20:23:14.4256339Z [ 68%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_pdist_forward.cpp.o
2025-03-21T20:23:14.4257303Z [ 68%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_round.cpp.o
2025-03-21T20:23:14.4258273Z [ 68%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_permute_copy.cpp.o
2025-03-21T20:23:14.4259236Z [ 69%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_rsqrt.cpp.o
2025-03-21T20:23:14.4260240Z [ 69%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_pixel_shuffle.cpp.o
2025-03-21T20:23:14.4261199Z [ 69%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_rsub.cpp.o
2025-03-21T20:23:14.4262298Z [ 70%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_pixel_unshuffle.cpp.o
2025-03-21T20:23:14.4263305Z [ 70%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_scalar_tensor.cpp.o
2025-03-21T20:23:14.4264267Z [ 70%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_pow.cpp.o
2025-03-21T20:23:14.4265201Z [ 70%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_scatter.cpp.o
2025-03-21T20:23:14.4266306Z [ 70%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_prod.cpp.o
2025-03-21T20:23:14.4267266Z [ 70%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_scatter_add.cpp.o
2025-03-21T20:23:14.4268261Z [ 70%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_reciprocal.cpp.o
2025-03-21T20:23:14.4269251Z [ 70%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_select_copy.cpp.o
2025-03-21T20:23:14.4270258Z [ 70%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_reflection_pad1d.cpp.o
2025-03-21T20:23:14.4271286Z [ 71%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_select_scatter.cpp.o
2025-03-21T20:23:14.4272444Z [ 71%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_reflection_pad2d.cpp.o
2025-03-21T20:23:14.4273533Z [ 72%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_reflection_pad3d.cpp.o
2025-03-21T20:23:14.4274523Z [ 72%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_sigmoid.cpp.o
2025-03-21T20:23:14.4275465Z [ 72%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_relu.cpp.o
2025-03-21T20:23:14.4276383Z [ 72%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_sign.cpp.o
2025-03-21T20:23:14.4277331Z [ 72%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_remainder.cpp.o
2025-03-21T20:23:14.4278272Z [ 72%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_sin.cpp.o
2025-03-21T20:23:14.4279143Z [ 72%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_sinh.cpp.o
2025-03-21T20:23:14.4280079Z [ 72%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_repeat.cpp.o
2025-03-21T20:23:14.4281040Z [ 72%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_slice_copy.cpp.o
2025-03-21T20:23:14.4282063Z [ 72%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_repeat_interleave.cpp.o
2025-03-21T20:23:14.4283085Z [ 73%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_slice_scatter.cpp.o
2025-03-21T20:23:14.4284106Z [ 73%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_replication_pad1d.cpp.o
2025-03-21T20:23:14.4285106Z [ 73%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_softmax.cpp.o
2025-03-21T20:23:14.4286113Z [ 74%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_replication_pad2d.cpp.o
2025-03-21T20:23:14.4287121Z [ 74%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_split_copy.cpp.o
2025-03-21T20:23:14.4288141Z [ 74%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_replication_pad3d.cpp.o
2025-03-21T20:23:14.4289259Z [ 74%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_split_with_sizes_copy.cpp.o
2025-03-21T20:23:14.4290264Z [ 74%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_roll.cpp.o
2025-03-21T20:23:14.4291229Z [ 74%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_round.cpp.o
2025-03-21T20:23:14.4292152Z [ 74%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_sqrt.cpp.o
2025-03-21T20:23:14.4293091Z [ 74%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_rsqrt.cpp.o
2025-03-21T20:23:14.4294268Z [ 74%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_squeeze_copy.cpp.o
2025-03-21T20:23:14.4295397Z [ 74%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_rsub.cpp.o
2025-03-21T20:23:14.4296327Z [ 75%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_stack.cpp.o
2025-03-21T20:23:14.4297304Z [ 76%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_scalar_tensor.cpp.o
2025-03-21T20:23:14.4298368Z [ 76%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_sub.cpp.o
2025-03-21T20:23:14.4299869Z [ 76%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_sum.cpp.o
2025-03-21T20:23:14.4301363Z [ 76%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_scatter.cpp.o
2025-03-21T20:23:14.4302967Z [ 76%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_scatter_add.cpp.o
2025-03-21T20:23:14.4304354Z [ 76%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_t_copy.cpp.o
2025-03-21T20:23:14.4305760Z [ 76%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_select_copy.cpp.o
2025-03-21T20:23:14.4307113Z [ 76%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_tan.cpp.o
2025-03-21T20:23:14.4308498Z [ 76%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_select_scatter.cpp.o
2025-03-21T20:23:14.4309981Z [ 76%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_tanh.cpp.o
2025-03-21T20:23:14.4311293Z [ 77%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_to_copy.cpp.o
2025-03-21T20:23:14.4312847Z [ 77%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_sigmoid.cpp.o
2025-03-21T20:23:19.6053456Z [ 78%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_sign.cpp.o
2025-03-21T20:23:19.6054547Z [ 78%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_topk.cpp.o
2025-03-21T20:23:19.6055483Z [ 78%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_sin.cpp.o
2025-03-21T20:23:19.6056455Z [ 78%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_transpose_copy.cpp.o
2025-03-21T20:23:19.6057422Z [ 78%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_sinh.cpp.o
2025-03-21T20:23:19.6058324Z [ 78%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_tril.cpp.o
2025-03-21T20:23:19.6059280Z [ 78%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_slice_copy.cpp.o
2025-03-21T20:23:19.6060229Z [ 78%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_trunc.cpp.o
2025-03-21T20:23:19.6061215Z [ 78%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_slice_scatter.cpp.o
2025-03-21T20:23:19.6062211Z [ 78%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_unbind_copy.cpp.o
2025-03-21T20:23:19.6063185Z [ 79%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_softmax.cpp.o
2025-03-21T20:23:19.6064158Z [ 79%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_unfold_copy.cpp.o
2025-03-21T20:23:19.6065133Z [ 80%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_split_copy.cpp.o
2025-03-21T20:23:19.6066127Z [ 80%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_unsqueeze_copy.cpp.o
2025-03-21T20:23:19.6067129Z [ 80%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_upsample_bilinear2d.cpp.o
2025-03-21T20:23:19.6068629Z [ 80%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_split_with_sizes_copy.cpp.o
2025-03-21T20:23:19.6070072Z [ 80%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_upsample_nearest2d.cpp.o
2025-03-21T20:23:19.6071467Z [ 80%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_sqrt.cpp.o
2025-03-21T20:23:19.6072404Z [ 80%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_var.cpp.o
2025-03-21T20:23:19.6073359Z [ 80%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_squeeze_copy.cpp.o
2025-03-21T20:23:19.6074343Z [ 80%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_view_copy.cpp.o
2025-03-21T20:23:19.6075301Z [ 80%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_stack.cpp.o
2025-03-21T20:23:19.6076249Z [ 81%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_where.cpp.o
2025-03-21T20:23:19.6077177Z [ 82%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_sub.cpp.o
2025-03-21T20:23:19.6078098Z [ 82%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_zeros.cpp.o
2025-03-21T20:23:19.6079010Z [ 82%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_sum.cpp.o
2025-03-21T20:23:19.6080014Z [ 82%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/pattern/unary_ufunc_realh.cpp.o
2025-03-21T20:23:19.6081023Z [ 82%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_t_copy.cpp.o
2025-03-21T20:23:19.6082089Z [ 82%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/pattern/unary_ufunc_realhb_to_bool.cpp.o
2025-03-21T20:23:19.6083135Z [ 82%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_tan.cpp.o
2025-03-21T20:23:19.6084244Z [ 82%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/pattern/unary_ufunc_realhbbf16_to_floathbf16.cpp.o
2025-03-21T20:23:19.6085368Z [ 82%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_tanh.cpp.o
2025-03-21T20:23:19.6086458Z [ 82%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/activation_ops_util.cpp.o
2025-03-21T20:23:19.6087461Z [ 82%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_to_copy.cpp.o
2025-03-21T20:23:19.6088472Z [ 83%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/advanced_index_util.cpp.o
2025-03-21T20:23:19.6089573Z [ 84%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_topk.cpp.o
2025-03-21T20:23:19.6090570Z [ 84%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/broadcast_util.cpp.o
2025-03-21T20:23:19.6091678Z [ 84%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_transpose_copy.cpp.o
2025-03-21T20:23:19.6092685Z [ 84%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_tril.cpp.o
2025-03-21T20:23:19.6093656Z [ 84%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/copy_ops_util.cpp.o
2025-03-21T20:23:19.6094627Z [ 84%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_trunc.cpp.o
2025-03-21T20:23:19.6095614Z [ 84%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/delinearize_index.cpp.o
2025-03-21T20:23:19.6096749Z [ 84%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/distance_util.cpp.o
2025-03-21T20:23:19.6097948Z [ 84%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_unbind_copy.cpp.o
2025-03-21T20:23:19.6098942Z [ 84%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/dtype_util.cpp.o
2025-03-21T20:23:19.6099935Z [ 84%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_unfold_copy.cpp.o
2025-03-21T20:23:19.6100922Z [ 85%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/index_util.cpp.o
2025-03-21T20:23:19.6101933Z [ 86%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_unsqueeze_copy.cpp.o
2025-03-21T20:23:19.6102951Z [ 86%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/kernel_ops_util.cpp.o
2025-03-21T20:23:19.6104017Z [ 86%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_upsample_bilinear2d.cpp.o
2025-03-21T20:23:19.6105080Z [ 86%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/matmul_ops_util.cpp.o
2025-03-21T20:23:19.6106137Z [ 86%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_upsample_nearest2d.cpp.o
2025-03-21T20:23:19.6107219Z [ 86%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/normalization_ops_util.cpp.o
2025-03-21T20:23:19.6108234Z [ 86%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_var.cpp.o
2025-03-21T20:23:19.6109207Z [ 86%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/padding_util.cpp.o
2025-03-21T20:23:19.6110440Z [ 86%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_view_copy.cpp.o
2025-03-21T20:23:19.6111443Z [ 86%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/reduce_util.cpp.o
2025-03-21T20:23:19.6112429Z [ 86%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_where.cpp.o
2025-03-21T20:23:19.6113401Z [ 87%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/repeat_util.cpp.o
2025-03-21T20:23:19.6114373Z [ 88%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_zeros.cpp.o
2025-03-21T20:23:19.6115372Z [ 88%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/select_copy_util.cpp.o
2025-03-21T20:23:19.6116456Z [ 88%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/pattern/unary_ufunc_realh.cpp.o
2025-03-21T20:23:19.6117480Z [ 88%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/slice_util.cpp.o
2025-03-21T20:23:19.6118576Z [ 88%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/pattern/unary_ufunc_realhb_to_bool.cpp.o
2025-03-21T20:23:19.6119677Z [ 88%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/upsample_util.cpp.o
2025-03-21T20:23:19.6120868Z [ 88%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/pattern/unary_ufunc_realhbbf16_to_floathbf16.cpp.o
2025-03-21T20:23:19.6121785Z [ 88%] Linking CXX static library libportable_kernels.a
2025-03-21T20:23:19.6122200Z [ 88%] Built target portable_kernels
2025-03-21T20:23:19.6122968Z [ 89%] Building CXX object backends/qualcomm/CMakeFiles/qnn_context.dir/runtime/backends/QnnContextCommon.cpp.o
2025-03-21T20:23:19.6124067Z [ 89%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/activation_ops_util.cpp.o
2025-03-21T20:23:19.6125181Z [ 89%] Building CXX object backends/qualcomm/CMakeFiles/qnn_context.dir/runtime/backends/htpbackend/HtpContext.cpp.o
2025-03-21T20:23:27.2591726Z [ 89%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/advanced_index_util.cpp.o
2025-03-21T20:23:27.2593080Z [ 90%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/broadcast_util.cpp.o
2025-03-21T20:23:27.2594296Z [ 90%] Building CXX object backends/qualcomm/CMakeFiles/qnn_context.dir/runtime/backends/htpbackend/x86_64/HtpContextCustomConfig.cpp.o
2025-03-21T20:23:27.2595481Z [ 90%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/copy_ops_util.cpp.o
2025-03-21T20:23:27.2596259Z [ 90%] Linking CXX static library libqnn_context.a
2025-03-21T20:23:27.2596653Z [ 90%] Built target qnn_context
2025-03-21T20:23:27.2597401Z [ 90%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/delinearize_index.cpp.o
2025-03-21T20:23:27.2598459Z [ 90%] Building CXX object extension/flat_tensor/CMakeFiles/extension_flat_tensor.dir/flat_tensor_data_map.cpp.o
2025-03-21T20:23:27.2599524Z [ 90%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/distance_util.cpp.o
2025-03-21T20:23:27.2600615Z [ 90%] Building CXX object extension/flat_tensor/CMakeFiles/extension_flat_tensor.dir/serialize/flat_tensor_header.cpp.o
2025-03-21T20:23:27.2601682Z [ 90%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/dtype_util.cpp.o
2025-03-21T20:23:27.2602488Z [ 90%] Linking CXX static library libextension_flat_tensor.a
2025-03-21T20:23:27.2602927Z [ 90%] Built target extension_flat_tensor
2025-03-21T20:23:27.2603669Z [ 90%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/index_util.cpp.o
2025-03-21T20:23:27.2604479Z [ 91%] Generating selected_operators.yaml for quantized_ops_lib
2025-03-21T20:23:27.2605360Z [ 92%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/kernel_ops_util.cpp.o
2025-03-21T20:23:27.2606141Z [ 92%] Generating code for kernel registration
2025-03-21T20:23:27.2606957Z [ 92%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/matmul_ops_util.cpp.o
2025-03-21T20:23:27.2608275Z [ 92%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/normalization_ops_util.cpp.o
2025-03-21T20:23:27.2609838Z [ 92%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/padding_util.cpp.o
2025-03-21T20:23:27.2611276Z [ 92%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/reduce_util.cpp.o
2025-03-21T20:23:27.2612663Z [ 92%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/repeat_util.cpp.o
2025-03-21T20:23:27.2614230Z [ 93%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/select_copy_util.cpp.o
2025-03-21T20:23:27.2615666Z [ 93%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/slice_util.cpp.o
2025-03-21T20:23:27.2617033Z [ 93%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/upsample_util.cpp.o
2025-03-21T20:23:27.2618649Z [ 93%] Building CXX object kernels/quantized/CMakeFiles/quantized_ops_lib.dir/quantized_ops_lib/RegisterCodegenUnboxedKernelsEverything.cpp.o
2025-03-21T20:23:27.2619914Z [ 93%] Linking CXX static library liboptimized_portable_kernels.a
2025-03-21T20:23:27.2620653Z [ 93%] Linking CXX static library libquantized_ops_lib.a
2025-03-21T20:23:27.2621242Z [ 93%] Built target quantized_ops_lib
2025-03-21T20:23:27.2621803Z [ 94%] Generating selected_operators.yaml for portable_ops_lib
2025-03-21T20:23:27.2622379Z [ 94%] Built target optimized_portable_kernels
2025-03-21T20:23:27.2623405Z [ 94%] Building CXX object backends/qualcomm/CMakeFiles/qnn_graph.dir/runtime/backends/QnnGraphCommon.cpp.o
2025-03-21T20:23:27.2624418Z [ 94%] Generating code for kernel registration
2025-03-21T20:23:27.2625330Z [ 95%] Building CXX object backends/qualcomm/CMakeFiles/qnn_graph.dir/runtime/backends/htpbackend/HtpGraph.cpp.o
2025-03-21T20:23:27.2626701Z [ 95%] Building CXX object backends/qualcomm/CMakeFiles/qnn_graph.dir/runtime/backends/htpbackend/HtpGraphCustomConfig.cpp.o
2025-03-21T20:23:27.2628220Z [ 95%] Building CXX object backends/qualcomm/CMakeFiles/qnn_graph.dir/runtime/backends/htpbackend/x86_64/HtpGraphCustomConfig.cpp.o
2025-03-21T20:23:27.2629235Z [ 95%] Linking CXX static library libqnn_graph.a
2025-03-21T20:23:27.2629675Z [ 95%] Built target qnn_graph
2025-03-21T20:23:27.2630539Z [ 95%] Building CXX object backends/qualcomm/CMakeFiles/qnn_mem_manager.dir/runtime/backends/QnnMemManager.cpp.o
2025-03-21T20:23:27.2631432Z [ 96%] Linking CXX static library libqnn_mem_manager.a
2025-03-21T20:23:27.2632028Z [ 96%] Built target qnn_mem_manager
2025-03-21T20:23:27.2633110Z [ 97%] Building CXX object extension/module/CMakeFiles/extension_module.dir/__/flat_tensor/flat_tensor_data_map.cpp.o
2025-03-21T20:23:27.2634541Z [ 97%] Building CXX object extension/module/CMakeFiles/extension_module.dir/__/flat_tensor/serialize/flat_tensor_header.cpp.o
2025-03-21T20:23:27.2635831Z [ 97%] Building CXX object extension/module/CMakeFiles/extension_module.dir/module.cpp.o
2025-03-21T20:23:27.2636592Z [ 97%] Linking CXX shared library libextension_module.so
2025-03-21T20:23:27.2637076Z [ 97%] Built target extension_module
2025-03-21T20:23:27.2638080Z [ 97%] Building CXX object extension/module/CMakeFiles/extension_module_static.dir/__/flat_tensor/flat_tensor_data_map.cpp.o
2025-03-21T20:23:27.2639604Z [ 97%] Building CXX object extension/module/CMakeFiles/extension_module_static.dir/__/flat_tensor/serialize/flat_tensor_header.cpp.o
2025-03-21T20:23:27.2640845Z [ 98%] Building CXX object extension/module/CMakeFiles/extension_module_static.dir/module.cpp.o
2025-03-21T20:23:27.2642253Z [ 98%] Building CXX object kernels/portable/CMakeFiles/portable_ops_lib.dir/portable_ops_lib/RegisterCodegenUnboxedKernelsEverything.cpp.o
2025-03-21T20:23:27.2643433Z [ 98%] Linking CXX static library libextension_module_static.a
2025-03-21T20:23:27.2644230Z [ 98%] Linking CXX static library libportable_ops_lib.a
2025-03-21T20:23:27.2644674Z [ 98%] Built target extension_module_static
2025-03-21T20:23:27.2645117Z [ 98%] Built target portable_ops_lib
2025-03-21T20:23:27.2646067Z [ 98%] Building CXX object backends/qualcomm/CMakeFiles/qnn_factory.dir/runtime/backends/QnnBackendFactory.cpp.o
2025-03-21T20:23:27.2647284Z [ 98%] Building CXX object CMakeFiles/executor_runner.dir/examples/portable/executor_runner/executor_runner.cpp.o
2025-03-21T20:23:27.2648462Z [ 98%] Building CXX object CMakeFiles/executor_runner.dir/extension/data_loader/file_data_loader.cpp.o
2025-03-21T20:23:27.2649428Z [ 98%] Linking CXX static library libqnn_factory.a
2025-03-21T20:23:27.2649829Z [ 98%] Built target qnn_factory
2025-03-21T20:23:27.2650626Z [ 99%] Building CXX object CMakeFiles/executor_runner.dir/extension/evalue_util/print_evalue.cpp.o
2025-03-21T20:23:27.2651640Z [ 99%] Building CXX object CMakeFiles/executor_runner.dir/extension/runner_util/inputs.cpp.o
2025-03-21T20:23:27.2652704Z [ 99%] Building CXX object backends/qualcomm/CMakeFiles/qnn_manager.dir/runtime/QnnManager.cpp.o
2025-03-21T20:23:27.2653795Z [ 99%] Building CXX object CMakeFiles/executor_runner.dir/extension/runner_util/inputs_portable.cpp.o
2025-03-21T20:23:27.2654838Z [ 99%] Building CXX object backends/qualcomm/CMakeFiles/qnn_manager.dir/aot/wrappers/TensorWrapper.cpp.o
2025-03-21T20:23:27.2656152Z [ 99%] Building CXX object CMakeFiles/executor_runner.dir/runtime/executor/test/test_backend_compiler_lib.cpp.o
2025-03-21T20:23:27.2657174Z [ 99%] Linking CXX static library libqnn_manager.a
2025-03-21T20:23:27.2657615Z [ 99%] Built target qnn_manager
2025-03-21T20:23:27.2658494Z [ 99%] Building CXX object backends/qualcomm/CMakeFiles/qnn_executorch_backend.dir/runtime/QnnExecuTorchBackend.cpp.o
2025-03-21T20:23:27.2659390Z [ 99%] Linking CXX executable executor_runner
2025-03-21T20:23:27.2659986Z [100%] Linking CXX shared library libqnn_executorch_backend.so
2025-03-21T20:23:27.2660477Z [100%] Built target executor_runner
2025-03-21T20:23:27.2661300Z [100%] Building CXX object backends/qualcomm/CMakeFiles/PyQnnManagerAdaptor.dir/aot/python/PyQnnManagerAdaptor.cpp.o
2025-03-21T20:23:27.2662070Z [100%] Built target qnn_executorch_backend
2025-03-21T20:23:27.2662711Z [100%] Linking CXX shared module PyQnnManagerAdaptor.cpython-310-x86_64-linux-gnu.so
2025-03-21T20:23:27.2663321Z [100%] Built target PyQnnManagerAdaptor
2025-03-21T20:23:27.2663741Z Install the project...
2025-03-21T20:23:27.2664062Z -- Install configuration: "Release"
2025-03-21T20:23:27.2664508Z -- Installing: /pytorch/executorch/build-x86/include/fxdiv.h
2025-03-21T20:23:27.2665064Z -- Installing: /pytorch/executorch/build-x86/share/cpuinfo/cpuinfo-config.cmake
2025-03-21T20:23:27.2665682Z -- Installing: /pytorch/executorch/build-x86/lib/libcpuinfo.a
2025-03-21T20:23:27.2666169Z -- Installing: /pytorch/executorch/build-x86/include/cpuinfo.h
2025-03-21T20:23:27.2666785Z -- Installing: /pytorch/executorch/build-x86/share/cpuinfo/cpuinfo-targets.cmake
2025-03-21T20:23:27.2667701Z -- Installing: /pytorch/executorch/build-x86/share/cpuinfo/cpuinfo-targets-release.cmake
2025-03-21T20:23:27.2668487Z -- Installing: /pytorch/executorch/build-x86/lib/pkgconfig/libcpuinfo.pc
2025-03-21T20:23:27.2669153Z -- Installing: /pytorch/executorch/build-x86/include/pthreadpool.h
2025-03-21T20:23:27.2669732Z -- Installing: /pytorch/executorch/build-x86/lib/libpthreadpool.a
2025-03-21T20:23:27.2670475Z -- Installing: /pytorch/executorch/build-x86/lib/liboptimized_portable_kernels.a
2025-03-21T20:23:27.2671285Z -- Installing: /pytorch/executorch/build-x86/lib/libportable_kernels.a
2025-03-21T20:23:27.2672054Z -- Installing: /pytorch/executorch/build-x86/lib/libportable_ops_lib.a
2025-03-21T20:23:27.2672962Z -- Installing: /pytorch/executorch/build-x86/include/executorch/kernels/portable/Functions.h
2025-03-21T20:23:27.2695370Z -- Installing: /pytorch/executorch/build-x86/include/executorch/kernels/portable/NativeFunctions.h
2025-03-21T20:23:27.2696626Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core
2025-03-21T20:23:27.2697469Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/array_ref.h
2025-03-21T20:23:27.2698195Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/data_loader.h
2025-03-21T20:23:27.2699049Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/defines.h
2025-03-21T20:23:27.2699915Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/error.h
2025-03-21T20:23:27.2700811Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/evalue.h
2025-03-21T20:23:27.2701673Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/event_tracer.h
2025-03-21T20:23:27.2702591Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/event_tracer_hooks.h
2025-03-21T20:23:27.2703598Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/event_tracer_hooks_delegate.h
2025-03-21T20:23:27.2704522Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/exec_aten
2025-03-21T20:23:27.2705416Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/exec_aten/exec_aten.h
2025-03-21T20:23:27.2706322Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/exec_aten/testing_util
2025-03-21T20:23:27.2707520Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/exec_aten/testing_util/tensor_factory.h
2025-03-21T20:23:27.2708626Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/exec_aten/testing_util/tensor_util.h
2025-03-21T20:23:27.2709698Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/exec_aten/testing_util/test
2025-03-21T20:23:27.2710598Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/exec_aten/util
2025-03-21T20:23:27.2711499Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/exec_aten/util/dim_order_util.h
2025-03-21T20:23:27.2712455Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/exec_aten/util/scalar_type_util.h
2025-03-21T20:23:27.2713688Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/exec_aten/util/tensor_dimension_limit.h
2025-03-21T20:23:27.2714683Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/exec_aten/util/tensor_shape_to_c_string.h
2025-03-21T20:23:27.2715896Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/exec_aten/util/tensor_util.h
2025-03-21T20:23:27.2716885Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/exec_aten/util/test
2025-03-21T20:23:27.2717799Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/freeable_buffer.h
2025-03-21T20:23:27.2719006Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/hierarchical_allocator.h
2025-03-21T20:23:27.2719825Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/memory_allocator.h
2025-03-21T20:23:27.2720595Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/named_data_map.h
2025-03-21T20:23:27.2721338Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/portable_type
2025-03-21T20:23:27.2722120Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/portable_type/bfloat16.h
2025-03-21T20:23:27.2722987Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/portable_type/bfloat16_math.h
2025-03-21T20:23:27.2723858Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/portable_type/bits_types.h
2025-03-21T20:23:27.2724669Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/portable_type/c10
2025-03-21T20:23:27.2725460Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/portable_type/c10/c10
2025-03-21T20:23:27.2726409Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/portable_type/c10/c10/macros
2025-03-21T20:23:27.2727332Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/portable_type/c10/c10/macros/Export.h
2025-03-21T20:23:27.2728275Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/portable_type/c10/c10/macros/Macros.h
2025-03-21T20:23:27.2729265Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/portable_type/c10/c10/util
2025-03-21T20:23:27.2730194Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/portable_type/c10/c10/util/BFloat16-inl.h
2025-03-21T20:23:27.2731197Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/portable_type/c10/c10/util/BFloat16-math.h
2025-03-21T20:23:27.2732183Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/portable_type/c10/c10/util/BFloat16.h
2025-03-21T20:23:27.2733413Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/portable_type/c10/c10/util/Half-inl.h
2025-03-21T20:23:27.2734353Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/portable_type/c10/c10/util/Half.h
2025-03-21T20:23:27.2735318Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/portable_type/c10/c10/util/TypeSafeSignMath.h
2025-03-21T20:23:27.2736531Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/portable_type/c10/c10/util/bit_cast.h
2025-03-21T20:23:27.2737546Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/portable_type/c10/c10/util/floating_point_utils.h
2025-03-21T20:23:27.2738550Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/portable_type/c10/c10/util/irange.h
2025-03-21T20:23:27.2739443Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/portable_type/complex.h
2025-03-21T20:23:27.2740278Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/portable_type/device.h
2025-03-21T20:23:27.2741082Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/portable_type/half.h
2025-03-21T20:23:27.2741901Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/portable_type/optional.h
2025-03-21T20:23:27.2742751Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/portable_type/qint_types.h
2025-03-21T20:23:27.2743596Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/portable_type/scalar.h
2025-03-21T20:23:27.2744439Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/portable_type/scalar_type.h
2025-03-21T20:23:27.2745307Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/portable_type/string_view.h
2025-03-21T20:23:27.2746150Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/portable_type/tensor.h
2025-03-21T20:23:27.2746980Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/portable_type/tensor_impl.h
2025-03-21T20:23:27.2747862Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/portable_type/tensor_options.h
2025-03-21T20:23:27.2748699Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/portable_type/test
2025-03-21T20:23:27.2749428Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/result.h
2025-03-21T20:23:27.2750101Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/span.h
2025-03-21T20:23:27.2750757Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/tag.h
2025-03-21T20:23:27.2751440Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/tensor_layout.h
2025-03-21T20:23:27.2752221Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/tensor_shape_dynamism.h
2025-03-21T20:23:27.2752956Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/core/test
2025-03-21T20:23:27.2753591Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/kernel
2025-03-21T20:23:27.2754294Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/kernel/kernel_includes.h
2025-03-21T20:23:27.2755110Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/kernel/kernel_runtime_context.h
2025-03-21T20:23:27.2755958Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/kernel/operator_registry.h
2025-03-21T20:23:27.2756683Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/kernel/test
2025-03-21T20:23:27.2757403Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/kernel/test/test_util.h
2025-03-21T20:23:27.2758228Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/kernel/thread_parallel_interface.h
2025-03-21T20:23:27.2758997Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/platform
2025-03-21T20:23:27.2759670Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/platform/abort.h
2025-03-21T20:23:27.2760381Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/platform/assert.h
2025-03-21T20:23:27.2761081Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/platform/clock.h
2025-03-21T20:23:27.2761886Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/platform/compat_unistd.h
2025-03-21T20:23:27.2762706Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/platform/compiler.h
2025-03-21T20:23:27.2763430Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/platform/default
2025-03-21T20:23:27.2764127Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/platform/log.h
2025-03-21T20:23:27.2764843Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/platform/platform.h
2025-03-21T20:23:27.2765569Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/platform/profiler.h
2025-03-21T20:23:27.2766305Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/platform/runtime.h
2025-03-21T20:23:40.2766250Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/platform/system.h
2025-03-21T20:23:40.2767349Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/platform/test
2025-03-21T20:23:40.2768158Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/platform/test/stub_platform.h
2025-03-21T20:23:40.2769104Z -- Installing: /pytorch/executorch/build-x86/include/executorch/runtime/platform/types.h
2025-03-21T20:23:40.2769887Z -- Installing: /pytorch/executorch/build-x86/include/executorch/extension/kernel_util
2025-03-21T20:23:40.2770739Z -- Installing: /pytorch/executorch/build-x86/include/executorch/extension/kernel_util/make_boxed_from_unboxed_functor.h
2025-03-21T20:23:40.2771675Z -- Installing: /pytorch/executorch/build-x86/include/executorch/extension/kernel_util/meta_programming.h
2025-03-21T20:23:40.2772528Z -- Installing: /pytorch/executorch/build-x86/include/executorch/extension/kernel_util/test
2025-03-21T20:23:40.2773406Z -- Installing: /pytorch/executorch/build-x86/include/executorch/extension/kernel_util/type_list.h
2025-03-21T20:23:40.2774130Z -- Installing: /pytorch/executorch/build-x86/include/executorch/extension/tensor
2025-03-21T20:23:40.2774817Z -- Installing: /pytorch/executorch/build-x86/include/executorch/extension/tensor/tensor.h
2025-03-21T20:23:40.2775594Z -- Installing: /pytorch/executorch/build-x86/include/executorch/extension/tensor/tensor_accessor.h
2025-03-21T20:23:40.2776409Z -- Installing: /pytorch/executorch/build-x86/include/executorch/extension/tensor/tensor_ptr.h
2025-03-21T20:23:40.2777201Z -- Installing: /pytorch/executorch/build-x86/include/executorch/extension/tensor/tensor_ptr_maker.h
2025-03-21T20:23:40.2777952Z -- Installing: /pytorch/executorch/build-x86/include/executorch/extension/tensor/test
2025-03-21T20:23:40.2778632Z -- Installing: /pytorch/executorch/build-x86/include/executorch/extension/threadpool
2025-03-21T20:23:40.2779389Z -- Installing: /pytorch/executorch/build-x86/include/executorch/extension/threadpool/cpuinfo_utils.h
2025-03-21T20:23:40.2780235Z -- Installing: /pytorch/executorch/build-x86/include/executorch/extension/threadpool/test
2025-03-21T20:23:40.2781103Z -- Installing: /pytorch/executorch/build-x86/include/executorch/extension/threadpool/threadpool.h
2025-03-21T20:23:40.2781954Z -- Installing: /pytorch/executorch/build-x86/include/executorch/extension/threadpool/threadpool_guard.h
2025-03-21T20:23:40.2782645Z -- Installing: /pytorch/executorch/build-x86/lib/libexecutorch.a
2025-03-21T20:23:40.2783180Z -- Installing: /pytorch/executorch/build-x86/lib/libexecutorch_core.a
2025-03-21T20:23:40.2783868Z -- Installing: /pytorch/executorch/build-x86/lib/cmake/ExecuTorch/executorch-config.cmake
2025-03-21T20:23:40.2784656Z -- Installing: /pytorch/executorch/build-x86/lib/libqnn_executorch_backend.so
2025-03-21T20:23:40.2785243Z -- Installing: /pytorch/executorch/build-x86/lib/libbundled_program.a
2025-03-21T20:23:40.2785765Z -- Installing: /pytorch/executorch/build-x86/lib/libetdump.a
2025-03-21T20:23:40.2786253Z -- Installing: /pytorch/executorch/build-x86/lib/libflatccrt.a
2025-03-21T20:23:40.2786787Z -- Installing: /pytorch/executorch/build-x86/lib/libextension_data_loader.a
2025-03-21T20:23:40.2787598Z -- Installing: /pytorch/executorch/build-x86/lib/libextension_flat_tensor.a
2025-03-21T20:23:40.2788314Z -- Installing: /pytorch/executorch/build-x86/lib/libextension_module.so
2025-03-21T20:23:40.2788907Z -- Installing: /pytorch/executorch/build-x86/lib/libextension_module_static.a
2025-03-21T20:23:40.2789542Z -- Installing: /pytorch/executorch/build-x86/lib/libextension_tensor.a
2025-03-21T20:23:40.2790226Z -- Installing: /pytorch/executorch/build-x86/lib/libextension_threadpool.a
2025-03-21T20:23:40.2790798Z -- Installing: /pytorch/executorch/build-x86/lib/libquantized_kernels.a
2025-03-21T20:23:40.2791363Z -- Installing: /pytorch/executorch/build-x86/lib/libquantized_ops_lib.a
2025-03-21T20:23:40.2792023Z -- Installing: /pytorch/executorch/build-x86/include/executorch/kernels/quantized/Functions.h
2025-03-21T20:23:40.2792816Z -- Installing: /pytorch/executorch/build-x86/include/executorch/kernels/quantized/NativeFunctions.h
2025-03-21T20:23:40.2793501Z + rm -f '/pytorch/executorch/backends/qualcomm/python/*'
2025-03-21T20:23:40.2794978Z + cp -fv /pytorch/executorch/build-x86/backends/qualcomm/PyQnnManagerAdaptor.cpython-310-x86_64-linux-gnu.so /pytorch/executorch/build-x86/backends/qualcomm/PyQnnWrapperAdaptor.cpython-310-x86_64-linux-gnu.so /pytorch/executorch/backends/qualcomm/python
2025-03-21T20:23:40.2797087Z '/pytorch/executorch/build-x86/backends/qualcomm/PyQnnManagerAdaptor.cpython-310-x86_64-linux-gnu.so' -> '/pytorch/executorch/backends/qualcomm/python/PyQnnManagerAdaptor.cpython-310-x86_64-linux-gnu.so'
2025-03-21T20:23:40.2799042Z '/pytorch/executorch/build-x86/backends/qualcomm/PyQnnWrapperAdaptor.cpython-310-x86_64-linux-gnu.so' -> '/pytorch/executorch/backends/qualcomm/python/PyQnnWrapperAdaptor.cpython-310-x86_64-linux-gnu.so'
2025-03-21T20:23:40.2800339Z + cp -fv /pytorch/executorch/schema/program.fbs /pytorch/executorch/exir/_serialize/program.fbs
2025-03-21T20:23:40.2801141Z '/pytorch/executorch/schema/program.fbs' -> '/pytorch/executorch/exir/_serialize/program.fbs'
2025-03-21T20:23:40.2802043Z + cp -fv /pytorch/executorch/schema/scalar_type.fbs /pytorch/executorch/exir/_serialize/scalar_type.fbs
2025-03-21T20:23:40.2802858Z '/pytorch/executorch/schema/scalar_type.fbs' -> '/pytorch/executorch/exir/_serialize/scalar_type.fbs'
2025-03-21T20:23:40.2803436Z + EXAMPLE_ROOT=examples/qualcomm
2025-03-21T20:23:40.2804091Z + CMAKE_PREFIX_PATH='/pytorch/executorch/build-x86/lib/cmake/ExecuTorch;/pytorch/executorch/build-x86/third-party/gflags;'
2025-03-21T20:23:40.2804780Z + echo 'Update tokenizers submodule...'
2025-03-21T20:23:40.2805112Z Update tokenizers submodule...
2025-03-21T20:23:40.2805469Z + pushd /pytorch/executorch/extension/llm/tokenizers
2025-03-21T20:23:40.2806001Z /pytorch/executorch/extension/llm/tokenizers /pytorch/executorch/build-x86
2025-03-21T20:23:40.2806501Z + git submodule update --init
2025-03-21T20:23:40.2807159Z Submodule 'third-party/abseil-cpp' (https://github.com/abseil/abseil-cpp.git) registered for path 'third-party/abseil-cpp'
2025-03-21T20:23:40.2808090Z Submodule 'third-party/json' (https://github.com/nlohmann/json.git) registered for path 'third-party/json'
2025-03-21T20:23:40.2809128Z Submodule 'third-party/re2' (https://github.com/google/re2.git) registered for path 'third-party/re2'
2025-03-21T20:23:40.2810165Z Submodule 'third-party/sentencepiece' (https://github.com/google/sentencepiece.git) registered for path 'third-party/sentencepiece'
2025-03-21T20:23:40.2811084Z Cloning into '/pytorch/executorch/extension/llm/tokenizers/third-party/abseil-cpp'...
2025-03-21T20:23:40.2811774Z Cloning into '/pytorch/executorch/extension/llm/tokenizers/third-party/json'...
2025-03-21T20:23:40.2812426Z Cloning into '/pytorch/executorch/extension/llm/tokenizers/third-party/re2'...
2025-03-21T20:23:40.2813111Z Cloning into '/pytorch/executorch/extension/llm/tokenizers/third-party/sentencepiece'...
2025-03-21T20:23:40.2813865Z Submodule path 'third-party/abseil-cpp': checked out '7d96b2e93d9a84530748b68abd2f97595c51ecf4'
2025-03-21T20:23:40.2814595Z Submodule path 'third-party/json': checked out 'e6cafa573aac6ed9227f752a5371c0b3f436307d'
2025-03-21T20:23:40.2815437Z Submodule path 'third-party/re2': checked out '6dcd83d60f7944926bfd308cc13979fc53dd69ca'
2025-03-21T20:23:40.2816168Z Submodule path 'third-party/sentencepiece': checked out 'd8f741853847553169444afc12c00f4bbff3e9ce'
2025-03-21T20:23:40.2816706Z + popd
2025-03-21T20:23:40.2816935Z /pytorch/executorch/build-x86
2025-03-21T20:23:40.2818269Z + cmake /pytorch/executorch/examples/qualcomm -DCMAKE_BUILD_TYPE=Release '-DCMAKE_PREFIX_PATH=/pytorch/executorch/build-x86/lib/cmake/ExecuTorch;/pytorch/executorch/build-x86/third-party/gflags;' -DCMAKE_FIND_ROOT_PATH_MODE_PACKAGE=BOTH -DPYTHON_EXECUTABLE=python -Bexamples/qualcomm
2025-03-21T20:23:40.2819827Z -- The C compiler identification is Clang 12.0.1
2025-03-21T20:23:40.2820232Z -- The CXX compiler identification is Clang 12.0.1
2025-03-21T20:23:40.2820608Z -- Detecting C compiler ABI info
2025-03-21T20:23:40.2820939Z -- Detecting C compiler ABI info - done
2025-03-21T20:23:40.2821338Z -- Check for working C compiler: /opt/cache/bin/cc - skipped
2025-03-21T20:23:40.2821746Z -- Detecting C compile features
2025-03-21T20:23:40.2822064Z -- Detecting C compile features - done
2025-03-21T20:23:40.2822396Z -- Detecting CXX compiler ABI info
2025-03-21T20:23:40.2822729Z -- Detecting CXX compiler ABI info - done
2025-03-21T20:23:40.2823128Z -- Check for working CXX compiler: /opt/cache/bin/c++ - skipped
2025-03-21T20:23:40.2823582Z -- Detecting CXX compile features
2025-03-21T20:23:40.2823916Z -- Detecting CXX compile features - done
2025-03-21T20:23:40.2824699Z CMake Warning (dev) at CMakeLists.txt:31 (find_package):
2025-03-21T20:23:40.2825233Z   Policy CMP0144 is not set: find_package uses upper-case <PACKAGENAME>_ROOT
2025-03-21T20:23:40.2825809Z   variables.  Run "cmake --help-policy CMP0144" for policy details.  Use the
2025-03-21T20:23:40.2826384Z   cmake_policy command to set the policy and suppress this warning.
2025-03-21T20:23:40.2826788Z 
2025-03-21T20:23:40.2826938Z   CMake variable EXECUTORCH_ROOT is set to:
2025-03-21T20:23:40.2827225Z 
2025-03-21T20:23:40.2827423Z     /pytorch/executorch/examples/qualcomm/../..
2025-03-21T20:23:40.2827769Z 
2025-03-21T20:23:40.2827950Z   Environment variable EXECUTORCH_ROOT is set to:
2025-03-21T20:23:40.2828199Z 
2025-03-21T20:23:40.2828316Z     /pytorch/executorch
2025-03-21T20:23:40.2828477Z 
2025-03-21T20:23:40.2828719Z   For compatibility, find_package is ignoring the variable, but code in a
2025-03-21T20:23:40.2829165Z   .cmake module might still use it.
2025-03-21T20:23:40.2829586Z This warning is for project developers.  Use -Wno-dev to suppress it.
2025-03-21T20:23:40.2830051Z 
2025-03-21T20:23:40.2830345Z coremldelegate library is not found.
2025-03-21T20:23:40.2830859Z             If needed rebuild with the proper options in CMakeLists.txt
2025-03-21T20:23:40.2831333Z mpsdelegate library is not found.
2025-03-21T20:23:40.2831828Z             If needed rebuild with the proper options in CMakeLists.txt
2025-03-21T20:23:40.2832785Z neuron_backend library is not found.
2025-03-21T20:23:40.2833312Z             If needed rebuild with the proper options in CMakeLists.txt
2025-03-21T20:23:40.2833789Z custom_ops library is not found.
2025-03-21T20:23:40.2834257Z             If needed rebuild with the proper options in CMakeLists.txt
2025-03-21T20:23:40.2834763Z extension_runner_util library is not found.
2025-03-21T20:23:40.2835276Z             If needed rebuild with the proper options in CMakeLists.txt
2025-03-21T20:23:40.2835772Z extension_training library is not found.
2025-03-21T20:23:40.2836276Z             If needed rebuild with the proper options in CMakeLists.txt
2025-03-21T20:23:40.2836759Z xnnpack_backend library is not found.
2025-03-21T20:23:40.2837241Z             If needed rebuild with the proper options in CMakeLists.txt
2025-03-21T20:23:40.2837713Z XNNPACK library is not found.
2025-03-21T20:23:43.7371808Z             If needed rebuild with the proper options in CMakeLists.txt
2025-03-21T20:23:43.7372869Z microkernels-prod library is not found.
2025-03-21T20:23:43.7373403Z             If needed rebuild with the proper options in CMakeLists.txt
2025-03-21T20:23:43.7373889Z kleidiai library is not found.
2025-03-21T20:23:43.7374409Z             If needed rebuild with the proper options in CMakeLists.txt
2025-03-21T20:23:43.7374896Z vulkan_backend library is not found.
2025-03-21T20:23:43.7375393Z             If needed rebuild with the proper options in CMakeLists.txt
2025-03-21T20:23:43.7375887Z optimized_kernels library is not found.
2025-03-21T20:23:43.7376375Z             If needed rebuild with the proper options in CMakeLists.txt
2025-03-21T20:23:43.7376846Z cpublas library is not found.
2025-03-21T20:23:43.7377319Z             If needed rebuild with the proper options in CMakeLists.txt
2025-03-21T20:23:43.7377790Z eigen_blas library is not found.
2025-03-21T20:23:43.7378273Z             If needed rebuild with the proper options in CMakeLists.txt
2025-03-21T20:23:43.7378757Z optimized_ops_lib library is not found.
2025-03-21T20:23:43.7379255Z             If needed rebuild with the proper options in CMakeLists.txt
2025-03-21T20:23:43.7379788Z optimized_native_cpu_ops_lib library is not found.
2025-03-21T20:23:43.7380322Z             If needed rebuild with the proper options in CMakeLists.txt
2025-03-21T20:23:43.7380822Z quantized_ops_aot_lib library is not found.
2025-03-21T20:23:43.7381338Z             If needed rebuild with the proper options in CMakeLists.txt
2025-03-21T20:23:43.7382038Z -- executorch: Using source file list /pytorch/executorch/build-x86/examples/qualcomm/../../executorch_srcs.cmake
2025-03-21T20:23:43.7382663Z -- Generating operator lib:
2025-03-21T20:23:43.7382971Z --   LIB_NAME: full_portable_ops_lib
2025-03-21T20:23:43.7383287Z --   OPS_SCHEMA_YAML: 
2025-03-21T20:23:43.7383545Z --   ROOT_OPS: 
2025-03-21T20:23:43.7383776Z --   INCLUDE_ALL_OPS: ON
2025-03-21T20:23:43.7384792Z Command - python;-m;codegen.tools.gen_oplist;--output_path=/pytorch/executorch/build-x86/examples/qualcomm/full_portable_ops_lib/selected_operators.yaml;--include_all_operators
2025-03-21T20:23:43.7385710Z -- Generating kernel bindings:
2025-03-21T20:23:43.7386014Z --   LIB_NAME: full_portable_ops_lib
2025-03-21T20:23:43.7386553Z --   FUNCTIONS_YAML: /pytorch/executorch/examples/qualcomm/../../kernels/portable/functions.yaml
2025-03-21T20:23:43.7387084Z --   CUSTOM_OPS_YAML: 
2025-03-21T20:23:43.7387360Z --   ADD_EXCEPTION_BOUNDARY: FALSE
2025-03-21T20:23:43.7387673Z -- Generating operator lib:
2025-03-21T20:23:43.7387969Z --   LIB_NAME: full_portable_ops_lib
2025-03-21T20:23:43.7388290Z --   KERNEL_LIBS: portable_kernels
2025-03-21T20:23:43.7388576Z --   DEPS: executorch
2025-03-21T20:23:43.7388877Z -- Performing Test ABSL_INTERNAL_AT_LEAST_CXX17
2025-03-21T20:23:43.7389294Z -- Performing Test ABSL_INTERNAL_AT_LEAST_CXX17 - Success
2025-03-21T20:23:43.7389711Z -- Performing Test ABSL_INTERNAL_AT_LEAST_CXX20
2025-03-21T20:23:43.7390133Z -- Performing Test ABSL_INTERNAL_AT_LEAST_CXX20 - Failed
2025-03-21T20:23:43.7390524Z -- Performing Test CMAKE_HAVE_LIBC_PTHREAD
2025-03-21T20:23:43.7390909Z -- Performing Test CMAKE_HAVE_LIBC_PTHREAD - Success
2025-03-21T20:23:43.7391269Z -- Found Threads: TRUE
2025-03-21T20:23:43.7392004Z CMake Warning at /pytorch/executorch/extension/llm/tokenizers/third-party/abseil-cpp/CMakeLists.txt:177 (message):
2025-03-21T20:23:43.7393251Z     The default and system-level install directories are unsupported except in LTS   releases of Abseil.  Please set CMAKE_INSTALL_PREFIX to install Abseil in your   source or build tree directly.    
2025-03-21T20:23:43.7394063Z 
2025-03-21T20:23:43.7394186Z 
2025-03-21T20:23:43.7394400Z -- Configuring done (1.4s)
2025-03-21T20:23:43.7394691Z -- Generating done (0.3s)
2025-03-21T20:23:43.7395127Z -- Build files have been written to: /pytorch/executorch/build-x86/examples/qualcomm
2025-03-21T20:23:43.7395623Z + cmake --build examples/qualcomm -j2
2025-03-21T20:23:43.7396328Z [  1%] Generating selected_operators.yaml for full_portable_ops_lib
2025-03-21T20:23:43.7397111Z [  1%] Building CXX object abseil-cpp/absl/base/CMakeFiles/log_severity.dir/log_severity.cc.o
2025-03-21T20:23:43.7397803Z [  2%] Linking CXX static library libabsl_log_severity.a
2025-03-21T20:23:43.7398216Z [  2%] Built target log_severity
2025-03-21T20:23:43.7398896Z [  3%] Building CXX object abseil-cpp/absl/base/CMakeFiles/spinlock_wait.dir/internal/spinlock_wait.cc.o
2025-03-21T20:23:43.7399609Z [  3%] Generating code for kernel registration
2025-03-21T20:23:43.7400137Z [  3%] Linking CXX static library libabsl_spinlock_wait.a
2025-03-21T20:23:43.7400535Z [  3%] Built target spinlock_wait
2025-03-21T20:23:43.7401168Z [  4%] Building CXX object abseil-cpp/absl/base/CMakeFiles/strerror.dir/internal/strerror.cc.o
2025-03-21T20:23:43.7401856Z [  4%] Linking CXX static library libabsl_strerror.a
2025-03-21T20:23:43.7402253Z [  4%] Built target strerror
2025-03-21T20:23:43.7402940Z [  4%] Building CXX object abseil-cpp/absl/time/CMakeFiles/time_zone.dir/internal/cctz/src/time_zone_fixed.cc.o
2025-03-21T20:23:43.7403959Z [  4%] Building CXX object abseil-cpp/absl/time/CMakeFiles/time_zone.dir/internal/cctz/src/time_zone_format.cc.o
2025-03-21T20:23:43.7404947Z [  5%] Building CXX object abseil-cpp/absl/time/CMakeFiles/time_zone.dir/internal/cctz/src/time_zone_if.cc.o
2025-03-21T20:23:43.7405942Z [  5%] Building CXX object abseil-cpp/absl/time/CMakeFiles/time_zone.dir/internal/cctz/src/time_zone_impl.cc.o
2025-03-21T20:23:43.7406942Z [  5%] Building CXX object abseil-cpp/absl/time/CMakeFiles/time_zone.dir/internal/cctz/src/time_zone_info.cc.o
2025-03-21T20:23:43.7407932Z [  5%] Building CXX object abseil-cpp/absl/time/CMakeFiles/time_zone.dir/internal/cctz/src/time_zone_libc.cc.o
2025-03-21T20:23:43.7408947Z [  6%] Building CXX object abseil-cpp/absl/time/CMakeFiles/time_zone.dir/internal/cctz/src/time_zone_lookup.cc.o
2025-03-21T20:23:43.7410075Z [  6%] Building CXX object abseil-cpp/absl/time/CMakeFiles/time_zone.dir/internal/cctz/src/time_zone_posix.cc.o
2025-03-21T20:23:43.7411095Z [  6%] Building CXX object abseil-cpp/absl/time/CMakeFiles/time_zone.dir/internal/cctz/src/zone_info_source.cc.o
2025-03-21T20:23:43.7411843Z [  7%] Linking CXX static library libabsl_time_zone.a
2025-03-21T20:23:43.7412233Z [  7%] Built target time_zone
2025-03-21T20:23:43.7412983Z [  8%] Building CXX object abseil-cpp/absl/debugging/CMakeFiles/utf8_for_code_point.dir/internal/utf8_for_code_point.cc.o
2025-03-21T20:23:43.7413818Z [  8%] Linking CXX static library libabsl_utf8_for_code_point.a
2025-03-21T20:23:43.7414256Z [  8%] Built target utf8_for_code_point
2025-03-21T20:23:43.7414847Z [  9%] Building CXX object abseil-cpp/absl/numeric/CMakeFiles/int128.dir/int128.cc.o
2025-03-21T20:23:43.7415861Z [  9%] Building CXX object CMakeFiles/full_portable_ops_lib.dir/full_portable_ops_lib/RegisterCodegenUnboxedKernelsEverything.cpp.o
2025-03-21T20:23:43.7416700Z [  9%] Linking CXX static library libabsl_int128.a
2025-03-21T20:23:43.7417082Z [  9%] Built target int128
2025-03-21T20:23:43.7417832Z [  9%] Building CXX object abseil-cpp/absl/profiling/CMakeFiles/exponential_biased.dir/internal/exponential_biased.cc.o
2025-03-21T20:23:43.7418668Z [  9%] Linking CXX static library libfull_portable_ops_lib.a
2025-03-21T20:23:43.7419105Z [  9%] Built target full_portable_ops_lib
2025-03-21T20:23:43.7419840Z [  9%] Building CXX object abseil-cpp/absl/time/CMakeFiles/civil_time.dir/internal/cctz/src/civil_time_detail.cc.o
2025-03-21T20:23:43.7420658Z [ 10%] Linking CXX static library libabsl_exponential_biased.a
2025-03-21T20:23:43.7421111Z [ 10%] Built target exponential_biased
2025-03-21T20:23:43.7421856Z [ 10%] Building CXX object abseil-cpp/absl/debugging/CMakeFiles/leak_check.dir/leak_check.cc.o
2025-03-21T20:23:43.7422620Z [ 10%] Linking CXX static library libabsl_civil_time.a
2025-03-21T20:23:43.7423008Z [ 10%] Built target civil_time
2025-03-21T20:23:43.7423792Z [ 10%] Building CXX object abseil-cpp/absl/flags/CMakeFiles/flags_commandlineflag_internal.dir/internal/commandlineflag.cc.o
2025-03-21T20:23:43.7424637Z [ 10%] Linking CXX static library libabsl_leak_check.a
2025-03-21T20:23:43.7425033Z [ 10%] Built target leak_check
2025-03-21T20:23:43.7425719Z [ 10%] Building CXX object abseil-cpp/absl/log/CMakeFiles/log_internal_nullguard.dir/internal/nullguard.cc.o
2025-03-21T20:23:43.7426633Z [ 10%] Linking CXX static library libabsl_flags_commandlineflag_internal.a
2025-03-21T20:23:43.7427133Z [ 10%] Built target flags_commandlineflag_internal
2025-03-21T20:23:43.7427938Z [ 10%] Building CXX object abseil-cpp/absl/profiling/CMakeFiles/periodic_sampler.dir/internal/periodic_sampler.cc.o
2025-03-21T20:23:43.7428795Z [ 11%] Linking CXX static library libabsl_log_internal_nullguard.a
2025-03-21T20:23:43.7429264Z [ 11%] Built target log_internal_nullguard
2025-03-21T20:23:43.7430024Z [ 11%] Building CXX object abseil-cpp/absl/random/CMakeFiles/random_seed_gen_exception.dir/seed_gen_exception.cc.o
2025-03-21T20:23:43.7430840Z [ 11%] Linking CXX static library libabsl_periodic_sampler.a
2025-03-21T20:23:43.7431258Z [ 11%] Built target periodic_sampler
2025-03-21T20:23:43.7432041Z [ 11%] Building CXX object abseil-cpp/absl/random/CMakeFiles/random_internal_platform.dir/internal/randen_round_keys.cc.o
2025-03-21T20:23:43.7433562Z [ 11%] Linking CXX static library libabsl_random_internal_platform.a
2025-03-21T20:23:43.7434262Z [ 12%] Linking CXX static library libabsl_random_seed_gen_exception.a
2025-03-21T20:23:43.7434736Z [ 12%] Built target random_internal_platform
2025-03-21T20:23:43.7435092Z [ 12%] Built target random_seed_gen_exception
2025-03-21T20:23:43.7435788Z [ 12%] Building CXX object executor_runner/CMakeFiles/qnn_executor_runner.dir/qnn_executor_runner.cpp.o
2025-03-21T20:23:43.7436905Z [ 12%] Building CXX object oss_scripts/llama/CMakeFiles/custom_ops.dir/pytorch/executorch/extension/llm/custom_ops/op_fallback.cpp.o
2025-03-21T20:23:43.7437751Z [ 13%] Linking CXX static library libcustom_ops.a
2025-03-21T20:23:43.7438692Z [ 13%] Building CXX object executor_runner/CMakeFiles/qnn_executor_runner.dir/pytorch/executorch/extension/data_loader/file_data_loader.cpp.o
2025-03-21T20:23:43.7439450Z [ 13%] Built target custom_ops
2025-03-21T20:23:43.7440278Z [ 14%] Building CXX object executor_runner/CMakeFiles/qnn_executor_runner.dir/pytorch/executorch/extension/evalue_util/print_evalue.cpp.o
2025-03-21T20:23:43.7441521Z [ 14%] Building CXX object executor_runner/CMakeFiles/qnn_executor_runner.dir/pytorch/executorch/extension/runner_util/inputs.cpp.o
2025-03-21T20:23:45.5477611Z [ 14%] Building CXX object executor_runner/CMakeFiles/qnn_executor_runner.dir/pytorch/executorch/extension/runner_util/inputs_portable.cpp.o
2025-03-21T20:23:45.5479045Z [ 15%] Building CXX object executor_runner/CMakeFiles/qnn_executor_runner.dir/pytorch/executorch/runtime/executor/test/test_backend_compiler_lib.cpp.o
2025-03-21T20:23:45.5480251Z [ 15%] Building CXX object abseil-cpp/absl/base/CMakeFiles/raw_logging_internal.dir/internal/raw_logging.cc.o
2025-03-21T20:23:45.5481094Z In file included from /pytorch/executorch/runtime/executor/test/test_backend_compiler_lib.cpp:9:
2025-03-21T20:23:45.5481931Z In file included from /pytorch/executorch/examples/qualcomm/../../../executorch/runtime/backend/interface.h:14:
2025-03-21T20:23:45.5483272Z /pytorch/executorch/examples/qualcomm/../../../executorch/runtime/backend/backend_init_context.h:26:13: warning: 'NamedDataMap' is deprecated: This API is experimental and may change without notice. [-Wdeprecated-declarations]
2025-03-21T20:23:45.5484706Z       const NamedDataMap* named_data_map = nullptr)
2025-03-21T20:23:45.5485055Z             ^
2025-03-21T20:23:45.5485764Z /pytorch/executorch/examples/qualcomm/../../../executorch/runtime/core/named_data_map.h:31:7: note: 'NamedDataMap' has been explicitly marked deprecated here
2025-03-21T20:23:45.5486555Z class ET_EXPERIMENTAL NamedDataMap {
2025-03-21T20:23:45.5486868Z       ^
2025-03-21T20:23:45.5487497Z /pytorch/executorch/examples/qualcomm/../../../executorch/runtime/platform/compiler.h:80:5: note: expanded from macro 'ET_EXPERIMENTAL'
2025-03-21T20:23:45.5488338Z   [[deprecated("This API is experimental and may change without notice.")]]
2025-03-21T20:23:45.5488798Z     ^
2025-03-21T20:23:45.5489345Z In file included from /pytorch/executorch/runtime/executor/test/test_backend_compiler_lib.cpp:9:
2025-03-21T20:23:45.5490180Z In file included from /pytorch/executorch/examples/qualcomm/../../../executorch/runtime/backend/interface.h:14:
2025-03-21T20:23:45.5491519Z /pytorch/executorch/examples/qualcomm/../../../executorch/runtime/backend/backend_init_context.h:62:9: warning: 'NamedDataMap' is deprecated: This API is experimental and may change without notice. [-Wdeprecated-declarations]
2025-03-21T20:23:45.5492612Z   const NamedDataMap* get_named_data_map() const {
2025-03-21T20:23:45.5492956Z         ^
2025-03-21T20:23:45.5493651Z /pytorch/executorch/examples/qualcomm/../../../executorch/runtime/core/named_data_map.h:31:7: note: 'NamedDataMap' has been explicitly marked deprecated here
2025-03-21T20:23:45.5494533Z class ET_EXPERIMENTAL NamedDataMap {
2025-03-21T20:23:45.5494843Z       ^
2025-03-21T20:23:45.5495464Z /pytorch/executorch/examples/qualcomm/../../../executorch/runtime/platform/compiler.h:80:5: note: expanded from macro 'ET_EXPERIMENTAL'
2025-03-21T20:23:45.5496288Z   [[deprecated("This API is experimental and may change without notice.")]]
2025-03-21T20:23:45.5496718Z     ^
2025-03-21T20:23:45.5497182Z In file included from /pytorch/executorch/runtime/executor/test/test_backend_compiler_lib.cpp:9:
2025-03-21T20:23:45.5498021Z In file included from /pytorch/executorch/examples/qualcomm/../../../executorch/runtime/backend/interface.h:14:
2025-03-21T20:23:45.5499354Z /pytorch/executorch/examples/qualcomm/../../../executorch/runtime/backend/backend_init_context.h:70:9: warning: 'NamedDataMap' is deprecated: This API is experimental and may change without notice. [-Wdeprecated-declarations]
2025-03-21T20:23:45.5500441Z   const NamedDataMap* named_data_map_ = nullptr;
2025-03-21T20:23:45.5500766Z         ^
2025-03-21T20:23:45.5501459Z /pytorch/executorch/examples/qualcomm/../../../executorch/runtime/core/named_data_map.h:31:7: note: 'NamedDataMap' has been explicitly marked deprecated here
2025-03-21T20:23:45.5502258Z class ET_EXPERIMENTAL NamedDataMap {
2025-03-21T20:23:45.5502563Z       ^
2025-03-21T20:23:45.5503182Z /pytorch/executorch/examples/qualcomm/../../../executorch/runtime/platform/compiler.h:80:5: note: expanded from macro 'ET_EXPERIMENTAL'
2025-03-21T20:23:45.5504030Z   [[deprecated("This API is experimental and may change without notice.")]]
2025-03-21T20:23:45.5504448Z     ^
2025-03-21T20:23:45.5504671Z 3 warnings generated.
2025-03-21T20:23:45.5505160Z [ 15%] Linking CXX executable qnn_executor_runner
2025-03-21T20:23:45.5505745Z [ 16%] Linking CXX static library libabsl_raw_logging_internal.a
2025-03-21T20:23:45.5506257Z [ 16%] Built target raw_logging_internal
2025-03-21T20:23:45.5507058Z [ 16%] Building CXX object abseil-cpp/absl/debugging/CMakeFiles/decode_rust_punycode.dir/internal/decode_rust_punycode.cc.o
2025-03-21T20:23:45.5507927Z [ 16%] Linking CXX static library libabsl_decode_rust_punycode.a
2025-03-21T20:23:45.5508377Z [ 16%] Built target decode_rust_punycode
2025-03-21T20:23:45.5509094Z [ 16%] Building CXX object abseil-cpp/absl/types/CMakeFiles/bad_variant_access.dir/bad_variant_access.cc.o
2025-03-21T20:23:45.5509870Z [ 16%] Linking CXX static library libabsl_bad_variant_access.a
2025-03-21T20:23:45.5510472Z [ 16%] Built target qnn_executor_runner
2025-03-21T20:23:45.5510793Z [ 16%] Built target bad_variant_access
2025-03-21T20:23:45.5511499Z [ 16%] Building CXX object abseil-cpp/absl/types/CMakeFiles/bad_optional_access.dir/bad_optional_access.cc.o
2025-03-21T20:23:45.5512529Z [ 16%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/cordz_functions.dir/internal/cordz_functions.cc.o
2025-03-21T20:23:45.5513340Z [ 17%] Linking CXX static library libabsl_bad_optional_access.a
2025-03-21T20:23:45.5520523Z [ 17%] Built target bad_optional_access
2025-03-21T20:23:45.5521475Z [ 18%] Building CXX object abseil-cpp/absl/random/CMakeFiles/random_internal_randen_hwaes_impl.dir/internal/randen_hwaes.cc.o
2025-03-21T20:23:45.5522333Z [ 18%] Linking CXX static library libabsl_cordz_functions.a
2025-03-21T20:23:45.5522772Z [ 18%] Built target cordz_functions
2025-03-21T20:23:45.5523551Z [ 18%] Building CXX object abseil-cpp/absl/random/CMakeFiles/random_internal_randen_slow.dir/internal/randen_slow.cc.o
2025-03-21T20:23:45.5524438Z [ 18%] Linking CXX static library libabsl_random_internal_randen_slow.a
2025-03-21T20:23:45.5524937Z [ 18%] Built target random_internal_randen_slow
2025-03-21T20:23:45.5525636Z [ 18%] Building CXX object abseil-cpp/absl/types/CMakeFiles/bad_any_cast_impl.dir/bad_any_cast.cc.o
2025-03-21T20:23:45.5526445Z [ 18%] Linking CXX static library libabsl_random_internal_randen_hwaes_impl.a
2025-03-21T20:23:45.5526981Z [ 18%] Built target random_internal_randen_hwaes_impl
2025-03-21T20:23:45.5527666Z [ 19%] Building CXX object abseil-cpp/absl/base/CMakeFiles/base.dir/internal/cycleclock.cc.o
2025-03-21T20:23:45.5528389Z [ 19%] Linking CXX static library libabsl_bad_any_cast_impl.a
2025-03-21T20:23:45.5528829Z [ 19%] Built target bad_any_cast_impl
2025-03-21T20:23:45.5529548Z [ 19%] Building CXX object abseil-cpp/absl/base/CMakeFiles/base.dir/internal/spinlock.cc.o
2025-03-21T20:23:45.5530485Z [ 19%] Building CXX object abseil-cpp/absl/base/CMakeFiles/throw_delegate.dir/internal/throw_delegate.cc.o
2025-03-21T20:23:45.5531260Z [ 20%] Linking CXX static library libabsl_throw_delegate.a
2025-03-21T20:23:45.5531978Z [ 20%] Building CXX object abseil-cpp/absl/base/CMakeFiles/base.dir/internal/sysinfo.cc.o
2025-03-21T20:23:45.5532770Z [ 20%] Built target throw_delegate
2025-03-21T20:23:45.5533543Z [ 20%] Building CXX object abseil-cpp/absl/base/CMakeFiles/scoped_set_env.dir/internal/scoped_set_env.cc.o
2025-03-21T20:23:45.5534316Z [ 20%] Linking CXX static library libabsl_scoped_set_env.a
2025-03-21T20:23:45.5535051Z [ 21%] Building CXX object abseil-cpp/absl/base/CMakeFiles/base.dir/internal/thread_identity.cc.o
2025-03-21T20:23:45.5535632Z [ 21%] Built target scoped_set_env
2025-03-21T20:23:45.5536306Z [ 21%] Building CXX object abseil-cpp/absl/base/CMakeFiles/base.dir/internal/unscaledcycleclock.cc.o
2025-03-21T20:23:45.5537369Z [ 21%] Building CXX object abseil-cpp/absl/debugging/CMakeFiles/debugging_internal.dir/internal/address_is_readable.cc.o
2025-03-21T20:23:45.5538162Z [ 21%] Linking CXX static library libabsl_base.a
2025-03-21T20:23:45.5538535Z [ 21%] Built target base
2025-03-21T20:23:45.5539201Z [ 21%] Building CXX object abseil-cpp/absl/debugging/CMakeFiles/demangle_rust.dir/internal/demangle_rust.cc.o
2025-03-21T20:23:45.5540252Z [ 21%] Building CXX object abseil-cpp/absl/debugging/CMakeFiles/debugging_internal.dir/internal/elf_mem_image.cc.o
2025-03-21T20:23:45.5541052Z [ 22%] Linking CXX static library libabsl_demangle_rust.a
2025-03-21T20:23:45.5541886Z [ 23%] Building CXX object abseil-cpp/absl/debugging/CMakeFiles/debugging_internal.dir/internal/vdso_support.cc.o
2025-03-21T20:23:45.5542543Z [ 23%] Built target demangle_rust
2025-03-21T20:23:45.5543175Z [ 23%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/string_view.dir/string_view.cc.o
2025-03-21T20:23:45.5544135Z [ 23%] Linking CXX static library libabsl_debugging_internal.a
2025-03-21T20:23:45.5544578Z [ 23%] Built target debugging_internal
2025-03-21T20:23:45.5545255Z [ 24%] Building CXX object abseil-cpp/absl/crc/CMakeFiles/crc_cpu_detect.dir/internal/cpu_detect.cc.o
2025-03-21T20:23:45.5545981Z [ 25%] Linking CXX static library libabsl_string_view.a
2025-03-21T20:23:45.5546386Z [ 25%] Built target string_view
2025-03-21T20:23:45.5546991Z [ 26%] Building CXX object abseil-cpp/absl/hash/CMakeFiles/city.dir/internal/city.cc.o
2025-03-21T20:23:45.5547657Z [ 26%] Linking CXX static library libabsl_crc_cpu_detect.a
2025-03-21T20:23:45.5548077Z [ 26%] Built target crc_cpu_detect
2025-03-21T20:23:45.5548763Z [ 27%] Building CXX object abseil-cpp/absl/hash/CMakeFiles/low_level_hash.dir/internal/low_level_hash.cc.o
2025-03-21T20:23:45.5549485Z [ 27%] Linking CXX static library libabsl_city.a
2025-03-21T20:23:45.5549873Z [ 27%] Built target city
2025-03-21T20:23:45.5550534Z [ 28%] Building CXX object abseil-cpp/absl/log/CMakeFiles/log_internal_conditions.dir/internal/conditions.cc.o
2025-03-21T20:23:45.5551313Z [ 28%] Linking CXX static library libabsl_low_level_hash.a
2025-03-21T20:23:45.5551726Z [ 28%] Built target low_level_hash
2025-03-21T20:23:45.5552227Z [ 28%] Linking CXX static library libabsl_log_internal_conditions.a
2025-03-21T20:23:45.5553133Z [ 28%] Building CXX object abseil-cpp/absl/random/CMakeFiles/random_internal_randen_hwaes.dir/internal/randen_detect.cc.o
2025-03-21T20:23:45.5553827Z [ 28%] Built target log_internal_conditions
2025-03-21T20:23:49.0276377Z [ 28%] Building CXX object abseil-cpp/absl/base/CMakeFiles/malloc_internal.dir/internal/low_level_alloc.cc.o
2025-03-21T20:23:49.0277268Z [ 28%] Linking CXX static library libabsl_random_internal_randen_hwaes.a
2025-03-21T20:23:49.0277756Z [ 28%] Built target random_internal_randen_hwaes
2025-03-21T20:23:49.0278524Z [ 28%] Building CXX object abseil-cpp/absl/base/CMakeFiles/tracing_internal.dir/internal/tracing.cc.o
2025-03-21T20:23:49.0279287Z [ 29%] Linking CXX static library libabsl_malloc_internal.a
2025-03-21T20:23:49.0279872Z [ 29%] Linking CXX static library libabsl_tracing_internal.a
2025-03-21T20:23:49.0280329Z [ 29%] Built target malloc_internal
2025-03-21T20:23:49.0281068Z [ 29%] Building CXX object abseil-cpp/absl/debugging/CMakeFiles/stacktrace.dir/stacktrace.cc.o
2025-03-21T20:23:49.0281655Z [ 29%] Built target tracing_internal
2025-03-21T20:23:49.0282387Z [ 30%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/strings_internal.dir/internal/ostringstream.cc.o
2025-03-21T20:23:49.0283148Z [ 30%] Linking CXX static library libabsl_stacktrace.a
2025-03-21T20:23:49.0283556Z [ 30%] Built target stacktrace
2025-03-21T20:23:49.0284269Z [ 31%] Building CXX object abseil-cpp/absl/debugging/CMakeFiles/demangle_internal.dir/internal/demangle.cc.o
2025-03-21T20:23:49.0285263Z [ 31%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/strings_internal.dir/internal/utf8.cc.o
2025-03-21T20:23:49.0286232Z [ 31%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/strings_internal.dir/internal/escaping.cc.o
2025-03-21T20:23:49.0287008Z [ 31%] Linking CXX static library libabsl_demangle_internal.a
2025-03-21T20:23:49.0287434Z [ 31%] Built target demangle_internal
2025-03-21T20:23:49.0288235Z [ 31%] Building CXX object abseil-cpp/absl/synchronization/CMakeFiles/graphcycles_internal.dir/internal/graphcycles.cc.o
2025-03-21T20:23:49.0289092Z [ 32%] Linking CXX static library libabsl_strings_internal.a
2025-03-21T20:23:49.0289582Z [ 32%] Built target strings_internal
2025-03-21T20:23:49.0290212Z [ 32%] Building CXX object abseil-cpp/absl/crc/CMakeFiles/crc_internal.dir/internal/crc.cc.o
2025-03-21T20:23:49.0291261Z [ 33%] Linking CXX static library libabsl_graphcycles_internal.a
2025-03-21T20:23:49.0291703Z [ 33%] Built target graphcycles_internal
2025-03-21T20:23:49.0292429Z [ 33%] Building CXX object abseil-cpp/absl/random/CMakeFiles/random_internal_randen.dir/internal/randen.cc.o
2025-03-21T20:23:49.0293435Z [ 34%] Building CXX object abseil-cpp/absl/crc/CMakeFiles/crc_internal.dir/internal/crc_x86_arm_combined.cc.o
2025-03-21T20:23:49.0294237Z [ 35%] Linking CXX static library libabsl_random_internal_randen.a
2025-03-21T20:23:49.0294702Z [ 35%] Built target random_internal_randen
2025-03-21T20:23:49.0295347Z [ 36%] Building CXX object abseil-cpp/absl/base/CMakeFiles/poison.dir/internal/poison.cc.o
2025-03-21T20:23:49.0296005Z [ 36%] Linking CXX static library libabsl_poison.a
2025-03-21T20:23:49.0296392Z [ 36%] Built target poison
2025-03-21T20:23:49.0296949Z [ 36%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/strings.dir/ascii.cc.o
2025-03-21T20:23:49.0297619Z [ 36%] Linking CXX static library libabsl_crc_internal.a
2025-03-21T20:23:49.0298030Z [ 36%] Built target crc_internal
2025-03-21T20:23:49.0298609Z [ 36%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/strings.dir/charconv.cc.o
2025-03-21T20:23:49.0299427Z [ 37%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/strings.dir/escaping.cc.o
2025-03-21T20:23:49.0300328Z [ 37%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/strings.dir/internal/charconv_bigint.cc.o
2025-03-21T20:23:49.0301291Z [ 37%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/strings.dir/internal/charconv_parse.cc.o
2025-03-21T20:23:49.0302323Z [ 38%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/strings.dir/internal/damerau_levenshtein_distance.cc.o
2025-03-21T20:23:49.0303305Z [ 38%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/strings.dir/internal/memutil.cc.o
2025-03-21T20:23:49.0304233Z [ 38%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/strings.dir/internal/stringify_sink.cc.o
2025-03-21T20:23:49.0305091Z [ 38%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/strings.dir/match.cc.o
2025-03-21T20:23:49.0305885Z [ 39%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/strings.dir/numbers.cc.o
2025-03-21T20:23:49.0306688Z [ 39%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/strings.dir/str_cat.cc.o
2025-03-21T20:23:49.0307509Z [ 39%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/strings.dir/str_replace.cc.o
2025-03-21T20:23:49.0308342Z [ 40%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/strings.dir/str_split.cc.o
2025-03-21T20:23:49.0309166Z [ 40%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/strings.dir/substitute.cc.o
2025-03-21T20:23:49.0309816Z [ 40%] Linking CXX static library libabsl_strings.a
2025-03-21T20:23:49.0310205Z [ 40%] Built target strings
2025-03-21T20:23:49.0310821Z [ 40%] Building CXX object abseil-cpp/absl/debugging/CMakeFiles/symbolize.dir/symbolize.cc.o
2025-03-21T20:23:49.0311645Z [ 40%] Building CXX object abseil-cpp/absl/time/CMakeFiles/time.dir/civil_time.cc.o
2025-03-21T20:23:49.0312290Z [ 40%] Linking CXX static library libabsl_symbolize.a
2025-03-21T20:23:49.0312690Z [ 40%] Built target symbolize
2025-03-21T20:23:49.0313205Z [ 40%] Building CXX object abseil-cpp/absl/time/CMakeFiles/time.dir/clock.cc.o
2025-03-21T20:23:49.0313941Z [ 41%] Building CXX object abseil-cpp/absl/time/CMakeFiles/time.dir/duration.cc.o
2025-03-21T20:23:49.0314681Z [ 41%] Building CXX object abseil-cpp/absl/time/CMakeFiles/time.dir/format.cc.o
2025-03-21T20:23:49.0315398Z [ 41%] Building CXX object abseil-cpp/absl/time/CMakeFiles/time.dir/time.cc.o
2025-03-21T20:23:49.0315995Z [ 42%] Linking CXX static library libabsl_time.a
2025-03-21T20:23:49.0316868Z [ 43%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/str_format_internal.dir/internal/str_format/arg.cc.o
2025-03-21T20:23:49.0317544Z [ 43%] Built target time
2025-03-21T20:23:49.0318252Z [ 43%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/str_format_internal.dir/internal/str_format/bind.cc.o
2025-03-21T20:23:49.0319339Z [ 43%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/str_format_internal.dir/internal/str_format/extension.cc.o
2025-03-21T20:23:49.0320493Z [ 44%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/str_format_internal.dir/internal/str_format/float_conversion.cc.o
2025-03-21T20:23:49.0321634Z [ 44%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/str_format_internal.dir/internal/str_format/output.cc.o
2025-03-21T20:23:49.0322565Z [ 44%] Building CXX object abseil-cpp/absl/hash/CMakeFiles/hash.dir/internal/hash.cc.o
2025-03-21T20:23:49.0323184Z [ 44%] Linking CXX static library libabsl_hash.a
2025-03-21T20:23:49.0323993Z [ 44%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/str_format_internal.dir/internal/str_format/parser.cc.o
2025-03-21T20:23:49.0324645Z [ 44%] Built target hash
2025-03-21T20:23:49.0325321Z [ 45%] Building CXX object abseil-cpp/absl/debugging/CMakeFiles/examine_stack.dir/internal/examine_stack.cc.o
2025-03-21T20:23:49.0326097Z [ 45%] Linking CXX static library libabsl_examine_stack.a
2025-03-21T20:23:49.0326683Z [ 45%] Linking CXX static library libabsl_str_format_internal.a
2025-03-21T20:23:49.0327108Z [ 45%] Built target examine_stack
2025-03-21T20:23:49.0327427Z [ 45%] Built target str_format_internal
2025-03-21T20:23:49.0328143Z [ 45%] Building CXX object abseil-cpp/absl/flags/CMakeFiles/flags_commandlineflag.dir/commandlineflag.cc.o
2025-03-21T20:23:49.0329125Z [ 45%] Building CXX object abseil-cpp/absl/log/CMakeFiles/log_internal_globals.dir/internal/globals.cc.o
2025-03-21T20:23:49.0329989Z [ 46%] Linking CXX static library libabsl_flags_commandlineflag.a
2025-03-21T20:23:49.0330463Z [ 46%] Built target flags_commandlineflag
2025-03-21T20:23:49.0331136Z [ 46%] Building CXX object abseil-cpp/absl/log/CMakeFiles/log_internal_proto.dir/internal/proto.cc.o
2025-03-21T20:23:49.0331895Z [ 47%] Linking CXX static library libabsl_log_internal_globals.a
2025-03-21T20:23:49.0332519Z [ 47%] Built target log_internal_globals
2025-03-21T20:23:49.0333235Z [ 47%] Building CXX object abseil-cpp/absl/log/CMakeFiles/log_internal_fnmatch.dir/internal/fnmatch.cc.o
2025-03-21T20:23:49.0334004Z [ 47%] Linking CXX static library libabsl_log_internal_proto.a
2025-03-21T20:23:49.0334452Z [ 47%] Built target log_internal_proto
2025-03-21T20:23:49.0335042Z [ 47%] Building CXX object abseil-cpp/absl/log/CMakeFiles/log_entry.dir/log_entry.cc.o
2025-03-21T20:23:49.0335741Z [ 47%] Linking CXX static library libabsl_log_internal_fnmatch.a
2025-03-21T20:23:49.0336191Z [ 47%] Built target log_internal_fnmatch
2025-03-21T20:23:49.0336957Z [ 47%] Building CXX object abseil-cpp/absl/random/CMakeFiles/random_distributions.dir/discrete_distribution.cc.o
2025-03-21T20:23:49.0337735Z [ 48%] Linking CXX static library libabsl_log_entry.a
2025-03-21T20:23:49.0338128Z [ 48%] Built target log_entry
2025-03-21T20:23:49.0338825Z [ 49%] Building CXX object abseil-cpp/absl/random/CMakeFiles/random_distributions.dir/gaussian_distribution.cc.o
2025-03-21T20:23:49.0339926Z [ 50%] Building CXX object abseil-cpp/absl/random/CMakeFiles/random_internal_seed_material.dir/internal/seed_material.cc.o
2025-03-21T20:23:49.0340792Z [ 50%] Linking CXX static library libabsl_random_distributions.a
2025-03-21T20:23:49.0341247Z [ 50%] Built target random_distributions
2025-03-21T20:23:49.0342159Z [ 50%] Building CXX object abseil-cpp/absl/random/CMakeFiles/random_internal_distribution_test_util.dir/internal/chi_square.cc.o
2025-03-21T20:23:49.0343271Z [ 50%] Linking CXX static library libabsl_random_internal_seed_material.a
2025-03-21T20:23:49.0343883Z [ 50%] Built target random_internal_seed_material
2025-03-21T20:23:49.0344861Z [ 50%] Building CXX object abseil-cpp/absl/random/CMakeFiles/random_internal_distribution_test_util.dir/internal/distribution_test_util.cc.o
2025-03-21T20:23:52.5713787Z [ 50%] Building CXX object abseil-cpp/absl/synchronization/CMakeFiles/kernel_timeout_internal.dir/internal/kernel_timeout.cc.o
2025-03-21T20:23:52.5714873Z [ 51%] Linking CXX static library libabsl_random_internal_distribution_test_util.a
2025-03-21T20:23:52.5715448Z [ 51%] Built target random_internal_distribution_test_util
2025-03-21T20:23:52.5716075Z [ 52%] Building CXX object abseil-cpp/absl/crc/CMakeFiles/crc32c.dir/crc32c.cc.o
2025-03-21T20:23:52.5716766Z [ 53%] Linking CXX static library libabsl_kernel_timeout_internal.a
2025-03-21T20:23:52.5717236Z [ 53%] Built target kernel_timeout_internal
2025-03-21T20:23:52.5718076Z [ 53%] Building CXX object abseil-cpp/absl/debugging/CMakeFiles/failure_signal_handler.dir/failure_signal_handler.cc.o
2025-03-21T20:23:52.5719105Z [ 53%] Building CXX object abseil-cpp/absl/crc/CMakeFiles/crc32c.dir/internal/crc_memcpy_fallback.cc.o
2025-03-21T20:23:52.5719894Z [ 53%] Linking CXX static library libabsl_failure_signal_handler.a
2025-03-21T20:23:52.5720345Z [ 53%] Built target failure_signal_handler
2025-03-21T20:23:52.5721025Z [ 53%] Building CXX object abseil-cpp/absl/flags/CMakeFiles/flags_marshalling.dir/marshalling.cc.o
2025-03-21T20:23:52.5722010Z [ 53%] Building CXX object abseil-cpp/absl/crc/CMakeFiles/crc32c.dir/internal/crc_memcpy_x86_arm_combined.cc.o
2025-03-21T20:23:52.5722801Z [ 53%] Linking CXX static library libabsl_flags_marshalling.a
2025-03-21T20:23:52.5723239Z [ 53%] Built target flags_marshalling
2025-03-21T20:23:52.5724077Z [ 53%] Building CXX object abseil-cpp/absl/flags/CMakeFiles/flags_private_handle_accessor.dir/internal/private_handle_accessor.cc.o
2025-03-21T20:23:52.5725168Z [ 54%] Building CXX object abseil-cpp/absl/crc/CMakeFiles/crc32c.dir/internal/crc_non_temporal_memcpy.cc.o
2025-03-21T20:23:52.5725994Z [ 54%] Linking CXX static library libabsl_flags_private_handle_accessor.a
2025-03-21T20:23:52.5726494Z [ 54%] Built target flags_private_handle_accessor
2025-03-21T20:23:52.5727265Z [ 55%] Building CXX object abseil-cpp/absl/log/CMakeFiles/log_internal_format.dir/internal/log_format.cc.o
2025-03-21T20:23:52.5727992Z [ 55%] Linking CXX static library libabsl_crc32c.a
2025-03-21T20:23:52.5728374Z [ 55%] Built target crc32c
2025-03-21T20:23:52.5728906Z [ 55%] Building CXX object abseil-cpp/absl/log/CMakeFiles/log_sink.dir/log_sink.cc.o
2025-03-21T20:23:52.5729694Z [ 55%] Linking CXX static library libabsl_log_internal_format.a
2025-03-21T20:23:52.5730155Z [ 55%] Built target log_internal_format
2025-03-21T20:23:52.5731010Z [ 56%] Building CXX object abseil-cpp/absl/random/CMakeFiles/random_internal_pool_urbg.dir/internal/pool_urbg.cc.o
2025-03-21T20:23:52.5731795Z [ 56%] Linking CXX static library libabsl_log_sink.a
2025-03-21T20:23:52.5733089Z [ 56%] Built target log_sink
2025-03-21T20:23:52.5734090Z [ 56%] Building CXX object abseil-cpp/absl/synchronization/CMakeFiles/synchronization.dir/barrier.cc.o
2025-03-21T20:23:52.5734937Z [ 56%] Linking CXX static library libabsl_random_internal_pool_urbg.a
2025-03-21T20:23:52.5735423Z [ 56%] Built target random_internal_pool_urbg
2025-03-21T20:23:52.5736143Z [ 56%] Building CXX object abseil-cpp/absl/crc/CMakeFiles/crc_cord_state.dir/internal/crc_cord_state.cc.o
2025-03-21T20:23:52.5737160Z [ 57%] Building CXX object abseil-cpp/absl/synchronization/CMakeFiles/synchronization.dir/blocking_counter.cc.o
2025-03-21T20:23:52.5737973Z [ 57%] Linking CXX static library libabsl_crc_cord_state.a
2025-03-21T20:23:52.5738566Z [ 57%] Built target crc_cord_state
2025-03-21T20:23:52.5739371Z [ 57%] Building CXX object abseil-cpp/absl/random/CMakeFiles/random_seed_sequences.dir/seed_sequences.cc.o
2025-03-21T20:23:52.5740505Z [ 57%] Building CXX object abseil-cpp/absl/synchronization/CMakeFiles/synchronization.dir/internal/create_thread_identity.cc.o
2025-03-21T20:23:52.5741416Z [ 57%] Linking CXX static library libabsl_random_seed_sequences.a
2025-03-21T20:23:52.5741860Z [ 57%] Built target random_seed_sequences
2025-03-21T20:23:52.5742644Z [ 57%] Building CXX object abseil-cpp/absl/synchronization/CMakeFiles/synchronization.dir/internal/futex_waiter.cc.o
2025-03-21T20:23:52.5743786Z [ 58%] Building CXX object abseil-cpp/absl/synchronization/CMakeFiles/synchronization.dir/internal/per_thread_sem.cc.o
2025-03-21T20:23:52.5744929Z [ 58%] Building CXX object abseil-cpp/absl/synchronization/CMakeFiles/synchronization.dir/internal/pthread_waiter.cc.o
2025-03-21T20:23:52.5746052Z [ 58%] Building CXX object abseil-cpp/absl/synchronization/CMakeFiles/synchronization.dir/internal/sem_waiter.cc.o
2025-03-21T20:23:52.5747165Z [ 59%] Building CXX object abseil-cpp/absl/synchronization/CMakeFiles/synchronization.dir/internal/stdcpp_waiter.cc.o
2025-03-21T20:23:52.5748278Z [ 59%] Building CXX object abseil-cpp/absl/synchronization/CMakeFiles/synchronization.dir/internal/waiter_base.cc.o
2025-03-21T20:23:52.5749375Z [ 59%] Building CXX object abseil-cpp/absl/synchronization/CMakeFiles/synchronization.dir/internal/win32_waiter.cc.o
2025-03-21T20:23:52.5750447Z [ 60%] Building CXX object abseil-cpp/absl/synchronization/CMakeFiles/synchronization.dir/notification.cc.o
2025-03-21T20:23:52.5751438Z [ 60%] Building CXX object abseil-cpp/absl/synchronization/CMakeFiles/synchronization.dir/mutex.cc.o
2025-03-21T20:23:52.5752569Z [ 60%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/cord_internal.dir/internal/cord_internal.cc.o
2025-03-21T20:23:52.5753433Z [ 60%] Linking CXX static library libabsl_synchronization.a
2025-03-21T20:23:52.5753865Z [ 60%] Built target synchronization
2025-03-21T20:23:52.5754595Z [ 60%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/cord_internal.dir/internal/cord_rep_btree.cc.o
2025-03-21T20:23:52.5755682Z [ 61%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/cord_internal.dir/internal/cord_rep_btree_navigator.cc.o
2025-03-21T20:23:52.5756757Z [ 61%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/cord_internal.dir/internal/cord_rep_btree_reader.cc.o
2025-03-21T20:23:52.5757956Z [ 61%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/cord_internal.dir/internal/cord_rep_crc.cc.o
2025-03-21T20:23:52.5758990Z [ 62%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/cord_internal.dir/internal/cord_rep_consume.cc.o
2025-03-21T20:23:52.5760104Z [ 63%] Building CXX object abseil-cpp/absl/container/CMakeFiles/hashtablez_sampler.dir/internal/hashtablez_sampler.cc.o
2025-03-21T20:23:52.5760941Z [ 63%] Linking CXX static library libabsl_cord_internal.a
2025-03-21T20:23:52.5761350Z [ 63%] Built target cord_internal
2025-03-21T20:23:52.5762246Z [ 63%] Building CXX object abseil-cpp/absl/container/CMakeFiles/hashtablez_sampler.dir/internal/hashtablez_sampler_force_weak_definition.cc.o
2025-03-21T20:23:52.5763598Z [ 64%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/cordz_handle.dir/internal/cordz_handle.cc.o
2025-03-21T20:23:52.5764376Z [ 64%] Linking CXX static library libabsl_hashtablez_sampler.a
2025-03-21T20:23:52.5764819Z [ 64%] Built target hashtablez_sampler
2025-03-21T20:23:52.5765541Z [ 65%] Building CXX object abseil-cpp/absl/flags/CMakeFiles/flags_program_name.dir/internal/program_name.cc.o
2025-03-21T20:23:52.5766295Z [ 65%] Linking CXX static library libabsl_cordz_handle.a
2025-03-21T20:23:52.5766749Z [ 65%] Built target cordz_handle
2025-03-21T20:23:52.5767965Z [ 65%] Building CXX object abseil-cpp/absl/log/CMakeFiles/vlog_config_internal.dir/internal/vlog_config.cc.o
2025-03-21T20:23:52.5768855Z [ 65%] Linking CXX static library libabsl_flags_program_name.a
2025-03-21T20:23:52.5769522Z [ 65%] Built target flags_program_name
2025-03-21T20:23:52.5770226Z [ 65%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/cordz_info.dir/internal/cordz_info.cc.o
2025-03-21T20:23:52.5770985Z [ 66%] Linking CXX static library libabsl_vlog_config_internal.a
2025-03-21T20:23:52.5771439Z [ 66%] Built target vlog_config_internal
2025-03-21T20:23:52.5772413Z [ 67%] Building CXX object abseil-cpp/absl/flags/CMakeFiles/flags_config.dir/usage_config.cc.o
2025-03-21T20:23:52.5773621Z [ 68%] Linking CXX static library libabsl_cordz_info.a
2025-03-21T20:23:52.5774295Z [ 68%] Built target cordz_info
2025-03-21T20:23:52.5775327Z [ 69%] Building CXX object abseil-cpp/absl/log/CMakeFiles/log_globals.dir/globals.cc.o
2025-03-21T20:23:52.5776517Z [ 69%] Linking CXX static library libabsl_flags_config.a
2025-03-21T20:23:52.5777112Z [ 69%] Built target flags_config
2025-03-21T20:23:52.5778336Z [ 69%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/cordz_sample_token.dir/internal/cordz_sample_token.cc.o
2025-03-21T20:23:52.5779543Z [ 69%] Linking CXX static library libabsl_log_globals.a
2025-03-21T20:23:52.5780137Z [ 69%] Built target log_globals
2025-03-21T20:23:52.5780945Z [ 70%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/cord.dir/cord.cc.o
2025-03-21T20:23:52.5781922Z [ 70%] Linking CXX static library libabsl_cordz_sample_token.a
2025-03-21T20:23:52.5782521Z [ 70%] Built target cordz_sample_token
2025-03-21T20:23:52.5783588Z [ 70%] Building CXX object abseil-cpp/absl/flags/CMakeFiles/flags_internal.dir/internal/flag.cc.o
2025-03-21T20:23:52.5784897Z [ 70%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/cord.dir/cord_analysis.cc.o
2025-03-21T20:23:52.5786032Z [ 71%] Linking CXX static library libabsl_flags_internal.a
2025-03-21T20:23:52.5786693Z [ 71%] Built target flags_internal
2025-03-21T20:23:52.5787872Z [ 71%] Building CXX object abseil-cpp/absl/log/CMakeFiles/log_internal_log_sink_set.dir/internal/log_sink_set.cc.o
2025-03-21T20:23:52.5788806Z [ 71%] Building CXX object abseil-cpp/absl/strings/CMakeFiles/cord.dir/cord_buffer.cc.o
2025-03-21T20:23:52.5789460Z [ 72%] Linking CXX static library libabsl_cord.a
2025-03-21T20:23:52.5790037Z [ 72%] Linking CXX static library libabsl_log_internal_log_sink_set.a
2025-03-21T20:23:52.5790482Z [ 72%] Built target cord
2025-03-21T20:23:52.5790766Z [ 72%] Built target log_internal_log_sink_set
2025-03-21T20:23:52.5791419Z [ 72%] Building CXX object abseil-cpp/absl/log/CMakeFiles/log_initialize.dir/initialize.cc.o
2025-03-21T20:23:57.5093874Z [ 73%] Building CXX object abseil-cpp/absl/status/CMakeFiles/status.dir/internal/status_internal.cc.o
2025-03-21T20:23:57.5094716Z [ 74%] Linking CXX static library libabsl_log_initialize.a
2025-03-21T20:23:57.5095136Z [ 74%] Built target log_initialize
2025-03-21T20:23:57.5095724Z [ 74%] Building CXX object abseil-cpp/absl/status/CMakeFiles/status.dir/status.cc.o
2025-03-21T20:23:57.5096596Z [ 74%] Building CXX object abseil-cpp/absl/status/CMakeFiles/status.dir/status_payload_printer.cc.o
2025-03-21T20:23:57.5097562Z [ 75%] Building CXX object abseil-cpp/absl/container/CMakeFiles/raw_hash_set.dir/internal/raw_hash_set.cc.o
2025-03-21T20:23:57.5098298Z [ 76%] Linking CXX static library libabsl_status.a
2025-03-21T20:23:57.5098681Z [ 76%] Built target status
2025-03-21T20:23:57.5099395Z [ 77%] Building CXX object abseil-cpp/absl/log/CMakeFiles/log_internal_message.dir/internal/log_message.cc.o
2025-03-21T20:23:57.5100187Z [ 77%] Linking CXX static library libabsl_log_internal_message.a
2025-03-21T20:23:57.5100957Z [ 77%] Built target log_internal_message
2025-03-21T20:23:57.5101510Z [ 77%] Linking CXX static library libabsl_raw_hash_set.a
2025-03-21T20:23:57.5102274Z [ 77%] Building CXX object abseil-cpp/absl/status/CMakeFiles/statusor.dir/statusor.cc.o
2025-03-21T20:23:57.5102860Z [ 77%] Built target raw_hash_set
2025-03-21T20:23:57.5103563Z [ 77%] Building CXX object abseil-cpp/absl/flags/CMakeFiles/flags_reflection.dir/reflection.cc.o
2025-03-21T20:23:57.5104331Z [ 77%] Linking CXX static library libabsl_statusor.a
2025-03-21T20:23:57.5104724Z [ 77%] Built target statusor
2025-03-21T20:23:57.5105447Z [ 77%] Building CXX object abseil-cpp/absl/log/CMakeFiles/log_internal_check_op.dir/internal/check_op.cc.o
2025-03-21T20:23:57.5106282Z [ 78%] Linking CXX static library libabsl_flags_reflection.a
2025-03-21T20:23:57.5106806Z [ 78%] Built target flags_reflection
2025-03-21T20:23:57.5107483Z [ 78%] Building CXX object abseil-cpp/absl/log/CMakeFiles/die_if_null.dir/die_if_null.cc.o
2025-03-21T20:23:57.5108265Z [ 78%] Linking CXX static library libabsl_log_internal_check_op.a
2025-03-21T20:23:57.5108741Z [ 78%] Built target log_internal_check_op
2025-03-21T20:23:57.5109368Z [ 78%] Building CXX object abseil-cpp/absl/log/CMakeFiles/log_flags.dir/flags.cc.o
2025-03-21T20:23:57.5110074Z [ 78%] Linking CXX static library libabsl_die_if_null.a
2025-03-21T20:23:57.5110538Z [ 78%] Built target die_if_null
2025-03-21T20:23:57.5111044Z [ 78%] Building CXX object re2/CMakeFiles/re2.dir/re2/bitmap256.cc.o
2025-03-21T20:23:57.5111655Z [ 78%] Linking CXX static library libabsl_log_flags.a
2025-03-21T20:23:57.5112102Z [ 78%] Built target log_flags
2025-03-21T20:23:57.5112617Z [ 78%] Building CXX object re2/CMakeFiles/re2.dir/re2/bitstate.cc.o
2025-03-21T20:23:57.5113249Z [ 78%] Building CXX object re2/CMakeFiles/re2.dir/re2/compile.cc.o
2025-03-21T20:23:57.5113921Z [ 79%] Building CXX object re2/CMakeFiles/re2.dir/re2/dfa.cc.o
2025-03-21T20:23:57.5114759Z [ 80%] Building CXX object abseil-cpp/absl/flags/CMakeFiles/flags_usage_internal.dir/internal/usage.cc.o
2025-03-21T20:23:57.5115655Z [ 80%] Building CXX object re2/CMakeFiles/re2.dir/re2/filtered_re2.cc.o
2025-03-21T20:23:57.5116313Z [ 80%] Linking CXX static library libabsl_flags_usage_internal.a
2025-03-21T20:23:57.5116820Z [ 80%] Built target flags_usage_internal
2025-03-21T20:23:57.5117405Z [ 80%] Building CXX object re2/CMakeFiles/re2.dir/re2/mimics_pcre.cc.o
2025-03-21T20:23:57.5118069Z [ 81%] Building CXX object re2/CMakeFiles/re2.dir/re2/nfa.cc.o
2025-03-21T20:23:57.5118807Z [ 81%] Building CXX object abseil-cpp/absl/flags/CMakeFiles/flags_usage.dir/usage.cc.o
2025-03-21T20:23:57.5119528Z [ 81%] Linking CXX static library libabsl_flags_usage.a
2025-03-21T20:23:57.5119937Z [ 81%] Built target flags_usage
2025-03-21T20:23:57.5120484Z [ 81%] Building CXX object re2/CMakeFiles/re2.dir/re2/onepass.cc.o
2025-03-21T20:23:57.5121160Z [ 81%] Building CXX object re2/CMakeFiles/re2.dir/re2/parse.cc.o
2025-03-21T20:23:57.5121819Z [ 82%] Building CXX object re2/CMakeFiles/re2.dir/re2/perl_groups.cc.o
2025-03-21T20:23:57.5122471Z [ 82%] Building CXX object re2/CMakeFiles/re2.dir/re2/prefilter.cc.o
2025-03-21T20:23:57.5123184Z [ 82%] Building CXX object re2/CMakeFiles/re2.dir/re2/prefilter_tree.cc.o
2025-03-21T20:23:57.5123999Z [ 83%] Building CXX object abseil-cpp/absl/flags/CMakeFiles/flags_parse.dir/parse.cc.o
2025-03-21T20:23:57.5124759Z [ 84%] Building CXX object re2/CMakeFiles/re2.dir/re2/prog.cc.o
2025-03-21T20:23:57.5125389Z [ 84%] Linking CXX static library libabsl_flags_parse.a
2025-03-21T20:23:57.5125843Z [ 84%] Built target flags_parse
2025-03-21T20:23:57.5126317Z [ 84%] Building CXX object re2/CMakeFiles/re2.dir/re2/re2.cc.o
2025-03-21T20:23:57.5127722Z [ 84%] Building CXX object re2/CMakeFiles/re2.dir/re2/regexp.cc.o
2025-03-21T20:23:57.5128401Z [ 84%] Building CXX object re2/CMakeFiles/re2.dir/re2/set.cc.o
2025-03-21T20:23:57.5129065Z [ 85%] Building CXX object re2/CMakeFiles/re2.dir/re2/simplify.cc.o
2025-03-21T20:23:57.5129797Z [ 85%] Building CXX object re2/CMakeFiles/re2.dir/re2/tostring.cc.o
2025-03-21T20:23:57.5130498Z [ 85%] Building CXX object re2/CMakeFiles/re2.dir/re2/unicode_casefold.cc.o
2025-03-21T20:23:57.5131188Z [ 86%] Building CXX object re2/CMakeFiles/re2.dir/re2/unicode_groups.cc.o
2025-03-21T20:23:57.5131824Z [ 86%] Building CXX object re2/CMakeFiles/re2.dir/util/rune.cc.o
2025-03-21T20:23:57.5132641Z [ 86%] Building CXX object re2/CMakeFiles/re2.dir/util/strutil.cc.o
2025-03-21T20:23:57.5133183Z [ 87%] Linking CXX static library libre2.a
2025-03-21T20:23:57.5133540Z [ 87%] Built target re2
2025-03-21T20:23:57.5134142Z [ 87%] Building CXX object oss_scripts/llama/CMakeFiles/qnn_llama_runner.dir/qnn_llama_runner.cpp.o
2025-03-21T20:23:57.5135180Z [ 87%] Building CXX object qaihub_scripts/llama/CMakeFiles/qaihub_llama2_7b_runner.dir/llama2/qaihub_llama2_7b_runner.cpp.o
2025-03-21T20:23:57.5136221Z [ 88%] Building CXX object oss_scripts/llama/CMakeFiles/qnn_llama_runner.dir/runner/runner.cpp.o
2025-03-21T20:23:57.5137163Z [ 88%] Building CXX object qaihub_scripts/llama/CMakeFiles/qaihub_llama2_7b_runner.dir/runner/runner.cpp.o
2025-03-21T20:23:57.5138162Z [ 89%] Building CXX object qaihub_scripts/llama/CMakeFiles/qaihub_llama2_7b_runner.dir/runner/io_memory.cpp.o
2025-03-21T20:23:57.5139120Z [ 89%] Building CXX object oss_scripts/llama/CMakeFiles/qnn_llama_runner.dir/runner/io_manager.cpp.o
2025-03-21T20:23:57.5140353Z [ 89%] Building CXX object qaihub_scripts/llama/CMakeFiles/qaihub_llama2_7b_runner.dir/pytorch/executorch/examples/models/llama/tokenizer/llama_tiktoken.cpp.o
2025-03-21T20:23:57.5141813Z [ 89%] Building CXX object oss_scripts/llama/CMakeFiles/qnn_llama_runner.dir/pytorch/executorch/examples/models/llama/tokenizer/llama_tiktoken.cpp.o
2025-03-21T20:23:57.5143204Z [ 89%] Building CXX object oss_scripts/llama/CMakeFiles/qnn_llama_runner.dir/pytorch/executorch/extension/evalue_util/print_evalue.cpp.o
2025-03-21T20:23:57.5144536Z [ 89%] Building CXX object qaihub_scripts/llama/CMakeFiles/qaihub_llama2_7b_runner.dir/pytorch/executorch/extension/evalue_util/print_evalue.cpp.o
2025-03-21T20:23:57.5145875Z [ 90%] Building CXX object qaihub_scripts/llama/CMakeFiles/qaihub_llama2_7b_runner.dir/pytorch/executorch/extension/llm/sampler/sampler.cpp.o
2025-03-21T20:23:57.5147148Z [ 91%] Building CXX object oss_scripts/llama/CMakeFiles/qnn_llama_runner.dir/pytorch/executorch/extension/llm/sampler/sampler.cpp.o
2025-03-21T20:23:57.5148437Z [ 91%] Building CXX object qaihub_scripts/llama/CMakeFiles/qaihub_llama2_7b_runner.dir/pytorch/executorch/extension/llm/tokenizer/tiktoken.cpp.o
2025-03-21T20:23:57.5150003Z [ 91%] Building CXX object oss_scripts/llama/CMakeFiles/qnn_llama_runner.dir/pytorch/executorch/extension/llm/tokenizer/tiktoken.cpp.o
2025-03-21T20:23:57.5151484Z [ 91%] Building CXX object qaihub_scripts/llama/CMakeFiles/qaihub_llama2_7b_runner.dir/pytorch/executorch/extension/llm/tokenizers/src/bpe_tokenizer_base.cpp.o
2025-03-21T20:23:57.5152921Z [ 91%] Building CXX object oss_scripts/llama/CMakeFiles/qnn_llama_runner.dir/pytorch/executorch/extension/llm/tokenizers/src/bpe_tokenizer_base.cpp.o
2025-03-21T20:23:57.5154377Z [ 92%] Building CXX object qaihub_scripts/llama/CMakeFiles/qaihub_llama2_7b_runner.dir/pytorch/executorch/extension/llm/tokenizers/src/llama2c_tokenizer.cpp.o
2025-03-21T20:23:57.5155889Z [ 93%] Building CXX object oss_scripts/llama/CMakeFiles/qnn_llama_runner.dir/pytorch/executorch/extension/llm/tokenizers/src/llama2c_tokenizer.cpp.o
2025-03-21T20:23:57.5157529Z [ 93%] Building CXX object qaihub_scripts/llama/CMakeFiles/qaihub_llama2_7b_runner.dir/pytorch/executorch/extension/llm/tokenizers/src/tiktoken.cpp.o
2025-03-21T20:23:57.5158979Z [ 93%] Building CXX object oss_scripts/llama/CMakeFiles/qnn_llama_runner.dir/pytorch/executorch/extension/llm/tokenizers/src/tiktoken.cpp.o
2025-03-21T20:23:57.5160286Z [ 93%] Building CXX object qaihub_scripts/llama/CMakeFiles/qaihub_llama2_7b_runner.dir/pytorch/executorch/extension/tensor/tensor_ptr.cpp.o
2025-03-21T20:23:57.5161532Z [ 93%] Building CXX object oss_scripts/llama/CMakeFiles/qnn_llama_runner.dir/pytorch/executorch/extension/tensor/tensor_ptr.cpp.o
2025-03-21T20:23:57.5162816Z [ 94%] Building CXX object qaihub_scripts/llama/CMakeFiles/qaihub_llama2_7b_runner.dir/pytorch/executorch/extension/tensor/tensor_ptr_maker.cpp.o
2025-03-21T20:23:57.5164102Z [ 95%] Building CXX object oss_scripts/llama/CMakeFiles/qnn_llama_runner.dir/pytorch/executorch/extension/tensor/tensor_ptr_maker.cpp.o
2025-03-21T20:23:57.5164981Z [ 95%] Linking CXX executable qaihub_llama2_7b_runner
2025-03-21T20:23:57.5165485Z [ 95%] Linking CXX executable qnn_llama_runner
2025-03-21T20:23:57.5165879Z [ 95%] Built target qaihub_llama2_7b_runner
2025-03-21T20:23:57.5166669Z [ 95%] Building CXX object qaihub_scripts/llama/CMakeFiles/qaihub_llama3_8b_runner.dir/llama3/qaihub_llama3_8b_runner.cpp.o
2025-03-21T20:24:03.7288616Z [ 95%] Building CXX object qaihub_scripts/llama/CMakeFiles/qaihub_llama3_8b_runner.dir/runner/runner.cpp.o
2025-03-21T20:24:03.7289777Z [ 95%] Built target qnn_llama_runner
2025-03-21T20:24:03.7290940Z [ 95%] Building CXX object qaihub_scripts/stable_diffusion/CMakeFiles/qaihub_stable_diffusion_runner.dir/qaihub_stable_diffusion_runner.cpp.o
2025-03-21T20:24:03.7292214Z [ 96%] Building CXX object qaihub_scripts/llama/CMakeFiles/qaihub_llama3_8b_runner.dir/runner/io_memory.cpp.o
2025-03-21T20:24:03.7293326Z [ 96%] Building CXX object qaihub_scripts/stable_diffusion/CMakeFiles/qaihub_stable_diffusion_runner.dir/runner/runner.cpp.o
2025-03-21T20:24:03.7294676Z [ 96%] Building CXX object qaihub_scripts/llama/CMakeFiles/qaihub_llama3_8b_runner.dir/pytorch/executorch/examples/models/llama/tokenizer/llama_tiktoken.cpp.o
2025-03-21T20:24:03.7295680Z [ 97%] Linking CXX executable qaihub_stable_diffusion_runner
2025-03-21T20:24:03.7296715Z [ 97%] Building CXX object qaihub_scripts/llama/CMakeFiles/qaihub_llama3_8b_runner.dir/pytorch/executorch/extension/evalue_util/print_evalue.cpp.o
2025-03-21T20:24:03.7297529Z [ 97%] Built target qaihub_stable_diffusion_runner
2025-03-21T20:24:03.7298619Z [ 98%] Building CXX object qaihub_scripts/llama/CMakeFiles/qaihub_llama3_8b_runner.dir/pytorch/executorch/extension/llm/sampler/sampler.cpp.o
2025-03-21T20:24:03.7299969Z [ 98%] Building CXX object qaihub_scripts/llama/CMakeFiles/qaihub_llama3_8b_runner.dir/pytorch/executorch/extension/llm/tokenizer/tiktoken.cpp.o
2025-03-21T20:24:03.7301416Z [ 98%] Building CXX object qaihub_scripts/llama/CMakeFiles/qaihub_llama3_8b_runner.dir/pytorch/executorch/extension/llm/tokenizers/src/bpe_tokenizer_base.cpp.o
2025-03-21T20:24:03.7302921Z [ 99%] Building CXX object qaihub_scripts/llama/CMakeFiles/qaihub_llama3_8b_runner.dir/pytorch/executorch/extension/llm/tokenizers/src/llama2c_tokenizer.cpp.o
2025-03-21T20:24:03.7304362Z [ 99%] Building CXX object qaihub_scripts/llama/CMakeFiles/qaihub_llama3_8b_runner.dir/pytorch/executorch/extension/llm/tokenizers/src/tiktoken.cpp.o
2025-03-21T20:24:03.7305706Z [ 99%] Building CXX object qaihub_scripts/llama/CMakeFiles/qaihub_llama3_8b_runner.dir/pytorch/executorch/extension/tensor/tensor_ptr.cpp.o
2025-03-21T20:24:03.7307038Z [100%] Building CXX object qaihub_scripts/llama/CMakeFiles/qaihub_llama3_8b_runner.dir/pytorch/executorch/extension/tensor/tensor_ptr_maker.cpp.o
2025-03-21T20:24:03.7307969Z [100%] Linking CXX executable qaihub_llama3_8b_runner
2025-03-21T20:24:03.7308882Z [100%] Built target qaihub_llama3_8b_runner
2025-03-21T20:24:03.7309231Z + set_up_aot
2025-03-21T20:24:03.7309468Z + cd /pytorch/executorch
2025-03-21T20:24:03.7309762Z + '[' '!' -d cmake-out ']'
2025-03-21T20:24:03.7310040Z + mkdir cmake-out
2025-03-21T20:24:03.7310294Z + pushd cmake-out
2025-03-21T20:24:03.7310591Z /pytorch/executorch/cmake-out /pytorch/executorch
2025-03-21T20:24:03.7312134Z + cmake .. -DCMAKE_INSTALL_PREFIX=/pytorch/executorch/cmake-out -DEXECUTORCH_BUILD_QNN=ON -DQNN_SDK_ROOT=/tmp/qnn/2.28.0.241029 -DEXECUTORCH_BUILD_DEVTOOLS=ON -DEXECUTORCH_BUILD_EXTENSION_MODULE=ON -DEXECUTORCH_BUILD_EXTENSION_TENSOR=ON -DEXECUTORCH_ENABLE_EVENT_TRACER=ON -DPYTHON_EXECUTABLE=python3 -DEXECUTORCH_SEPARATE_FLATCC_HOST_PROJECT=OFF
2025-03-21T20:24:03.7313783Z -- The C compiler identification is Clang 12.0.1
2025-03-21T20:24:03.7314171Z -- The CXX compiler identification is Clang 12.0.1
2025-03-21T20:24:03.7314548Z -- Detecting C compiler ABI info
2025-03-21T20:24:03.7314890Z -- Detecting C compiler ABI info - done
2025-03-21T20:24:03.7315293Z -- Check for working C compiler: /opt/cache/bin/cc - skipped
2025-03-21T20:24:03.7315697Z -- Detecting C compile features
2025-03-21T20:24:03.7316004Z -- Detecting C compile features - done
2025-03-21T20:24:03.7316340Z -- Detecting CXX compiler ABI info
2025-03-21T20:24:03.7316669Z -- Detecting CXX compiler ABI info - done
2025-03-21T20:24:03.7317086Z -- Check for working CXX compiler: /opt/cache/bin/c++ - skipped
2025-03-21T20:24:03.7317497Z -- Detecting CXX compile features
2025-03-21T20:24:03.7317811Z -- Detecting CXX compile features - done
2025-03-21T20:24:03.7318563Z CMake Deprecation Warning at backends/xnnpack/third-party/FXdiv/CMakeLists.txt:1 (CMAKE_MINIMUM_REQUIRED):
2025-03-21T20:24:03.7319298Z   Compatibility with CMake < 3.10 will be removed from a future version of
2025-03-21T20:24:03.7319733Z   CMake.
2025-03-21T20:24:03.7319857Z 
2025-03-21T20:24:03.7320098Z   Update the VERSION argument <min> value.  Or, use the <min>...<max> syntax
2025-03-21T20:24:03.7320677Z   to tell CMake that the project requires at least <min> but has been updated
2025-03-21T20:24:03.7321166Z   to work with policies introduced by <max> or earlier.
2025-03-21T20:24:03.7321442Z 
2025-03-21T20:24:03.7321550Z 
2025-03-21T20:24:03.7322169Z CMake Deprecation Warning at backends/xnnpack/third-party/cpuinfo/CMakeLists.txt:1 (CMAKE_MINIMUM_REQUIRED):
2025-03-21T20:24:03.7322911Z   Compatibility with CMake < 3.10 will be removed from a future version of
2025-03-21T20:24:03.7323345Z   CMake.
2025-03-21T20:24:03.7323466Z 
2025-03-21T20:24:03.7323692Z   Update the VERSION argument <min> value.  Or, use the <min>...<max> syntax
2025-03-21T20:24:03.7324263Z   to tell CMake that the project requires at least <min> but has been updated
2025-03-21T20:24:03.7324760Z   to work with policies introduced by <max> or earlier.
2025-03-21T20:24:03.7325032Z 
2025-03-21T20:24:03.7325138Z 
2025-03-21T20:24:03.7325389Z -- Performing Test CMAKE_HAVE_LIBC_PTHREAD
2025-03-21T20:24:03.7325791Z -- Performing Test CMAKE_HAVE_LIBC_PTHREAD - Success
2025-03-21T20:24:03.7326145Z -- Found Threads: TRUE
2025-03-21T20:24:03.7326834Z CMake Deprecation Warning at backends/xnnpack/third-party/pthreadpool/CMakeLists.txt:1 (CMAKE_MINIMUM_REQUIRED):
2025-03-21T20:24:03.7327598Z   Compatibility with CMake < 3.10 will be removed from a future version of
2025-03-21T20:24:03.7328031Z   CMake.
2025-03-21T20:24:03.7328154Z 
2025-03-21T20:24:03.7328393Z   Update the VERSION argument <min> value.  Or, use the <min>...<max> syntax
2025-03-21T20:24:03.7328959Z   to tell CMake that the project requires at least <min> but has been updated
2025-03-21T20:24:03.7329521Z   to work with policies introduced by <max> or earlier.
2025-03-21T20:24:03.7329795Z 
2025-03-21T20:24:03.7329905Z 
2025-03-21T20:24:03.7330146Z -- Using python executable 'python3'
2025-03-21T20:24:03.7330482Z -- Resolved buck2 as buck2.
2025-03-21T20:24:03.7330772Z -- Killing buck2 daemon
2025-03-21T20:24:03.7331121Z 'buck2 killall'
2025-03-21T20:24:03.7331449Z -- executorch: Generating source lists
2025-03-21T20:24:03.7331987Z -- executorch: Generating source file list /pytorch/executorch/cmake-out/executorch_srcs.cmake
2025-03-21T20:24:03.7333250Z -- executorch: Using sources file /pytorch/executorch/cmake-out/executorch_srcs.cmake
2025-03-21T20:24:03.7333769Z -- executorch: Using PAL default 'posix'
2025-03-21T20:24:03.7334099Z -- Generating operator lib:
2025-03-21T20:24:03.7334400Z --   LIB_NAME: portable_ops_lib
2025-03-21T20:24:03.7334824Z --   OPS_SCHEMA_YAML: /pytorch/executorch/kernels/portable/functions.yaml
2025-03-21T20:24:03.7335257Z --   ROOT_OPS: 
2025-03-21T20:24:03.7335500Z --   INCLUDE_ALL_OPS: 
2025-03-21T20:24:03.7336767Z Command - python3;-m;codegen.tools.gen_oplist;--output_path=/pytorch/executorch/cmake-out/kernels/portable/portable_ops_lib/selected_operators.yaml;--ops_schema_yaml_path="/pytorch/executorch/kernels/portable/functions.yaml"
2025-03-21T20:24:03.7337886Z -- Generating kernel bindings:
2025-03-21T20:24:03.7338208Z --   LIB_NAME: portable_ops_lib
2025-03-21T20:24:03.7338624Z --   FUNCTIONS_YAML: /pytorch/executorch/kernels/portable/functions.yaml
2025-03-21T20:24:03.7339062Z --   CUSTOM_OPS_YAML: 
2025-03-21T20:24:03.7339343Z --   ADD_EXCEPTION_BOUNDARY: FALSE
2025-03-21T20:24:03.7341023Z Generated files /pytorch/executorch/cmake-out/kernels/portable/portable_ops_lib/RegisterCodegenUnboxedKernelsEverything.cpp;/pytorch/executorch/cmake-out/kernels/portable/portable_ops_lib/Functions.h;/pytorch/executorch/cmake-out/kernels/portable/portable_ops_lib/NativeFunctions.h
2025-03-21T20:24:03.7342486Z -- Generating operator lib:
2025-03-21T20:24:03.7342783Z --   LIB_NAME: portable_ops_lib
2025-03-21T20:24:03.7343092Z --   KERNEL_LIBS: portable_kernels
2025-03-21T20:24:03.7343395Z --   DEPS: executorch
2025-03-21T20:24:03.7343971Z CMake Deprecation Warning at third-party/gflags/CMakeLists.txt:73 (cmake_minimum_required):
2025-03-21T20:24:03.7344631Z   Compatibility with CMake < 3.10 will be removed from a future version of
2025-03-21T20:24:03.7345071Z   CMake.
2025-03-21T20:24:03.7345213Z 
2025-03-21T20:24:03.7345441Z   Update the VERSION argument <min> value.  Or, use the <min>...<max> syntax
2025-03-21T20:24:03.7346015Z   to tell CMake that the project requires at least <min> but has been updated
2025-03-21T20:24:03.7346520Z   to work with policies introduced by <max> or earlier.
2025-03-21T20:24:03.7346779Z 
2025-03-21T20:24:03.7346885Z 
2025-03-21T20:24:03.7347120Z -- Looking for C++ include unistd.h
2025-03-21T20:24:03.7347457Z -- Looking for C++ include unistd.h - found
2025-03-21T20:24:03.7347801Z -- Looking for C++ include stdint.h
2025-03-21T20:24:03.7348137Z -- Looking for C++ include stdint.h - found
2025-03-21T20:24:03.7348474Z -- Looking for C++ include inttypes.h
2025-03-21T20:24:03.7348823Z -- Looking for C++ include inttypes.h - found
2025-03-21T20:24:03.7349179Z -- Looking for C++ include sys/types.h
2025-03-21T20:24:03.7349528Z -- Looking for C++ include sys/types.h - found
2025-03-21T20:24:03.7349895Z -- Looking for C++ include sys/stat.h
2025-03-21T20:24:03.7350225Z -- Looking for C++ include sys/stat.h - found
2025-03-21T20:24:03.7350578Z -- Looking for C++ include fnmatch.h
2025-03-21T20:24:03.7350918Z -- Looking for C++ include fnmatch.h - found
2025-03-21T20:24:03.7351266Z -- Looking for C++ include stddef.h
2025-03-21T20:24:03.7351604Z -- Looking for C++ include stddef.h - found
2025-03-21T20:24:03.7351929Z -- Check size of uint32_t
2025-03-21T20:24:03.7352223Z -- Check size of uint32_t - done
2025-03-21T20:24:03.7352529Z -- Looking for strtoll
2025-03-21T20:24:03.7352809Z -- Looking for strtoll - found
2025-03-21T20:24:03.7353130Z -- Using qnn sdk root /tmp/qnn/2.28.0.241029
2025-03-21T20:24:03.7353499Z -- Using EXECUTORCH_SOURCE_DIR /pytorch/executorch
2025-03-21T20:24:03.7354188Z CMake Deprecation Warning at third-party/pybind11/CMakeLists.txt:13 (cmake_minimum_required):
2025-03-21T20:24:03.7354865Z   Compatibility with CMake < 3.10 will be removed from a future version of
2025-03-21T20:24:03.7355523Z   CMake.
2025-03-21T20:24:03.7355644Z 
2025-03-21T20:24:03.7355883Z   Update the VERSION argument <min> value.  Or, use the <min>...<max> syntax
2025-03-21T20:24:03.7356456Z   to tell CMake that the project requires at least <min> but has been updated
2025-03-21T20:24:03.7356939Z   to work with policies introduced by <max> or earlier.
2025-03-21T20:24:03.7357215Z 
2025-03-21T20:24:03.7357329Z 
2025-03-21T20:24:03.7357555Z -- pybind11 v2.13.6 
2025-03-21T20:24:03.7358010Z -- Found PythonInterp: python3 (found suitable version "3.10.16", minimum required is "3.7")
2025-03-21T20:24:03.7358623Z -- Found PythonLibs: /opt/conda/envs/py_3.10/lib/libpython3.10.so
2025-03-21T20:24:03.7359039Z -- Performing Test HAS_FLTO_THIN
2025-03-21T20:24:03.7359364Z -- Performing Test HAS_FLTO_THIN - Success
2025-03-21T20:24:03.7359996Z CMake Deprecation Warning at third-party/flatcc/CMakeLists.txt:2 (cmake_minimum_required):
2025-03-21T20:24:03.7360663Z   Compatibility with CMake < 3.10 will be removed from a future version of
2025-03-21T20:24:03.7361095Z   CMake.
2025-03-21T20:24:03.7361214Z 
2025-03-21T20:24:03.7361451Z   Update the VERSION argument <min> value.  Or, use the <min>...<max> syntax
2025-03-21T20:24:03.7362009Z   to tell CMake that the project requires at least <min> but has been updated
2025-03-21T20:24:06.7923095Z   to work with policies introduced by <max> or earlier.
2025-03-21T20:24:06.7923680Z 
2025-03-21T20:24:06.7924149Z 
2025-03-21T20:24:06.7924607Z -- dist install dir /pytorch/executorch/third-party/flatcc
2025-03-21T20:24:06.7925364Z -- lib install dir /pytorch/executorch/third-party/flatcc/lib
2025-03-21T20:24:06.7926015Z -- Setting Clang compiler options
2025-03-21T20:24:06.7927179Z -- Configured C_FLAGS:  -DFLATCC_REFLECTION=0 -Wstrict-prototypes -Wsign-conversion -Wconversion -std=c11 -pedantic -Wall -Wextra -Werror
2025-03-21T20:24:06.7928328Z -- 
2025-03-21T20:24:06.7928663Z -- ******** Summary ********
2025-03-21T20:24:06.7929272Z --   CMAKE_BUILD_TYPE              : Debug
2025-03-21T20:24:06.7929813Z --   CMAKE_CXX_STANDARD            : 17
2025-03-21T20:24:06.7930342Z --   CMAKE_CXX_COMPILER_ID         : Clang
2025-03-21T20:24:06.7930875Z --   CMAKE_TOOLCHAIN_FILE          : 
2025-03-21T20:24:06.7931363Z --   BUCK2                         : buck2
2025-03-21T20:24:06.7931891Z --   PYTHON_EXECUTABLE             : python3
2025-03-21T20:24:06.7932889Z --   FLATC_EXECUTABLE              : /pytorch/executorch/cmake-out/third-party/flatbuffers/flatc
2025-03-21T20:24:06.7933726Z --   EXECUTORCH_ENABLE_LOGGING              : ON
2025-03-21T20:24:06.7934328Z --   EXECUTORCH_ENABLE_PROGRAM_VERIFICATION : ON
2025-03-21T20:24:06.7934908Z --   EXECUTORCH_LOG_LEVEL                   : Info
2025-03-21T20:24:06.7935515Z --   EXECUTORCH_BUILD_ANDROID_JNI           : OFF
2025-03-21T20:24:06.7936124Z --   EXECUTORCH_BUILD_ARM_BAREMETAL         : OFF
2025-03-21T20:24:06.7936724Z --   EXECUTORCH_BUILD_CADENCE               : OFF
2025-03-21T20:24:06.7937348Z --   EXECUTORCH_BUILD_COREML                : OFF
2025-03-21T20:24:06.7937916Z --   EXECUTORCH_BUILD_CPUINFO               : ON
2025-03-21T20:24:06.7938500Z --   EXECUTORCH_BUILD_DEVTOOLS              : ON
2025-03-21T20:24:06.7939094Z --   EXECUTORCH_BUILD_EXECUTOR_RUNNER       : ON
2025-03-21T20:24:06.7939693Z --   EXECUTORCH_BUILD_EXTENSION_DATA_LOADER : ON
2025-03-21T20:24:06.7940286Z --   EXECUTORCH_BUILD_EXTENSION_FLAT_TENSOR : ON
2025-03-21T20:24:06.7940885Z --   EXECUTORCH_BUILD_EXTENSION_LLM : OFF
2025-03-21T20:24:06.7941440Z --   EXECUTORCH_BUILD_EXTENSION_MODULE      : ON
2025-03-21T20:24:06.7942056Z --   EXECUTORCH_BUILD_EXTENSION_RUNNER_UTIL : OFF
2025-03-21T20:24:06.7942679Z --   EXECUTORCH_BUILD_EXTENSION_TENSOR      : ON
2025-03-21T20:24:06.7943340Z --   EXECUTORCH_BUILD_EXTENSION_TRAINING    : OFF
2025-03-21T20:24:06.7944004Z --   EXECUTORCH_BUILD_FLATC                 : ON
2025-03-21T20:24:06.7944638Z --   EXECUTORCH_BUILD_GFLAGS                : ON
2025-03-21T20:24:06.7945279Z --   EXECUTORCH_BUILD_HOST_TARGETS          : ON
2025-03-21T20:24:06.7947023Z --   EXECUTORCH_BUILD_KERNELS_CUSTOM        : OFF
2025-03-21T20:24:06.7947731Z --   EXECUTORCH_BUILD_KERNELS_CUSTOM_AOT    : OFF
2025-03-21T20:24:06.7948446Z --   EXECUTORCH_BUILD_KERNELS_OPTIMIZED     : OFF
2025-03-21T20:24:06.7949102Z --   EXECUTORCH_BUILD_KERNELS_QUANTIZED     : OFF
2025-03-21T20:24:06.7949779Z --   EXECUTORCH_BUILD_MPS                   : OFF
2025-03-21T20:24:06.7950438Z --   EXECUTORCH_BUILD_NEURON                : OFF
2025-03-21T20:24:06.7951102Z --   EXECUTORCH_BUILD_PTHREADPOOL           : ON
2025-03-21T20:24:06.7951758Z --   EXECUTORCH_BUILD_PYBIND                : OFF
2025-03-21T20:24:06.7952403Z --   EXECUTORCH_BUILD_QNN                   : ON
2025-03-21T20:24:06.7953074Z --   EXECUTORCH_BUILD_SIZE_TEST             : OFF
2025-03-21T20:24:06.7953729Z --   EXECUTORCH_BUILD_TESTS                 : OFF
2025-03-21T20:24:06.7954386Z --   EXECUTORCH_BUILD_VULKAN                : OFF
2025-03-21T20:24:06.7955033Z --   EXECUTORCH_BUILD_XNNPACK               : OFF
2025-03-21T20:24:06.7955687Z -- Configuring done (4.9s)
2025-03-21T20:24:06.7956206Z -- Generating done (0.2s)
2025-03-21T20:24:06.7956880Z -- Build files have been written to: /pytorch/executorch/cmake-out
2025-03-21T20:24:06.7957604Z ++ nproc
2025-03-21T20:24:06.7958467Z + cmake --build /pytorch/executorch/cmake-out --target PyQnnManagerAdaptor PyQnnWrapperAdaptor -j8
2025-03-21T20:24:06.7959794Z [  0%] Creating directories for 'flatbuffers'
2025-03-21T20:24:06.7960647Z [  0%] No download step for 'flatbuffers'
2025-03-21T20:24:06.7961434Z [  0%] No update step for 'flatbuffers'
2025-03-21T20:24:06.7962206Z [  0%] No patch step for 'flatbuffers'
2025-03-21T20:24:06.7963066Z [  0%] Performing configure step for 'flatbuffers'
2025-03-21T20:24:06.7963820Z CMake Warning:
2025-03-21T20:24:06.7964411Z   Ignoring empty string ("") provided on the command line.
2025-03-21T20:24:06.7964926Z 
2025-03-21T20:24:06.7965180Z 
2025-03-21T20:24:06.7965637Z fatal: No names found, cannot describe anything.
2025-03-21T20:24:06.7966452Z CMake Warning at CMake/Version.cmake:32 (message):
2025-03-21T20:24:06.7967078Z   git describe failed with exit code: 128
2025-03-21T20:24:06.7967438Z 
2025-03-21T20:24:06.7967736Z   Make sure you cloned with tags or run 'git fetch --tags'.
2025-03-21T20:24:06.7968404Z Call Stack (most recent call first):
2025-03-21T20:24:06.7968914Z   CMakeLists.txt:5 (include)
2025-03-21T20:24:06.7969319Z 
2025-03-21T20:24:06.7969523Z 
2025-03-21T20:24:06.7969895Z -- Proceeding with version: 24.3.25.0
2025-03-21T20:24:06.7970483Z -- The CXX compiler identification is Clang 12.0.1
2025-03-21T20:24:06.7971090Z -- Detecting CXX compiler ABI info
2025-03-21T20:24:06.7971612Z -- Detecting CXX compiler ABI info - done
2025-03-21T20:24:06.7972302Z -- Check for working CXX compiler: /opt/cache/bin/c++ - skipped
2025-03-21T20:24:06.7972984Z -- Detecting CXX compile features
2025-03-21T20:24:06.7973535Z -- Detecting CXX compile features - done
2025-03-21T20:24:06.7974070Z -- Looking for strtof_l
2025-03-21T20:24:06.7974503Z -- Looking for strtof_l - found
2025-03-21T20:24:06.7974984Z -- Looking for strtoull_l
2025-03-21T20:24:06.7975454Z -- Looking for strtoull_l - found
2025-03-21T20:24:06.7975947Z -- Looking for realpath
2025-03-21T20:24:06.7976390Z -- Looking for realpath - found
2025-03-21T20:24:06.7976941Z -- CMAKE_CXX_FLAGS: "-DFLATBUFFERS_MAX_ALIGNMENT=1024"
2025-03-21T20:24:06.7977548Z -- Configuring done (0.8s)
2025-03-21T20:24:06.7978007Z -- Generating done (0.0s)
2025-03-21T20:24:06.7978770Z -- Build files have been written to: /pytorch/executorch/cmake-out/third-party/flatbuffers
2025-03-21T20:24:06.7979845Z [  0%] Performing build step for 'flatbuffers'
2025-03-21T20:24:06.7980790Z [  2%] Building CXX object CMakeFiles/flatc.dir/src/idl_parser.cpp.o
2025-03-21T20:24:06.7981879Z [  5%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_text.cpp.o
2025-03-21T20:24:06.7983298Z [  7%] Building CXX object CMakeFiles/flatc.dir/src/reflection.cpp.o
2025-03-21T20:24:06.7984345Z [ 10%] Building CXX object CMakeFiles/flatc.dir/src/util.cpp.o
2025-03-21T20:24:06.7985391Z [ 15%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_binary.cpp.o
2025-03-21T20:24:06.7986484Z [ 15%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_cpp.cpp.o
2025-03-21T20:24:06.7987612Z [ 18%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_csharp.cpp.o
2025-03-21T20:24:06.7988762Z [ 21%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_dart.cpp.o
2025-03-21T20:24:06.7989921Z [ 23%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_kotlin.cpp.o
2025-03-21T20:24:06.7991118Z [ 26%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_kotlin_kmp.cpp.o
2025-03-21T20:24:06.7992321Z [ 28%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_go.cpp.o
2025-03-21T20:24:06.7993473Z [ 31%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_java.cpp.o
2025-03-21T20:24:06.7994592Z [ 34%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_ts.cpp.o
2025-03-21T20:24:06.7995706Z [ 36%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_php.cpp.o
2025-03-21T20:24:06.7996824Z [ 39%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_python.cpp.o
2025-03-21T20:24:06.7997994Z [ 42%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_lobster.cpp.o
2025-03-21T20:24:06.7999192Z [ 44%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_rust.cpp.o
2025-03-21T20:24:06.8000312Z [ 47%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_fbs.cpp.o
2025-03-21T20:24:06.8001489Z [ 50%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_json_schema.cpp.o
2025-03-21T20:24:06.8002683Z [ 52%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_grpc.cpp.o
2025-03-21T20:24:06.8003850Z [ 55%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_swift.cpp.o
2025-03-21T20:24:06.8005126Z [ 57%] Building CXX object CMakeFiles/flatc.dir/src/file_name_saving_file_manager.cpp.o
2025-03-21T20:24:06.8006405Z [ 60%] Building CXX object CMakeFiles/flatc.dir/src/file_binary_writer.cpp.o
2025-03-21T20:24:06.8007563Z [ 63%] Building CXX object CMakeFiles/flatc.dir/src/file_writer.cpp.o
2025-03-21T20:24:06.8008645Z [ 65%] Building CXX object CMakeFiles/flatc.dir/src/flatc.cpp.o
2025-03-21T20:24:06.8009849Z [ 68%] Building CXX object CMakeFiles/flatc.dir/src/flatc_main.cpp.o
2025-03-21T20:24:06.8011045Z [ 71%] Building CXX object CMakeFiles/flatc.dir/src/binary_annotator.cpp.o
2025-03-21T20:24:06.8012361Z [ 73%] Building CXX object CMakeFiles/flatc.dir/src/annotated_binary_text_gen.cpp.o
2025-03-21T20:24:06.8013631Z [ 76%] Building CXX object CMakeFiles/flatc.dir/src/bfbs_gen_lua.cpp.o
2025-03-21T20:24:06.8014736Z [ 78%] Building CXX object CMakeFiles/flatc.dir/src/bfbs_gen_nim.cpp.o
2025-03-21T20:24:06.8015887Z [ 81%] Building CXX object CMakeFiles/flatc.dir/src/code_generators.cpp.o
2025-03-21T20:24:06.8017156Z [ 84%] Building CXX object CMakeFiles/flatc.dir/grpc/src/compiler/cpp_generator.cc.o
2025-03-21T20:24:06.8018203Z [ 86%] Building CXX object CMakeFiles/flatc.dir/grpc/src/compiler/go_generator.cc.o
2025-03-21T20:24:06.8019558Z [ 89%] Building CXX object CMakeFiles/flatc.dir/grpc/src/compiler/java_generator.cc.o
2025-03-21T20:24:06.8020865Z [ 92%] Building CXX object CMakeFiles/flatc.dir/grpc/src/compiler/python_generator.cc.o
2025-03-21T20:24:06.8022271Z [ 94%] Building CXX object CMakeFiles/flatc.dir/grpc/src/compiler/swift_generator.cc.o
2025-03-21T20:24:06.8023635Z [ 97%] Building CXX object CMakeFiles/flatc.dir/grpc/src/compiler/ts_generator.cc.o
2025-03-21T20:24:06.8024641Z [100%] Linking CXX executable flatc
2025-03-21T20:24:06.8025247Z [100%] Built target flatc
2025-03-21T20:24:06.8026154Z [  6%] No install step for 'flatbuffers'
2025-03-21T20:24:06.8026920Z [  6%] Completed 'flatbuffers'
2025-03-21T20:24:06.8027498Z [  6%] Built target flatbuffers
2025-03-21T20:24:06.8028164Z [  6%] Generating common_schema headers
2025-03-21T20:24:06.8028996Z [ 12%] Generating qualcomm ir schema headers
2025-03-21T20:24:06.8029785Z [ 18%] Generating qnn_schema headers
2025-03-21T20:24:06.8030439Z [ 18%] Built target common_schema
2025-03-21T20:24:06.8030984Z [ 18%] Built target qcir
2025-03-21T20:24:06.8031468Z [ 18%] Built target qnn_schema
2025-03-21T20:24:06.8032182Z [ 18%] Generating program_schema headers
2025-03-21T20:24:06.8033704Z [ 18%] Building CXX object backends/qualcomm/CMakeFiles/qcir_utils.dir/aot/ir/qcir_utils.cpp.o
2025-03-21T20:24:06.8035365Z [ 18%] Building CXX object backends/qualcomm/CMakeFiles/qnn_executorch_logging.dir/runtime/Logging.cpp.o
2025-03-21T20:24:06.8036370Z [ 18%] Built target program_schema
2025-03-21T20:24:06.8037395Z [ 18%] Building CXX object CMakeFiles/executorch_core.dir/runtime/backend/interface.cpp.o
2025-03-21T20:24:06.8038737Z [ 25%] Building CXX object CMakeFiles/executorch_core.dir/runtime/core/evalue.cpp.o
2025-03-21T20:24:06.8040273Z [ 25%] Building CXX object CMakeFiles/executorch_core.dir/runtime/core/exec_aten/util/tensor_shape_to_c_string.cpp.o
2025-03-21T20:24:09.6857192Z [ 25%] Building CXX object CMakeFiles/executorch_core.dir/runtime/core/portable_type/tensor_impl.cpp.o
2025-03-21T20:24:09.6858262Z [ 25%] Building CXX object CMakeFiles/executorch_core.dir/runtime/core/exec_aten/util/tensor_util_portable.cpp.o
2025-03-21T20:24:09.6859158Z [ 25%] Building CXX object CMakeFiles/executorch_core.dir/runtime/core/tag.cpp.o
2025-03-21T20:24:09.6859962Z [ 25%] Building CXX object CMakeFiles/executorch_core.dir/runtime/core/tensor_layout.cpp.o
2025-03-21T20:24:09.6860822Z [ 31%] Building CXX object CMakeFiles/executorch_core.dir/runtime/executor/method.cpp.o
2025-03-21T20:24:09.6861538Z [ 31%] Linking CXX static library libqnn_executorch_logging.a
2025-03-21T20:24:09.6862083Z [ 31%] Linking CXX static library libqcir_utils.a
2025-03-21T20:24:09.6862488Z [ 31%] Built target qnn_executorch_logging
2025-03-21T20:24:09.6863137Z [ 31%] Building CXX object CMakeFiles/executorch_core.dir/runtime/executor/method_meta.cpp.o
2025-03-21T20:24:09.6864273Z [ 31%] Building CXX object backends/qualcomm/CMakeFiles/qnn_implementation.dir/runtime/backends/QnnImplementation.cpp.o
2025-03-21T20:24:09.6864961Z [ 31%] Built target qcir_utils
2025-03-21T20:24:09.6865544Z [ 31%] Building CXX object CMakeFiles/executorch_core.dir/runtime/executor/program.cpp.o
2025-03-21T20:24:09.6866557Z [ 31%] Building CXX object backends/qualcomm/CMakeFiles/qnn_sys_implementation.dir/runtime/backends/QnnSysImplementation.cpp.o
2025-03-21T20:24:09.6867767Z [ 37%] Building CXX object backends/qualcomm/CMakeFiles/qnn_custom_protocol.dir/runtime/backends/QnnCustomProtocol.cpp.o
2025-03-21T20:24:09.6868820Z [ 37%] Building CXX object backends/qualcomm/CMakeFiles/qnn_profiler.dir/runtime/backends/QnnProfiler.cpp.o
2025-03-21T20:24:09.6869741Z [ 37%] Building CXX object CMakeFiles/executorch_core.dir/runtime/executor/pte_data_map.cpp.o
2025-03-21T20:24:09.6870651Z [ 37%] Building CXX object CMakeFiles/executorch_core.dir/runtime/executor/tensor_parser_exec_aten.cpp.o
2025-03-21T20:24:09.6871403Z [ 37%] Linking CXX static library libqnn_implementation.a
2025-03-21T20:24:09.6871830Z [ 37%] Built target qnn_implementation
2025-03-21T20:24:09.6872430Z [ 43%] Building CXX object backends/qualcomm/CMakeFiles/utils.dir/runtime/Utils.cpp.o
2025-03-21T20:24:09.6873109Z [ 43%] Linking CXX static library libqnn_sys_implementation.a
2025-03-21T20:24:09.6873979Z [ 43%] Building CXX object CMakeFiles/executorch_core.dir/runtime/executor/tensor_parser_portable.cpp.o
2025-03-21T20:24:09.6874862Z [ 43%] Built target qnn_sys_implementation
2025-03-21T20:24:09.6875561Z [ 43%] Building CXX object backends/qualcomm/CMakeFiles/shared_buffer.dir/runtime/SharedBuffer.cpp.o
2025-03-21T20:24:09.6876307Z [ 43%] Linking CXX static library libqnn_custom_protocol.a
2025-03-21T20:24:09.6877052Z [ 50%] Building CXX object CMakeFiles/executorch_core.dir/runtime/kernel/operator_registry.cpp.o
2025-03-21T20:24:09.6877729Z [ 50%] Linking CXX static library libqnn_profiler.a
2025-03-21T20:24:09.6878127Z [ 50%] Built target qnn_custom_protocol
2025-03-21T20:24:09.6878729Z [ 50%] Building CXX object CMakeFiles/executorch_core.dir/runtime/platform/abort.cpp.o
2025-03-21T20:24:09.6879623Z [ 50%] Building CXX object backends/qualcomm/CMakeFiles/wrappers.dir/aot/wrappers/TensorWrapper.cpp.o
2025-03-21T20:24:09.6880227Z [ 50%] Built target qnn_profiler
2025-03-21T20:24:09.6880897Z [ 50%] Building CXX object backends/qualcomm/CMakeFiles/qnn_logger.dir/runtime/backends/QnnLogger.cpp.o
2025-03-21T20:24:09.6881915Z [ 50%] Building CXX object backends/qualcomm/CMakeFiles/qnn_backend_cache.dir/runtime/backends/QnnBackendCache.cpp.o
2025-03-21T20:24:09.6882831Z [ 50%] Building CXX object CMakeFiles/executorch_core.dir/runtime/platform/log.cpp.o
2025-03-21T20:24:09.6883451Z [ 50%] Linking CXX static library libutils.a
2025-03-21T20:24:09.6883811Z [ 50%] Built target utils
2025-03-21T20:24:09.6884384Z [ 50%] Building CXX object CMakeFiles/executorch_core.dir/runtime/platform/profiler.cpp.o
2025-03-21T20:24:09.6885035Z [ 50%] Linking CXX static library libqnn_logger.a
2025-03-21T20:24:09.6885820Z [ 50%] Building CXX object backends/qualcomm/CMakeFiles/wrappers.dir/aot/wrappers/QuantizeParamsWrapper.cpp.o
2025-03-21T20:24:09.6886463Z [ 50%] Built target qnn_logger
2025-03-21T20:24:09.6887103Z [ 50%] Building CXX object backends/qualcomm/CMakeFiles/wrappers.dir/aot/wrappers/OpWrapper.cpp.o
2025-03-21T20:24:09.6887816Z [ 50%] Linking CXX static library libshared_buffer.a
2025-03-21T20:24:09.6888705Z [ 56%] Building CXX object backends/qualcomm/CMakeFiles/qnn_backend_cache.dir/runtime/backends/htpbackend/HtpBackendCache.cpp.o
2025-03-21T20:24:09.6889908Z [ 56%] Building CXX object backends/qualcomm/CMakeFiles/qnn_backend.dir/runtime/backends/QnnBackendCommon.cpp.o
2025-03-21T20:24:09.6890822Z [ 56%] Building CXX object CMakeFiles/executorch_core.dir/runtime/platform/runtime.cpp.o
2025-03-21T20:24:09.6891360Z [ 56%] Built target shared_buffer
2025-03-21T20:24:09.6891944Z [ 56%] Building CXX object CMakeFiles/executorch_core.dir/schema/extended_header.cpp.o
2025-03-21T20:24:09.6892858Z [ 56%] Building CXX object backends/qualcomm/CMakeFiles/qnn_device.dir/runtime/backends/QnnDeviceCommon.cpp.o
2025-03-21T20:24:09.6893914Z [ 56%] Building CXX object backends/qualcomm/CMakeFiles/qnn_device.dir/runtime/backends/htpbackend/HtpDevice.cpp.o
2025-03-21T20:24:09.6894879Z [ 62%] Building CXX object CMakeFiles/executorch_core.dir/runtime/platform/default/posix.cpp.o
2025-03-21T20:24:09.6896012Z [ 62%] Building CXX object backends/qualcomm/CMakeFiles/qnn_device.dir/runtime/backends/htpbackend/x86_64/HtpDevicePlatformInfoConfig.cpp.o
2025-03-21T20:24:09.6897310Z [ 62%] Building CXX object backends/qualcomm/CMakeFiles/qnn_device.dir/runtime/backends/htpbackend/x86_64/HtpDeviceCustomConfig.cpp.o
2025-03-21T20:24:09.6898173Z [ 62%] Linking CXX static library libqnn_backend.a
2025-03-21T20:24:09.6898559Z [ 62%] Built target qnn_backend
2025-03-21T20:24:09.6898994Z [ 62%] Linking CXX static library libexecutorch_core.a
2025-03-21T20:24:09.6899536Z [ 62%] Linking CXX static library libqnn_backend_cache.a
2025-03-21T20:24:09.6900055Z [ 68%] Linking CXX static library libwrappers.a
2025-03-21T20:24:09.6900426Z [ 68%] Built target qnn_backend_cache
2025-03-21T20:24:09.6900867Z [ 68%] Built target wrappers
2025-03-21T20:24:09.6901163Z [ 68%] Built target executorch_core
2025-03-21T20:24:09.6901796Z [ 68%] Building CXX object extension/tensor/CMakeFiles/extension_tensor.dir/tensor_ptr.cpp.o
2025-03-21T20:24:09.6902609Z [ 68%] Building CXX object CMakeFiles/executorch.dir/kernels/prim_ops/et_view.cpp.o
2025-03-21T20:24:09.6903402Z [ 75%] Building CXX object CMakeFiles/executorch.dir/kernels/prim_ops/et_copy_index.cpp.o
2025-03-21T20:24:09.6904278Z [ 75%] Building CXX object extension/tensor/CMakeFiles/extension_tensor.dir/tensor_ptr_maker.cpp.o
2025-03-21T20:24:09.6905174Z [ 75%] Building CXX object CMakeFiles/executorch.dir/kernels/prim_ops/register_prim_ops.cpp.o
2025-03-21T20:24:09.6905847Z [ 81%] Linking CXX static library libqnn_device.a
2025-03-21T20:24:09.6906232Z [ 81%] Built target qnn_device
2025-03-21T20:24:09.6906946Z [ 81%] Building CXX object backends/qualcomm/CMakeFiles/qnn_context.dir/runtime/backends/QnnContextCommon.cpp.o
2025-03-21T20:24:09.6908009Z [ 81%] Building CXX object backends/qualcomm/CMakeFiles/qnn_context.dir/runtime/backends/htpbackend/HtpContext.cpp.o
2025-03-21T20:24:09.6909220Z [ 81%] Building CXX object backends/qualcomm/CMakeFiles/qnn_context.dir/runtime/backends/htpbackend/x86_64/HtpContextCustomConfig.cpp.o
2025-03-21T20:24:09.6910121Z [ 81%] Linking CXX static library libextension_tensor.a
2025-03-21T20:24:09.6910531Z [ 81%] Built target extension_tensor
2025-03-21T20:24:09.6910969Z [ 81%] Linking CXX static library libexecutorch.a
2025-03-21T20:24:09.6911356Z [ 81%] Built target executorch
2025-03-21T20:24:09.6911759Z [ 81%] Linking CXX static library libqnn_context.a
2025-03-21T20:24:09.6912143Z [ 81%] Built target qnn_context
2025-03-21T20:24:09.6912832Z [ 81%] Building CXX object backends/qualcomm/CMakeFiles/qnn_graph.dir/runtime/backends/QnnGraphCommon.cpp.o
2025-03-21T20:24:09.6913945Z [ 81%] Building CXX object backends/qualcomm/CMakeFiles/qnn_graph.dir/runtime/backends/htpbackend/HtpGraphCustomConfig.cpp.o
2025-03-21T20:24:09.6915184Z [ 81%] Building CXX object backends/qualcomm/CMakeFiles/qnn_graph.dir/runtime/backends/htpbackend/x86_64/HtpGraphCustomConfig.cpp.o
2025-03-21T20:24:09.6916336Z [ 81%] Building CXX object backends/qualcomm/CMakeFiles/qnn_mem_manager.dir/runtime/backends/QnnMemManager.cpp.o
2025-03-21T20:24:09.6917389Z [ 81%] Building CXX object backends/qualcomm/CMakeFiles/qnn_graph.dir/runtime/backends/htpbackend/HtpGraph.cpp.o
2025-03-21T20:24:09.6918134Z [ 87%] Linking CXX static library libqnn_graph.a
2025-03-21T20:24:09.6918514Z [ 87%] Built target qnn_graph
2025-03-21T20:24:09.6918946Z [ 87%] Linking CXX static library libqnn_mem_manager.a
2025-03-21T20:24:09.6919351Z [ 87%] Built target qnn_mem_manager
2025-03-21T20:24:09.6920081Z [ 93%] Building CXX object backends/qualcomm/CMakeFiles/qnn_factory.dir/runtime/backends/QnnBackendFactory.cpp.o
2025-03-21T20:24:09.6920864Z [ 93%] Linking CXX static library libqnn_factory.a
2025-03-21T20:24:09.6921251Z [ 93%] Built target qnn_factory
2025-03-21T20:24:09.6921881Z [ 93%] Building CXX object backends/qualcomm/CMakeFiles/qnn_manager.dir/runtime/QnnManager.cpp.o
2025-03-21T20:24:09.6922840Z [100%] Building CXX object backends/qualcomm/CMakeFiles/qnn_manager.dir/aot/wrappers/TensorWrapper.cpp.o
2025-03-21T20:24:09.6923572Z [100%] Linking CXX static library libqnn_manager.a
2025-03-21T20:24:09.6923963Z [100%] Built target qnn_manager
2025-03-21T20:24:09.6924735Z [100%] Building CXX object backends/qualcomm/CMakeFiles/PyQnnManagerAdaptor.dir/aot/python/PyQnnManagerAdaptor.cpp.o
2025-03-21T20:24:09.6925727Z [100%] Linking CXX shared module PyQnnManagerAdaptor.cpython-310-x86_64-linux-gnu.so
2025-03-21T20:24:09.6926373Z [100%] Built target PyQnnManagerAdaptor
2025-03-21T20:24:09.6926772Z [ 33%] Built target flatbuffers
2025-03-21T20:24:09.6927116Z [ 66%] Built target qnn_schema
2025-03-21T20:24:09.6927489Z [ 66%] Built target qnn_executorch_logging
2025-03-21T20:24:17.8253942Z [100%] Built target wrappers
2025-03-21T20:24:17.8255647Z [100%] Building CXX object backends/qualcomm/CMakeFiles/PyQnnWrapperAdaptor.dir/aot/python/PyQnnWrapperAdaptor.cpp.o
2025-03-21T20:24:17.8257698Z [100%] Building CXX object backends/qualcomm/CMakeFiles/PyQnnWrapperAdaptor.dir/aot/wrappers/TensorWrapper.cpp.o
2025-03-21T20:24:17.8259507Z [100%] Linking CXX shared module PyQnnWrapperAdaptor.cpython-310-x86_64-linux-gnu.so
2025-03-21T20:24:17.8260545Z [100%] Built target PyQnnWrapperAdaptor
2025-03-21T20:24:17.8261764Z + cp -f backends/qualcomm/PyQnnManagerAdaptor.cpython-310-x86_64-linux-gnu.so /pytorch/executorch/backends/qualcomm/python
2025-03-21T20:24:17.8263865Z + cp -f backends/qualcomm/PyQnnWrapperAdaptor.cpython-310-x86_64-linux-gnu.so /pytorch/executorch/backends/qualcomm/python
2025-03-21T20:24:17.8265115Z + popd
2025-03-21T20:24:17.8265453Z /pytorch/executorch
2025-03-21T20:24:17.8265945Z + cp schema/program.fbs exir/_serialize/program.fbs
2025-03-21T20:24:17.8266729Z + cp schema/scalar_type.fbs exir/_serialize/scalar_type.fbs
2025-03-21T20:24:17.8267464Z + PYTHON_EXECUTABLE=python
2025-03-21T20:24:17.8268080Z + bash .ci/scripts/setup-linux.sh --build-tool cmake
2025-03-21T20:24:17.8268760Z ++ dirname .ci/scripts/setup-linux.sh
2025-03-21T20:24:17.8269358Z + source .ci/scripts/utils.sh
2025-03-21T20:24:17.8269918Z + read -r BUILD_TOOL BUILD_MODE EDITABLE
2025-03-21T20:24:17.8270518Z ++ parse_args --build-tool cmake
2025-03-21T20:24:17.8271077Z ++ args=('--build-tool' 'cmake')
2025-03-21T20:24:17.8271529Z ++ local args
2025-03-21T20:24:17.8271875Z ++ local i
2025-03-21T20:24:17.8272209Z ++ local BUILD_TOOL=
2025-03-21T20:24:17.8272610Z ++ local BUILD_MODE=
2025-03-21T20:24:17.8272993Z ++ local EDITABLE=
2025-03-21T20:24:17.8273374Z ++ (( i=0 ))
2025-03-21T20:24:17.8273741Z ++ (( i<2 ))
2025-03-21T20:24:17.8274112Z ++ case "${args[$i]}" in
2025-03-21T20:24:17.8274539Z ++ BUILD_TOOL=cmake
2025-03-21T20:24:17.8274903Z ++ i=1
2025-03-21T20:24:17.8275248Z ++ (( i++ ))
2025-03-21T20:24:17.8275599Z ++ (( i<2 ))
2025-03-21T20:24:17.8275971Z ++ '[' -z cmake ']'
2025-03-21T20:24:17.8276398Z ++ [[ cmake =~ ^(cmake|buck2)$ ]]
2025-03-21T20:24:17.8276883Z ++ BUILD_MODE=Release
2025-03-21T20:24:17.8277297Z ++ [[ Release =~ ^(Debug|Release)$ ]]
2025-03-21T20:24:17.8277833Z ++ EDITABLE=false
2025-03-21T20:24:17.8278258Z ++ [[ false =~ ^(true|false)$ ]]
2025-03-21T20:24:17.8278763Z ++ echo 'cmake Release false'
2025-03-21T20:24:17.8279230Z + [[ false == \t\r\u\e ]]
2025-03-21T20:24:17.8279736Z + install_executorch --use-pt-pinned-commit
2025-03-21T20:24:17.8280256Z + which pip
2025-03-21T20:24:17.8280622Z /opt/conda/envs/py_3.10/bin/pip
2025-03-21T20:24:17.8281314Z + ./install_executorch.sh --pybind xnnpack --use-pt-pinned-commit
2025-03-21T20:24:17.8282311Z 2025-03-21 20:24:10,474 [ExecuTorch] INFO: All required submodules are present.
2025-03-21T20:24:17.8283467Z Looking in indexes: https://pypi.org/simple, https://download.pytorch.org/whl/nightly/cpu
2025-03-21T20:24:17.8284931Z Requirement already satisfied: torch in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (2.7.0a0+git295f2ed)
2025-03-21T20:24:17.8286654Z Requirement already satisfied: torchvision in /var/lib/ci-user/.local/lib/python3.10/site-packages (0.19.0a0+d23a6e1)
2025-03-21T20:24:17.8288387Z Requirement already satisfied: torchaudio in /var/lib/ci-user/.local/lib/python3.10/site-packages (2.6.0a0+c670ad8)
2025-03-21T20:24:17.8290474Z Requirement already satisfied: timm==1.0.7 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from -r requirements-examples.txt (line 3)) (1.0.7)
2025-03-21T20:24:17.8292680Z Requirement already satisfied: torchsr==1.0.4 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from -r requirements-examples.txt (line 4)) (1.0.4)
2025-03-21T20:24:17.8295397Z Requirement already satisfied: transformers==4.47.1 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from -r requirements-examples.txt (line 5)) (4.47.1)
2025-03-21T20:24:17.8297816Z Requirement already satisfied: cmake>=3.19 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from -r requirements-dev.txt (line 1)) (3.31.6)
2025-03-21T20:24:17.8299953Z Requirement already satisfied: pip>=23 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from -r requirements-dev.txt (line 2)) (25.0)
2025-03-21T20:24:17.8302071Z Requirement already satisfied: pyyaml in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from -r requirements-dev.txt (line 3)) (6.0.1)
2025-03-21T20:24:17.8304270Z Requirement already satisfied: setuptools>=63 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from -r requirements-dev.txt (line 4)) (75.8.0)
2025-03-21T20:24:17.8306437Z Requirement already satisfied: tomli in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from -r requirements-dev.txt (line 5)) (2.0.1)
2025-03-21T20:24:17.8308572Z Requirement already satisfied: wheel in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from -r requirements-dev.txt (line 6)) (0.45.1)
2025-03-21T20:24:17.8310668Z Requirement already satisfied: zstd in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from -r requirements-dev.txt (line 7)) (1.5.5.1)
2025-03-21T20:24:17.8312998Z Requirement already satisfied: huggingface_hub in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from timm==1.0.7->-r requirements-examples.txt (line 3)) (0.29.3)
2025-03-21T20:24:17.8315535Z Requirement already satisfied: safetensors in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from timm==1.0.7->-r requirements-examples.txt (line 3)) (0.5.3)
2025-03-21T20:24:17.8318033Z Requirement already satisfied: filelock in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from transformers==4.47.1->-r requirements-examples.txt (line 5)) (3.18.0)
2025-03-21T20:24:17.8320625Z Requirement already satisfied: numpy>=1.17 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from transformers==4.47.1->-r requirements-examples.txt (line 5)) (2.2.4)
2025-03-21T20:24:17.8323221Z Requirement already satisfied: packaging>=20.0 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from transformers==4.47.1->-r requirements-examples.txt (line 5)) (24.2)
2025-03-21T20:24:17.8325943Z Requirement already satisfied: regex!=2019.12.17 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from transformers==4.47.1->-r requirements-examples.txt (line 5)) (2024.11.6)
2025-03-21T20:24:17.8328551Z Requirement already satisfied: requests in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from transformers==4.47.1->-r requirements-examples.txt (line 5)) (2.32.3)
2025-03-21T20:24:17.8331331Z Requirement already satisfied: tokenizers<0.22,>=0.21 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from transformers==4.47.1->-r requirements-examples.txt (line 5)) (0.21.1)
2025-03-21T20:24:17.8344310Z Requirement already satisfied: tqdm>=4.27 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from transformers==4.47.1->-r requirements-examples.txt (line 5)) (4.67.1)
2025-03-21T20:24:17.8346645Z Requirement already satisfied: typing-extensions>=4.10.0 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from torch) (4.12.2)
2025-03-21T20:24:17.8348561Z Requirement already satisfied: sympy>=1.13.3 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from torch) (1.13.3)
2025-03-21T20:24:17.8350355Z Requirement already satisfied: networkx in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from torch) (3.4.2)
2025-03-21T20:24:17.8352087Z Requirement already satisfied: jinja2 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from torch) (3.1.6)
2025-03-21T20:24:17.8353828Z Requirement already satisfied: fsspec in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from torch) (2025.3.0)
2025-03-21T20:24:17.8355637Z Requirement already satisfied: pillow!=8.3.*,>=5.3.0 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from torchvision) (11.1.0)
2025-03-21T20:24:17.8357928Z Requirement already satisfied: mpmath<1.4,>=1.1.0 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from sympy>=1.13.3->torch) (1.3.0)
2025-03-21T20:24:17.8359863Z Requirement already satisfied: MarkupSafe>=2.0 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from jinja2->torch) (3.0.2)
2025-03-21T20:24:17.8362295Z Requirement already satisfied: charset-normalizer<4,>=2 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from requests->transformers==4.47.1->-r requirements-examples.txt (line 5)) (3.4.1)
2025-03-21T20:24:17.8365088Z Requirement already satisfied: idna<4,>=2.5 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from requests->transformers==4.47.1->-r requirements-examples.txt (line 5)) (3.10)
2025-03-21T20:24:17.8367826Z Requirement already satisfied: urllib3<3,>=1.21.1 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from requests->transformers==4.47.1->-r requirements-examples.txt (line 5)) (2.3.0)
2025-03-21T20:24:17.8370818Z Requirement already satisfied: certifi>=2017.4.17 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from requests->transformers==4.47.1->-r requirements-examples.txt (line 5)) (2025.1.31)
2025-03-21T20:24:17.8372541Z Processing ./third-party/ao
2025-03-21T20:24:17.8373342Z   Preparing metadata (setup.py) ... [?25l- done
2025-03-21T20:24:17.8374211Z [?25hBuilding wheels for collected packages: torchao
2025-03-21T20:24:17.8375176Z   Building wheel for torchao (setup.py) ... [?25l- \ | done
2025-03-21T20:24:17.8377191Z [?25h  Created wheel for torchao: filename=torchao-0.10.0+git64bcf4c-py3-none-any.whl size=758276 sha256=d7ccb37b03973548c776245eb080be20df2cdf70b771df3002cf9579693f5f70
2025-03-21T20:24:17.8379490Z   Stored in directory: /tmp/pip-ephem-wheel-cache-7artng77/wheels/0b/23/ff/2261dc1c4a27252503fe159d9fc88676b133e0e8d621abf36f
2025-03-21T20:24:17.8380777Z Successfully built torchao
2025-03-21T20:24:17.8381331Z Installing collected packages: torchao
2025-03-21T20:24:17.8381938Z   Attempting uninstall: torchao
2025-03-21T20:24:17.8382616Z     Found existing installation: torchao 0.10.0+git64bcf4c
2025-03-21T20:24:17.8383327Z     Uninstalling torchao-0.10.0+git64bcf4c:
2025-03-21T20:24:17.8384051Z       Successfully uninstalled torchao-0.10.0+git64bcf4c
2025-03-21T20:24:17.8384807Z Successfully installed torchao-0.10.0+git64bcf4c
2025-03-21T20:24:17.8385818Z Using pip 25.0 from /opt/conda/envs/py_3.10/lib/python3.10/site-packages/pip (python 3.10)
2025-03-21T20:24:17.8387124Z Looking in indexes: https://pypi.org/simple, https://download.pytorch.org/whl/nightly/cpu
2025-03-21T20:24:17.8388101Z Processing /pytorch/executorch
2025-03-21T20:24:17.8388735Z   Running command Preparing metadata (pyproject.toml)
2025-03-21T20:24:17.8389392Z   running dist_info
2025-03-21T20:24:17.8390051Z   creating /tmp/pip-modern-metadata-p8tca5va/executorch.egg-info
2025-03-21T20:24:31.0708671Z   writing /tmp/pip-modern-metadata-p8tca5va/executorch.egg-info/PKG-INFO
2025-03-21T20:24:31.0710099Z   writing dependency_links to /tmp/pip-modern-metadata-p8tca5va/executorch.egg-info/dependency_links.txt
2025-03-21T20:24:31.0711619Z   writing entry points to /tmp/pip-modern-metadata-p8tca5va/executorch.egg-info/entry_points.txt
2025-03-21T20:24:31.0712967Z   writing requirements to /tmp/pip-modern-metadata-p8tca5va/executorch.egg-info/requires.txt
2025-03-21T20:24:31.0714362Z   writing top-level names to /tmp/pip-modern-metadata-p8tca5va/executorch.egg-info/top_level.txt
2025-03-21T20:24:31.0715672Z   writing manifest file '/tmp/pip-modern-metadata-p8tca5va/executorch.egg-info/SOURCES.txt'
2025-03-21T20:24:31.0716968Z   reading manifest file '/tmp/pip-modern-metadata-p8tca5va/executorch.egg-info/SOURCES.txt'
2025-03-21T20:24:31.0717898Z   adding license file 'LICENSE'
2025-03-21T20:24:31.0718800Z   writing manifest file '/tmp/pip-modern-metadata-p8tca5va/executorch.egg-info/SOURCES.txt'
2025-03-21T20:24:31.0720130Z   creating '/tmp/pip-modern-metadata-p8tca5va/executorch-0.6.0a0+be92d7d.dist-info'
2025-03-21T20:24:31.0722094Z   Preparing metadata (pyproject.toml) ... [?25l[?25hdone
2025-03-21T20:24:31.0723544Z Requirement already satisfied: expecttest in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from executorch==0.6.0a0+be92d7d) (0.1.6)
2025-03-21T20:24:31.0724973Z Collecting flatbuffers (from executorch==0.6.0a0+be92d7d)
2025-03-21T20:24:31.0727149Z   Obtaining dependency information for flatbuffers from https://files.pythonhosted.org/packages/b8/25/155f9f080d5e4bc0082edfda032ea2bc2b8fab3f4d25d46c1e9dd22a1a89/flatbuffers-25.2.10-py2.py3-none-any.whl.metadata
2025-03-21T20:24:31.0729650Z   Downloading flatbuffers-25.2.10-py2.py3-none-any.whl.metadata (875 bytes)
2025-03-21T20:24:31.0731278Z Requirement already satisfied: hypothesis in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from executorch==0.6.0a0+be92d7d) (6.84.2)
2025-03-21T20:24:31.0733551Z Requirement already satisfied: mpmath==1.3.0 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from executorch==0.6.0a0+be92d7d) (1.3.0)
2025-03-21T20:24:31.0735687Z Requirement already satisfied: numpy>=2.0.0 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from executorch==0.6.0a0+be92d7d) (2.2.4)
2025-03-21T20:24:31.0737761Z Requirement already satisfied: packaging in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from executorch==0.6.0a0+be92d7d) (24.2)
2025-03-21T20:24:31.0739827Z Requirement already satisfied: pandas>=2.2.2 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from executorch==0.6.0a0+be92d7d) (2.2.3)
2025-03-21T20:24:31.0741856Z Requirement already satisfied: parameterized in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from executorch==0.6.0a0+be92d7d) (0.9.0)
2025-03-21T20:24:31.0743703Z Requirement already satisfied: pytest in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from executorch==0.6.0a0+be92d7d) (7.2.0)
2025-03-21T20:24:31.0745094Z Collecting pytest-xdist (from executorch==0.6.0a0+be92d7d)
2025-03-21T20:24:31.0747213Z   Obtaining dependency information for pytest-xdist from https://files.pythonhosted.org/packages/6d/82/1d96bf03ee4c0fdc3c0cbe61470070e659ca78dc0086fb88b66c185e2449/pytest_xdist-3.6.1-py3-none-any.whl.metadata
2025-03-21T20:24:31.0749711Z   Downloading pytest_xdist-3.6.1-py3-none-any.whl.metadata (4.3 kB)
2025-03-21T20:24:31.0750748Z Collecting pytest-rerunfailures (from executorch==0.6.0a0+be92d7d)
2025-03-21T20:24:31.0753397Z   Obtaining dependency information for pytest-rerunfailures from https://files.pythonhosted.org/packages/89/37/54e5ffc7c0cebee7cf30a3ac5915faa7e7abf8bdfdf3228c277f7c192489/pytest_rerunfailures-15.0-py3-none-any.whl.metadata
2025-03-21T20:24:31.0755867Z   Downloading pytest_rerunfailures-15.0-py3-none-any.whl.metadata (19 kB)
2025-03-21T20:24:31.0757365Z Requirement already satisfied: pyyaml in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from executorch==0.6.0a0+be92d7d) (6.0.1)
2025-03-21T20:24:31.0759353Z Requirement already satisfied: ruamel.yaml in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from executorch==0.6.0a0+be92d7d) (0.17.32)
2025-03-21T20:24:31.0761382Z Requirement already satisfied: sympy in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from executorch==0.6.0a0+be92d7d) (1.13.3)
2025-03-21T20:24:31.0762657Z Collecting tabulate (from executorch==0.6.0a0+be92d7d)
2025-03-21T20:24:31.0764632Z   Obtaining dependency information for tabulate from https://files.pythonhosted.org/packages/40/44/4a5f08c96eb108af5cb50b41f76142f0afa346dfa99d5296fe7202a11854/tabulate-0.9.0-py3-none-any.whl.metadata
2025-03-21T20:24:31.0766882Z   Downloading tabulate-0.9.0-py3-none-any.whl.metadata (34 kB)
2025-03-21T20:24:31.0768524Z Requirement already satisfied: typing-extensions in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from executorch==0.6.0a0+be92d7d) (4.12.2)
2025-03-21T20:24:31.0770932Z Requirement already satisfied: python-dateutil>=2.8.2 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from pandas>=2.2.2->executorch==0.6.0a0+be92d7d) (2.9.0.post0)
2025-03-21T20:24:31.0773520Z Requirement already satisfied: pytz>=2020.1 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from pandas>=2.2.2->executorch==0.6.0a0+be92d7d) (2025.1)
2025-03-21T20:24:31.0775955Z Requirement already satisfied: tzdata>=2022.7 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from pandas>=2.2.2->executorch==0.6.0a0+be92d7d) (2025.1)
2025-03-21T20:24:31.0778227Z Requirement already satisfied: attrs>=19.2.0 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from hypothesis->executorch==0.6.0a0+be92d7d) (25.3.0)
2025-03-21T20:24:31.0780681Z Requirement already satisfied: sortedcontainers<3.0.0,>=2.1.0 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from hypothesis->executorch==0.6.0a0+be92d7d) (2.4.0)
2025-03-21T20:24:31.0783217Z Requirement already satisfied: exceptiongroup>=1.0.0 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from hypothesis->executorch==0.6.0a0+be92d7d) (1.2.2)
2025-03-21T20:24:31.0785598Z Requirement already satisfied: iniconfig in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from pytest->executorch==0.6.0a0+be92d7d) (2.1.0)
2025-03-21T20:24:31.0787771Z Requirement already satisfied: pluggy<2.0,>=0.12 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from pytest->executorch==0.6.0a0+be92d7d) (1.5.0)
2025-03-21T20:24:31.0789857Z Requirement already satisfied: tomli>=1.0.0 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from pytest->executorch==0.6.0a0+be92d7d) (2.0.1)
2025-03-21T20:24:31.0791259Z Collecting pytest (from executorch==0.6.0a0+be92d7d)
2025-03-21T20:24:31.0793236Z   Obtaining dependency information for pytest from https://files.pythonhosted.org/packages/30/3d/64ad57c803f1fa1e963a7946b6e0fea4a70df53c1a7fed304586539c2bac/pytest-8.3.5-py3-none-any.whl.metadata
2025-03-21T20:24:31.0795454Z   Downloading pytest-8.3.5-py3-none-any.whl.metadata (7.6 kB)
2025-03-21T20:24:31.0796401Z Collecting execnet>=2.1 (from pytest-xdist->executorch==0.6.0a0+be92d7d)
2025-03-21T20:24:31.0798665Z   Obtaining dependency information for execnet>=2.1 from https://files.pythonhosted.org/packages/43/09/2aea36ff60d16dd8879bdb2f5b3ee0ba8d08cbbdcdfe870e695ce3784385/execnet-2.1.1-py3-none-any.whl.metadata
2025-03-21T20:24:31.0800822Z   Downloading execnet-2.1.1-py3-none-any.whl.metadata (2.9 kB)
2025-03-21T20:24:31.0802415Z Requirement already satisfied: ruamel.yaml.clib>=0.2.7 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from ruamel.yaml->executorch==0.6.0a0+be92d7d) (0.2.12)
2025-03-21T20:24:31.0804711Z Requirement already satisfied: six>=1.5 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from python-dateutil>=2.8.2->pandas>=2.2.2->executorch==0.6.0a0+be92d7d) (1.17.0)
2025-03-21T20:24:31.0806398Z Downloading flatbuffers-25.2.10-py2.py3-none-any.whl (30 kB)
2025-03-21T20:24:31.0807336Z Downloading pytest_rerunfailures-15.0-py3-none-any.whl (13 kB)
2025-03-21T20:24:31.0808146Z Downloading pytest-8.3.5-py3-none-any.whl (343 kB)
2025-03-21T20:24:31.0808919Z Downloading pytest_xdist-3.6.1-py3-none-any.whl (46 kB)
2025-03-21T20:24:31.0809780Z Downloading tabulate-0.9.0-py3-none-any.whl (35 kB)
2025-03-21T20:24:31.0810477Z Downloading execnet-2.1.1-py3-none-any.whl (40 kB)
2025-03-21T20:24:31.0811186Z Building wheels for collected packages: executorch
2025-03-21T20:24:31.0811996Z   Running command Building wheel for executorch (pyproject.toml)
2025-03-21T20:24:31.0812745Z   running bdist_wheel
2025-03-21T20:24:31.0813212Z   running build
2025-03-21T20:24:31.0813671Z   command options for 'CustomBuild':
2025-03-21T20:24:31.0814188Z     build_base = pip-out
2025-03-21T20:24:31.0814645Z     build_purelib = pip-out/lib
2025-03-21T20:24:31.0815219Z     build_platlib = pip-out/lib.linux-x86_64-cpython-310
2025-03-21T20:24:31.0815952Z     build_lib = pip-out/lib.linux-x86_64-cpython-310
2025-03-21T20:24:31.0816504Z     build_scripts = pip-out/scripts-3.10
2025-03-21T20:24:31.0816884Z     build_temp = pip-out/temp.linux-x86_64-cpython-310
2025-03-21T20:24:31.0817260Z     plat_name = linux-x86_64
2025-03-21T20:24:31.0817587Z     compiler = None
2025-03-21T20:24:31.0818194Z     parallel = 7
2025-03-21T20:24:31.0818845Z     debug = None
2025-03-21T20:24:31.0819234Z     force = None
2025-03-21T20:24:31.0819704Z     executable = /opt/conda/envs/py_3.10/bin/python
2025-03-21T20:24:31.0820570Z   creating /pytorch/executorch/pip-out/temp.linux-x86_64-cpython-310/cmake-out
2025-03-21T20:24:31.0821852Z   deleting /pytorch/executorch/pip-out/temp.linux-x86_64-cpython-310/cmake-out/CMakeCache.txt
2025-03-21T20:24:31.0823863Z   cmake --build /pytorch/executorch/pip-out/temp.linux-x86_64-cpython-310/cmake-out -j7 --target portable_lib --target custom_ops_aot_lib --target quantized_ops_aot_lib --config Release
2025-03-21T20:24:31.0824936Z   [  0%] Creating directories for 'flatbuffers'
2025-03-21T20:24:31.0825514Z   [  0%] Building C object third-party/flatcc/src/runtime/CMakeFiles/flatccrt.dir/builder.c.o
2025-03-21T20:24:31.0826329Z   [  0%] Building C object backends/xnnpack/third-party/pthreadpool/CMakeFiles/pthreadpool.dir/src/legacy-api.c.o
2025-03-21T20:24:31.0827136Z   [  0%] Building C object third-party/flatcc/src/runtime/CMakeFiles/flatccrt.dir/emitter.c.o
2025-03-21T20:24:31.0827868Z   [  0%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/api.c.o
2025-03-21T20:24:32.1168183Z   [  0%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/__/__/external/hash/str_set.c.o
2025-03-21T20:24:32.1169980Z   [  0%] Building CXX object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/single.cpp.o
2025-03-21T20:24:32.1171183Z   [  0%] No download step for 'flatbuffers'
2025-03-21T20:24:32.1171833Z   [  0%] No update step for 'flatbuffers'
2025-03-21T20:24:32.1172463Z   [  0%] No patch step for 'flatbuffers'
2025-03-21T20:24:32.1173126Z   [  0%] Performing configure step for 'flatbuffers'
2025-03-21T20:24:32.1173769Z   CMake Warning:
2025-03-21T20:24:32.1174349Z     Ignoring empty string ("") provided on the command line.
2025-03-21T20:24:32.1174900Z 
2025-03-21T20:24:32.1174909Z 
2025-03-21T20:24:32.1175170Z   fatal: No names found, cannot describe anything.
2025-03-21T20:24:32.1175956Z   CMake Warning at CMake/Version.cmake:32 (message):
2025-03-21T20:24:32.1176778Z     git describe failed with exit code: 128
2025-03-21T20:24:32.1177206Z 
2025-03-21T20:24:32.1177536Z     Make sure you cloned with tags or run 'git fetch --tags'.
2025-03-21T20:24:32.1178266Z   Call Stack (most recent call first):
2025-03-21T20:24:32.1178851Z     CMakeLists.txt:5 (include)
2025-03-21T20:24:32.1179215Z 
2025-03-21T20:24:32.1179223Z 
2025-03-21T20:24:32.1179437Z   -- Proceeding with version: 24.3.25.0
2025-03-21T20:24:32.1180534Z   [  0%] Building CXX object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/double.cpp.o
2025-03-21T20:24:32.1182127Z   [  0%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/__/__/external/hash/ptr_set.c.o
2025-03-21T20:24:32.1183636Z   [  0%] Building C object third-party/flatcc/src/runtime/CMakeFiles/flatccrt.dir/refmap.c.o
2025-03-21T20:24:32.1185041Z   [  0%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/cache.c.o
2025-03-21T20:24:32.1186657Z   [  0%] Building C object backends/xnnpack/third-party/pthreadpool/CMakeFiles/pthreadpool.dir/src/portable-api.c.o
2025-03-21T20:24:32.1188239Z   [  0%] Building C object third-party/flatcc/src/runtime/CMakeFiles/flatccrt.dir/verifier.c.o
2025-03-21T20:24:32.1189744Z   [  0%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/hash_tables/symbol_table.c.o
2025-03-21T20:24:32.1191275Z   [  0%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/init.c.o
2025-03-21T20:24:32.1192824Z   [  0%] Building C object backends/xnnpack/third-party/pthreadpool/CMakeFiles/pthreadpool.dir/src/memory.c.o
2025-03-21T20:24:32.1194035Z   -- The CXX compiler identification is Clang 12.0.1
2025-03-21T20:24:32.1194702Z   -- Detecting CXX compiler ABI info
2025-03-21T20:24:32.1195697Z   [  0%] Building C object third-party/flatcc/src/runtime/CMakeFiles/flatccrt.dir/json_parser.c.o
2025-03-21T20:24:32.1197535Z   [  0%] Building C object third-party/flatcc/src/runtime/CMakeFiles/flatccrt.dir/json_printer.c.o
2025-03-21T20:24:32.1199076Z   [  1%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/hash_tables/scope_table.c.o
2025-03-21T20:24:32.1200599Z   [  1%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/log.c.o
2025-03-21T20:24:32.1202159Z   [  1%] Building C object backends/xnnpack/third-party/pthreadpool/CMakeFiles/pthreadpool.dir/src/pthreads.c.o
2025-03-21T20:24:32.1203880Z   [  1%] Building CXX object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/complex_single.cpp.o
2025-03-21T20:24:32.1205602Z   [  1%] Building CXX object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/complex_double.cpp.o
2025-03-21T20:24:32.1207111Z   [  1%] Linking C static library /pytorch/executorch/third-party/flatcc/lib/libflatccrt.a
2025-03-21T20:24:32.1208542Z   [  1%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/hash_tables/name_table.c.o
2025-03-21T20:24:32.1209753Z   [  1%] Built target flatccrt
2025-03-21T20:24:32.1210737Z   [  1%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/init.c.o
2025-03-21T20:24:32.1212227Z   [  1%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/info.c.o
2025-03-21T20:24:32.1213785Z   [  1%] Building C object backends/xnnpack/third-party/pthreadpool/CMakeFiles/pthreadpool.dir/src/fastpath.c.o
2025-03-21T20:24:32.1214979Z   -- Detecting CXX compiler ABI info - done
2025-03-21T20:24:32.1216133Z   [  1%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/hash_tables/schema_table.c.o
2025-03-21T20:24:32.1217417Z   -- Check for working CXX compiler: /opt/cache/bin/c++ - skipped
2025-03-21T20:24:32.1218198Z   -- Detecting CXX compile features
2025-03-21T20:24:32.1218825Z   -- Detecting CXX compile features - done
2025-03-21T20:24:32.1219944Z   [  2%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/vendor.c.o
2025-03-21T20:24:32.1221540Z   [  2%] Building CXX object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/xerbla.cpp.o
2025-03-21T20:24:32.1222687Z   [  2%] Linking C static library libpthreadpool.a
2025-03-21T20:24:32.1223342Z   -- Looking for strtof_l
2025-03-21T20:24:32.1223864Z   [  2%] Built target pthreadpool
2025-03-21T20:24:32.1224935Z   [  3%] Building C object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/f2c/srotm.c.o
2025-03-21T20:24:32.1226505Z   [  3%] Building C object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/f2c/srotmg.c.o
2025-03-21T20:24:32.1228071Z   [  3%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/uarch.c.o
2025-03-21T20:24:32.1229629Z   [  3%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/hash_tables/value_set.c.o
2025-03-21T20:24:32.1231082Z   [  3%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/fileio.c.o
2025-03-21T20:24:32.1232603Z   [  3%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/parser.c.o
2025-03-21T20:24:32.1234025Z   [  3%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/name.c.o
2025-03-21T20:24:32.1235359Z   [  3%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/semantics.c.o
2025-03-21T20:24:32.1236802Z   [  3%] Building C object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/f2c/drotm.c.o
2025-03-21T20:24:32.1238249Z   [  3%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/coerce.c.o
2025-03-21T20:24:32.1239715Z   [  3%] Building C object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/f2c/drotmg.c.o
2025-03-21T20:24:32.1241311Z   [  3%] Building C object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/f2c/lsame.c.o
2025-03-21T20:24:32.1243082Z   [  3%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/topology.c.o
2025-03-21T20:24:32.1244861Z   [  3%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/logging.dir/src/enums/allocation-type.c.o
2025-03-21T20:24:32.1246051Z   -- Looking for strtof_l - found
2025-03-21T20:24:32.1246614Z   -- Looking for strtoull_l
2025-03-21T20:24:32.1247502Z   [  3%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/flatcc.c.o
2025-03-21T20:24:32.1249006Z   [  3%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/indirection.dir/src/indirection.c.o
2025-03-21T20:24:32.1250684Z   [  3%] Building C object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/f2c/dspmv.c.o
2025-03-21T20:24:32.1252651Z   [  3%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-avgpool/f16-avgpool-9p8x-minmax-f16c-c8.c.o
2025-03-21T20:24:32.1254732Z   [  3%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/logging.dir/src/enums/datatype-strings.c.o
2025-03-21T20:24:32.1256341Z   [  3%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/isa.c.o
2025-03-21T20:24:32.1257774Z   [  3%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/codegen_c.c.o
2025-03-21T20:24:32.1259243Z   [  3%] Building C object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/f2c/ssbmv.c.o
2025-03-21T20:24:32.1260309Z   [  3%] Built target indirection
2025-03-21T20:24:32.1261379Z   [  3%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/cache/init.c.o
2025-03-21T20:24:32.1263087Z   [  3%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/logging.dir/src/enums/microkernel-type.c.o
2025-03-21T20:24:32.1265047Z   [  3%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microparams-init.dir/src/microparams-init.c.o
2025-03-21T20:24:32.1266733Z   [  3%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/codegen_c_reader.c.o
2025-03-21T20:24:32.1268291Z   [  3%] Building C object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/f2c/chbmv.c.o
2025-03-21T20:24:32.1270262Z   [  3%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-avgpool/f16-avgpool-9x-minmax-f16c-c8.c.o
2025-03-21T20:24:32.1272286Z   [  3%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/cache/descriptor.c.o
2025-03-21T20:24:32.1273469Z   -- Looking for strtoull_l - found
2025-03-21T20:24:32.1274021Z   -- Looking for realpath
2025-03-21T20:24:32.1275044Z   [  3%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/logging.dir/src/enums/node-type.c.o
2025-03-21T20:24:32.1276659Z   [  3%] Building C object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/f2c/sspmv.c.o
2025-03-21T20:24:32.1277770Z   [  3%] Built target microparams-init
2025-03-21T20:24:32.1279159Z   [  3%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/cache/deterministic.c.o
2025-03-21T20:24:32.1280802Z   [  3%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/codegen_c_sort.c.o
2025-03-21T20:24:32.1282376Z   [  3%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/logging.dir/src/enums/operator-type.c.o
2025-03-21T20:24:32.1284013Z   [  3%] Building C object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/f2c/zhbmv.c.o
2025-03-21T20:24:32.1285569Z   [  3%] Building C object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/f2c/chpmv.c.o
2025-03-21T20:24:32.1287135Z   [  3%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/linux/init.c.o
2025-03-21T20:24:32.1289282Z   [  3%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-dwconv/gen/f16-dwconv-25p8c-minmax-fma3-acc2.c.o
2025-03-21T20:24:33.1237226Z   [  3%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/codegen_c_builder.c.o
2025-03-21T20:24:33.1238826Z   [  3%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/logging.dir/src/log.c.o
2025-03-21T20:24:33.1240231Z   [  3%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/codegen_c_verifier.c.o
2025-03-21T20:24:33.1241791Z   [  3%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/linux/cpuinfo.c.o
2025-03-21T20:24:33.1242829Z   -- Looking for realpath - found
2025-03-21T20:24:33.1243386Z   -- CMAKE_CXX_FLAGS: "-DFLATBUFFERS_MAX_ALIGNMENT=1024"
2025-03-21T20:24:33.1243956Z   -- Configuring done (1.1s)
2025-03-21T20:24:33.1244384Z   -- Generating done (0.0s)
2025-03-21T20:24:33.1245415Z   -- Build files have been written to: /pytorch/executorch/pip-out/temp.linux-x86_64-cpython-310/cmake-out/third-party/flatbuffers
2025-03-21T20:24:33.1247045Z   [  3%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/linux/smallfile.c.o
2025-03-21T20:24:33.1248176Z   [  3%] Performing build step for 'flatbuffers'
2025-03-21T20:24:33.1248776Z   [  3%] Built target logging
2025-03-21T20:24:33.1249825Z   [  3%] Building C object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/f2c/dsbmv.c.o
2025-03-21T20:24:33.1251243Z   [  3%] Building C object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/f2c/zhpmv.c.o
2025-03-21T20:24:33.1252407Z   [  2%] Building CXX object CMakeFiles/flatc.dir/src/idl_parser.cpp.o
2025-03-21T20:24:33.1253294Z   [  4%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-dwconv/gen/f16-dwconv-3p16c-minmax-fma3.c.o
2025-03-21T20:24:33.1254580Z   [  4%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-dwconv/gen/f16-dwconv-4p16c-minmax-fma3.c.o
2025-03-21T20:24:33.1256539Z   [  4%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/codegen_c_sorter.c.o
2025-03-21T20:24:33.1257918Z   [  5%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_text.cpp.o
2025-03-21T20:24:33.1259224Z   [  4%] Building C object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/f2c/dtbmv.c.o
2025-03-21T20:24:33.1261001Z   [  4%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/linux/multiline.c.o
2025-03-21T20:24:33.1262777Z   [  4%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/codegen_c_json_parser.c.o
2025-03-21T20:24:33.1264648Z   [  4%] Building C object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/f2c/stbmv.c.o
2025-03-21T20:24:33.1266250Z   [  4%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/linux/cpulist.c.o
2025-03-21T20:24:33.1267715Z   [  4%] Building C object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/f2c/ctbmv.c.o
2025-03-21T20:24:33.1268684Z   [  6%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/codegen_c_json_printer.c.o
2025-03-21T20:24:33.1269696Z   [  6%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/linux/processors.c.o
2025-03-21T20:24:33.1270516Z   [  7%] Building CXX object CMakeFiles/flatc.dir/src/reflection.cpp.o
2025-03-21T20:24:33.1271738Z   [  6%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-dwconv/gen/f16-dwconv-9p16c-minmax-fma3.c.o
2025-03-21T20:24:33.1272768Z   [  7%] Building C object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/f2c/ztbmv.c.o
2025-03-21T20:24:33.1273420Z   [ 10%] Building CXX object CMakeFiles/flatc.dir/src/util.cpp.o
2025-03-21T20:24:33.1274097Z   [  7%] Building C object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/f2c/complexdots.c.o
2025-03-21T20:24:33.1274935Z   [  7%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/__/runtime/builder.c.o
2025-03-21T20:24:33.1275516Z   [  7%] Linking C static library libcpuinfo.a
2025-03-21T20:24:33.1276193Z   [ 13%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_binary.cpp.o
2025-03-21T20:24:33.1276658Z   [  7%] Linking CXX static library libeigen_blas.a
2025-03-21T20:24:33.1277012Z   [  7%] Built target cpuinfo
2025-03-21T20:24:33.1277599Z   [  7%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/normalization.dir/src/normalization.c.o
2025-03-21T20:24:33.1278452Z   [  7%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/__/runtime/emitter.c.o
2025-03-21T20:24:33.1279446Z   [  7%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-f32-vcvt/gen/f16-f32-vcvt-avx-int16-u16.c.o
2025-03-21T20:24:33.1280650Z   [  7%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-f32-vcvt/gen/f16-f32-vcvt-avx512skx-u16.c.o
2025-03-21T20:24:33.1281419Z   [  7%] Built target eigen_blas
2025-03-21T20:24:33.1282019Z   [  7%] Building CXX object backends/xnnpack/third-party/XNNPACK/CMakeFiles/packing.dir/src/reference/packing.cc.o
2025-03-21T20:24:33.1282648Z   [  7%] Built target normalization
2025-03-21T20:24:33.1283209Z   [  7%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/allocator.dir/src/allocator.c.o
2025-03-21T20:24:33.1283986Z   [  7%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/cache.dir/src/cache.c.o
2025-03-21T20:24:33.1284737Z   [  7%] Building C object third-party/flatcc/src/compiler/CMakeFiles/flatcc.dir/__/runtime/refmap.c.o
2025-03-21T20:24:33.1285531Z   [  7%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/datatype.dir/src/datatype.c.o
2025-03-21T20:24:33.1286190Z   [ 15%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_cpp.cpp.o
2025-03-21T20:24:33.1286611Z   [  7%] Built target allocator
2025-03-21T20:24:33.1287123Z   [  7%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/memory.dir/src/memory.c.o
2025-03-21T20:24:33.1287649Z   [  7%] Built target cache
2025-03-21T20:24:33.1288046Z   [ 18%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_csharp.cpp.o
2025-03-21T20:24:33.1288640Z   [  7%] Linking C static library /pytorch/executorch/third-party/flatcc/lib/libflatcc.a
2025-03-21T20:24:33.1289218Z   [  7%] Built target packing
2025-03-21T20:24:33.1289614Z   [ 21%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_dart.cpp.o
2025-03-21T20:24:33.1290461Z   [  7%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-f32-vcvt/gen/f16-f32-vcvt-f16c-u16.c.o
2025-03-21T20:24:33.1291190Z   [  7%] Built target flatcc
2025-03-21T20:24:33.1291483Z   [  7%] Built target datatype
2025-03-21T20:24:33.1292109Z   [  7%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernel-utils.dir/src/microkernel-utils.c.o
2025-03-21T20:24:33.1292972Z   [  7%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/mutex.dir/src/mutex.c.o
2025-03-21T20:24:33.1293507Z   [  7%] Built target memory
2025-03-21T20:24:33.1294201Z   [  7%] Building CXX object backends/xnnpack/third-party/XNNPACK/CMakeFiles/reference-ukernels.dir/src/reference/unary-elementwise.cc.o
2025-03-21T20:24:33.1294930Z   [  7%] Built target microkernel-utils
2025-03-21T20:24:33.1295655Z   [  7%] Building CXX object backends/xnnpack/third-party/XNNPACK/CMakeFiles/reference-ukernels.dir/src/reference/binary-elementwise.cc.o
2025-03-21T20:24:33.1296384Z   [  7%] Built target mutex
2025-03-21T20:24:33.1297098Z   [  7%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-f32-vcvt/gen/f16-f32-vcvt-scalar-u1.c.o
2025-03-21T20:24:33.1298149Z   [  7%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/operator-utils.dir/src/operator-utils.c.o
2025-03-21T20:24:33.1299195Z   [  7%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-f32-vcvt/gen/f16-f32-vcvt-scalar-u4.c.o
2025-03-21T20:24:33.1300218Z   [  7%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/operator-run.dir/src/operator-run.c.o
2025-03-21T20:24:33.1301385Z   [  7%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-f32-vcvt/gen/f16-f32-vcvt-sse2-int16-u32.c.o
2025-03-21T20:24:33.1302169Z   [  7%] Built target operator-utils
2025-03-21T20:24:33.1302935Z   [  7%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-f32-vcvt/gen/f16-f32-vcvt-sse41-int16-u16.c.o
2025-03-21T20:24:33.1303817Z   [ 23%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_kotlin.cpp.o
2025-03-21T20:24:33.1304444Z   [  7%] Building C object third-party/flatcc/src/cli/CMakeFiles/flatcc_cli.dir/flatcc_cli.c.o
2025-03-21T20:24:33.1304976Z   [  7%] Built target reference-ukernels
2025-03-21T20:24:33.1305413Z   [ 26%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_kotlin_kmp.cpp.o
2025-03-21T20:24:33.1306401Z   [  7%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-f32acc-gemm/gen/f16-f32acc-gemm-1x16-minmax-avx2-broadcast.c.o
2025-03-21T20:24:33.1307281Z   [  7%] Built target operator-run
2025-03-21T20:24:33.1307940Z   [  7%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/hardware-config.dir/src/configs/hardware-config.c.o
2025-03-21T20:24:33.1308884Z   [  7%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/operators.dir/src/operator-delete.c.o
2025-03-21T20:24:33.1309618Z   [  7%] Linking C executable /pytorch/executorch/third-party/flatcc/bin/flatcc
2025-03-21T20:24:33.1310594Z   [  7%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-f32acc-gemm/gen/f16-f32acc-gemm-4x16-minmax-avx2-broadcast.c.o
2025-03-21T20:24:33.1311454Z   [  7%] Built target flatcc_cli
2025-03-21T20:24:33.1312300Z   [  7%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-f32acc-igemm/gen/f16-f32acc-igemm-1x16-minmax-avx2-broadcast.c.o
2025-03-21T20:24:33.1313520Z   [  7%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/operators.dir/src/operators/argmax-pooling-nhwc.c.o
2025-03-21T20:24:33.1314208Z   [  7%] Built target hardware-config
2025-03-21T20:24:33.1314538Z   [  7%] Generating etdump headers
2025-03-21T20:24:33.1315807Z   [  7%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-f32acc-igemm/gen/f16-f32acc-igemm-4x16-minmax-avx2-broadcast.c.o
2025-03-21T20:24:34.5338148Z   [  7%] Built target etdump_schema
2025-03-21T20:24:34.5339096Z   [  7%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-f32acc-rdsum/gen/f16-f32acc-rdsum-7p7x-avx512skx-c64.c.o
2025-03-21T20:24:34.5340021Z   [ 28%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_go.cpp.o
2025-03-21T20:24:34.5340814Z   [  7%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/operators.dir/src/operators/average-pooling-nhwc.c.o
2025-03-21T20:24:34.5341904Z   [  8%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/operators.dir/src/operators/batch-matrix-multiply-nc.c.o
2025-03-21T20:24:34.5342978Z   [  8%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/operators.dir/src/operators/binary-elementwise-nd.c.o
2025-03-21T20:24:34.5344004Z   [  8%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/operators.dir/src/operators/channel-shuffle-nc.c.o
2025-03-21T20:24:34.5345148Z   [  8%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-f32acc-rdsum/gen/f16-f32acc-rdsum-7p7x-f16c-c32.c.o
2025-03-21T20:24:34.5346279Z   [  8%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/operators.dir/src/operators/constant-pad-nd.c.o
2025-03-21T20:24:34.5347428Z   [  9%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-f32acc-rsum/gen/f16-f32acc-rsum-avx512skx-u64-acc4.c.o
2025-03-21T20:24:34.5349027Z   [  9%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/operators.dir/src/operators/convolution-nchw.c.o
2025-03-21T20:24:34.5350257Z   [  9%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-f32acc-rsum/gen/f16-f32acc-rsum-f16c-u32-acc4.c.o
2025-03-21T20:24:34.5351478Z   [  9%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-ibilinear/gen/f16-ibilinear-fma3-c8.c.o
2025-03-21T20:24:34.5352339Z   [ 31%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_java.cpp.o
2025-03-21T20:24:34.5352860Z   [ 34%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_ts.cpp.o
2025-03-21T20:24:34.5353610Z   [  9%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/operators.dir/src/operators/convolution-nhwc.c.o
2025-03-21T20:24:34.5354717Z   [  9%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-maxpool/f16-maxpool-9p8x-minmax-f16c-c8.c.o
2025-03-21T20:24:34.5355823Z   [  9%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/operators.dir/src/operators/deconvolution-nhwc.c.o
2025-03-21T20:24:34.5356879Z   [  9%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/operators.dir/src/operators/dynamic-fully-connected-nc.c.o
2025-03-21T20:24:34.5357955Z   [  9%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/operators.dir/src/operators/fully-connected-nc.c.o
2025-03-21T20:24:34.5358956Z   [  9%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/operators.dir/src/operators/max-pooling-nhwc.c.o
2025-03-21T20:24:34.5359712Z   [ 36%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_php.cpp.o
2025-03-21T20:24:34.5360250Z   [ 39%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_python.cpp.o
2025-03-21T20:24:34.5360797Z   [ 42%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_lobster.cpp.o
2025-03-21T20:24:34.5361701Z   [  9%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-pavgpool/f16-pavgpool-9p8x-minmax-avx2-c8.c.o
2025-03-21T20:24:34.5362588Z   [ 44%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_rust.cpp.o
2025-03-21T20:24:34.5363299Z   [  9%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/operators.dir/src/operators/pack-lh.c.o
2025-03-21T20:24:34.5364472Z   [  9%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-pavgpool/f16-pavgpool-9x-minmax-avx2-c8.c.o
2025-03-21T20:24:34.5365549Z   [  9%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/operators.dir/src/operators/reduce-nd.c.o
2025-03-21T20:24:34.5366267Z   [ 47%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_fbs.cpp.o
2025-03-21T20:24:34.5366790Z   [ 50%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_grpc.cpp.o
2025-03-21T20:24:34.5367668Z   [  9%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-qs8-vcvt/gen/f16-qs8-vcvt-scalar-imagic-u4.c.o
2025-03-21T20:24:34.5368812Z   [  9%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/operators.dir/src/operators/resize-bilinear-nchw.c.o
2025-03-21T20:24:34.5369733Z   [ 52%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_json_schema.cpp.o
2025-03-21T20:24:34.5370308Z   [ 55%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_swift.cpp.o
2025-03-21T20:24:34.5370904Z   [ 57%] Building CXX object CMakeFiles/flatc.dir/src/file_name_saving_file_manager.cpp.o
2025-03-21T20:24:34.5371755Z   [  9%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/operators.dir/src/operators/resize-bilinear-nhwc.c.o
2025-03-21T20:24:34.5373018Z   [  9%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-raddstoreexpminusmax/gen/f16-raddstoreexpminusmax-avx2-rr1-p2-u32.c.o
2025-03-21T20:24:34.5374323Z   [  9%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-rminmax/f16-rmax-f16c-u32.c.o
2025-03-21T20:24:34.5375431Z   [  9%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/operators.dir/src/operators/rope-nthc.c.o
2025-03-21T20:24:34.5376545Z   [  9%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/operators.dir/src/operators/scaled-dot-product-attention-nhtc.c.o
2025-03-21T20:24:34.5377739Z   [  9%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-rminmax/gen/f16-rmax-avx512skx-u64-acc4.c.o
2025-03-21T20:24:34.5378805Z   [ 10%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/operators.dir/src/operators/slice-nd.c.o
2025-03-21T20:24:34.5379736Z   [ 10%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/operators.dir/src/operators/softmax-nc.c.o
2025-03-21T20:24:34.5380494Z   [ 60%] Building CXX object CMakeFiles/flatc.dir/src/file_binary_writer.cpp.o
2025-03-21T20:24:34.5381036Z   [ 63%] Building CXX object CMakeFiles/flatc.dir/src/file_writer.cpp.o
2025-03-21T20:24:34.5381786Z   [ 10%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/operators.dir/src/operators/transpose-nd.c.o
2025-03-21T20:24:34.5382793Z   [ 10%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/operators.dir/src/operators/unary-elementwise-nc.c.o
2025-03-21T20:24:34.5383558Z   [ 65%] Building CXX object CMakeFiles/flatc.dir/src/flatc.cpp.o
2025-03-21T20:24:34.5384051Z   [ 68%] Building CXX object CMakeFiles/flatc.dir/src/flatc_main.cpp.o
2025-03-21T20:24:34.5384905Z   [ 10%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-rminmax/gen/f16-rmax-scalar-u2-acc2.c.o
2025-03-21T20:24:34.5386114Z   [ 10%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-rminmax/gen/f16-rminmax-avx512skx-u64-acc4.c.o
2025-03-21T20:24:34.5387350Z   [ 10%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/operators.dir/src/operators/unpooling-nhwc.c.o
2025-03-21T20:24:34.5388125Z   [ 71%] Building CXX object CMakeFiles/flatc.dir/src/binary_annotator.cpp.o
2025-03-21T20:24:34.5388734Z   [ 73%] Building CXX object CMakeFiles/flatc.dir/src/annotated_binary_text_gen.cpp.o
2025-03-21T20:24:34.5389663Z   [ 10%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-rminmax/gen/f16-rminmax-scalar-u2-acc2.c.o
2025-03-21T20:24:34.5390531Z   [ 76%] Building CXX object CMakeFiles/flatc.dir/src/bfbs_gen_lua.cpp.o
2025-03-21T20:24:34.5390960Z   [ 10%] Built target operators
2025-03-21T20:24:34.5391344Z   [ 78%] Building CXX object CMakeFiles/flatc.dir/src/bfbs_gen_nim.cpp.o
2025-03-21T20:24:34.5392175Z   [ 10%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-vbinary/gen/f16-vadd-f16c-u16.c.o
2025-03-21T20:24:34.5393295Z   [ 10%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-vbinary/gen/f16-vaddc-f16c-u16.c.o
2025-03-21T20:24:34.5394129Z   [ 81%] Building CXX object CMakeFiles/flatc.dir/src/code_generators.cpp.o
2025-03-21T20:24:34.5394728Z   [ 84%] Building CXX object CMakeFiles/flatc.dir/grpc/src/compiler/cpp_generator.cc.o
2025-03-21T20:24:34.5395370Z   [ 86%] Building CXX object CMakeFiles/flatc.dir/grpc/src/compiler/go_generator.cc.o
2025-03-21T20:24:34.5395994Z   [ 89%] Building CXX object CMakeFiles/flatc.dir/grpc/src/compiler/java_generator.cc.o
2025-03-21T20:24:34.5396649Z   [ 92%] Building CXX object CMakeFiles/flatc.dir/grpc/src/compiler/python_generator.cc.o
2025-03-21T20:24:34.5397544Z   [ 12%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-vbinary/gen/f16-vdiv-f16c-u8.c.o
2025-03-21T20:24:34.5398659Z   [ 12%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-vbinary/gen/f16-vdivc-f16c-u8.c.o
2025-03-21T20:24:34.5399720Z   [ 12%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/subgraph.dir/src/memory-planner.c.o
2025-03-21T20:24:34.5400555Z   [ 13%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/subgraph.dir/src/runtime.c.o
2025-03-21T20:24:34.5401518Z   [ 13%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/subgraph.dir/src/subgraph.c.o
2025-03-21T20:24:34.5402234Z   [ 94%] Building CXX object CMakeFiles/flatc.dir/grpc/src/compiler/swift_generator.cc.o
2025-03-21T20:24:34.5402882Z   [ 97%] Building CXX object CMakeFiles/flatc.dir/grpc/src/compiler/ts_generator.cc.o
2025-03-21T20:24:35.7264004Z   [ 13%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/subgraph.dir/src/subgraph/argmax-pooling-2d.c.o
2025-03-21T20:24:35.7265922Z   [ 13%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/subgraph.dir/src/subgraph/average-pooling-2d.c.o
2025-03-21T20:24:35.7267928Z   [ 13%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-vbinary/gen/f16-vmax-f16c-u16.c.o
2025-03-21T20:24:35.7269992Z   [ 13%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/subgraph.dir/src/subgraph/batch-matrix-multiply.c.o
2025-03-21T20:24:35.7271825Z   [ 13%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/subgraph.dir/src/subgraph/binary.c.o
2025-03-21T20:24:35.7273444Z   [ 13%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/subgraph.dir/src/subgraph/concatenate.c.o
2025-03-21T20:24:35.7275360Z   [ 13%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-vbinary/gen/f16-vmaxc-f16c-u16.c.o
2025-03-21T20:24:35.7277477Z   [ 13%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-vbinary/gen/f16-vmin-f16c-u16.c.o
2025-03-21T20:24:35.7279452Z   [ 13%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/subgraph.dir/src/subgraph/convolution-2d.c.o
2025-03-21T20:24:35.7281102Z   [ 13%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/subgraph.dir/src/subgraph/copy.c.o
2025-03-21T20:24:35.7282231Z   [100%] Linking CXX executable flatc
2025-03-21T20:24:35.7283410Z   [ 13%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/subgraph.dir/src/subgraph/deconvolution-2d.c.o
2025-03-21T20:24:35.7285190Z   [ 13%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-vbinary/gen/f16-vminc-f16c-u16.c.o
2025-03-21T20:24:35.7286635Z   [ 13%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/subgraph.dir/src/subgraph/deprecated.c.o
2025-03-21T20:24:35.7288097Z   [ 13%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-vbinary/gen/f16-vmul-f16c-u16.c.o
2025-03-21T20:24:35.7289339Z   [ 13%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-vbinary/gen/f16-vmulc-f16c-u16.c.o
2025-03-21T20:24:35.7290467Z   [ 13%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-vbinary/gen/f16-vprelu-f16c-u16.c.o
2025-03-21T20:24:35.7291525Z   [ 13%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/subgraph.dir/src/subgraph/depth-to-space-2d.c.o
2025-03-21T20:24:35.7292569Z   [ 13%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/subgraph.dir/src/subgraph/depthwise-convolution-2d.c.o
2025-03-21T20:24:35.7293536Z   [ 13%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/subgraph.dir/src/subgraph/even-split.c.o
2025-03-21T20:24:35.7294503Z   [ 13%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/subgraph.dir/src/subgraph/fully-connected-sparse.c.o
2025-03-21T20:24:35.7295594Z   [ 13%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-vbinary/gen/f16-vpreluc-f16c-u16.c.o
2025-03-21T20:24:35.7296731Z   [ 13%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-vbinary/gen/f16-vrdivc-f16c-u8.c.o
2025-03-21T20:24:35.7297775Z   [ 13%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/subgraph.dir/src/subgraph/fully-connected.c.o
2025-03-21T20:24:35.7299121Z   [ 13%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-vbinary/gen/f16-vrpreluc-f16c-u16.c.o
2025-03-21T20:24:35.7300178Z   [ 14%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/subgraph.dir/src/subgraph/max-pooling-2d.c.o
2025-03-21T20:24:35.7301074Z   [ 14%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/subgraph.dir/src/subgraph/pack-lh.c.o
2025-03-21T20:24:35.7302082Z   [ 14%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-vbinary/gen/f16-vrsubc-f16c-u16.c.o
2025-03-21T20:24:35.7303223Z   [ 14%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-vbinary/gen/f16-vsqrdiff-f16c-u16.c.o
2025-03-21T20:24:35.7304277Z   [ 14%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/subgraph.dir/src/subgraph/reshape-helpers.c.o
2025-03-21T20:24:35.7305345Z   [ 14%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-vbinary/gen/f16-vsqrdiffc-f16c-u16.c.o
2025-03-21T20:24:35.7306490Z   [ 14%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-vbinary/gen/f16-vsub-f16c-u16.c.o
2025-03-21T20:24:35.7307607Z   [ 15%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-vbinary/gen/f16-vsubc-f16c-u16.c.o
2025-03-21T20:24:35.7308727Z   [ 15%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-vclamp/gen/f16-vclamp-f16c-u16.c.o
2025-03-21T20:24:35.7309828Z   [ 15%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/subgraph.dir/src/subgraph/scaled-dot-product-attention.c.o
2025-03-21T20:24:35.7310812Z   [ 15%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/subgraph.dir/src/subgraph/softmax.c.o
2025-03-21T20:24:35.7312063Z   [ 15%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-velu/gen/f16-velu-avx2-rr1-p3-u16.c.o
2025-03-21T20:24:35.7313819Z   [ 15%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-vhswish/gen/f16-vhswish-f16c-u16.c.o
2025-03-21T20:24:35.7315356Z   [ 15%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-vlrelu/gen/f16-vlrelu-f16c-u16.c.o
2025-03-21T20:24:35.7316427Z   [ 15%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/subgraph.dir/src/subgraph/space-to-depth-2d.c.o
2025-03-21T20:24:35.7317424Z   [ 15%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/subgraph.dir/src/subgraph/static-constant-pad.c.o
2025-03-21T20:24:35.7318571Z   [ 15%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-vmulcaddc/gen/f16-vmulcaddc-c8-minmax-fma3-2x.c.o
2025-03-21T20:24:35.7319666Z   [ 15%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/subgraph.dir/src/subgraph/static-reduce.c.o
2025-03-21T20:24:35.7320685Z   [ 15%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/subgraph.dir/src/subgraph/static-resize-bilinear-2d.c.o
2025-03-21T20:24:35.7321677Z   [ 15%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/subgraph.dir/src/subgraph/static-slice.c.o
2025-03-21T20:24:35.7322628Z   [ 15%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/subgraph.dir/src/subgraph/static-transpose.c.o
2025-03-21T20:24:35.7323842Z   [ 15%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-vrnd/gen/f16-vrndd-f16c-u16.c.o
2025-03-21T20:24:35.7325460Z   [ 15%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/subgraph.dir/src/subgraph/unpooling-2d.c.o
2025-03-21T20:24:35.7326954Z   [ 15%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/subgraph.dir/src/subgraph/unary.c.o
2025-03-21T20:24:35.7328352Z   [ 15%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/subgraph.dir/src/subgraph/validation.c.o
2025-03-21T20:24:35.7329889Z   [ 15%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/subgraph.dir/src/tensor.c.o
2025-03-21T20:24:35.7331353Z   [ 15%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-vrnd/gen/f16-vrndne-f16c-u16.c.o
2025-03-21T20:24:35.7333356Z   [ 15%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-vrnd/gen/f16-vrndu-f16c-u16.c.o
2025-03-21T20:24:35.7335125Z   [ 15%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-vrnd/gen/f16-vrndz-f16c-u16.c.o
2025-03-21T20:24:35.7337267Z   [ 15%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-vrsqrt/gen/f16-vrsqrt-f16c-rsqrt-u32.c.o
2025-03-21T20:24:35.7339695Z   [ 15%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-vsigmoid/gen/f16-vsigmoid-avx2-rr1-p2-rcp-u32.c.o
2025-03-21T20:24:35.7341235Z   [ 15%] Built target subgraph
2025-03-21T20:24:35.7342486Z   [ 15%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-vsqrt/gen/f16-vsqrt-f16c-rsqrt-u32.c.o
2025-03-21T20:24:35.7343735Z   [100%] Built target flatc
2025-03-21T20:24:35.7344240Z   [ 15%] No install step for 'flatbuffers'
2025-03-21T20:24:35.7344755Z   [ 15%] Completed 'flatbuffers'
2025-03-21T20:24:35.7346387Z   [ 15%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-vtanh/gen/f16-vtanh-f16c-expm1minus-rr1-p3h2ts-rcp-u72.c.o
2025-03-21T20:24:35.7347761Z   [ 15%] Built target flatbuffers
2025-03-21T20:24:35.7349169Z   [ 15%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-vtanh/gen/f16-vtanh-fma3-polynomial-p19h9t2-u32.c.o
2025-03-21T20:24:35.7350755Z   [ 15%] Generating common_schema headers
2025-03-21T20:24:35.7351283Z   [ 15%] Built target common_schema
2025-03-21T20:24:35.7351779Z   [ 17%] Generating xnnpack_schema headers
2025-03-21T20:24:35.7352370Z   [ 17%] Built target xnnpack_schema
2025-03-21T20:24:35.7352927Z   [ 17%] Generating bundled_program headers
2025-03-21T20:24:35.7353483Z   [ 17%] Built target bundled_program_schema
2025-03-21T20:24:35.7354014Z   [ 17%] Generating program_schema headers
2025-03-21T20:24:36.9059227Z   [ 17%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-vunary/gen/f16-vabs-sse2-u16.c.o
2025-03-21T20:24:36.9060005Z   [ 17%] Built target program_schema
2025-03-21T20:24:36.9060769Z   [ 18%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-vunary/gen/f16-vneg-sse2-u16.c.o
2025-03-21T20:24:36.9061872Z   [ 18%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f16-vunary/gen/f16-vsqr-f16c-u16.c.o
2025-03-21T20:24:36.9062767Z   [ 18%] Building CXX object CMakeFiles/executorch_core.dir/runtime/backend/interface.cpp.o
2025-03-21T20:24:36.9063475Z   [ 18%] Building CXX object CMakeFiles/executorch_core.dir/runtime/core/evalue.cpp.o
2025-03-21T20:24:36.9064404Z   [ 18%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-argmaxpool/f32-argmaxpool-4x-scalar-c1.c.o
2025-03-21T20:24:36.9065616Z   [ 18%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-argmaxpool/f32-argmaxpool-4x-sse2-c4.c.o
2025-03-21T20:24:36.9066661Z   [ 18%] Building CXX object CMakeFiles/executorch_core.dir/runtime/core/exec_aten/util/tensor_shape_to_c_string.cpp.o
2025-03-21T20:24:36.9067541Z   [ 18%] Building CXX object CMakeFiles/executorch_core.dir/runtime/core/exec_aten/util/tensor_util_portable.cpp.o
2025-03-21T20:24:36.9068356Z   [ 18%] Building CXX object CMakeFiles/executorch_core.dir/runtime/core/portable_type/tensor_impl.cpp.o
2025-03-21T20:24:36.9069376Z   [ 18%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-argmaxpool/f32-argmaxpool-9p8x-scalar-c1.c.o
2025-03-21T20:24:36.9070607Z   [ 18%] Building CXX object CMakeFiles/executorch_core.dir/runtime/core/tag.cpp.o
2025-03-21T20:24:36.9071522Z   [ 18%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-argmaxpool/f32-argmaxpool-9p8x-sse2-c4.c.o
2025-03-21T20:24:36.9072743Z   [ 18%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-argmaxpool/f32-argmaxpool-9x-scalar-c1.c.o
2025-03-21T20:24:36.9073950Z   [ 18%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-argmaxpool/f32-argmaxpool-9x-sse2-c4.c.o
2025-03-21T20:24:36.9075168Z   [ 18%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-avgpool/f32-avgpool-9p8x-minmax-scalar-c1.c.o
2025-03-21T20:24:36.9076385Z   [ 18%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-avgpool/f32-avgpool-9p8x-minmax-sse-c4.c.o
2025-03-21T20:24:36.9077339Z   [ 18%] Building CXX object CMakeFiles/executorch_core.dir/runtime/core/tensor_layout.cpp.o
2025-03-21T20:24:36.9078017Z   [ 18%] Building CXX object CMakeFiles/executorch_core.dir/runtime/executor/method.cpp.o
2025-03-21T20:24:36.9078963Z   [ 18%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-avgpool/f32-avgpool-9x-minmax-scalar-c1.c.o
2025-03-21T20:24:36.9079920Z   [ 18%] Building CXX object CMakeFiles/executorch_core.dir/runtime/executor/method_meta.cpp.o
2025-03-21T20:24:36.9080871Z   [ 18%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-avgpool/f32-avgpool-9x-minmax-sse-c4.c.o
2025-03-21T20:24:36.9081804Z   [ 18%] Building CXX object CMakeFiles/executorch_core.dir/runtime/executor/program.cpp.o
2025-03-21T20:24:36.9082482Z   [ 18%] Building CXX object CMakeFiles/executorch_core.dir/runtime/executor/pte_data_map.cpp.o
2025-03-21T20:24:36.9083547Z   [ 18%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-conv-hwc2chw/f32-conv-hwc2chw-3x3s2p1c3x4-scalar-1x1.c.o
2025-03-21T20:24:36.9084936Z   [ 19%] Building CXX object CMakeFiles/executorch_core.dir/runtime/executor/tensor_parser_exec_aten.cpp.o
2025-03-21T20:24:36.9085816Z   [ 19%] Building CXX object CMakeFiles/executorch_core.dir/runtime/executor/tensor_parser_portable.cpp.o
2025-03-21T20:24:36.9086873Z   [ 19%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-conv-hwc2chw/f32-conv-hwc2chw-3x3s2p1c3x4-sse-2x2.c.o
2025-03-21T20:24:36.9088162Z   [ 19%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv/gen/f32-dwconv-25p16c-minmax-avx512f.c.o
2025-03-21T20:24:36.9089251Z   [ 19%] Building CXX object CMakeFiles/executorch_core.dir/runtime/kernel/operator_registry.cpp.o
2025-03-21T20:24:36.9089957Z   [ 19%] Building CXX object CMakeFiles/executorch_core.dir/runtime/platform/abort.cpp.o
2025-03-21T20:24:36.9090937Z   [ 20%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv/gen/f32-dwconv-25p1c-minmax-scalar-acc2.c.o
2025-03-21T20:24:36.9091903Z   [ 20%] Building CXX object CMakeFiles/executorch_core.dir/runtime/platform/log.cpp.o
2025-03-21T20:24:36.9092572Z   [ 20%] Building CXX object CMakeFiles/executorch_core.dir/runtime/platform/profiler.cpp.o
2025-03-21T20:24:36.9093531Z   [ 20%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv/gen/f32-dwconv-25p1c-scalar-acc2.c.o
2025-03-21T20:24:36.9094743Z   [ 20%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv/gen/f32-dwconv-25p8c-minmax-avx.c.o
2025-03-21T20:24:36.9095680Z   [ 20%] Building CXX object CMakeFiles/executorch_core.dir/runtime/platform/runtime.cpp.o
2025-03-21T20:24:36.9096346Z   [ 20%] Building CXX object CMakeFiles/executorch_core.dir/schema/extended_header.cpp.o
2025-03-21T20:24:36.9097196Z   [ 20%] Building CXX object CMakeFiles/executorch_core.dir/runtime/platform/default/posix.cpp.o
2025-03-21T20:24:36.9098172Z   [ 20%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv/gen/f32-dwconv-25p8c-minmax-fma3.c.o
2025-03-21T20:24:36.9099381Z   [ 20%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv/gen/f32-dwconv-25p8c-minmax-sse.c.o
2025-03-21T20:24:36.9100657Z   [ 20%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv/gen/f32-dwconv-2f2m2l4c1s1r-minmax-scalar-acc2.c.o
2025-03-21T20:24:36.9101942Z   [ 20%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv/gen/f32-dwconv-3p16c-minmax-avx.c.o
2025-03-21T20:24:36.9103170Z   [ 20%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv/gen/f32-dwconv-3p16c-minmax-avx512f.c.o
2025-03-21T20:24:36.9104406Z   [ 20%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv/gen/f32-dwconv-3p16c-minmax-fma3.c.o
2025-03-21T20:24:36.9105212Z   [ 20%] Linking CXX static library libexecutorch_core.a
2025-03-21T20:24:36.9106063Z   [ 20%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv/gen/f32-dwconv-3p1c-minmax-scalar-acc2.c.o
2025-03-21T20:24:36.9106877Z   [ 20%] Built target executorch_core
2025-03-21T20:24:36.9107375Z   [ 21%] Building CXX object CMakeFiles/executorch.dir/kernels/prim_ops/et_copy_index.cpp.o
2025-03-21T20:24:36.9108326Z   [ 21%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv/gen/f32-dwconv-3p1c-scalar-acc2.c.o
2025-03-21T20:24:36.9109238Z   [ 21%] Building CXX object CMakeFiles/executorch.dir/kernels/prim_ops/et_view.cpp.o
2025-03-21T20:24:36.9109910Z   [ 21%] Building CXX object CMakeFiles/executorch.dir/kernels/prim_ops/register_prim_ops.cpp.o
2025-03-21T20:24:36.9110619Z   [ 21%] Building CXX object extension/tensor/CMakeFiles/extension_tensor.dir/tensor_ptr.cpp.o
2025-03-21T20:24:36.9111359Z   [ 21%] Building CXX object extension/tensor/CMakeFiles/extension_tensor.dir/tensor_ptr_maker.cpp.o
2025-03-21T20:24:36.9112343Z   [ 21%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv/gen/f32-dwconv-3p8c-minmax-sse.c.o
2025-03-21T20:24:36.9113344Z   [ 23%] Building CXX object extension/threadpool/CMakeFiles/extension_threadpool.dir/threadpool.cpp.o
2025-03-21T20:24:36.9114168Z   [ 23%] Building CXX object extension/threadpool/CMakeFiles/extension_threadpool.dir/threadpool_guard.cpp.o
2025-03-21T20:24:36.9115013Z   [ 23%] Building CXX object extension/threadpool/CMakeFiles/extension_threadpool.dir/thread_parallel.cpp.o
2025-03-21T20:24:36.9116060Z   [ 23%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv/gen/f32-dwconv-4p16c-minmax-avx.c.o
2025-03-21T20:24:36.9116856Z   [ 23%] Linking CXX static library libexecutorch.a
2025-03-21T20:24:36.9117468Z   [ 23%] Building CXX object extension/threadpool/CMakeFiles/extension_threadpool.dir/cpuinfo_utils.cpp.o
2025-03-21T20:24:36.9118049Z   [ 23%] Built target executorch
2025-03-21T20:24:36.9118818Z   [ 23%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv/gen/f32-dwconv-4p16c-minmax-avx512f.c.o
2025-03-21T20:24:36.9119866Z   [ 23%] Building CXX object extension/data_loader/CMakeFiles/extension_data_loader.dir/file_data_loader.cpp.o
2025-03-21T20:24:36.9120895Z   [ 23%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv/gen/f32-dwconv-4p16c-minmax-fma3.c.o
2025-03-21T20:24:36.9121708Z   [ 23%] Linking CXX static library libextension_tensor.a
2025-03-21T20:24:36.9122094Z   [ 23%] Built target extension_tensor
2025-03-21T20:24:36.9122577Z   [ 23%] Building CXX object devtools/CMakeFiles/etdump.dir/etdump/etdump_flatcc.cpp.o
2025-03-21T20:24:36.9123420Z   [ 23%] Building CXX object devtools/CMakeFiles/bundled_program.dir/bundled_program/bundled_program.cpp.o
2025-03-21T20:24:36.9124123Z   [ 23%] Building CXX object devtools/CMakeFiles/etdump.dir/etdump/emitter.cpp.o
2025-03-21T20:24:39.0252419Z   [ 23%] Linking CXX static library libextension_threadpool.a
2025-03-21T20:24:39.0253229Z   [ 23%] Built target extension_threadpool
2025-03-21T20:24:39.0254269Z   [ 23%] Building CXX object devtools/CMakeFiles/etdump.dir/etdump/data_sinks/buffer_data_sink.cpp.o
2025-03-21T20:24:39.0255807Z   [ 23%] Building CXX object extension/data_loader/CMakeFiles/extension_data_loader.dir/mmap_data_loader.cpp.o
2025-03-21T20:24:39.0258013Z   [ 23%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv/gen/f32-dwconv-4p1c-minmax-scalar-acc2.c.o
2025-03-21T20:24:39.0259991Z   [ 23%] Building CXX object devtools/CMakeFiles/etdump.dir/etdump/data_sinks/file_data_sink.cpp.o
2025-03-21T20:24:39.0261174Z   [ 23%] Linking CXX static library libextension_data_loader.a
2025-03-21T20:24:39.0261978Z   [ 23%] Linking CXX static library libbundled_program.a
2025-03-21T20:24:39.0262674Z   [ 23%] Built target extension_data_loader
2025-03-21T20:24:39.0264072Z   [ 24%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv/gen/f32-dwconv-4p1c-scalar-acc2.c.o
2025-03-21T20:24:39.0265539Z   [ 24%] Built target bundled_program
2025-03-21T20:24:39.0266439Z   [ 24%] Building CXX object CMakeFiles/util.dir/extension/evalue_util/print_evalue.cpp.o
2025-03-21T20:24:39.0268176Z   [ 24%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv/gen/f32-dwconv-4p8c-minmax-sse.c.o
2025-03-21T20:24:39.0270074Z   [ 25%] Building CXX object CMakeFiles/util.dir/extension/aten_util/aten_bridge.cpp.o
2025-03-21T20:24:39.0271336Z   [ 25%] Building CXX object kernels/optimized/CMakeFiles/cpublas.dir/blas/BlasKernel.cpp.o
2025-03-21T20:24:39.0272670Z   [ 25%] Building CXX object kernels/optimized/CMakeFiles/cpublas.dir/blas/CPUBlas.cpp.o
2025-03-21T20:24:39.0274185Z   [ 26%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op__empty_dim_order.cpp.o
2025-03-21T20:24:39.0275407Z   [ 26%] Linking CXX static library libetdump.a
2025-03-21T20:24:39.0276969Z   [ 26%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv/gen/f32-dwconv-5f5m5l32c16s1r-minmax-avx512f.c.o
2025-03-21T20:24:39.0278571Z   [ 26%] Built target etdump
2025-03-21T20:24:39.0280060Z   [ 26%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv/gen/f32-dwconv-5f5m5l8c8s4r-minmax-fma3.c.o
2025-03-21T20:24:39.0282526Z   [ 26%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv/gen/f32-dwconv-6f6m7l8c8s4r-minmax-avx.c.o
2025-03-21T20:24:39.0284674Z   [ 26%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op__to_dim_order_copy.cpp.o
2025-03-21T20:24:39.0286306Z   [ 26%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_abs.cpp.o
2025-03-21T20:24:39.0287445Z   [ 26%] Linking CXX static library libcpublas.a
2025-03-21T20:24:39.0288562Z   [ 26%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_acos.cpp.o
2025-03-21T20:24:39.0290765Z   [ 26%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv/gen/f32-dwconv-8f8m9l16c4s4r-minmax-sse.c.o
2025-03-21T20:24:39.0292308Z   [ 26%] Built target cpublas
2025-03-21T20:24:39.0293248Z   [ 26%] Building CXX object kernels/optimized/CMakeFiles/optimized_kernels.dir/cpu/op_add.cpp.o
2025-03-21T20:24:39.0294667Z   [ 26%] Building CXX object kernels/optimized/CMakeFiles/optimized_kernels.dir/cpu/op_bmm.cpp.o
2025-03-21T20:24:39.0296828Z   [ 26%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv/gen/f32-dwconv-9p16c-minmax-avx.c.o
2025-03-21T20:24:39.0298930Z   [ 26%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_acosh.cpp.o
2025-03-21T20:24:39.0300504Z   [ 26%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_add.cpp.o
2025-03-21T20:24:39.0302062Z   [ 26%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_addmm.cpp.o
2025-03-21T20:24:39.0303554Z   [ 26%] Building CXX object kernels/optimized/CMakeFiles/optimized_kernels.dir/cpu/op_div.cpp.o
2025-03-21T20:24:39.0304590Z   [ 26%] Linking CXX static library libutil.a
2025-03-21T20:24:39.0306131Z   [ 26%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv/gen/f32-dwconv-9p16c-minmax-avx512f.c.o
2025-03-21T20:24:39.0307641Z   [ 26%] Built target util
2025-03-21T20:24:39.0309045Z   [ 26%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv/gen/f32-dwconv-9p16c-minmax-fma3.c.o
2025-03-21T20:24:39.0310938Z   [ 26%] Building CXX object kernels/optimized/CMakeFiles/optimized_kernels.dir/cpu/op_exp.cpp.o
2025-03-21T20:24:39.0312476Z   [ 26%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_alias_copy.cpp.o
2025-03-21T20:24:39.0314047Z   [ 26%] Building CXX object kernels/optimized/CMakeFiles/optimized_kernels.dir/cpu/op_fft_r2c.cpp.o
2025-03-21T20:24:39.0315606Z   [ 26%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_allclose.cpp.o
2025-03-21T20:24:39.0317665Z   [ 26%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv/gen/f32-dwconv-9p1c-minmax-scalar-acc2.c.o
2025-03-21T20:24:39.0319619Z   [ 26%] Building CXX object kernels/optimized/CMakeFiles/optimized_kernels.dir/cpu/op_gelu.cpp.o
2025-03-21T20:24:39.0321519Z   [ 26%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv/gen/f32-dwconv-9p1c-scalar-acc2.c.o
2025-03-21T20:24:39.0323394Z   [ 26%] Building CXX object kernels/optimized/CMakeFiles/optimized_kernels.dir/cpu/op_le.cpp.o
2025-03-21T20:24:39.0324879Z   [ 26%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_amax.cpp.o
2025-03-21T20:24:39.0326844Z   [ 26%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv/gen/f32-dwconv-9p8c-minmax-sse.c.o
2025-03-21T20:24:39.0329535Z   [ 26%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv2d-chw/gen/f32-dwconv2d-chw-3x3p1-minmax-scalar-2x1-acc2.c.o
2025-03-21T20:24:39.0331728Z   [ 26%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_amin.cpp.o
2025-03-21T20:24:39.0333467Z   [ 26%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_any.cpp.o
2025-03-21T20:24:39.0335631Z   [ 26%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv2d-chw/gen/f32-dwconv2d-chw-3x3p1-minmax-scalar-4x1.c.o
2025-03-21T20:24:39.0337732Z   [ 26%] Building CXX object kernels/optimized/CMakeFiles/optimized_kernels.dir/cpu/op_linear.cpp.o
2025-03-21T20:24:39.0339862Z   [ 26%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv2d-chw/gen/f32-dwconv2d-chw-3x3p1-minmax-sse-2x4-acc2.c.o
2025-03-21T20:24:39.0342633Z   [ 26%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv2d-chw/gen/f32-dwconv2d-chw-3x3p1-minmax-ssse3-2x4-acc2.c.o
2025-03-21T20:24:39.0345443Z   [ 28%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv2d-chw/gen/f32-dwconv2d-chw-3x3s2p1-minmax-scalar-1x1-acc2.c.o
2025-03-21T20:24:39.0347501Z   [ 28%] Building CXX object kernels/optimized/CMakeFiles/optimized_kernels.dir/cpu/op_log_softmax.cpp.o
2025-03-21T20:24:39.0349479Z   [ 28%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_arange.cpp.o
2025-03-21T20:24:39.0351603Z   [ 28%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv2d-chw/gen/f32-dwconv2d-chw-3x3s2p1-minmax-scalar-2x1-acc2.c.o
2025-03-21T20:24:39.0354265Z   [ 28%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv2d-chw/gen/f32-dwconv2d-chw-3x3s2p1-minmax-sse-1x4-acc3.c.o
2025-03-21T20:24:39.0356374Z   [ 28%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_argmax.cpp.o
2025-03-21T20:24:39.0358542Z   [ 28%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv2d-chw/gen/f32-dwconv2d-chw-5x5p2-minmax-scalar-1x1-acc5.c.o
2025-03-21T20:24:39.0360693Z   [ 28%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_argmin.cpp.o
2025-03-21T20:24:39.0362928Z   [ 28%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv2d-chw/gen/f32-dwconv2d-chw-5x5p2-minmax-scalar-2x1-acc2.c.o
2025-03-21T20:24:39.0365039Z   [ 28%] Building CXX object kernels/optimized/CMakeFiles/optimized_kernels.dir/cpu/op_mm.cpp.o
2025-03-21T20:24:39.0367052Z   [ 28%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv2d-chw/gen/f32-dwconv2d-chw-5x5p2-minmax-sse-4x4.c.o
2025-03-21T20:24:39.0369892Z   [ 28%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv2d-chw/gen/f32-dwconv2d-chw-5x5s2p2-minmax-scalar-1x1-acc5.c.o
2025-03-21T20:24:39.0372206Z   [ 28%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_as_strided_copy.cpp.o
2025-03-21T20:24:39.0373782Z   [ 28%] Building CXX object kernels/optimized/CMakeFiles/optimized_kernels.dir/cpu/op_mul.cpp.o
2025-03-21T20:24:39.0375902Z   [ 28%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv2d-chw/gen/f32-dwconv2d-chw-5x5s2p2-minmax-scalar-2x1-acc2.c.o
2025-03-21T20:24:39.0378134Z   [ 29%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_asin.cpp.o
2025-03-21T20:24:42.7223011Z   [ 29%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-dwconv2d-chw/gen/f32-dwconv2d-chw-5x5s2p2-minmax-sse-2x4.c.o
2025-03-21T20:24:42.7225430Z   [ 29%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-f16-vcvt/gen/f32-f16-vcvt-avx-u24.c.o
2025-03-21T20:24:42.7227321Z   [ 30%] Building CXX object kernels/optimized/CMakeFiles/optimized_kernels.dir/cpu/op_native_layer_norm.cpp.o
2025-03-21T20:24:42.7229215Z   [ 30%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-f16-vcvt/gen/f32-f16-vcvt-avx512skx-u16.c.o
2025-03-21T20:24:42.7231221Z   [ 30%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_asinh.cpp.o
2025-03-21T20:24:42.7233302Z   [ 30%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-f16-vcvt/gen/f32-f16-vcvt-f16c-u16.c.o
2025-03-21T20:24:42.7235211Z   [ 30%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_atan.cpp.o
2025-03-21T20:24:42.7237257Z   [ 30%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-f16-vcvt/gen/f32-f16-vcvt-scalar-bitcast-u4.c.o
2025-03-21T20:24:42.7239620Z   [ 30%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-f16-vcvt/gen/f32-f16-vcvt-scalar-fabsf-u2.c.o
2025-03-21T20:24:42.7241436Z   [ 30%] Building CXX object kernels/optimized/CMakeFiles/optimized_kernels.dir/cpu/op_neg.cpp.o
2025-03-21T20:24:42.7243187Z   [ 30%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-f16-vcvt/gen/f32-f16-vcvt-sse2-u16.c.o
2025-03-21T20:24:42.7245415Z   [ 30%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_atan2.cpp.o
2025-03-21T20:24:42.7247309Z   [ 30%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-f16-vcvt/gen/f32-f16-vcvt-sse41-u8.c.o
2025-03-21T20:24:42.7249729Z   [ 31%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-gemm/gen/f32-gemm-1x16-minmax-avx-broadcast.c.o
2025-03-21T20:24:42.7251769Z   [ 31%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_atanh.cpp.o
2025-03-21T20:24:42.7253404Z   [ 31%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_avg_pool2d.cpp.o
2025-03-21T20:24:42.7255425Z   [ 31%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-gemm/gen/f32-gemm-1x16-minmax-fma3-broadcast.c.o
2025-03-21T20:24:42.7257455Z   [ 31%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_bitwise_and.cpp.o
2025-03-21T20:24:42.7259487Z   [ 31%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-gemm/gen/f32-gemm-1x16s4-minmax-fma3-broadcast.c.o
2025-03-21T20:24:42.7261484Z   [ 31%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_bitwise_not.cpp.o
2025-03-21T20:24:42.7263112Z   [ 31%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_bitwise_or.cpp.o
2025-03-21T20:24:42.7265102Z   [ 31%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-gemm/gen/f32-gemm-1x32-minmax-avx512f-broadcast.c.o
2025-03-21T20:24:42.7267187Z   [ 31%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_bitwise_xor.cpp.o
2025-03-21T20:24:42.7269222Z   [ 31%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-gemm/gen/f32-gemm-1x4-minmax-scalar.c.o
2025-03-21T20:24:42.7271103Z   [ 31%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_bmm.cpp.o
2025-03-21T20:24:42.7272625Z   [ 31%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_cat.cpp.o
2025-03-21T20:24:42.7274429Z   [ 31%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-gemm/gen/f32-gemm-1x4-relu-scalar.c.o
2025-03-21T20:24:42.7276556Z   [ 31%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-gemm/gen/f32-gemm-1x4-scalar.c.o
2025-03-21T20:24:42.7278410Z   [ 31%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_cdist_forward.cpp.o
2025-03-21T20:24:42.7280041Z   [ 31%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_ceil.cpp.o
2025-03-21T20:24:42.7281927Z   [ 31%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-gemm/gen/f32-gemm-1x8-minmax-sse-load1.c.o
2025-03-21T20:24:42.7283961Z   [ 31%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_clamp.cpp.o
2025-03-21T20:24:42.7285861Z   [ 31%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-gemm/gen/f32-gemm-2x4-minmax-scalar.c.o
2025-03-21T20:24:42.7288103Z   [ 31%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-gemm/gen/f32-gemm-2x4-relu-scalar.c.o
2025-03-21T20:24:42.7290250Z   [ 31%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-gemm/gen/f32-gemm-2x4-scalar.c.o
2025-03-21T20:24:42.7292503Z   [ 31%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-gemm/gen/f32-gemm-4x16s4-minmax-fma3-broadcast.c.o
2025-03-21T20:24:42.7294454Z   [ 31%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_clone.cpp.o
2025-03-21T20:24:42.7296315Z   [ 32%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_constant_pad_nd.cpp.o
2025-03-21T20:24:42.7298254Z   [ 32%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-gemm/gen/f32-gemm-4x2-minmax-scalar.c.o
2025-03-21T20:24:42.7300227Z   [ 32%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_convolution.cpp.o
2025-03-21T20:24:42.7302069Z   [ 32%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-gemm/gen/f32-gemm-4x2-scalar.c.o
2025-03-21T20:24:42.7304212Z   [ 32%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-gemm/gen/f32-gemm-4x2c4-minmax-sse.c.o
2025-03-21T20:24:42.7306428Z   [ 34%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-gemm/gen/f32-gemm-4x4-minmax-scalar.c.o
2025-03-21T20:24:42.7308639Z   [ 34%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-gemm/gen/f32-gemm-4x4-relu-scalar.c.o
2025-03-21T20:24:42.7310649Z   [ 34%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_convolution_backward.cpp.o
2025-03-21T20:24:42.7312699Z   [ 34%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-gemm/gen/f32-gemm-4x4-scalar.c.o
2025-03-21T20:24:42.7314900Z   [ 34%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-gemm/gen/f32-gemm-4x8-minmax-sse-load1.c.o
2025-03-21T20:24:42.7317242Z   [ 34%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-gemm/gen/f32-gemm-5x16-minmax-avx-broadcast.c.o
2025-03-21T20:24:42.7319155Z   [ 34%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_copy.cpp.o
2025-03-21T20:24:42.7321095Z   [ 34%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-gemm/gen/f32-gemm-5x16-minmax-fma3-broadcast.c.o
2025-03-21T20:24:42.7323593Z   [ 34%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-gemm/gen/f32-gemm-7x32-minmax-avx512f-broadcast.c.o
2025-03-21T20:24:42.7325490Z   [ 34%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_cos.cpp.o
2025-03-21T20:24:42.7327543Z   [ 34%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-ibilinear-chw/gen/f32-ibilinear-chw-scalar-p4.c.o
2025-03-21T20:24:42.7330077Z   [ 34%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-ibilinear-chw/gen/f32-ibilinear-chw-sse-p8.c.o
2025-03-21T20:24:42.7332784Z   [ 34%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-ibilinear/gen/f32-ibilinear-scalar-c2.c.o
2025-03-21T20:24:42.7334656Z   [ 34%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_cosh.cpp.o
2025-03-21T20:24:42.7336533Z   [ 34%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-ibilinear/gen/f32-ibilinear-sse-c8.c.o
2025-03-21T20:24:42.7338815Z   [ 34%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-igemm/gen/f32-igemm-1x16-minmax-avx-broadcast.c.o
2025-03-21T20:24:42.7340807Z   [ 34%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_cumsum.cpp.o
2025-03-21T20:24:42.7342349Z   [ 34%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_detach_copy.cpp.o
2025-03-21T20:24:42.7344484Z   [ 34%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-igemm/gen/f32-igemm-1x16-minmax-fma3-broadcast.c.o
2025-03-21T20:24:42.7346461Z   [ 34%] Building CXX object kernels/optimized/CMakeFiles/optimized_kernels.dir/cpu/op_sigmoid.cpp.o
2025-03-21T20:24:46.0284098Z   [ 34%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-igemm/gen/f32-igemm-1x16s4-minmax-fma3-broadcast.c.o
2025-03-21T20:24:46.0286285Z   [ 34%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_diagonal_copy.cpp.o
2025-03-21T20:24:46.0288418Z   [ 34%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-igemm/gen/f32-igemm-1x32-minmax-avx512f-broadcast.c.o
2025-03-21T20:24:46.0290457Z   [ 34%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_div.cpp.o
2025-03-21T20:24:46.0291906Z   [ 34%] Building CXX object kernels/optimized/CMakeFiles/optimized_kernels.dir/cpu/op_sub.cpp.o
2025-03-21T20:24:46.0293706Z   [ 34%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-igemm/gen/f32-igemm-1x4-minmax-scalar.c.o
2025-03-21T20:24:46.0295746Z   [ 34%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_embedding.cpp.o
2025-03-21T20:24:46.0297623Z   [ 35%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-igemm/gen/f32-igemm-1x4-relu-scalar.c.o
2025-03-21T20:24:46.0299576Z   [ 35%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_empty.cpp.o
2025-03-21T20:24:46.0301490Z   [ 35%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-igemm/gen/f32-igemm-1x4-scalar.c.o
2025-03-21T20:24:46.0303756Z   [ 35%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-igemm/gen/f32-igemm-1x8-minmax-sse-load1.c.o
2025-03-21T20:24:46.0305643Z   [ 35%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_eq.cpp.o
2025-03-21T20:24:46.0307549Z   [ 35%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-igemm/gen/f32-igemm-2x4-minmax-scalar.c.o
2025-03-21T20:24:46.0309776Z   [ 35%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-igemm/gen/f32-igemm-2x4-relu-scalar.c.o
2025-03-21T20:24:46.0311671Z   [ 35%] Building CXX object kernels/optimized/CMakeFiles/optimized_kernels.dir/cpu/op_where.cpp.o
2025-03-21T20:24:46.0313388Z   [ 35%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-igemm/gen/f32-igemm-2x4-scalar.c.o
2025-03-21T20:24:46.0315248Z   [ 35%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_erf.cpp.o
2025-03-21T20:24:46.0317391Z   [ 35%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-igemm/gen/f32-igemm-4x16s4-minmax-fma3-broadcast.c.o
2025-03-21T20:24:46.0319782Z   [ 35%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-igemm/gen/f32-igemm-4x2-minmax-scalar.c.o
2025-03-21T20:24:46.0321686Z   [ 35%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_exp.cpp.o
2025-03-21T20:24:46.0323512Z   [ 35%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-igemm/gen/f32-igemm-4x2-scalar.c.o
2025-03-21T20:24:46.0325675Z   [ 35%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-igemm/gen/f32-igemm-4x2c4-minmax-sse.c.o
2025-03-21T20:24:46.0328009Z   [ 35%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-igemm/gen/f32-igemm-4x4-minmax-scalar.c.o
2025-03-21T20:24:46.0329995Z   [ 35%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_expand_copy.cpp.o
2025-03-21T20:24:46.0332017Z   [ 35%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-igemm/gen/f32-igemm-4x4-relu-scalar.c.o
2025-03-21T20:24:46.0334680Z   [ 35%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-igemm/gen/f32-igemm-4x4-scalar.c.o
2025-03-21T20:24:46.0337076Z   [ 35%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-igemm/gen/f32-igemm-4x8-minmax-sse-load1.c.o
2025-03-21T20:24:46.0338963Z   [ 36%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_expm1.cpp.o
2025-03-21T20:24:46.0340515Z   [ 36%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_fill.cpp.o
2025-03-21T20:24:46.0342451Z   [ 36%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-igemm/gen/f32-igemm-5x16-minmax-avx-broadcast.c.o
2025-03-21T20:24:46.0344474Z   [ 36%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_flip.cpp.o
2025-03-21T20:24:46.0346468Z   [ 36%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-igemm/gen/f32-igemm-5x16-minmax-fma3-broadcast-prfm.c.o
2025-03-21T20:24:46.0348616Z   [ 36%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_floor.cpp.o
2025-03-21T20:24:46.0350675Z   [ 37%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-igemm/gen/f32-igemm-7x32-minmax-avx512f-broadcast.c.o
2025-03-21T20:24:46.0352774Z   [ 37%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_floor_divide.cpp.o
2025-03-21T20:24:46.0354776Z   [ 37%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-maxpool/f32-maxpool-9p8x-minmax-scalar-c1.c.o
2025-03-21T20:24:46.0357080Z   [ 37%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-maxpool/f32-maxpool-9p8x-minmax-sse-c4.c.o
2025-03-21T20:24:46.0358971Z   [ 37%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_fmod.cpp.o
2025-03-21T20:24:46.0361006Z   [ 37%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-pavgpool/f32-pavgpool-9p8x-minmax-scalar-c1.c.o
2025-03-21T20:24:46.0363353Z   [ 37%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-pavgpool/f32-pavgpool-9p8x-minmax-sse-c4.c.o
2025-03-21T20:24:46.0365836Z   [ 37%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-pavgpool/f32-pavgpool-9x-minmax-scalar-c1.c.o
2025-03-21T20:24:46.0368526Z   [ 37%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-pavgpool/f32-pavgpool-9x-minmax-sse-c4.c.o
2025-03-21T20:24:46.0371076Z   [ 37%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qc4w-gemm/gen/f32-qc4w-gemm-1x16-minmax-avx-broadcast.c.o
2025-03-21T20:24:46.0373415Z   [ 37%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_full.cpp.o
2025-03-21T20:24:46.0374962Z   [ 37%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_full_like.cpp.o
2025-03-21T20:24:46.0377107Z   [ 37%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qc4w-gemm/gen/f32-qc4w-gemm-1x16-minmax-avx2-broadcast.c.o
2025-03-21T20:24:46.0379115Z   [ 37%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_gather.cpp.o
2025-03-21T20:24:46.0383216Z   [ 37%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_ge.cpp.o
2025-03-21T20:24:46.0384764Z   [ 37%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_gelu.cpp.o
2025-03-21T20:24:46.0386769Z   [ 37%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qc4w-gemm/gen/f32-qc4w-gemm-1x16-minmax-fma3-broadcast.c.o
2025-03-21T20:24:46.0388809Z   [ 37%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_glu.cpp.o
2025-03-21T20:24:46.0391179Z   [ 37%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_gt.cpp.o
2025-03-21T20:24:46.0392747Z   [ 37%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_hardtanh.cpp.o
2025-03-21T20:24:46.0394260Z   [ 37%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_index.cpp.o
2025-03-21T20:24:46.0395876Z   [ 39%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_index_put.cpp.o
2025-03-21T20:24:46.0397981Z   [ 39%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qc4w-gemm/gen/f32-qc4w-gemm-1x4-minmax-scalar.c.o
2025-03-21T20:24:46.0399944Z   [ 39%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_index_select.cpp.o
2025-03-21T20:24:46.0401938Z   [ 39%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qc4w-gemm/gen/f32-qc4w-gemm-1x8-minmax-sse41-dup.c.o
2025-03-21T20:24:46.0404409Z   [ 39%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qc4w-gemm/gen/f32-qc4w-gemm-3x16-minmax-avx-broadcast.c.o
2025-03-21T20:24:46.0406482Z   [ 39%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_isinf.cpp.o
2025-03-21T20:24:46.0407993Z   [ 39%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_isnan.cpp.o
2025-03-21T20:24:46.0410200Z   [ 39%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qc4w-gemm/gen/f32-qc4w-gemm-3x16-minmax-avx2-broadcast.c.o
2025-03-21T20:24:47.5171533Z   [ 39%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qc4w-gemm/gen/f32-qc4w-gemm-3x16-minmax-fma3-broadcast.c.o
2025-03-21T20:24:47.5173736Z   [ 39%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_le.cpp.o
2025-03-21T20:24:47.5175252Z   [ 39%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_leaky_relu.cpp.o
2025-03-21T20:24:47.5176778Z   [ 39%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_lift_fresh_copy.cpp.o
2025-03-21T20:24:47.5178441Z   [ 39%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_linear_scratch_example.cpp.o
2025-03-21T20:24:47.5180401Z   [ 40%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qc4w-gemm/gen/f32-qc4w-gemm-4x4-minmax-scalar.c.o
2025-03-21T20:24:47.5182670Z   [ 40%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qc4w-gemm/gen/f32-qc4w-gemm-4x8-minmax-sse41-dup.c.o
2025-03-21T20:24:47.5185077Z   [ 40%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qc8w-gemm/gen/f32-qc4w-gemm-1x32-minmax-avx512skx-broadcast.c.o
2025-03-21T20:24:47.5187653Z   [ 40%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qc8w-gemm/gen/f32-qc4w-gemm-7x32-minmax-avx512skx-broadcast.c.o
2025-03-21T20:24:47.5190088Z   [ 40%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qc8w-gemm/gen/f32-qc8w-gemm-1x16-minmax-avx-broadcast.c.o
2025-03-21T20:24:47.5191991Z   [ 40%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_log.cpp.o
2025-03-21T20:24:47.5193412Z   [ 40%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_log10.cpp.o
2025-03-21T20:24:47.5194833Z   [ 40%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_log1p.cpp.o
2025-03-21T20:24:47.5196789Z   [ 40%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qc8w-gemm/gen/f32-qc8w-gemm-1x16-minmax-avx2-broadcast.c.o
2025-03-21T20:24:47.5199877Z   [ 40%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qc8w-gemm/gen/f32-qc8w-gemm-1x16-minmax-fma3-broadcast.c.o
2025-03-21T20:24:47.5202365Z   [ 40%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qc8w-gemm/gen/f32-qc8w-gemm-1x32-minmax-avx512skx-broadcast.c.o
2025-03-21T20:24:47.5204364Z   [ 40%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_log2.cpp.o
2025-03-21T20:24:47.5205854Z   [ 40%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_log_softmax.cpp.o
2025-03-21T20:24:47.5207400Z   [ 40%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_logical_and.cpp.o
2025-03-21T20:24:47.5209398Z   [ 40%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qc8w-gemm/gen/f32-qc8w-gemm-1x4-minmax-scalar.c.o
2025-03-21T20:24:47.5211673Z   [ 40%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qc8w-gemm/gen/f32-qc8w-gemm-1x8-minmax-sse41-dup.c.o
2025-03-21T20:24:47.5213955Z   [ 40%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qc8w-gemm/gen/f32-qc8w-gemm-4x4-minmax-scalar.c.o
2025-03-21T20:24:47.5215860Z   [ 40%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_logical_not.cpp.o
2025-03-21T20:24:47.5217772Z   [ 40%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qc8w-gemm/gen/f32-qc8w-gemm-4x8-minmax-sse41-dup.c.o
2025-03-21T20:24:47.5220124Z   [ 40%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qc8w-gemm/gen/f32-qc8w-gemm-5x16-minmax-avx-broadcast.c.o
2025-03-21T20:24:47.5222578Z   [ 40%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qc8w-gemm/gen/f32-qc8w-gemm-5x16-minmax-avx2-broadcast.c.o
2025-03-21T20:24:47.5224609Z   [ 40%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_logical_or.cpp.o
2025-03-21T20:24:47.5226625Z   [ 40%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qc8w-gemm/gen/f32-qc8w-gemm-5x16-minmax-fma3-broadcast.c.o
2025-03-21T20:24:47.5229119Z   [ 40%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qc8w-gemm/gen/f32-qc8w-gemm-7x32-minmax-avx512skx-broadcast.c.o
2025-03-21T20:24:47.5230744Z   [ 40%] Linking CXX static library liboptimized_kernels.a
2025-03-21T20:24:47.5232112Z   [ 41%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qs8-vcvt/gen/f32-qs8-vcvt-avx-u32.c.o
2025-03-21T20:24:47.5234292Z   [ 41%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qs8-vcvt/gen/f32-qs8-vcvt-avx2-u64.c.o
2025-03-21T20:24:47.5236469Z   [ 41%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qs8-vcvt/gen/f32-qs8-vcvt-avx512skx-u128.c.o
2025-03-21T20:24:47.5238338Z   [ 42%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_logical_xor.cpp.o
2025-03-21T20:24:47.5240306Z   [ 42%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qs8-vcvt/gen/f32-qs8-vcvt-scalar-imagic-u1.c.o
2025-03-21T20:24:47.5242359Z   [ 42%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_logit.cpp.o
2025-03-21T20:24:47.5256561Z   [ 42%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_lt.cpp.o
2025-03-21T20:24:47.5257773Z   [ 42%] Built target optimized_kernels
2025-03-21T20:24:47.5258829Z   [ 42%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_masked_fill.cpp.o
2025-03-21T20:24:47.5260613Z   [ 42%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_masked_scatter.cpp.o
2025-03-21T20:24:47.5262430Z   [ 42%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qs8-vcvt/gen/f32-qs8-vcvt-scalar-imagic-u4.c.o
2025-03-21T20:24:47.5264642Z   [ 42%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qs8-vcvt/gen/f32-qs8-vcvt-scalar-lrintf-u4.c.o
2025-03-21T20:24:47.5266611Z   [ 42%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_masked_select.cpp.o
2025-03-21T20:24:47.5268151Z   [ 42%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_max.cpp.o
2025-03-21T20:24:47.5269997Z   [ 42%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qs8-vcvt/gen/f32-qs8-vcvt-sse2-u32.c.o
2025-03-21T20:24:47.5272100Z   [ 42%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_max_pool2d_with_indices.cpp.o
2025-03-21T20:24:47.5274159Z   [ 42%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_max_pool2d_with_indices_backward.cpp.o
2025-03-21T20:24:47.5276058Z   [ 42%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_maximum.cpp.o
2025-03-21T20:24:47.5277614Z   [ 42%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_mean.cpp.o
2025-03-21T20:24:47.5279377Z   [ 42%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qs8-vcvt/gen/f32-qs8-vcvt-sse41-u32.c.o
2025-03-21T20:24:47.5281364Z   [ 42%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qu8-vcvt/gen/f32-qu8-vcvt-avx-u32.c.o
2025-03-21T20:24:47.5283362Z   [ 42%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qu8-vcvt/gen/f32-qu8-vcvt-avx2-u64.c.o
2025-03-21T20:24:47.5285513Z   [ 42%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qu8-vcvt/gen/f32-qu8-vcvt-avx512skx-u128.c.o
2025-03-21T20:24:47.5287732Z   [ 42%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qu8-vcvt/gen/f32-qu8-vcvt-scalar-imagic-u1.c.o
2025-03-21T20:24:47.5289698Z   [ 42%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_min.cpp.o
2025-03-21T20:24:47.5291192Z   [ 42%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_minimum.cpp.o
2025-03-21T20:24:47.5292614Z   [ 42%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_mm.cpp.o
2025-03-21T20:24:47.5294450Z   [ 42%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qu8-vcvt/gen/f32-qu8-vcvt-scalar-imagic-u4.c.o
2025-03-21T20:24:47.5296301Z   [ 42%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_mul.cpp.o
2025-03-21T20:24:47.5298257Z   [ 42%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qu8-vcvt/gen/f32-qu8-vcvt-scalar-lrintf-u4.c.o
2025-03-21T20:24:47.5300252Z   [ 42%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_narrow_copy.cpp.o
2025-03-21T20:24:48.9434997Z   [ 42%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-qu8-vcvt/gen/f32-qu8-vcvt-sse2-u32.c.o
2025-03-21T20:24:48.9437531Z   [ 42%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-raddstoreexpminusmax/gen/f32-raddstoreexpminusmax-avx2-rr2-p5-u32-acc2.c.o
2025-03-21T20:24:48.9439905Z   [ 43%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_native_batch_norm.cpp.o
2025-03-21T20:24:48.9441677Z   [ 43%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_native_group_norm.cpp.o
2025-03-21T20:24:48.9444367Z   [ 45%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-raddstoreexpminusmax/gen/f32-raddstoreexpminusmax-avx512f-rr2-p5-u64-acc2.c.o
2025-03-21T20:24:48.9446605Z   [ 45%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_native_layer_norm.cpp.o
2025-03-21T20:24:48.9448152Z   [ 45%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_ne.cpp.o
2025-03-21T20:24:48.9449748Z   [ 45%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_neg.cpp.o
2025-03-21T20:24:48.9451209Z   [ 45%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_nonzero.cpp.o
2025-03-21T20:24:48.9453301Z   [ 45%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-raddstoreexpminusmax/gen/f32-raddstoreexpminusmax-scalar-rr2-p5-u4-acc2.c.o
2025-03-21T20:24:48.9456176Z   [ 45%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-raddstoreexpminusmax/gen/f32-raddstoreexpminusmax-sse2-rr2-p5-u16-acc2.c.o
2025-03-21T20:24:48.9458429Z   [ 45%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_ones.cpp.o
2025-03-21T20:24:48.9460339Z   [ 45%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-rdsum/gen/f32-rdsum-7p7x-minmax-avx-c32.c.o
2025-03-21T20:24:48.9462289Z   [ 45%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_pdist_forward.cpp.o
2025-03-21T20:24:48.9463885Z   [ 45%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_permute_copy.cpp.o
2025-03-21T20:24:48.9465954Z   [ 45%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-rdsum/gen/f32-rdsum-7p7x-minmax-avx512f-c64.c.o
2025-03-21T20:24:48.9468319Z   [ 45%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-rdsum/gen/f32-rdsum-7p7x-minmax-scalar.c.o
2025-03-21T20:24:48.9470552Z   [ 45%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-rdsum/gen/f32-rdsum-7p7x-minmax-sse-c16.c.o
2025-03-21T20:24:48.9472515Z   [ 45%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_pixel_shuffle.cpp.o
2025-03-21T20:24:48.9474164Z   [ 45%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_pixel_unshuffle.cpp.o
2025-03-21T20:24:48.9475980Z   [ 45%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-rminmax/gen/f32-rmax-avx-u32-acc4.c.o
2025-03-21T20:24:48.9477788Z   [ 45%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_pow.cpp.o
2025-03-21T20:24:48.9479338Z   [ 45%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_prod.cpp.o
2025-03-21T20:24:48.9481257Z   [ 45%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-rminmax/gen/f32-rmax-avx512f-u64-acc4.c.o
2025-03-21T20:24:48.9483292Z   [ 45%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_reciprocal.cpp.o
2025-03-21T20:24:48.9485271Z   [ 45%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-rminmax/gen/f32-rmax-scalar-u4-acc4.c.o
2025-03-21T20:24:48.9487275Z   [ 45%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_reflection_pad1d.cpp.o
2025-03-21T20:24:48.9489255Z   [ 45%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-rminmax/gen/f32-rmax-sse-u16-acc4.c.o
2025-03-21T20:24:48.9490653Z   [ 46%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_reflection_pad2d.cpp.o
2025-03-21T20:24:48.9491578Z   [ 46%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_reflection_pad3d.cpp.o
2025-03-21T20:24:48.9492872Z   [ 46%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-rminmax/gen/f32-rminmax-avx-u32-acc4.c.o
2025-03-21T20:24:48.9494087Z   [ 46%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-rminmax/gen/f32-rminmax-avx512f-u64-acc4.c.o
2025-03-21T20:24:48.9495101Z   [ 46%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_relu.cpp.o
2025-03-21T20:24:48.9495946Z   [ 46%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_remainder.cpp.o
2025-03-21T20:24:48.9496802Z   [ 46%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_repeat.cpp.o
2025-03-21T20:24:48.9497691Z   [ 46%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_repeat_interleave.cpp.o
2025-03-21T20:24:48.9498769Z   [ 46%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-rminmax/gen/f32-rminmax-scalar-u4-acc4.c.o
2025-03-21T20:24:48.9499850Z   [ 46%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_replication_pad1d.cpp.o
2025-03-21T20:24:48.9500916Z   [ 46%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-rminmax/gen/f32-rminmax-sse-u16-acc4.c.o
2025-03-21T20:24:48.9502063Z   [ 47%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-rsum/gen/f32-rsum-avx-u32-acc4.c.o
2025-03-21T20:24:48.9503093Z   [ 47%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_replication_pad2d.cpp.o
2025-03-21T20:24:48.9504140Z   [ 47%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-rsum/gen/f32-rsum-avx512f-u64-acc4.c.o
2025-03-21T20:24:48.9505185Z   [ 47%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_replication_pad3d.cpp.o
2025-03-21T20:24:48.9506066Z   [ 47%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_roll.cpp.o
2025-03-21T20:24:48.9507056Z   [ 47%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-rsum/gen/f32-rsum-scalar-u4-acc4.c.o
2025-03-21T20:24:48.9508194Z   [ 47%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-rsum/gen/f32-rsum-sse-u16-acc4.c.o
2025-03-21T20:24:48.9509174Z   [ 47%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_round.cpp.o
2025-03-21T20:24:48.9509990Z   [ 47%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_rsqrt.cpp.o
2025-03-21T20:24:48.9510991Z   [ 47%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-spmm/gen/f32-spmm-32x1-minmax-sse.c.o
2025-03-21T20:24:48.9511984Z   [ 47%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_rsub.cpp.o
2025-03-21T20:24:48.9512989Z   [ 47%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-spmm/gen/f32-spmm-8x1-minmax-scalar.c.o
2025-03-21T20:24:48.9514026Z   [ 47%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_scalar_tensor.cpp.o
2025-03-21T20:24:48.9514895Z   [ 47%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_scatter.cpp.o
2025-03-21T20:24:48.9515750Z   [ 47%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_scatter_add.cpp.o
2025-03-21T20:24:48.9516607Z   [ 48%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_select_copy.cpp.o
2025-03-21T20:24:48.9517915Z   [ 48%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-spmm/gen/f32-spmm-8x2-minmax-scalar.c.o
2025-03-21T20:24:48.9519373Z   [ 48%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-spmm/gen/f32-spmm-8x4-minmax-scalar.c.o
2025-03-21T20:24:48.9521471Z   [ 48%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vadd-avx-u16.c.o
2025-03-21T20:24:48.9523478Z   [ 48%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vadd-avx512f-u32.c.o
2025-03-21T20:24:48.9524975Z   [ 48%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vadd-scalar-u8.c.o
2025-03-21T20:24:48.9526132Z   [ 48%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vadd-sse-u8.c.o
2025-03-21T20:24:48.9527370Z   [ 48%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_select_scatter.cpp.o
2025-03-21T20:24:48.9528260Z   [ 48%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_sigmoid.cpp.o
2025-03-21T20:24:50.3258226Z   [ 48%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vaddc-avx-u16.c.o
2025-03-21T20:24:50.3260246Z   [ 48%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vaddc-avx512f-u32.c.o
2025-03-21T20:24:50.3262215Z   [ 48%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vaddc-scalar-u8.c.o
2025-03-21T20:24:50.3264261Z   [ 48%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vaddc-sse-u8.c.o
2025-03-21T20:24:50.3266389Z   [ 50%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vdiv-avx-u16.c.o
2025-03-21T20:24:50.3268590Z   [ 50%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vdiv-avx512f-u32.c.o
2025-03-21T20:24:50.3270717Z   [ 50%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vdiv-scalar-u2.c.o
2025-03-21T20:24:50.3272863Z   [ 50%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vdiv-sse-u8.c.o
2025-03-21T20:24:50.3274696Z   [ 50%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_sign.cpp.o
2025-03-21T20:24:50.3276537Z   [ 50%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vdivc-avx-u16.c.o
2025-03-21T20:24:50.3278378Z   [ 50%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_sin.cpp.o
2025-03-21T20:24:50.3280211Z   [ 50%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vdivc-avx512f-u32.c.o
2025-03-21T20:24:50.3282414Z   [ 50%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vdivc-scalar-u2.c.o
2025-03-21T20:24:50.3284515Z   [ 50%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vdivc-sse-u8.c.o
2025-03-21T20:24:50.3286656Z   [ 50%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vmax-avx-u16.c.o
2025-03-21T20:24:50.3288494Z   [ 50%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_sinh.cpp.o
2025-03-21T20:24:50.3290460Z   [ 50%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vmax-avx512f-u32.c.o
2025-03-21T20:24:50.3292621Z   [ 50%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vmax-scalar-u8.c.o
2025-03-21T20:24:50.3295007Z   [ 50%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vmax-sse-u8.c.o
2025-03-21T20:24:50.3297283Z   [ 50%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vmaxc-avx-u16.c.o
2025-03-21T20:24:50.3299182Z   [ 50%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_slice_copy.cpp.o
2025-03-21T20:24:50.3301100Z   [ 50%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vmaxc-avx512f-u32.c.o
2025-03-21T20:24:50.3303278Z   [ 50%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vmaxc-scalar-u8.c.o
2025-03-21T20:24:50.3305447Z   [ 50%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vmaxc-sse-u8.c.o
2025-03-21T20:24:50.3307393Z   [ 50%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_slice_scatter.cpp.o
2025-03-21T20:24:50.3309361Z   [ 51%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vmin-avx-u16.c.o
2025-03-21T20:24:50.3311543Z   [ 51%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vmin-avx512f-u32.c.o
2025-03-21T20:24:50.3313818Z   [ 51%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vmin-scalar-u8.c.o
2025-03-21T20:24:50.3315705Z   [ 51%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_softmax.cpp.o
2025-03-21T20:24:50.3317349Z   [ 51%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_split_copy.cpp.o
2025-03-21T20:24:50.3319236Z   [ 51%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vmin-sse-u8.c.o
2025-03-21T20:24:50.3321414Z   [ 51%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vminc-avx-u16.c.o
2025-03-21T20:24:50.3323644Z   [ 51%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vminc-avx512f-u32.c.o
2025-03-21T20:24:50.3325849Z   [ 51%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vminc-scalar-u8.c.o
2025-03-21T20:24:50.3328045Z   [ 51%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vminc-sse-u8.c.o
2025-03-21T20:24:50.3330138Z   [ 51%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_split_with_sizes_copy.cpp.o
2025-03-21T20:24:50.3331831Z   [ 51%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_sqrt.cpp.o
2025-03-21T20:24:50.3333600Z   [ 51%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_squeeze_copy.cpp.o
2025-03-21T20:24:50.3335288Z   [ 51%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_stack.cpp.o
2025-03-21T20:24:50.3336854Z   [ 51%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_sub.cpp.o
2025-03-21T20:24:50.3338721Z   [ 51%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vmul-avx-u16.c.o
2025-03-21T20:24:50.3340927Z   [ 51%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vmul-avx512f-u32.c.o
2025-03-21T20:24:50.3343135Z   [ 51%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vmul-scalar-u8.c.o
2025-03-21T20:24:50.3345006Z   [ 51%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_sum.cpp.o
2025-03-21T20:24:50.3346767Z   [ 52%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_t_copy.cpp.o
2025-03-21T20:24:50.3348808Z   [ 52%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vmul-sse-u8.c.o
2025-03-21T20:24:50.3350934Z   [ 52%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vmulc-avx-u16.c.o
2025-03-21T20:24:50.3352797Z   [ 52%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_tan.cpp.o
2025-03-21T20:24:50.3354345Z   [ 52%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_tanh.cpp.o
2025-03-21T20:24:50.3355942Z   [ 52%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_to_copy.cpp.o
2025-03-21T20:24:50.3357884Z   [ 52%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vmulc-avx512f-u32.c.o
2025-03-21T20:24:50.3359830Z   [ 52%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_topk.cpp.o
2025-03-21T20:24:50.3361496Z   [ 52%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_transpose_copy.cpp.o
2025-03-21T20:24:50.3363168Z   [ 52%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_tril.cpp.o
2025-03-21T20:24:50.3365070Z   [ 52%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vmulc-scalar-u8.c.o
2025-03-21T20:24:50.3367228Z   [ 52%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vmulc-sse-u8.c.o
2025-03-21T20:24:50.3369122Z   [ 52%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_trunc.cpp.o
2025-03-21T20:24:50.3371122Z   [ 53%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vprelu-avx-u16.c.o
2025-03-21T20:24:50.3373090Z   [ 53%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_unbind_copy.cpp.o
2025-03-21T20:24:50.3374745Z   [ 53%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_unfold_copy.cpp.o
2025-03-21T20:24:50.3376462Z   [ 53%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_unsqueeze_copy.cpp.o
2025-03-21T20:24:50.3378478Z   [ 53%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vprelu-avx512f-u32.c.o
2025-03-21T20:24:50.3380526Z   [ 53%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_upsample_bilinear2d.cpp.o
2025-03-21T20:24:51.6470545Z   [ 53%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vprelu-scalar-u8.c.o
2025-03-21T20:24:51.6472466Z   [ 53%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_upsample_nearest2d.cpp.o
2025-03-21T20:24:51.6474354Z   [ 53%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vprelu-sse2-u8.c.o
2025-03-21T20:24:51.6476465Z   [ 53%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vpreluc-avx-u16.c.o
2025-03-21T20:24:51.6478227Z   [ 53%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_var.cpp.o
2025-03-21T20:24:51.6479685Z   [ 53%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_view_copy.cpp.o
2025-03-21T20:24:51.6481206Z   [ 54%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_where.cpp.o
2025-03-21T20:24:51.6483008Z   [ 54%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vpreluc-avx512f-u32.c.o
2025-03-21T20:24:51.6485450Z   [ 54%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vpreluc-scalar-u8.c.o
2025-03-21T20:24:51.6487762Z   [ 54%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vpreluc-sse2-u8.c.o
2025-03-21T20:24:51.6489664Z   [ 54%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_zeros.cpp.o
2025-03-21T20:24:51.6491355Z   [ 54%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/pattern/unary_ufunc_realh.cpp.o
2025-03-21T20:24:51.6493326Z   [ 54%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vrdivc-avx-u16.c.o
2025-03-21T20:24:51.6495492Z   [ 54%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vrdivc-avx512f-u32.c.o
2025-03-21T20:24:51.6497536Z   [ 54%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/pattern/unary_ufunc_realhb_to_bool.cpp.o
2025-03-21T20:24:51.6499547Z   [ 54%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vrdivc-scalar-u2.c.o
2025-03-21T20:24:51.6501543Z   [ 54%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/pattern/unary_ufunc_realhbbf16_to_floathbf16.cpp.o
2025-03-21T20:24:51.6503487Z   [ 54%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vrdivc-sse-u8.c.o
2025-03-21T20:24:51.6505564Z   [ 54%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vrpreluc-avx-u16.c.o
2025-03-21T20:24:51.6507801Z   [ 54%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vrpreluc-avx512f-u32.c.o
2025-03-21T20:24:51.6510083Z   [ 54%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vrpreluc-scalar-u8.c.o
2025-03-21T20:24:51.6512268Z   [ 56%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vrpreluc-sse2-u8.c.o
2025-03-21T20:24:51.6514298Z   [ 56%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/activation_ops_util.cpp.o
2025-03-21T20:24:51.6516204Z   [ 56%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vrsubc-avx-u16.c.o
2025-03-21T20:24:51.6518063Z   [ 56%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/advanced_index_util.cpp.o
2025-03-21T20:24:51.6520035Z   [ 56%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vrsubc-avx512f-u32.c.o
2025-03-21T20:24:51.6522120Z   [ 56%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vrsubc-scalar-u8.c.o
2025-03-21T20:24:51.6524263Z   [ 56%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vrsubc-sse-u8.c.o
2025-03-21T20:24:51.6526410Z   [ 56%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vsqrdiff-avx-u16.c.o
2025-03-21T20:24:51.6528266Z   [ 56%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/broadcast_util.cpp.o
2025-03-21T20:24:51.6530297Z   [ 56%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vsqrdiff-avx512f-u32.c.o
2025-03-21T20:24:51.6532515Z   [ 56%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/copy_ops_util.cpp.o
2025-03-21T20:24:51.6534324Z   [ 56%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vsqrdiff-scalar-u8.c.o
2025-03-21T20:24:51.6536585Z   [ 56%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/delinearize_index.cpp.o
2025-03-21T20:24:51.6538329Z   [ 56%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vsqrdiff-sse-u8.c.o
2025-03-21T20:24:51.6540367Z   [ 56%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vsqrdiffc-avx-u16.c.o
2025-03-21T20:24:51.6542419Z   [ 56%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vsqrdiffc-avx512f-u32.c.o
2025-03-21T20:24:51.6544144Z   [ 56%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/distance_util.cpp.o
2025-03-21T20:24:51.6545710Z   [ 56%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/dtype_util.cpp.o
2025-03-21T20:24:51.6547497Z   [ 56%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vsqrdiffc-scalar-u8.c.o
2025-03-21T20:24:51.6549478Z   [ 56%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vsqrdiffc-sse-u8.c.o
2025-03-21T20:24:51.6551188Z   [ 56%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/index_util.cpp.o
2025-03-21T20:24:51.6552844Z   [ 56%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vsub-avx-u16.c.o
2025-03-21T20:24:51.6553893Z   [ 56%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/kernel_ops_util.cpp.o
2025-03-21T20:24:51.6554805Z   [ 56%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/matmul_ops_util.cpp.o
2025-03-21T20:24:51.6555773Z   [ 56%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/normalization_ops_util.cpp.o
2025-03-21T20:24:51.6556736Z   [ 57%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/padding_util.cpp.o
2025-03-21T20:24:51.6557766Z   [ 57%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vsub-avx512f-u32.c.o
2025-03-21T20:24:51.6558900Z   [ 57%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vsub-scalar-u8.c.o
2025-03-21T20:24:51.6560013Z   [ 58%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vsub-sse-u8.c.o
2025-03-21T20:24:51.6561122Z   [ 58%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vsubc-avx-u16.c.o
2025-03-21T20:24:51.6562282Z   [ 58%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vsubc-avx512f-u32.c.o
2025-03-21T20:24:51.6563429Z   [ 58%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vsubc-scalar-u8.c.o
2025-03-21T20:24:51.6564433Z   [ 58%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/reduce_util.cpp.o
2025-03-21T20:24:51.6565440Z   [ 58%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vbinary/gen/f32-vsubc-sse-u8.c.o
2025-03-21T20:24:51.6566444Z   [ 58%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/repeat_util.cpp.o
2025-03-21T20:24:51.6567362Z   [ 58%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/select_copy_util.cpp.o
2025-03-21T20:24:51.6568388Z   [ 58%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vclamp/gen/f32-vclamp-avx-u16.c.o
2025-03-21T20:24:51.6569514Z   [ 58%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/slice_util.cpp.o
2025-03-21T20:24:51.6570592Z   [ 58%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/upsample_util.cpp.o
2025-03-21T20:24:51.6571615Z   [ 58%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vclamp/gen/f32-vclamp-avx512f-u16.c.o
2025-03-21T20:24:52.7104401Z   [ 58%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vclamp/gen/f32-vclamp-scalar-u4.c.o
2025-03-21T20:24:52.7107343Z   [ 58%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vclamp/gen/f32-vclamp-sse-u8.c.o
2025-03-21T20:24:52.7110167Z   [ 58%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vcmul/gen/f32-vcmul-avx512f-u32.c.o
2025-03-21T20:24:52.7112428Z   [ 58%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vcmul/gen/f32-vcmul-fma3-u16.c.o
2025-03-21T20:24:52.7114764Z   [ 58%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vcmul/gen/f32-vcmul-scalar-u4.c.o
2025-03-21T20:24:52.7117043Z   [ 58%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vcmul/gen/f32-vcmul-sse-u8.c.o
2025-03-21T20:24:52.7119293Z   [ 58%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vcopysign/gen/f32-vcopysign-avx.c.o
2025-03-21T20:24:52.7121570Z   [ 58%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vcopysign/gen/f32-vcopysign-avx512f.c.o
2025-03-21T20:24:52.7123270Z   [ 58%] Linking CXX static library liboptimized_portable_kernels.a
2025-03-21T20:24:52.7125581Z   [ 58%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vcopysign/gen/f32-vcopysign-scalar.c.o
2025-03-21T20:24:52.7127825Z   [ 59%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vcopysign/gen/f32-vcopysign-sse2.c.o
2025-03-21T20:24:52.7130198Z   [ 59%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vcopysign/gen/f32-vcopysignc-avx.c.o
2025-03-21T20:24:52.7133079Z   [ 59%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vcopysign/gen/f32-vcopysignc-avx512f.c.o
2025-03-21T20:24:52.7134920Z   [ 59%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vcopysign/gen/f32-vcopysignc-scalar.c.o
2025-03-21T20:24:52.7137184Z   [ 59%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vcopysign/gen/f32-vcopysignc-sse2.c.o
2025-03-21T20:24:52.7139454Z   [ 59%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vcopysign/gen/f32-vrcopysignc-avx.c.o
2025-03-21T20:24:52.7141772Z   [ 59%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vcopysign/gen/f32-vrcopysignc-avx512f.c.o
2025-03-21T20:24:52.7144129Z   [ 59%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vcopysign/gen/f32-vrcopysignc-scalar.c.o
2025-03-21T20:24:52.7146443Z   [ 59%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vcopysign/gen/f32-vrcopysignc-sse2.c.o
2025-03-21T20:24:52.7148812Z   [ 59%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-velu/gen/f32-velu-avx-rr2-lut4-p4-perm-u32.c.o
2025-03-21T20:24:52.7151259Z   [ 59%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-velu/gen/f32-velu-avx2-rr1-lut4-p4-perm-u56.c.o
2025-03-21T20:24:52.7152842Z   [ 59%] Built target optimized_portable_kernels
2025-03-21T20:24:52.7154341Z   [ 59%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-velu/gen/f32-velu-avx512f-rr1-p6-u128.c.o
2025-03-21T20:24:52.7156267Z   [ 59%] Merging kernel yaml files
2025-03-21T20:24:52.7157728Z   [ 59%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-velu/gen/f32-velu-scalar-rr2-lut16-p3-u2.c.o
2025-03-21T20:24:52.7160527Z   [ 59%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-velu/gen/f32-velu-scalar-rr2-lut16-p3-u4.c.o
2025-03-21T20:24:52.7162909Z   [ 59%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-velu/gen/f32-velu-sse2-rr2-lut16-p3-u12.c.o
2025-03-21T20:24:52.7165146Z   [ 60%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vexp/gen/f32-vexp-scalar-exp.c.o
2025-03-21T20:24:52.7167391Z   [ 60%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vgelu/gen/f32-vgelu-avx-rational-12-10-div.c.o
2025-03-21T20:24:52.7169908Z   [ 60%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vgelu/gen/f32-vgelu-avx512f-rational-12-10-nr.c.o
2025-03-21T20:24:52.7172614Z   [ 60%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vgelu/gen/f32-vgelu-fma3-rational-12-10-div.c.o
2025-03-21T20:24:52.7175084Z   [ 60%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vgelu/gen/f32-vgelu-scalar-rational-12-10-div.c.o
2025-03-21T20:24:52.7177529Z   [ 60%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vgelu/gen/f32-vgelu-sse2-rational-12-10-div.c.o
2025-03-21T20:24:52.7179266Z   [ 60%] Generating selected_operators.yaml for optimized_native_cpu_ops_lib
2025-03-21T20:24:52.7180939Z   [ 60%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vhswish/gen/f32-vhswish-avx-u16.c.o
2025-03-21T20:24:52.7183199Z   [ 60%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vhswish/gen/f32-vhswish-avx512f-u16.c.o
2025-03-21T20:24:52.7185483Z   [ 60%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vhswish/gen/f32-vhswish-fma3-u16.c.o
2025-03-21T20:24:52.7187754Z   [ 60%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vhswish/gen/f32-vhswish-scalar-u4.c.o
2025-03-21T20:24:52.7190019Z   [ 60%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vhswish/gen/f32-vhswish-sse-u8.c.o
2025-03-21T20:24:52.7192342Z   [ 60%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vlog/gen/f32-vlog-avx2-rational-3-3-div.c.o
2025-03-21T20:24:52.7194739Z   [ 60%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vlog/gen/f32-vlog-avx512f-rational-3-3-div.c.o
2025-03-21T20:24:52.7197132Z   [ 60%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vlog/gen/f32-vlog-fma3-rational-3-3-div.c.o
2025-03-21T20:24:52.7199474Z   [ 60%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vlog/gen/f32-vlog-scalar-rational-3-3-div.c.o
2025-03-21T20:24:52.7201899Z   [ 60%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vlog/gen/f32-vlog-sse2-rational-3-3-div.c.o
2025-03-21T20:24:52.7204212Z   [ 62%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vlrelu/gen/f32-vlrelu-avx-u16.c.o
2025-03-21T20:24:52.7206445Z   [ 62%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vlrelu/gen/f32-vlrelu-avx512f-u16.c.o
2025-03-21T20:24:52.7207937Z   [ 62%] Generating code for kernel registration
2025-03-21T20:24:52.7209650Z   [ 62%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vlrelu/gen/f32-vlrelu-scalar-u4.c.o
2025-03-21T20:24:52.7211971Z   [ 62%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vlrelu/gen/f32-vlrelu-sse-u8.c.o
2025-03-21T20:24:52.7214123Z   [ 62%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vlrelu/gen/f32-vlrelu-sse41-u8.c.o
2025-03-21T20:24:52.7216505Z   [ 62%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vmulcaddc/gen/f32-vmulcaddc-c1-minmax-scalar-2x.c.o
2025-03-21T20:24:52.7219008Z   [ 62%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vmulcaddc/gen/f32-vmulcaddc-c4-minmax-sse-2x.c.o
2025-03-21T20:24:52.7221350Z   [ 62%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vrelu/gen/f32-vrelu-scalar-u8.c.o
2025-03-21T20:24:52.7223534Z   [ 62%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vrnd/gen/f32-vrndd-avx-u16.c.o
2025-03-21T20:24:52.7225691Z   [ 62%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vrnd/gen/f32-vrndd-avx512f-u16.c.o
2025-03-21T20:24:52.7227898Z   [ 62%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vrnd/gen/f32-vrndd-scalar-libm-u1.c.o
2025-03-21T20:24:52.7230166Z   [ 62%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vrnd/gen/f32-vrndd-scalar-libm-u4.c.o
2025-03-21T20:24:52.7233671Z   [ 62%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vrnd/gen/f32-vrndd-sse2-u8.c.o
2025-03-21T20:24:52.7235835Z   [ 62%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vrnd/gen/f32-vrndd-sse41-u8.c.o
2025-03-21T20:24:53.8404115Z   [ 62%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vrnd/gen/f32-vrndne-avx-u16.c.o
2025-03-21T20:24:53.8406357Z   [ 62%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vrnd/gen/f32-vrndne-avx512f-u16.c.o
2025-03-21T20:24:53.8408678Z   [ 63%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vrnd/gen/f32-vrndne-scalar-libm-u1.c.o
2025-03-21T20:24:53.8410963Z   [ 63%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vrnd/gen/f32-vrndne-scalar-libm-u4.c.o
2025-03-21T20:24:53.8413137Z   [ 63%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vrnd/gen/f32-vrndne-sse2-u8.c.o
2025-03-21T20:24:53.8415248Z   [ 63%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vrnd/gen/f32-vrndne-sse41-u8.c.o
2025-03-21T20:24:53.8417378Z   [ 63%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vrnd/gen/f32-vrndu-avx-u16.c.o
2025-03-21T20:24:53.8419505Z   [ 63%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vrnd/gen/f32-vrndu-avx512f-u16.c.o
2025-03-21T20:24:53.8421658Z   [ 63%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vrnd/gen/f32-vrndu-scalar-libm-u1.c.o
2025-03-21T20:24:53.8423865Z   [ 63%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vrnd/gen/f32-vrndu-scalar-libm-u4.c.o
2025-03-21T20:24:53.8426006Z   [ 63%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vrnd/gen/f32-vrndu-sse2-u8.c.o
2025-03-21T20:24:53.8428096Z   [ 63%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vrnd/gen/f32-vrndu-sse41-u8.c.o
2025-03-21T20:24:53.8430178Z   [ 63%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vrnd/gen/f32-vrndz-avx-u16.c.o
2025-03-21T20:24:53.8433755Z   [ 63%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vrnd/gen/f32-vrndz-avx512f-u16.c.o
2025-03-21T20:24:53.8435992Z   [ 63%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vrnd/gen/f32-vrndz-scalar-libm-u1.c.o
2025-03-21T20:24:53.8438215Z   [ 63%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vrnd/gen/f32-vrndz-scalar-libm-u4.c.o
2025-03-21T20:24:53.8440369Z   [ 63%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vrnd/gen/f32-vrndz-sse2-u8.c.o
2025-03-21T20:24:53.8442464Z   [ 64%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vrnd/gen/f32-vrndz-sse41-u8.c.o
2025-03-21T20:24:53.8444597Z   [ 64%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vrsqrt/gen/f32-vrsqrt-avx-rsqrt-u16.c.o
2025-03-21T20:24:53.8446916Z   [ 64%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vrsqrt/gen/f32-vrsqrt-avx512f-rsqrt-u32.c.o
2025-03-21T20:24:53.8449290Z   [ 64%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vrsqrt/gen/f32-vrsqrt-fma3-rsqrt-u16.c.o
2025-03-21T20:24:53.8451583Z   [ 64%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vrsqrt/gen/f32-vrsqrt-scalar-rsqrt-u1.c.o
2025-03-21T20:24:53.8453870Z   [ 64%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vrsqrt/gen/f32-vrsqrt-scalar-rsqrt-u4.c.o
2025-03-21T20:24:53.8456123Z   [ 64%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vrsqrt/gen/f32-vrsqrt-sse-rsqrt-u8.c.o
2025-03-21T20:24:53.8458495Z   [ 64%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vsigmoid/gen/f32-vsigmoid-avx-rr2-p5-nr2-u40.c.o
2025-03-21T20:24:53.8460945Z   [ 64%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vsigmoid/gen/f32-vsigmoid-avx2-rr1-p5-div-u40.c.o
2025-03-21T20:24:53.8463460Z   [ 64%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vsigmoid/gen/f32-vsigmoid-scalar-rr2-lut64-p2-div-u2.c.o
2025-03-21T20:24:53.8466197Z   [ 64%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vsigmoid/gen/f32-vsigmoid-avx512f-rr2-lut32-p2-perm2-scalef-div-u64.c.o
2025-03-21T20:24:53.8468893Z   [ 64%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vsigmoid/gen/f32-vsigmoid-sse2-rr2-lut64-p2-div-u8.c.o
2025-03-21T20:24:53.8471434Z   [ 64%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vsigmoid/gen/f32-vsigmoid-sse41-rr2-lut64-p2-div-u8.c.o
2025-03-21T20:24:53.8473842Z   [ 64%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vsqrt/gen/f32-vsqrt-avx-rsqrt-u16.c.o
2025-03-21T20:24:53.8476087Z   [ 64%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vsqrt/gen/f32-vsqrt-avx512f-rsqrt-u16.c.o
2025-03-21T20:24:53.8478335Z   [ 64%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vsqrt/gen/f32-vsqrt-fma3-rsqrt-u16.c.o
2025-03-21T20:24:53.8480569Z   [ 65%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vsqrt/gen/f32-vsqrt-scalar-sqrt-u1.c.o
2025-03-21T20:24:53.8482791Z   [ 65%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vsqrt/gen/f32-vsqrt-sse-rsqrt-u12.c.o
2025-03-21T20:24:53.8485050Z   [ 65%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vtanh/gen/f32-vtanh-avx-rational-9-8-div.c.o
2025-03-21T20:24:53.8487731Z   [ 65%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vtanh/gen/f32-vtanh-avx512f-rational-9-8-nr.c.o
2025-03-21T20:24:53.8490206Z   [ 65%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vtanh/gen/f32-vtanh-fma3-rational-9-8-div.c.o
2025-03-21T20:24:53.8492576Z   [ 65%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vtanh/gen/f32-vtanh-scalar-rational-9-8-div.c.o
2025-03-21T20:24:53.8494922Z   [ 65%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vtanh/gen/f32-vtanh-sse2-rational-9-8-div.c.o
2025-03-21T20:24:53.8497118Z   [ 65%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vunary/gen/f32-vabs-avx.c.o
2025-03-21T20:24:53.8499188Z   [ 65%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vunary/gen/f32-vabs-avx512f.c.o
2025-03-21T20:24:53.8501288Z   [ 65%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vunary/gen/f32-vabs-scalar.c.o
2025-03-21T20:24:53.8503328Z   [ 65%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vunary/gen/f32-vabs-sse2.c.o
2025-03-21T20:24:53.8505370Z   [ 65%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vunary/gen/f32-vneg-avx.c.o
2025-03-21T20:24:53.8507438Z   [ 65%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vunary/gen/f32-vneg-avx512f.c.o
2025-03-21T20:24:53.8509529Z   [ 65%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vunary/gen/f32-vneg-scalar.c.o
2025-03-21T20:24:53.8511596Z   [ 65%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vunary/gen/f32-vneg-sse2.c.o
2025-03-21T20:24:53.8513651Z   [ 65%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vunary/gen/f32-vsqr-avx.c.o
2025-03-21T20:24:53.8515712Z   [ 67%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vunary/gen/f32-vsqr-avx512f.c.o
2025-03-21T20:24:53.8517785Z   [ 67%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vunary/gen/f32-vsqr-scalar.c.o
2025-03-21T20:24:53.8519839Z   [ 67%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/f32-vunary/gen/f32-vsqr-sse2.c.o
2025-03-21T20:24:53.8522148Z   [ 67%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f16-qb4w-gemm/gen/qd8-f16-qb4w-gemm-1x8c8-minmax-avx2.c.o
2025-03-21T20:24:53.8524705Z   [ 67%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f16-qb4w-gemm/gen/qd8-f16-qb4w-gemm-3x8c8-minmax-avx2.c.o
2025-03-21T20:24:53.8527381Z   [ 67%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f16-qc4w-gemm/gen/qd8-f16-qc4w-gemm-1x8c8-minmax-avx2-madd-prfm.c.o
2025-03-21T20:24:53.8530226Z   [ 67%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f16-qc4w-gemm/gen/qd8-f16-qc4w-gemm-4x8c8-minmax-avx2-madd-prfm.c.o
2025-03-21T20:24:54.9262993Z   [ 67%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f16-qc8w-gemm/gen/qd8-f16-qc8w-gemm-1x8c8-minmax-avx2.c.o
2025-03-21T20:24:54.9265710Z   [ 67%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f16-qc8w-gemm/gen/qd8-f16-qc8w-gemm-3x8c8-minmax-avx2.c.o
2025-03-21T20:24:54.9268388Z   [ 67%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f16-qc8w-igemm/gen/qd8-f16-qc8w-igemm-1x8c8-minmax-avx2.c.o
2025-03-21T20:24:54.9271619Z   [ 67%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f16-qc8w-igemm/gen/qd8-f16-qc8w-igemm-3x8c8-minmax-avx2.c.o
2025-03-21T20:24:54.9274446Z   [ 67%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qb4w-gemm/gen/qd8-f32-qb4w-gemm-14x16c8-minmax-avx512vnnigfni-prfm.c.o
2025-03-21T20:24:54.9277385Z   [ 67%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qb4w-gemm/gen/qd8-f32-qb4w-gemm-1x16c8-minmax-avx512vnni-prfm.c.o
2025-03-21T20:24:54.9280308Z   [ 67%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qb4w-gemm/gen/qd8-f32-qb4w-gemm-1x16c8-minmax-avx512vnnigfni-prfm.c.o
2025-03-21T20:24:54.9283116Z   [ 67%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qb4w-gemm/gen/qd8-f32-qb4w-gemm-1x4-minmax-scalar.c.o
2025-03-21T20:24:54.9285815Z   [ 67%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qb4w-gemm/gen/qd8-f32-qb4w-gemm-1x4c8-minmax-avx-ld128.c.o
2025-03-21T20:24:54.9288362Z   [ 68%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qb4w-gemm/gen/qd8-f32-qb4w-gemm-1x4c8-minmax-sse2-ld128.c.o
2025-03-21T20:24:54.9291220Z   [ 68%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qb4w-gemm/gen/qd8-f32-qb4w-gemm-1x4c8-minmax-sse41-ld128.c.o
2025-03-21T20:24:54.9293949Z   [ 68%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qb4w-gemm/gen/qd8-f32-qb4w-gemm-1x8c8-minmax-avx2.c.o
2025-03-21T20:24:54.9296669Z   [ 68%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qb4w-gemm/gen/qd8-f32-qb4w-gemm-3x4c8-minmax-sse41-ld128.c.o
2025-03-21T20:24:54.9299388Z   [ 68%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qb4w-gemm/gen/qd8-f32-qb4w-gemm-3x8c8-minmax-avx2.c.o
2025-03-21T20:24:54.9302033Z   [ 68%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qb4w-gemm/gen/qd8-f32-qb4w-gemm-4x4-minmax-scalar.c.o
2025-03-21T20:24:54.9304744Z   [ 68%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qb4w-gemm/gen/qd8-f32-qb4w-gemm-4x4c8-minmax-avx-ld128.c.o
2025-03-21T20:24:54.9307523Z   [ 68%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qb4w-gemm/gen/qd8-f32-qb4w-gemm-4x4c8-minmax-sse2-ld128.c.o
2025-03-21T20:24:54.9310311Z   [ 68%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qb4w-gemm/gen/qd8-f32-qb4w-gemm-8x16c8-minmax-avx512vnni-prfm.c.o
2025-03-21T20:24:54.9313642Z   [ 68%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc4w-gemm/gen/qd8-f32-qc4w-gemm-14x16c8-minmax-avx512vnnigfni-prfm.c.o
2025-03-21T20:24:54.9316942Z   [ 68%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc4w-gemm/gen/qd8-f32-qc4w-gemm-1x16c8-minmax-avx512skx-madd-prfm.c.o
2025-03-21T20:24:54.9319856Z   [ 68%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc4w-gemm/gen/qd8-f32-qc4w-gemm-1x16c8-minmax-avx512vnni-prfm.c.o
2025-03-21T20:24:54.9322912Z   [ 68%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc4w-gemm/gen/qd8-f32-qc4w-gemm-1x16c8-minmax-avx512vnnigfni-prfm.c.o
2025-03-21T20:24:54.9325717Z   [ 68%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc4w-gemm/gen/qd8-f32-qc4w-gemm-1x4-minmax-scalar.c.o
2025-03-21T20:24:54.9328511Z   [ 68%] Building CXX object configurations/CMakeFiles/optimized_native_cpu_ops_lib.dir/optimized_native_cpu_ops_lib/RegisterCodegenUnboxedKernelsEverything.cpp.o
2025-03-21T20:24:54.9331432Z   [ 68%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc4w-gemm/gen/qd8-f32-qc4w-gemm-1x4c8-minmax-sse2-ld128.c.o
2025-03-21T20:24:54.9334184Z   [ 69%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc4w-gemm/gen/qd8-f32-qc4w-gemm-1x4c8-minmax-ssse3-madd.c.o
2025-03-21T20:24:54.9336992Z   [ 69%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc4w-gemm/gen/qd8-f32-qc4w-gemm-1x8c8-minmax-avx2-madd-prfm.c.o
2025-03-21T20:24:54.9339749Z   [ 69%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc4w-gemm/gen/qd8-f32-qc4w-gemm-4x4-minmax-scalar.c.o
2025-03-21T20:24:54.9342462Z   [ 69%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc4w-gemm/gen/qd8-f32-qc4w-gemm-4x4c8-minmax-sse2-ld128.c.o
2025-03-21T20:24:54.9345237Z   [ 69%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc4w-gemm/gen/qd8-f32-qc4w-gemm-4x4c8-minmax-ssse3-madd.c.o
2025-03-21T20:24:54.9348058Z   [ 69%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc4w-gemm/gen/qd8-f32-qc4w-gemm-4x8c8-minmax-avx2-madd-prfm.c.o
2025-03-21T20:24:54.9350960Z   [ 69%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc4w-gemm/gen/qd8-f32-qc4w-gemm-8x16c8-minmax-avx512skx-madd-prfm.c.o
2025-03-21T20:24:54.9352919Z   [ 69%] Linking CXX static library liboptimized_native_cpu_ops_lib.a
2025-03-21T20:24:54.9353760Z   [ 69%] Built target optimized_native_cpu_ops_lib
2025-03-21T20:24:54.9355554Z   [ 69%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc4w-gemm/gen/qd8-f32-qc4w-gemm-8x16c8-minmax-avx512vnni-prfm.c.o
2025-03-21T20:24:54.9358469Z   [ 69%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc8w-gemm/gen/qd8-f32-qc8w-gemm-10x16c8-minmax-avx512vnni-prfm.c.o
2025-03-21T20:24:54.9361337Z   [ 69%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc8w-gemm/gen/qd8-f32-qc8w-gemm-1x16c8-minmax-avx512skx-prfm.c.o
2025-03-21T20:24:54.9364197Z   [ 69%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc8w-gemm/gen/qd8-f32-qc8w-gemm-1x16c8-minmax-avx512vnni-prfm.c.o
2025-03-21T20:24:54.9366963Z   [ 69%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc8w-gemm/gen/qd8-f32-qc8w-gemm-1x2-minmax-scalar.c.o
2025-03-21T20:24:54.9369667Z   [ 69%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc8w-gemm/gen/qd8-f32-qc8w-gemm-1x4-minmax-scalar.c.o
2025-03-21T20:24:54.9372395Z   [ 69%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc8w-gemm/gen/qd8-f32-qc8w-gemm-1x4c8-minmax-sse2-ld64.c.o
2025-03-21T20:24:54.9375419Z   [ 69%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc8w-gemm/gen/qd8-f32-qc8w-gemm-1x4c8-minmax-sse41-ld64.c.o
2025-03-21T20:24:54.9378129Z   [ 69%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc8w-gemm/gen/qd8-f32-qc8w-gemm-1x8c8-minmax-avx2.c.o
2025-03-21T20:24:54.9380789Z   [ 70%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc8w-gemm/gen/qd8-f32-qc8w-gemm-2x2-minmax-scalar.c.o
2025-03-21T20:24:54.9383438Z   [ 70%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc8w-gemm/gen/qd8-f32-qc8w-gemm-4x4-minmax-scalar.c.o
2025-03-21T20:24:54.9386331Z   [ 70%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc8w-gemm/gen/qd8-f32-qc8w-gemm-4x4c8-minmax-sse2-ld64.c.o
2025-03-21T20:24:54.9389191Z   [ 70%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc8w-gemm/gen/qd8-f32-qc8w-gemm-4x4c8-minmax-sse41-ld64.c.o
2025-03-21T20:24:54.9391891Z   [ 70%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc8w-gemm/gen/qd8-f32-qc8w-gemm-4x8c8-minmax-avx2.c.o
2025-03-21T20:24:54.9394642Z   [ 70%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc8w-gemm/gen/qd8-f32-qc8w-gemm-8x16c8-minmax-avx512skx-prfm.c.o
2025-03-21T20:24:55.7652146Z   [ 70%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc8w-igemm/gen/qd8-f32-qc8w-igemm-10x16c8-minmax-avx512vnni-prfm.c.o
2025-03-21T20:24:55.7653702Z   [ 70%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc8w-igemm/gen/qd8-f32-qc8w-igemm-1x16c8-minmax-avx512skx-prfm.c.o
2025-03-21T20:24:55.7655184Z   [ 70%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc8w-igemm/gen/qd8-f32-qc8w-igemm-1x16c8-minmax-avx512vnni-prfm.c.o
2025-03-21T20:24:55.7657416Z   [ 70%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc8w-igemm/gen/qd8-f32-qc8w-igemm-1x2-minmax-scalar.c.o
2025-03-21T20:24:55.7659953Z   [ 70%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc8w-igemm/gen/qd8-f32-qc8w-igemm-1x4-minmax-scalar.c.o
2025-03-21T20:24:55.7662368Z   [ 70%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc8w-igemm/gen/qd8-f32-qc8w-igemm-1x4c8-minmax-sse2-ld64.c.o
2025-03-21T20:24:55.7663820Z   [ 70%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc8w-igemm/gen/qd8-f32-qc8w-igemm-1x4c8-minmax-sse41-ld64.c.o
2025-03-21T20:24:55.7665223Z   [ 70%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc8w-igemm/gen/qd8-f32-qc8w-igemm-1x8c8-minmax-avx2.c.o
2025-03-21T20:24:55.7666581Z   [ 70%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc8w-igemm/gen/qd8-f32-qc8w-igemm-2x2-minmax-scalar.c.o
2025-03-21T20:24:55.7667935Z   [ 70%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc8w-igemm/gen/qd8-f32-qc8w-igemm-4x4-minmax-scalar.c.o
2025-03-21T20:24:55.7669402Z   [ 71%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc8w-igemm/gen/qd8-f32-qc8w-igemm-4x4c8-minmax-sse2-ld64.c.o
2025-03-21T20:24:55.7671790Z   [ 71%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc8w-igemm/gen/qd8-f32-qc8w-igemm-4x4c8-minmax-sse41-ld64.c.o
2025-03-21T20:24:55.7674003Z   [ 71%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc8w-igemm/gen/qd8-f32-qc8w-igemm-4x8c8-minmax-avx2.c.o
2025-03-21T20:24:55.7676166Z   [ 71%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qd8-f32-qc8w-igemm/gen/qd8-f32-qc8w-igemm-8x16c8-minmax-avx512skx-prfm.c.o
2025-03-21T20:24:55.7678549Z   [ 71%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-dwconv/gen/qs8-dwconv-25p16c-minmax-fp32-avx-mul16-add16.c.o
2025-03-21T20:24:55.7680780Z   [ 71%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-dwconv/gen/qs8-dwconv-25p16c-minmax-fp32-avx2-mul32.c.o
2025-03-21T20:24:55.7683032Z   [ 71%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-dwconv/gen/qs8-dwconv-25p1c-minmax-fp32-scalar-fmagic.c.o
2025-03-21T20:24:55.7685515Z   [ 71%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-dwconv/gen/qs8-dwconv-25p1c-minmax-fp32-scalar-imagic.c.o
2025-03-21T20:24:55.7687587Z   [ 71%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-dwconv/gen/qs8-dwconv-25p2c-minmax-fp32-scalar-lrintf.c.o
2025-03-21T20:24:55.7689989Z   [ 71%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-dwconv/gen/qs8-dwconv-25p32c-minmax-fp32-avx512skx-mul32.c.o
2025-03-21T20:24:55.7692164Z   [ 71%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-dwconv/gen/qs8-dwconv-25p8c-minmax-fp32-sse2-mul16-add16.c.o
2025-03-21T20:24:55.7694416Z   [ 71%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-dwconv/gen/qs8-dwconv-25p8c-minmax-fp32-sse41-mul16-add16.c.o
2025-03-21T20:24:55.7696770Z   [ 71%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-dwconv/gen/qs8-dwconv-9p16c-minmax-fp32-avx-mul16-add16.c.o
2025-03-21T20:24:55.7699141Z   [ 71%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-dwconv/gen/qs8-dwconv-9p16c-minmax-fp32-avx2-mul32.c.o
2025-03-21T20:24:55.7701740Z   [ 71%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-dwconv/gen/qs8-dwconv-9p1c-minmax-fp32-scalar-fmagic.c.o
2025-03-21T20:24:55.7704375Z   [ 73%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-dwconv/gen/qs8-dwconv-9p2c-minmax-fp32-scalar-imagic.c.o
2025-03-21T20:24:55.7706928Z   [ 73%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-dwconv/gen/qs8-dwconv-9p2c-minmax-fp32-scalar-lrintf.c.o
2025-03-21T20:24:55.7709524Z   [ 73%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-dwconv/gen/qs8-dwconv-9p32c-minmax-fp32-avx512skx-mul32.c.o
2025-03-21T20:24:55.7712030Z   [ 73%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-dwconv/gen/qs8-dwconv-9p8c-minmax-fp32-sse2-mul16-add16.c.o
2025-03-21T20:24:55.7714533Z   [ 73%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-dwconv/gen/qs8-dwconv-9p8c-minmax-fp32-sse41-mul16-add16.c.o
2025-03-21T20:24:55.7716865Z   [ 73%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-f16-vcvt/gen/qs8-f16-vcvt-avx2-u16.c.o
2025-03-21T20:24:55.7718867Z   [ 73%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-f32-vcvt/gen/qs8-f32-vcvt-avx-u32.c.o
2025-03-21T20:24:55.7720930Z   [ 73%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-f32-vcvt/gen/qs8-f32-vcvt-avx2-u16.c.o
2025-03-21T20:24:55.7723114Z   [ 73%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-f32-vcvt/gen/qs8-f32-vcvt-avx512skx-u32.c.o
2025-03-21T20:24:55.7725321Z   [ 73%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-f32-vcvt/gen/qs8-f32-vcvt-scalar-u1.c.o
2025-03-21T20:24:55.7727471Z   [ 73%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-f32-vcvt/gen/qs8-f32-vcvt-scalar-u4.c.o
2025-03-21T20:24:55.7729668Z   [ 73%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-f32-vcvt/gen/qs8-f32-vcvt-sse2-u32.c.o
2025-03-21T20:24:55.7731744Z   [ 73%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-f32-vcvt/gen/qs8-f32-vcvt-sse41-u16.c.o
2025-03-21T20:24:55.7736554Z   [ 73%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-packw/gen/qs8-packw-x16c8-gemm-goi-scalar.c.o
2025-03-21T20:24:55.7739313Z   [ 73%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-packw/gen/qs8-packw-x64c4-gemm-goi-scalar.c.o
2025-03-21T20:24:55.7741833Z   [ 73%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-25p16c-minmax-fp32-avx-mul16-add16.c.o
2025-03-21T20:24:55.7744479Z   [ 74%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-25p16c-minmax-fp32-avx2-mul32.c.o
2025-03-21T20:24:55.7747055Z   [ 74%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-25p1c-minmax-fp32-scalar-fmagic.c.o
2025-03-21T20:24:55.7749678Z   [ 74%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-25p1c-minmax-fp32-scalar-imagic.c.o
2025-03-21T20:24:55.7752321Z   [ 74%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-25p2c-minmax-fp32-scalar-lrintf.c.o
2025-03-21T20:24:55.7755001Z   [ 74%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-25p32c-minmax-fp32-avx512skx-mul32.c.o
2025-03-21T20:24:55.7757500Z   [ 74%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-25p8c-minmax-fp32-sse2-mul16.c.o
2025-03-21T20:24:55.7759975Z   [ 74%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-25p8c-minmax-fp32-sse41-mul16.c.o
2025-03-21T20:24:55.7762542Z   [ 74%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-3p16c-minmax-fp32-avx-mul16-add16.c.o
2025-03-21T20:24:55.7765179Z   [ 74%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-3p16c-minmax-fp32-avx2-mul32.c.o
2025-03-21T20:24:56.6119114Z   [ 74%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-3p1c-minmax-fp32-scalar-fmagic.c.o
2025-03-21T20:24:56.6122042Z   [ 74%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-3p2c-minmax-fp32-scalar-imagic.c.o
2025-03-21T20:24:56.6124889Z   [ 74%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-3p2c-minmax-fp32-scalar-lrintf.c.o
2025-03-21T20:24:56.6127718Z   [ 74%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-3p32c-minmax-fp32-avx512skx-mul32.c.o
2025-03-21T20:24:56.6130654Z   [ 74%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-3p8c-minmax-fp32-sse2-mul16.c.o
2025-03-21T20:24:56.6133611Z   [ 74%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-3p8c-minmax-fp32-sse41-mul16.c.o
2025-03-21T20:24:56.6136408Z   [ 74%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-9p16c-minmax-fp32-avx-mul16-add16.c.o
2025-03-21T20:24:56.6139260Z   [ 75%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-9p16c-minmax-fp32-avx2-mul32.c.o
2025-03-21T20:24:56.6142015Z   [ 75%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-9p1c-minmax-fp32-scalar-fmagic.c.o
2025-03-21T20:24:56.6145089Z   [ 75%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-9p2c-minmax-fp32-scalar-imagic.c.o
2025-03-21T20:24:56.6147908Z   [ 75%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-9p2c-minmax-fp32-scalar-lrintf.c.o
2025-03-21T20:24:56.6150743Z   [ 75%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-9p32c-minmax-fp32-avx512skx-mul32.c.o
2025-03-21T20:24:56.6153573Z   [ 75%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-9p8c-minmax-fp32-sse2-mul16.c.o
2025-03-21T20:24:56.6156325Z   [ 75%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-9p8c-minmax-fp32-sse41-mul16.c.o
2025-03-21T20:24:56.6159135Z   [ 75%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-gemm/gen/qs8-qc8w-gemm-1x16c8-minmax-fp32-avx512skx-prfm.c.o
2025-03-21T20:24:56.6161977Z   [ 75%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-gemm/gen/qs8-qc8w-gemm-1x16c8-minmax-fp32-avx512vnni-prfm.c.o
2025-03-21T20:24:56.6164753Z   [ 75%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-gemm/gen/qs8-qc8w-gemm-1x2-minmax-fp32-scalar-imagic.c.o
2025-03-21T20:24:56.6167499Z   [ 75%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-gemm/gen/qs8-qc8w-gemm-1x4-minmax-fp32-scalar-lrintf.c.o
2025-03-21T20:24:56.6170317Z   [ 75%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-gemm/gen/qs8-qc8w-gemm-1x4c8-minmax-fp32-avx-ld128.c.o
2025-03-21T20:24:56.6173022Z   [ 75%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-gemm/gen/qs8-qc8w-gemm-1x4c8-minmax-fp32-sse2-ld64.c.o
2025-03-21T20:24:56.6175645Z   [ 75%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-gemm/gen/qs8-qc8w-gemm-1x4c8-minmax-fp32-sse41-ld64.c.o
2025-03-21T20:24:56.6178277Z   [ 75%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-gemm/gen/qs8-qc8w-gemm-1x8c8-minmax-fp32-avx2.c.o
2025-03-21T20:24:56.6180937Z   [ 76%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-gemm/gen/qs8-qc8w-gemm-2x2-minmax-fp32-scalar-imagic.c.o
2025-03-21T20:24:56.6183650Z   [ 76%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-gemm/gen/qs8-qc8w-gemm-2x4c8-minmax-fp32-avx-ld128.c.o
2025-03-21T20:24:56.6186011Z   [ 76%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-gemm/gen/qs8-qc8w-gemm-3x4-minmax-fp32-scalar-lrintf.c.o
2025-03-21T20:24:56.6188702Z   [ 76%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-gemm/gen/qs8-qc8w-gemm-3x4c8-minmax-fp32-sse2-ld64.c.o
2025-03-21T20:24:56.6191441Z   [ 76%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-gemm/gen/qs8-qc8w-gemm-3x4c8-minmax-fp32-sse41-ld64.c.o
2025-03-21T20:24:56.6194072Z   [ 76%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-gemm/gen/qs8-qc8w-gemm-3x8c8-minmax-fp32-avx2.c.o
2025-03-21T20:24:56.6196770Z   [ 76%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-gemm/gen/qs8-qc8w-gemm-7x16c8-minmax-fp32-avx512skx-prfm.c.o
2025-03-21T20:24:56.6199592Z   [ 76%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-gemm/gen/qs8-qc8w-gemm-7x16c8-minmax-fp32-avx512vnni-prfm.c.o
2025-03-21T20:24:56.6202577Z   [ 76%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-igemm/gen/qs8-qc8w-igemm-1x16c8-minmax-avx512vnni-prfm.c.o
2025-03-21T20:24:56.6205434Z   [ 76%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-igemm/gen/qs8-qc8w-igemm-1x16c8-minmax-fp32-avx512skx-prfm.c.o
2025-03-21T20:24:56.6208180Z   [ 76%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-igemm/gen/qs8-qc8w-igemm-1x2-minmax-fp32-scalar-imagic.c.o
2025-03-21T20:24:56.6211071Z   [ 76%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-igemm/gen/qs8-qc8w-igemm-1x4-minmax-fp32-scalar-lrintf.c.o
2025-03-21T20:24:56.6213839Z   [ 76%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-igemm/gen/qs8-qc8w-igemm-1x4c8-minmax-fp32-avx-ld128.c.o
2025-03-21T20:24:56.6216636Z   [ 76%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-igemm/gen/qs8-qc8w-igemm-1x4c8-minmax-fp32-sse2-ld64.c.o
2025-03-21T20:24:56.6219417Z   [ 76%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-igemm/gen/qs8-qc8w-igemm-1x4c8-minmax-fp32-sse41-ld64.c.o
2025-03-21T20:24:56.6222116Z   [ 76%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-igemm/gen/qs8-qc8w-igemm-1x8c8-minmax-fp32-avx2.c.o
2025-03-21T20:24:56.6224845Z   [ 78%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-igemm/gen/qs8-qc8w-igemm-2x2-minmax-fp32-scalar-imagic.c.o
2025-03-21T20:24:56.6227626Z   [ 78%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-igemm/gen/qs8-qc8w-igemm-2x4c8-minmax-fp32-avx-ld128.c.o
2025-03-21T20:24:56.6230386Z   [ 78%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-igemm/gen/qs8-qc8w-igemm-3x4-minmax-fp32-scalar-lrintf.c.o
2025-03-21T20:24:56.6233298Z   [ 78%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-igemm/gen/qs8-qc8w-igemm-3x4c8-minmax-fp32-sse2-ld64.c.o
2025-03-21T20:24:56.6238500Z   [ 78%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-igemm/gen/qs8-qc8w-igemm-3x4c8-minmax-fp32-sse41-ld64.c.o
2025-03-21T20:24:56.6241215Z   [ 78%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-igemm/gen/qs8-qc8w-igemm-3x8c8-minmax-fp32-avx2.c.o
2025-03-21T20:24:56.6243933Z   [ 78%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-igemm/gen/qs8-qc8w-igemm-7x16c8-minmax-avx512vnni-prfm.c.o
2025-03-21T20:24:56.6246769Z   [ 78%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qc8w-igemm/gen/qs8-qc8w-igemm-7x16c8-minmax-fp32-avx512skx-prfm.c.o
2025-03-21T20:24:56.6249609Z   [ 78%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-qu8-packw/gen/qs8-qu8-packw-x16c8-gemm-goi-scalar.c.o
2025-03-21T20:24:56.6252167Z   [ 78%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-rdsum/gen/qs8-rdsum-7p7x-minmax-fp32-avx2-c64.c.o
2025-03-21T20:24:57.4438627Z   [ 78%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-rdsum/gen/qs8-rdsum-7p7x-minmax-fp32-avx512skx-c64.c.o
2025-03-21T20:24:57.4441233Z   [ 78%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-rdsum/gen/qs8-rdsum-7p7x-minmax-fp32-sse41-c64.c.o
2025-03-21T20:24:57.4443766Z   [ 78%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-rdsum/gen/qs8-rdsum-minmax-fp32-scalar-u1-acc1.c.o
2025-03-21T20:24:57.4446426Z   [ 78%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-rsum/gen/qs8-rsum-avx2-u64-acc2.c.o
2025-03-21T20:24:57.4448874Z   [ 78%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-rsum/gen/qs8-rsum-avx512skx-u128-acc2.c.o
2025-03-21T20:24:57.4451321Z   [ 78%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-rsum/gen/qs8-rsum-avx512vnni-u128-acc2.c.o
2025-03-21T20:24:57.4453541Z   [ 79%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-rsum/gen/qs8-rsum-scalar-u4.c.o
2025-03-21T20:24:57.4455751Z   [ 79%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-rsum/gen/qs8-rsum-ssse3-u32-acc2.c.o
2025-03-21T20:24:57.4458114Z   [ 79%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-vadd/gen/qs8-vadd-minmax-avx-mul32-ld32-u8.c.o
2025-03-21T20:24:57.4460604Z   [ 79%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-vadd/gen/qs8-vadd-minmax-avx2-mul32-ld64-u16.c.o
2025-03-21T20:24:57.4463105Z   [ 79%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-vadd/gen/qs8-vadd-minmax-avx512skx-mul32-ld128-u16.c.o
2025-03-21T20:24:57.4465541Z   [ 79%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-vadd/gen/qs8-vadd-minmax-scalar-u1.c.o
2025-03-21T20:24:57.4467894Z   [ 79%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-vadd/gen/qs8-vadd-minmax-scalar-u4.c.o
2025-03-21T20:24:57.4470297Z   [ 79%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-vadd/gen/qs8-vadd-minmax-sse2-mul16-ld64-u8.c.o
2025-03-21T20:24:57.4472811Z   [ 79%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-vadd/gen/qs8-vadd-minmax-sse41-mul16-ld64-u8.c.o
2025-03-21T20:24:57.4475340Z   [ 79%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-vaddc/gen/qs8-vaddc-minmax-avx-mul32-ld32-u8.c.o
2025-03-21T20:24:57.4477875Z   [ 79%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-vaddc/gen/qs8-vaddc-minmax-avx2-mul32-ld64-u16.c.o
2025-03-21T20:24:57.4480479Z   [ 79%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-vaddc/gen/qs8-vaddc-minmax-avx512skx-mul32-ld128-u16.c.o
2025-03-21T20:24:57.4482938Z   [ 79%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-vaddc/gen/qs8-vaddc-minmax-scalar-u1.c.o
2025-03-21T20:24:57.4485286Z   [ 79%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-vaddc/gen/qs8-vaddc-minmax-scalar-u4.c.o
2025-03-21T20:24:57.4487713Z   [ 79%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-vaddc/gen/qs8-vaddc-minmax-sse2-mul16-ld64-u8.c.o
2025-03-21T20:24:57.4490169Z   [ 79%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-vaddc/gen/qs8-vaddc-minmax-sse41-mul16-ld64-u8.c.o
2025-03-21T20:24:57.4492480Z   [ 80%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-vcvt/gen/qs8-vcvt-avx-u32.c.o
2025-03-21T20:24:57.4494632Z   [ 80%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-vcvt/gen/qs8-vcvt-avx2-u32.c.o
2025-03-21T20:24:57.4496749Z   [ 80%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-vcvt/gen/qs8-vcvt-scalar-u1.c.o
2025-03-21T20:24:57.4498927Z   [ 80%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-vcvt/gen/qs8-vcvt-scalar-u4.c.o
2025-03-21T20:24:57.4501105Z   [ 80%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-vcvt/gen/qs8-vcvt-sse2-u32.c.o
2025-03-21T20:24:57.4503494Z   [ 80%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-vcvt/gen/qs8-vcvt-sse41-u32.c.o
2025-03-21T20:24:57.4505667Z   [ 80%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-vcvt/gen/qs8-vcvt-ssse3-u32.c.o
2025-03-21T20:24:57.4507862Z   [ 80%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-vlrelu/gen/qs8-vlrelu-avx-u32.c.o
2025-03-21T20:24:57.4510072Z   [ 80%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-vlrelu/gen/qs8-vlrelu-avx2-u32.c.o
2025-03-21T20:24:57.4512392Z   [ 80%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-vlrelu/gen/qs8-vlrelu-scalar-andxor-u4.c.o
2025-03-21T20:24:57.4514791Z   [ 80%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-vlrelu/gen/qs8-vlrelu-scalar-select-u4.c.o
2025-03-21T20:24:57.4517122Z   [ 80%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-vlrelu/gen/qs8-vlrelu-sse2-u32.c.o
2025-03-21T20:24:57.4519339Z   [ 80%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-vlrelu/gen/qs8-vlrelu-sse41-u32.c.o
2025-03-21T20:24:57.4521565Z   [ 80%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-vlrelu/gen/qs8-vlrelu-ssse3-u32.c.o
2025-03-21T20:24:57.4523957Z   [ 80%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-vmul/gen/qs8-vmul-minmax-fp32-avx-mul16-ld64-u16.c.o
2025-03-21T20:24:57.4526453Z   [ 81%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-vmul/gen/qs8-vmul-minmax-fp32-scalar-u4.c.o
2025-03-21T20:24:57.4528807Z   [ 81%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-vmul/gen/qs8-vmul-minmax-fp32-sse2-mul16-ld64-u8.c.o
2025-03-21T20:24:57.4531452Z   [ 81%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-vmul/gen/qs8-vmul-minmax-fp32-sse41-mul16-ld64-u16.c.o
2025-03-21T20:24:57.4534190Z   [ 81%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-vmulc/gen/qs8-vmulc-minmax-fp32-avx-mul16-ld64-u16.c.o
2025-03-21T20:24:57.4536706Z   [ 81%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-vmulc/gen/qs8-vmulc-minmax-fp32-scalar-u4.c.o
2025-03-21T20:24:57.4539185Z   [ 81%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-vmulc/gen/qs8-vmulc-minmax-fp32-sse2-mul16-ld64-u8.c.o
2025-03-21T20:24:57.4541825Z   [ 81%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qs8-vmulc/gen/qs8-vmulc-minmax-fp32-sse41-mul16-ld64-u16.c.o
2025-03-21T20:24:57.4544458Z   [ 81%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-avgpool/qu8-avgpool-9p8x-minmax-fp32-scalar-imagic-c1.c.o
2025-03-21T20:24:57.4547068Z   [ 81%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-avgpool/qu8-avgpool-9p8x-minmax-fp32-sse2-c8.c.o
2025-03-21T20:24:57.4549668Z   [ 81%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-avgpool/qu8-avgpool-9x-minmax-fp32-scalar-imagic-c1.c.o
2025-03-21T20:24:57.4552228Z   [ 81%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-avgpool/qu8-avgpool-9x-minmax-fp32-sse2-c8.c.o
2025-03-21T20:24:57.4554771Z   [ 81%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-dwconv/gen/qu8-dwconv-25p16c-minmax-fp32-avx-mul16.c.o
2025-03-21T20:24:57.4557647Z   [ 81%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-dwconv/gen/qu8-dwconv-25p16c-minmax-fp32-avx2-mul32.c.o
2025-03-21T20:24:57.4560409Z   [ 81%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-dwconv/gen/qu8-dwconv-25p1c-minmax-fp32-scalar-fmagic.c.o
2025-03-21T20:24:57.4563092Z   [ 81%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-dwconv/gen/qu8-dwconv-25p1c-minmax-fp32-scalar-imagic.c.o
2025-03-21T20:24:57.4565590Z   [ 81%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-dwconv/gen/qu8-dwconv-25p2c-minmax-fp32-scalar-lrintf.c.o
2025-03-21T20:24:57.4568250Z   [ 82%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-dwconv/gen/qu8-dwconv-25p32c-minmax-fp32-avx512skx-mul32.c.o
2025-03-21T20:24:58.3746414Z   [ 82%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-dwconv/gen/qu8-dwconv-25p8c-minmax-fp32-sse2-mul16.c.o
2025-03-21T20:24:58.3747891Z   [ 82%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-dwconv/gen/qu8-dwconv-25p8c-minmax-fp32-sse41-mul16.c.o
2025-03-21T20:24:58.3749220Z   [ 82%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-dwconv/gen/qu8-dwconv-9p16c-minmax-fp32-avx-mul16.c.o
2025-03-21T20:24:58.3750553Z   [ 82%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-dwconv/gen/qu8-dwconv-9p16c-minmax-fp32-avx2-mul32.c.o
2025-03-21T20:24:58.3751898Z   [ 82%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-dwconv/gen/qu8-dwconv-9p1c-minmax-fp32-scalar-fmagic.c.o
2025-03-21T20:24:58.3753448Z   [ 82%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-dwconv/gen/qu8-dwconv-9p2c-minmax-fp32-scalar-imagic.c.o
2025-03-21T20:24:58.3755861Z   [ 82%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-dwconv/gen/qu8-dwconv-9p2c-minmax-fp32-scalar-lrintf.c.o
2025-03-21T20:24:58.3758373Z   [ 82%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-dwconv/gen/qu8-dwconv-9p32c-minmax-fp32-avx512skx-mul32.c.o
2025-03-21T20:24:58.3760837Z   [ 82%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-dwconv/gen/qu8-dwconv-9p8c-minmax-fp32-sse2-mul16.c.o
2025-03-21T20:24:58.3763299Z   [ 82%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-dwconv/gen/qu8-dwconv-9p8c-minmax-fp32-sse41-mul16.c.o
2025-03-21T20:24:58.3765599Z   [ 82%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-f32-vcvt/gen/qu8-f32-vcvt-avx-u32.c.o
2025-03-21T20:24:58.3767792Z   [ 82%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-f32-vcvt/gen/qu8-f32-vcvt-avx2-u16.c.o
2025-03-21T20:24:58.3770134Z   [ 82%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-f32-vcvt/gen/qu8-f32-vcvt-avx512skx-u32.c.o
2025-03-21T20:24:58.3772312Z   [ 82%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-f32-vcvt/gen/qu8-f32-vcvt-scalar-u1.c.o
2025-03-21T20:24:58.3774394Z   [ 82%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-f32-vcvt/gen/qu8-f32-vcvt-scalar-u4.c.o
2025-03-21T20:24:58.3776439Z   [ 84%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-f32-vcvt/gen/qu8-f32-vcvt-sse2-u32.c.o
2025-03-21T20:24:58.3778410Z   [ 84%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-f32-vcvt/gen/qu8-f32-vcvt-sse41-u16.c.o
2025-03-21T20:24:58.3781030Z   [ 84%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-gemm/gen/qu8-gemm-1x16c8-minmax-fp32-avx512skx-prfm.c.o
2025-03-21T20:24:58.3783686Z   [ 84%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-gemm/gen/qu8-gemm-1x2-minmax-fp32-scalar-imagic.c.o
2025-03-21T20:24:58.3786173Z   [ 84%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-gemm/gen/qu8-gemm-1x4-minmax-fp32-scalar-lrintf.c.o
2025-03-21T20:24:58.3788440Z   [ 84%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-gemm/gen/qu8-gemm-1x4c8-minmax-fp32-avx-ld128.c.o
2025-03-21T20:24:58.3790761Z   [ 84%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-gemm/gen/qu8-gemm-1x4c8-minmax-fp32-sse2-ld64.c.o
2025-03-21T20:24:58.3792589Z   [ 84%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-gemm/gen/qu8-gemm-1x4c8-minmax-fp32-sse41-ld64.c.o
2025-03-21T20:24:58.3794606Z   [ 84%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-gemm/gen/qu8-gemm-1x8c8-minmax-fp32-avx2.c.o
2025-03-21T20:24:58.3796937Z   [ 84%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-gemm/gen/qu8-gemm-2x2-minmax-fp32-scalar-imagic.c.o
2025-03-21T20:24:58.3799406Z   [ 84%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-gemm/gen/qu8-gemm-2x4c8-minmax-fp32-avx-ld128.c.o
2025-03-21T20:24:58.3801733Z   [ 84%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-gemm/gen/qu8-gemm-3x4-minmax-fp32-scalar-lrintf.c.o
2025-03-21T20:24:58.3804097Z   [ 84%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-gemm/gen/qu8-gemm-3x4c8-minmax-fp32-sse2-ld64.c.o
2025-03-21T20:24:58.3806434Z   [ 84%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-gemm/gen/qu8-gemm-3x4c8-minmax-fp32-sse41-ld64.c.o
2025-03-21T20:24:58.3808659Z   [ 84%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-gemm/gen/qu8-gemm-3x8c8-minmax-fp32-avx2.c.o
2025-03-21T20:24:58.3811076Z   [ 85%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-gemm/gen/qu8-gemm-7x16c8-minmax-fp32-avx512skx-prfm.c.o
2025-03-21T20:24:58.3813519Z   [ 85%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-igemm/gen/qu8-igemm-1x16c8-minmax-fp32-avx512skx-prfm.c.o
2025-03-21T20:24:58.3815955Z   [ 85%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-igemm/gen/qu8-igemm-1x2-minmax-fp32-scalar-imagic.c.o
2025-03-21T20:24:58.3818366Z   [ 85%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-igemm/gen/qu8-igemm-1x4-minmax-fp32-scalar-lrintf.c.o
2025-03-21T20:24:58.3820405Z   [ 85%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-igemm/gen/qu8-igemm-1x4c8-minmax-fp32-avx-ld128.c.o
2025-03-21T20:24:58.3822669Z   [ 85%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-igemm/gen/qu8-igemm-1x4c8-minmax-fp32-sse2-ld64.c.o
2025-03-21T20:24:58.3824511Z   [ 85%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-igemm/gen/qu8-igemm-1x4c8-minmax-fp32-sse41-ld64.c.o
2025-03-21T20:24:58.3826555Z   [ 85%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-igemm/gen/qu8-igemm-1x8c8-minmax-fp32-avx2.c.o
2025-03-21T20:24:58.3827822Z   [ 85%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-igemm/gen/qu8-igemm-2x4c8-minmax-fp32-avx-ld128.c.o
2025-03-21T20:24:58.3829775Z   [ 85%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-igemm/gen/qu8-igemm-2x2-minmax-fp32-scalar-imagic.c.o
2025-03-21T20:24:58.3832416Z   [ 85%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-igemm/gen/qu8-igemm-3x4-minmax-fp32-scalar-lrintf.c.o
2025-03-21T20:24:58.3834860Z   [ 85%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-igemm/gen/qu8-igemm-3x4c8-minmax-fp32-sse2-ld64.c.o
2025-03-21T20:24:58.3836984Z   [ 85%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-igemm/gen/qu8-igemm-3x4c8-minmax-fp32-sse41-ld64.c.o
2025-03-21T20:24:58.3838271Z   [ 85%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-igemm/gen/qu8-igemm-3x8c8-minmax-fp32-avx2.c.o
2025-03-21T20:24:58.3839576Z   [ 85%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-igemm/gen/qu8-igemm-7x16c8-minmax-fp32-avx512skx-prfm.c.o
2025-03-21T20:24:58.3840853Z   [ 85%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-rdsum/gen/qu8-rdsum-7p7x-ssse3-c64.c.o
2025-03-21T20:24:58.3842000Z   [ 86%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-rdsum/gen/qu8-rdsum-scalar.c.o
2025-03-21T20:24:58.3843107Z   [ 86%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-rsum/gen/qu8-rsum-avx2-u64-acc2.c.o
2025-03-21T20:24:58.3844231Z   [ 86%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-rsum/gen/qu8-rsum-scalar-u4.c.o
2025-03-21T20:24:58.3845351Z   [ 86%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-rsum/gen/qu8-rsum-sse2-u32-acc2.c.o
2025-03-21T20:24:58.3846544Z   [ 86%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-vadd/gen/qu8-vadd-minmax-avx-mul32-ld32-u8.c.o
2025-03-21T20:24:58.3847808Z   [ 86%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-vadd/gen/qu8-vadd-minmax-avx2-mul32-ld64-u16.c.o
2025-03-21T20:24:58.3849110Z   [ 86%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-vadd/gen/qu8-vadd-minmax-avx512skx-mul32-ld128-u16.c.o
2025-03-21T20:24:59.2119357Z   [ 86%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-vadd/gen/qu8-vadd-minmax-scalar-u1.c.o
2025-03-21T20:24:59.2122335Z   [ 86%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-vadd/gen/qu8-vadd-minmax-scalar-u4.c.o
2025-03-21T20:24:59.2124381Z   [ 86%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-vadd/gen/qu8-vadd-minmax-sse2-mul16-ld64-u8.c.o
2025-03-21T20:24:59.2126700Z   [ 86%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-vadd/gen/qu8-vadd-minmax-sse41-mul16-ld64-u8.c.o
2025-03-21T20:24:59.2128831Z   [ 86%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-vaddc/gen/qu8-vaddc-minmax-avx-mul32-ld32-u8.c.o
2025-03-21T20:24:59.2131248Z   [ 86%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-vaddc/gen/qu8-vaddc-minmax-avx2-mul32-ld64-u16.c.o
2025-03-21T20:24:59.2133846Z   [ 86%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-vaddc/gen/qu8-vaddc-minmax-avx512skx-mul32-ld128-u16.c.o
2025-03-21T20:24:59.2136172Z   [ 86%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-vaddc/gen/qu8-vaddc-minmax-scalar-u1.c.o
2025-03-21T20:24:59.2138328Z   [ 86%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-vaddc/gen/qu8-vaddc-minmax-scalar-u4.c.o
2025-03-21T20:24:59.2141231Z   [ 87%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-vaddc/gen/qu8-vaddc-minmax-sse2-mul16-ld64-u8.c.o
2025-03-21T20:24:59.2143752Z   [ 87%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-vaddc/gen/qu8-vaddc-minmax-sse41-mul16-ld64-u8.c.o
2025-03-21T20:24:59.2145897Z   [ 87%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-vcvt/gen/qu8-vcvt-avx-u32.c.o
2025-03-21T20:24:59.2147865Z   [ 87%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-vcvt/gen/qu8-vcvt-avx2-u32.c.o
2025-03-21T20:24:59.2149836Z   [ 87%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-vcvt/gen/qu8-vcvt-scalar-u1.c.o
2025-03-21T20:24:59.2151883Z   [ 87%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-vcvt/gen/qu8-vcvt-scalar-u4.c.o
2025-03-21T20:24:59.2153828Z   [ 87%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-vcvt/gen/qu8-vcvt-sse2-u32.c.o
2025-03-21T20:24:59.2155833Z   [ 87%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-vcvt/gen/qu8-vcvt-sse41-u32.c.o
2025-03-21T20:24:59.2157696Z   [ 87%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-vcvt/gen/qu8-vcvt-ssse3-u32.c.o
2025-03-21T20:24:59.2160289Z   [ 87%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-vlrelu/gen/qu8-vlrelu-avx-u32.c.o
2025-03-21T20:24:59.2162204Z   [ 87%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-vlrelu/gen/qu8-vlrelu-avx2-u32.c.o
2025-03-21T20:24:59.2164220Z   [ 87%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-vlrelu/gen/qu8-vlrelu-scalar-andxor-u4.c.o
2025-03-21T20:24:59.2166317Z   [ 87%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-vlrelu/gen/qu8-vlrelu-scalar-select-u4.c.o
2025-03-21T20:24:59.2168345Z   [ 87%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-vlrelu/gen/qu8-vlrelu-sse2-u32.c.o
2025-03-21T20:24:59.2170399Z   [ 87%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-vlrelu/gen/qu8-vlrelu-sse41-u32.c.o
2025-03-21T20:24:59.2172328Z   [ 89%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-vlrelu/gen/qu8-vlrelu-ssse3-u32.c.o
2025-03-21T20:24:59.2174441Z   [ 89%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-vmul/gen/qu8-vmul-minmax-fp32-avx-mul16-ld64-u16.c.o
2025-03-21T20:24:59.2177057Z   [ 89%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-vmul/gen/qu8-vmul-minmax-fp32-scalar-u4.c.o
2025-03-21T20:24:59.2179229Z   [ 89%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-vmul/gen/qu8-vmul-minmax-fp32-sse2-mul16-ld64-u8.c.o
2025-03-21T20:24:59.2181590Z   [ 89%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-vmul/gen/qu8-vmul-minmax-fp32-sse41-mul16-ld64-u16.c.o
2025-03-21T20:24:59.2183964Z   [ 89%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-vmulc/gen/qu8-vmulc-minmax-fp32-avx-mul16-ld64-u16.c.o
2025-03-21T20:24:59.2186314Z   [ 89%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-vmulc/gen/qu8-vmulc-minmax-fp32-scalar-u4.c.o
2025-03-21T20:24:59.2188621Z   [ 89%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-vmulc/gen/qu8-vmulc-minmax-fp32-sse2-mul16-ld64-u8.c.o
2025-03-21T20:24:59.2191032Z   [ 89%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/qu8-vmulc/gen/qu8-vmulc-minmax-fp32-sse41-mul16-ld64-u16.c.o
2025-03-21T20:24:59.2193650Z   [ 89%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/s32-f32-vcvt/gen/s32-f32-vcvt-avx2.c.o
2025-03-21T20:24:59.2195708Z   [ 89%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/s32-f32-vcvt/gen/s32-f32-vcvt-avx512f.c.o
2025-03-21T20:24:59.2197785Z   [ 89%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/s32-f32-vcvt/gen/s32-f32-vcvt-scalar.c.o
2025-03-21T20:24:59.2199880Z   [ 89%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/s8-ibilinear/gen/s8-ibilinear-scalar-c1.c.o
2025-03-21T20:24:59.2201997Z   [ 89%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/s8-ibilinear/gen/s8-ibilinear-sse2-c8.c.o
2025-03-21T20:24:59.2204023Z   [ 89%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/s8-ibilinear/gen/s8-ibilinear-sse41-c16.c.o
2025-03-21T20:24:59.2206174Z   [ 89%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/s8-maxpool/s8-maxpool-9p8x-minmax-scalar-c1.c.o
2025-03-21T20:24:59.2208316Z   [ 90%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/s8-maxpool/s8-maxpool-9p8x-minmax-sse2-c16.c.o
2025-03-21T20:24:59.2210571Z   [ 90%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/s8-maxpool/s8-maxpool-9p8x-minmax-sse41-c16.c.o
2025-03-21T20:24:59.2212610Z   [ 90%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/s8-vclamp/s8-vclamp-avx2-u128.c.o
2025-03-21T20:24:59.2214549Z   [ 90%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/s8-vclamp/s8-vclamp-avx512skx-u256.c.o
2025-03-21T20:24:59.2216506Z   [ 90%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/s8-vclamp/s8-vclamp-scalar-u4.c.o
2025-03-21T20:24:59.2218426Z   [ 90%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/s8-vclamp/s8-vclamp-sse2-u64.c.o
2025-03-21T20:24:59.2220610Z   [ 90%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/s8-vclamp/s8-vclamp-sse41-u64.c.o
2025-03-21T20:24:59.2222628Z   [ 90%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/u8-ibilinear/gen/u8-ibilinear-scalar-c1.c.o
2025-03-21T20:24:59.2224715Z   [ 90%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/u8-ibilinear/gen/u8-ibilinear-sse2-c8.c.o
2025-03-21T20:24:59.2226819Z   [ 90%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/u8-ibilinear/gen/u8-ibilinear-sse41-c16.c.o
2025-03-21T20:24:59.2228853Z   [ 90%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/u8-lut32norm/u8-lut32norm-scalar.c.o
2025-03-21T20:24:59.2230952Z   [ 90%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/u8-maxpool/u8-maxpool-9p8x-minmax-scalar-c1.c.o
2025-03-21T20:24:59.2237531Z   [ 90%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/u8-maxpool/u8-maxpool-9p8x-minmax-sse2-c16.c.o
2025-03-21T20:24:59.2239826Z   [ 90%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/u8-rmax/u8-rmax-scalar-u2.c.o
2025-03-21T20:24:59.2241684Z   [ 90%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/u8-rmax/u8-rmax-sse2-u16.c.o
2025-03-21T20:24:59.2243687Z   [ 90%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/u8-vclamp/u8-vclamp-avx2-u128.c.o
2025-03-21T20:24:59.9505919Z   [ 91%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/u8-vclamp/u8-vclamp-avx512skx-u256.c.o
2025-03-21T20:24:59.9508529Z   [ 91%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/u8-vclamp/u8-vclamp-scalar-u4.c.o
2025-03-21T20:24:59.9510547Z   [ 91%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/u8-vclamp/u8-vclamp-sse2-u64.c.o
2025-03-21T20:24:59.9512679Z   [ 91%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x16-packw/gen/x16-packw-x16-gemm-goi-avx2-u16-prfm.c.o
2025-03-21T20:24:59.9514205Z   [ 91%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x16-packw/gen/x16-packw-x64-gemm-goi-scalar-int-u4.c.o
2025-03-21T20:24:59.9515671Z   [ 91%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x16-transposec/gen/x16-transposec-16x16-reuse-switch-avx2.c.o
2025-03-21T20:24:59.9517105Z   [ 91%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x16-transposec/gen/x16-transposec-2x4-scalar-int.c.o
2025-03-21T20:24:59.9518541Z   [ 91%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x16-transposec/gen/x16-transposec-8x8-reuse-multi-sse2.c.o
2025-03-21T20:24:59.9519905Z   [ 91%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x24-transposec/gen/x24-transposec-1x2-scalar.c.o
2025-03-21T20:24:59.9521736Z   [ 91%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x24-transposec/x24-transposec-4x4-ssse3.c.o
2025-03-21T20:24:59.9523873Z   [ 91%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x32-packw/gen/x32-packw-x16-gemm-goi-avx-u4.c.o
2025-03-21T20:24:59.9526141Z   [ 91%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x32-packw/gen/x32-packw-x16s4-gemm-goi-avx-u4.c.o
2025-03-21T20:24:59.9528482Z   [ 91%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x32-packw/gen/x32-packw-x2-gemm-goi-scalar-float-u4.c.o
2025-03-21T20:24:59.9530956Z   [ 91%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x32-packw/gen/x32-packw-x2c4-gemm-goi-sse2-u4.c.o
2025-03-21T20:24:59.9536458Z   [ 91%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x32-packw/gen/x32-packw-x32-gemm-goi-avx512f-u4-prfm.c.o
2025-03-21T20:24:59.9538905Z   [ 91%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x32-packw/gen/x32-packw-x4-gemm-goi-scalar-float-u4.c.o
2025-03-21T20:24:59.9541227Z   [ 92%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x32-packw/gen/x32-packw-x8-gemm-goi-sse2-u4.c.o
2025-03-21T20:24:59.9543447Z   [ 92%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x32-transposec/gen/x32-transposec-2x4-scalar-int.c.o
2025-03-21T20:24:59.9545783Z   [ 92%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x32-transposec/gen/x32-transposec-8x8-reuse-multi-avx.c.o
2025-03-21T20:24:59.9548088Z   [ 92%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x32-transposec/x32-transposec-4x4-sse.c.o
2025-03-21T20:24:59.9550253Z   [ 92%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x32-unpool/x32-unpool-scalar.c.o
2025-03-21T20:24:59.9552317Z   [ 92%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x32-unpool/x32-unpool-sse2.c.o
2025-03-21T20:24:59.9554328Z   [ 92%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x32-zip/x32-zip-x2-scalar.c.o
2025-03-21T20:24:59.9556307Z   [ 92%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x32-zip/x32-zip-x2-sse2.c.o
2025-03-21T20:24:59.9558620Z   [ 92%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x32-zip/x32-zip-x3-scalar.c.o
2025-03-21T20:24:59.9560547Z   [ 92%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x32-zip/x32-zip-x3-sse2.c.o
2025-03-21T20:24:59.9562426Z   [ 92%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x32-zip/x32-zip-x4-scalar.c.o
2025-03-21T20:24:59.9564307Z   [ 92%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x32-zip/x32-zip-x4-sse2.c.o
2025-03-21T20:24:59.9566320Z   [ 92%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x32-zip/x32-zip-xm-scalar.c.o
2025-03-21T20:24:59.9568238Z   [ 92%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x32-zip/x32-zip-xm-sse2.c.o
2025-03-21T20:24:59.9570416Z   [ 93%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x64-transposec/gen/x64-transposec-4x2-scalar-int.c.o
2025-03-21T20:24:59.9572712Z   [ 93%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x64-transposec/gen/x64-transposec-2x2-multi-mov-sse2.c.o
2025-03-21T20:24:59.9574961Z   [ 93%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x64-transposec/gen/x64-transposec-4x4-reuse-multi-avx.c.o
2025-03-21T20:24:59.9577082Z   [ 93%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x8-lut/gen/x8-lut-avx-u64.c.o
2025-03-21T20:24:59.9578951Z   [ 93%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x8-lut/gen/x8-lut-avx2-u128.c.o
2025-03-21T20:24:59.9580981Z   [ 93%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x8-lut/gen/x8-lut-avx512skx-vpshufb-u64.c.o
2025-03-21T20:24:59.9583088Z   [ 93%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x8-lut/gen/x8-lut-avx512vbmi-vpermx2b-u128.c.o
2025-03-21T20:24:59.9585043Z   [ 93%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x8-lut/gen/x8-lut-scalar-u4.c.o
2025-03-21T20:24:59.9586951Z   [ 93%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x8-packq/x8-packq-scalar-f32qp8-u1.c.o
2025-03-21T20:24:59.9589095Z   [ 93%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x8-packw/gen/x8-packw-x16-gemm-goi-scalar-u2.c.o
2025-03-21T20:24:59.9591055Z   [ 93%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x8-packw/gen/x8-packw-x32-gemm-goi-scalar-u2.c.o
2025-03-21T20:24:59.9592288Z   [ 93%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x8-packw/gen/x8-packw-x4-gemm-goi-scalar-u2.c.o
2025-03-21T20:24:59.9593534Z   [ 93%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x8-packw/gen/x8-packw-x8-gemm-goi-scalar-u2.c.o
2025-03-21T20:24:59.9594801Z   [ 93%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x8-transposec/gen/x8-transposec-16x16-reuse-mov-sse2.c.o
2025-03-21T20:24:59.9596093Z   [ 93%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x8-transposec/gen/x8-transposec-2x4-scalar-int.c.o
2025-03-21T20:24:59.9598051Z   [ 93%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x8-transposec/gen/x8-transposec-32x32-reuse-switch-avx2.c.o
2025-03-21T20:24:59.9599641Z   [ 93%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x8-zip/x8-zip-x2-scalar.c.o
2025-03-21T20:24:59.9600873Z   [ 95%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x8-zip/x8-zip-x2-sse2.c.o
2025-03-21T20:24:59.9602132Z   [ 95%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x8-zip/x8-zip-x3-scalar.c.o
2025-03-21T20:24:59.9603163Z   [ 95%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x8-zip/x8-zip-x3-sse2.c.o
2025-03-21T20:24:59.9604212Z   [ 95%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x8-zip/x8-zip-x4-scalar.c.o
2025-03-21T20:24:59.9605242Z   [ 95%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x8-zip/x8-zip-x4-sse2.c.o
2025-03-21T20:24:59.9606267Z   [ 95%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x8-zip/x8-zip-xm-scalar.c.o
2025-03-21T20:24:59.9607296Z   [ 95%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/x8-zip/x8-zip-xm-sse2.c.o
2025-03-21T20:24:59.9608365Z   [ 95%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/xx-copy/xx-copy-scalar-memcpy.c.o
2025-03-21T20:24:59.9609543Z   [ 95%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/xx-fill/xx-fill-scalar-u16.c.o
2025-03-21T20:24:59.9610614Z   [ 95%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/xx-fill/xx-fill-sse2-u64.c.o
2025-03-21T20:25:06.6634369Z   [ 95%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/xx-pad/xx-pad-p16-sse2-u16.c.o
2025-03-21T20:25:06.6636615Z   [ 95%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/xx-pad/xx-pad-p4-scalar-u16.c.o
2025-03-21T20:25:06.6638756Z   [ 95%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/xx-transposev/xx-transposev-1x1-scalar-memcpy.c.o
2025-03-21T20:25:06.6640854Z   [ 95%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/tables/exp2-k-over-64.c.o
2025-03-21T20:25:06.6642568Z   [ 95%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/tables/exp2-k-over-2048.c.o
2025-03-21T20:25:06.6644587Z   [ 95%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/tables/exp2minus-k-over-4.c.o
2025-03-21T20:25:06.6646500Z   [ 96%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/tables/exp2minus-k-over-8.c.o
2025-03-21T20:25:06.6648456Z   [ 96%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/tables/exp2minus-k-over-16.c.o
2025-03-21T20:25:06.6650444Z   [ 96%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/tables/exp2minus-k-over-32.c.o
2025-03-21T20:25:06.6652330Z   [ 96%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/tables/exp2minus-k-over-64.c.o
2025-03-21T20:25:06.6654359Z   [ 96%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/tables/exp2minus-k-over-2048.c.o
2025-03-21T20:25:06.6656136Z   [ 96%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/microkernels-prod.dir/src/tables/vlog.c.o
2025-03-21T20:25:06.6657333Z   [ 96%] Linking C static library libmicrokernels-prod.a
2025-03-21T20:25:06.6657972Z   [ 96%] Built target microkernels-prod
2025-03-21T20:25:06.6658540Z   [ 96%] Generating build_identifier.c
2025-03-21T20:25:06.6659631Z   [ 96%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/XNNPACK.dir/src/configs/argmaxpool-config.c.o
2025-03-21T20:25:06.6661329Z   [ 96%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/XNNPACK.dir/src/configs/avgpool-config.c.o
2025-03-21T20:25:06.6663081Z   [ 96%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/XNNPACK.dir/src/configs/binary-elementwise-config.c.o
2025-03-21T20:25:06.6665111Z   [ 96%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/XNNPACK.dir/src/configs/cmul-config.c.o
2025-03-21T20:25:06.6666888Z   [ 96%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/XNNPACK.dir/src/configs/conv-hwc2chw-config.c.o
2025-03-21T20:25:06.6668627Z   [ 96%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/XNNPACK.dir/src/configs/dwconv2d-chw-config.c.o
2025-03-21T20:25:06.6670405Z   [ 96%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/XNNPACK.dir/src/configs/dwconv-config.c.o
2025-03-21T20:25:06.6672170Z   [ 96%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/XNNPACK.dir/src/configs/experiments-config.c.o
2025-03-21T20:25:06.6673900Z   [ 96%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/XNNPACK.dir/src/configs/gemm-config.c.o
2025-03-21T20:25:06.6675635Z   [ 96%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/XNNPACK.dir/src/configs/ibilinear-chw-config.c.o
2025-03-21T20:25:06.6677360Z   [ 96%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/XNNPACK.dir/src/configs/ibilinear-config.c.o
2025-03-21T20:25:06.6679716Z   [ 96%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/XNNPACK.dir/src/configs/lut32norm-config.c.o
2025-03-21T20:25:06.6681759Z   [ 96%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/XNNPACK.dir/src/configs/maxpool-config.c.o
2025-03-21T20:25:06.6683575Z   [ 96%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/XNNPACK.dir/src/configs/pavgpool-config.c.o
2025-03-21T20:25:06.6685357Z   [ 97%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/XNNPACK.dir/src/configs/pack-lh-config.c.o
2025-03-21T20:25:06.6687316Z   [ 97%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/XNNPACK.dir/src/configs/raddstoreexpminusmax-config.c.o
2025-03-21T20:25:06.6689305Z   [ 97%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/XNNPACK.dir/src/configs/reduce-config.c.o
2025-03-21T20:25:06.6691020Z   [ 97%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/XNNPACK.dir/src/configs/rmax-config.c.o
2025-03-21T20:25:06.6692508Z   [ 97%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/XNNPACK.dir/src/configs/spmm-config.c.o
2025-03-21T20:25:06.6694204Z   [ 97%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/XNNPACK.dir/src/configs/transpose-config.c.o
2025-03-21T20:25:06.6706938Z   [ 97%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/XNNPACK.dir/src/configs/unary-elementwise-config.c.o
2025-03-21T20:25:06.6708659Z   [ 97%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/XNNPACK.dir/src/configs/unpool-config.c.o
2025-03-21T20:25:06.6710253Z   [ 97%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/XNNPACK.dir/src/configs/vmulcaddc-config.c.o
2025-03-21T20:25:06.6711883Z   [ 97%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/XNNPACK.dir/src/configs/xx-fill-config.c.o
2025-03-21T20:25:06.6713529Z   [ 97%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/XNNPACK.dir/src/configs/xx-pad-config.c.o
2025-03-21T20:25:06.6715102Z   [ 97%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/XNNPACK.dir/src/configs/x8-lut-config.c.o
2025-03-21T20:25:06.6716684Z   [ 97%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/XNNPACK.dir/src/configs/zip-config.c.o
2025-03-21T20:25:06.6718089Z   [ 97%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/XNNPACK.dir/src/init.c.o
2025-03-21T20:25:06.6719377Z   [ 97%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/XNNPACK.dir/src/params.c.o
2025-03-21T20:25:06.6720720Z   [ 97%] Building C object backends/xnnpack/third-party/XNNPACK/CMakeFiles/XNNPACK.dir/build_identifier.c.o
2025-03-21T20:25:06.6721710Z   [ 98%] Linking CXX static library libXNNPACK.a
2025-03-21T20:25:06.6722306Z   [ 98%] Built target XNNPACK
2025-03-21T20:25:06.6723365Z   [ 98%] Building CXX object backends/xnnpack/CMakeFiles/xnnpack_backend.dir/runtime/XNNExecutor.cpp.o
2025-03-21T20:25:06.6724872Z   [ 98%] Building CXX object backends/xnnpack/CMakeFiles/xnnpack_backend.dir/runtime/XNNCompiler.cpp.o
2025-03-21T20:25:06.6725740Z   [ 98%] Building CXX object backends/xnnpack/CMakeFiles/xnnpack_backend.dir/runtime/XNNHeader.cpp.o
2025-03-21T20:25:06.6726542Z   [ 98%] Building CXX object backends/xnnpack/CMakeFiles/xnnpack_backend.dir/runtime/XNNPACKBackend.cpp.o
2025-03-21T20:25:06.6727395Z   [ 98%] Building CXX object backends/xnnpack/CMakeFiles/xnnpack_backend.dir/runtime/profiling/XNNProfiler.cpp.o
2025-03-21T20:25:06.6728255Z   [ 98%] Building CXX object backends/xnnpack/CMakeFiles/xnnpack_backend.dir/runtime/XNNWeightsCache.cpp.o
2025-03-21T20:25:06.6728873Z   [ 98%] Linking CXX static library libxnnpack_backend.a
2025-03-21T20:25:06.6729359Z   [ 98%] Built target xnnpack_backend
2025-03-21T20:25:06.6729881Z   [ 98%] Building CXX object CMakeFiles/portable_lib.dir/extension/pybindings/pybindings.cpp.o
2025-03-21T20:25:06.6730559Z   [100%] Linking CXX shared library _portable_lib.cpython-310-x86_64-linux-gnu.so
2025-03-21T20:25:06.6731030Z   [100%] Built target portable_lib
2025-03-21T20:25:06.6731341Z   [  0%] Built target flatbuffers
2025-03-21T20:25:06.6731638Z   [  0%] Built target flatccrt
2025-03-21T20:25:06.6731936Z   [  0%] Built target pthreadpool
2025-03-21T20:25:06.6732444Z   [  0%] Built target common_schema
2025-03-21T20:25:06.6732775Z   [  1%] Built target xnnpack_schema
2025-03-21T20:25:06.6733096Z   [  2%] Built target cpuinfo
2025-03-21T20:25:06.6733373Z   [  4%] Built target flatcc
2025-03-21T20:25:06.6733684Z   [  4%] Built target bundled_program_schema
2025-03-21T20:25:06.6734026Z   [  4%] Built target indirection
2025-03-21T20:25:06.6734344Z   [  4%] Built target microparams-init
2025-03-21T20:25:06.6734670Z   [  4%] Built target logging
2025-03-21T20:25:06.6734952Z   [  7%] Built target eigen_blas
2025-03-21T20:25:06.6735253Z   [  7%] Built target datatype
2025-03-21T20:25:06.6735562Z   [  7%] Built target normalization
2025-03-21T20:25:06.6735893Z   [  7%] Built target program_schema
2025-03-21T20:25:06.6736209Z   [  7%] Built target flatcc_cli
2025-03-21T20:25:06.6736542Z   [  7%] Built target hardware-config
2025-03-21T20:25:06.6736879Z   [  7%] Built target reference-ukernels
2025-03-21T20:25:06.6737208Z   [  7%] Built target allocator
2025-03-21T20:25:06.6737502Z   [  7%] Built target packing
2025-03-21T20:25:06.6737779Z   [  7%] Built target cache
2025-03-21T20:25:06.6738077Z   [  7%] Built target microkernel-utils
2025-03-21T20:25:06.6738409Z   [  7%] Built target memory
2025-03-21T20:25:06.6738692Z   [  7%] Built target mutex
2025-03-21T20:25:06.6738991Z   [  7%] Built target operator-utils
2025-03-21T20:25:06.6739303Z   [  7%] Built target operator-run
2025-03-21T20:25:06.6739618Z   [  7%] Built target etdump_schema
2025-03-21T20:25:06.6739931Z   [  9%] Built target operators
2025-03-21T20:25:06.6740240Z   [ 10%] Built target executorch_core
2025-03-21T20:25:06.6740559Z   [ 13%] Built target subgraph
2025-03-21T20:25:06.6740864Z   [ 14%] Built target extension_threadpool
2025-03-21T20:25:06.6741203Z   [ 15%] Built target executorch
2025-03-21T20:25:06.6741514Z   [ 15%] Built target extension_tensor
2025-03-21T20:25:06.6741852Z   [ 15%] Built target bundled_program
2025-03-21T20:25:06.6742192Z   [ 15%] Built target extension_data_loader
2025-03-21T20:25:06.6742516Z   [ 15%] Built target cpublas
2025-03-21T20:25:06.6742809Z   [ 15%] Built target etdump
2025-03-21T20:25:06.6743111Z   [ 16%] Built target optimized_kernels
2025-03-21T20:25:06.6743436Z   [ 18%] Built target util
2025-03-21T20:25:06.6743746Z   [ 32%] Built target optimized_portable_kernels
2025-03-21T20:25:06.6744110Z   [ 32%] Built target optimized_native_cpu_ops_lib
2025-03-21T20:25:06.6744485Z   [ 95%] Built target microkernels-prod
2025-03-21T20:25:06.6744815Z   [ 97%] Built target XNNPACK
2025-03-21T20:25:06.6745114Z   [ 97%] Built target xnnpack_backend
2025-03-21T20:25:06.6745436Z   [ 98%] Built target portable_lib
2025-03-21T20:25:06.6746262Z   [ 98%] Building CXX object extension/llm/custom_ops/CMakeFiles/custom_ops_aot_lib.dir/op_fallback.cpp.o
2025-03-21T20:25:06.6747123Z   [ 98%] Building CXX object extension/llm/custom_ops/CMakeFiles/custom_ops_aot_lib.dir/op_fast_hadamard_transform.cpp.o
2025-03-21T20:25:13.4792735Z   [ 98%] Building CXX object extension/llm/custom_ops/CMakeFiles/custom_ops_aot_lib.dir/op_sdpa.cpp.o
2025-03-21T20:25:13.4793572Z   [ 98%] Building CXX object extension/llm/custom_ops/CMakeFiles/custom_ops_aot_lib.dir/op_update_cache.cpp.o
2025-03-21T20:25:13.4794609Z   [100%] Building CXX object extension/llm/custom_ops/CMakeFiles/custom_ops_aot_lib.dir/spinquant/fast_hadamard_transform.cpp.o
2025-03-21T20:25:13.4796263Z   [100%] Building C object extension/llm/custom_ops/CMakeFiles/custom_ops_aot_lib.dir/spinquant/third-party/FFHT/fht_avx.c.o
2025-03-21T20:25:13.4797819Z   [100%] Building CXX object extension/llm/custom_ops/CMakeFiles/custom_ops_aot_lib.dir/op_sdpa_aot.cpp.o
2025-03-21T20:25:13.4798823Z   [100%] Building CXX object extension/llm/custom_ops/CMakeFiles/custom_ops_aot_lib.dir/op_fast_hadamard_transform_aten.cpp.o
2025-03-21T20:25:13.4799967Z   [100%] Building CXX object extension/llm/custom_ops/CMakeFiles/custom_ops_aot_lib.dir/op_tile_crop.cpp.o
2025-03-21T20:25:13.4800795Z   [100%] Building CXX object extension/llm/custom_ops/CMakeFiles/custom_ops_aot_lib.dir/op_tile_crop_aot.cpp.o
2025-03-21T20:25:13.4801443Z   [100%] Linking CXX shared library libcustom_ops_aot_lib.so
2025-03-21T20:25:13.4801827Z   [100%] Built target custom_ops_aot_lib
2025-03-21T20:25:13.4802166Z   [  0%] Built target flatbuffers
2025-03-21T20:25:13.4802474Z   [  0%] Built target flatccrt
2025-03-21T20:25:13.4802783Z   [  0%] Built target pthreadpool
2025-03-21T20:25:13.4803093Z   [  1%] Built target cpuinfo
2025-03-21T20:25:13.4803378Z   [  3%] Built target flatcc
2025-03-21T20:25:13.4803680Z   [  3%] Built target common_schema
2025-03-21T20:25:13.4804075Z   [  4%] Built target xnnpack_schema
2025-03-21T20:25:13.4804620Z   [  4%] Built target bundled_program_schema
2025-03-21T20:25:13.4805174Z   [  7%] Built target eigen_blas
2025-03-21T20:25:13.4805661Z   [  7%] Built target indirection
2025-03-21T20:25:13.4806154Z   [  7%] Built target logging
2025-03-21T20:25:13.4806644Z   [  7%] Built target microparams-init
2025-03-21T20:25:13.4807094Z   [  7%] Built target normalization
2025-03-21T20:25:13.4807416Z   [  7%] Built target datatype
2025-03-21T20:25:13.4807716Z   [  7%] Built target reference-ukernels
2025-03-21T20:25:13.4808130Z   [  7%] Built target flatcc_cli
2025-03-21T20:25:13.4808515Z   [  7%] Built target program_schema
2025-03-21T20:25:13.4808885Z   [  7%] Built target hardware-config
2025-03-21T20:25:13.4809360Z   [  7%] Built target allocator
2025-03-21T20:25:13.4809648Z   [  7%] Built target packing
2025-03-21T20:25:13.4809939Z   [  7%] Built target cache
2025-03-21T20:25:13.4810240Z   [  7%] Built target microkernel-utils
2025-03-21T20:25:13.4810566Z   [  7%] Built target memory
2025-03-21T20:25:13.4810871Z   [  7%] Built target mutex
2025-03-21T20:25:13.4811166Z   [  7%] Built target operator-utils
2025-03-21T20:25:13.4811493Z   [  7%] Built target operator-run
2025-03-21T20:25:13.4811807Z   [  7%] Built target etdump_schema
2025-03-21T20:25:13.4812133Z   [  9%] Built target operators
2025-03-21T20:25:13.4812604Z   [ 10%] Built target executorch_core
2025-03-21T20:25:13.4813123Z   [ 10%] Built target extension_tensor
2025-03-21T20:25:13.4813645Z   [ 11%] Built target executorch
2025-03-21T20:25:13.4814194Z   [ 13%] Built target extension_threadpool
2025-03-21T20:25:13.4814759Z   [ 15%] Built target subgraph
2025-03-21T20:25:13.4815259Z   [ 15%] Built target extension_data_loader
2025-03-21T20:25:13.4815795Z   [ 15%] Built target bundled_program
2025-03-21T20:25:13.4816312Z   [ 15%] Built target etdump
2025-03-21T20:25:13.4816801Z   [ 15%] Built target cpublas
2025-03-21T20:25:13.4817302Z   [ 16%] Built target optimized_kernels
2025-03-21T20:25:13.4817816Z   [ 17%] Built target util
2025-03-21T20:25:13.4818515Z   [ 32%] Built target optimized_portable_kernels
2025-03-21T20:25:13.4818903Z   [ 32%] Built target optimized_native_cpu_ops_lib
2025-03-21T20:25:13.4819345Z   [ 94%] Built target microkernels-prod
2025-03-21T20:25:13.4819772Z   [ 96%] Built target XNNPACK
2025-03-21T20:25:13.4820079Z   [ 96%] Built target xnnpack_backend
2025-03-21T20:25:13.4820393Z   [ 97%] Built target portable_lib
2025-03-21T20:25:13.4820990Z   [ 97%] Building CXX object kernels/quantized/CMakeFiles/quantized_pybind_kernels_lib.dir/cpu/embeddingxb.cpp.o
2025-03-21T20:25:13.4821850Z   [ 97%] Building CXX object kernels/quantized/CMakeFiles/quantized_pybind_kernels_lib.dir/cpu/op_add.cpp.o
2025-03-21T20:25:13.4822730Z   [ 97%] Building CXX object kernels/quantized/CMakeFiles/quantized_pybind_kernels_lib.dir/cpu/op_choose_qparams.cpp.o
2025-03-21T20:25:13.4823974Z   [ 97%] Building CXX object kernels/quantized/CMakeFiles/quantized_pybind_kernels_lib.dir/cpu/op_dequantize.cpp.o
2025-03-21T20:25:13.4825559Z   [ 97%] Building CXX object kernels/quantized/CMakeFiles/quantized_pybind_kernels_lib.dir/cpu/op_embedding.cpp.o
2025-03-21T20:25:13.4826677Z   [ 97%] Building CXX object kernels/quantized/CMakeFiles/quantized_pybind_kernels_lib.dir/cpu/op_embedding2b.cpp.o
2025-03-21T20:25:13.4827648Z   [ 97%] Building CXX object kernels/quantized/CMakeFiles/quantized_pybind_kernels_lib.dir/cpu/op_embedding4b.cpp.o
2025-03-21T20:25:13.4828560Z   [ 97%] Building CXX object kernels/quantized/CMakeFiles/quantized_pybind_kernels_lib.dir/cpu/op_mixed_linear.cpp.o
2025-03-21T20:25:13.4829446Z   [ 97%] Building CXX object kernels/quantized/CMakeFiles/quantized_pybind_kernels_lib.dir/cpu/op_mixed_mm.cpp.o
2025-03-21T20:25:13.4830313Z   [ 97%] Building CXX object kernels/quantized/CMakeFiles/quantized_pybind_kernels_lib.dir/cpu/op_quantize.cpp.o
2025-03-21T20:25:13.4831009Z   [ 97%] Linking CXX static library libquantized_pybind_kernels_lib.a
2025-03-21T20:25:13.4831676Z   [ 97%] Built target quantized_pybind_kernels_lib
2025-03-21T20:25:13.4832627Z   [ 97%] Generating selected_operators.yaml for quantized_ops_pybind_lib
2025-03-21T20:25:13.4833431Z   [ 97%] Generating code for kernel registration
2025-03-21T20:25:13.4834595Z   [ 97%] Building CXX object kernels/quantized/CMakeFiles/quantized_ops_pybind_lib.dir/quantized_ops_pybind_lib/RegisterCodegenUnboxedKernelsEverything.cpp.o
2025-03-21T20:25:13.4835565Z   [ 98%] Linking CXX static library libquantized_ops_pybind_lib.a
2025-03-21T20:25:13.4836007Z   [ 98%] Built target quantized_ops_pybind_lib
2025-03-21T20:25:13.4836445Z   [ 98%] Generating selected_operators.yaml for quantized_ops_aot_lib
2025-03-21T20:25:13.4839256Z   quantized_decomposed::add.out quantized_decomposed::choose_qparams.Tensor_out quantized_decomposed::choose_qparams_per_token_asymmetric.out quantized_decomposed::dequantize_per_channel.out quantized_decomposed::dequantize_per_tensor.out quantized_decomposed::dequantize_per_tensor.Tensor_out quantized_decomposed::dequantize_per_token.out quantized_decomposed::mixed_linear.out quantized_decomposed::mixed_mm.out quantized_decomposed::quantize_per_channel.out quantized_decomposed::quantize_per_tensor.out quantized_decomposed::quantize_per_tensor.Tensor_out quantized_decomposed::quantize_per_token.out
2025-03-21T20:25:13.4843995Z   [ 98%] Generating code for kernel registration
2025-03-21T20:25:13.4844773Z   [ 98%] Building CXX object kernels/quantized/CMakeFiles/quantized_ops_aot_lib.dir/quantized_ops_aot_lib/RegisterCPUCustomOps.cpp.o
2025-03-21T20:25:13.4845804Z   [ 98%] Building CXX object kernels/quantized/CMakeFiles/quantized_ops_aot_lib.dir/quantized_ops_aot_lib/RegisterSchema.cpp.o
2025-03-21T20:25:13.4846700Z   [ 98%] Building CXX object kernels/quantized/CMakeFiles/quantized_ops_aot_lib.dir/cpu/embeddingxb.cpp.o
2025-03-21T20:25:13.4847496Z   [ 98%] Building CXX object kernels/quantized/CMakeFiles/quantized_ops_aot_lib.dir/cpu/op_add.cpp.o
2025-03-21T20:25:13.4848316Z   [ 98%] Building CXX object kernels/quantized/CMakeFiles/quantized_ops_aot_lib.dir/cpu/op_choose_qparams.cpp.o
2025-03-21T20:25:13.4849577Z   [ 98%] Building CXX object kernels/quantized/CMakeFiles/quantized_ops_aot_lib.dir/cpu/op_dequantize.cpp.o
2025-03-21T20:25:13.4851028Z   [100%] Building CXX object kernels/quantized/CMakeFiles/quantized_ops_aot_lib.dir/cpu/op_embedding.cpp.o
2025-03-21T20:25:13.4852620Z   [100%] Building CXX object kernels/quantized/CMakeFiles/quantized_ops_aot_lib.dir/cpu/op_embedding2b.cpp.o
2025-03-21T20:25:13.4854235Z   [100%] Building CXX object kernels/quantized/CMakeFiles/quantized_ops_aot_lib.dir/cpu/op_embedding4b.cpp.o
2025-03-21T20:25:13.4855678Z   [100%] Building CXX object kernels/quantized/CMakeFiles/quantized_ops_aot_lib.dir/cpu/op_mixed_linear.cpp.o
2025-03-21T20:25:13.4857139Z   [100%] Building CXX object kernels/quantized/CMakeFiles/quantized_ops_aot_lib.dir/cpu/op_mixed_mm.cpp.o
2025-03-21T20:25:13.4857980Z   [100%] Building CXX object kernels/quantized/CMakeFiles/quantized_ops_aot_lib.dir/cpu/op_quantize.cpp.o
2025-03-21T20:25:13.4858885Z   [100%] Building CXX object kernels/quantized/CMakeFiles/quantized_ops_aot_lib.dir/__/portable/cpu/util/reduce_util.cpp.o
2025-03-21T20:25:13.4859905Z   [100%] Building CXX object kernels/quantized/CMakeFiles/quantized_ops_aot_lib.dir/__/__/runtime/core/exec_aten/util/tensor_util_aten.cpp.o
2025-03-21T20:25:13.4860678Z   [100%] Linking CXX shared library libquantized_ops_aot_lib.so
2025-03-21T20:25:13.4861103Z   [100%] Built target quantized_ops_aot_lib
2025-03-21T20:25:13.4861434Z   running build_py
2025-03-21T20:25:13.4861818Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm
2025-03-21T20:25:13.4862721Z   copying backends/arm/arm_backend.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm
2025-03-21T20:25:13.4864063Z   copying backends/arm/arm_vela.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm
2025-03-21T20:25:13.4865223Z   copying backends/arm/ethosu_backend.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm
2025-03-21T20:25:13.4866078Z   copying backends/arm/ethosu_partitioner.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm
2025-03-21T20:25:13.4866896Z   copying backends/arm/process_node.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm
2025-03-21T20:25:13.4867685Z   copying backends/arm/tosa_backend.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm
2025-03-21T20:25:13.4868461Z   copying backends/arm/tosa_mapping.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm
2025-03-21T20:25:13.4869259Z   copying backends/arm/tosa_partitioner.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm
2025-03-21T20:25:13.4870130Z   copying backends/arm/tosa_quant_utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm
2025-03-21T20:25:13.4871588Z   copying backends/arm/tosa_specification.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm
2025-03-21T20:25:13.4872891Z   copying backends/arm/tosa_utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm
2025-03-21T20:25:13.4873589Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/example
2025-03-21T20:25:13.4874340Z   copying backends/example/example_backend.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/example
2025-03-21T20:25:13.5250663Z   copying backends/example/example_partitioner.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/example
2025-03-21T20:25:13.5251721Z   copying backends/example/example_quantizer.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/example
2025-03-21T20:25:13.5252811Z   copying backends/example/test_example_delegate.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/example
2025-03-21T20:25:13.5254117Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/mediatek
2025-03-21T20:25:13.5255328Z   copying backends/mediatek/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/mediatek
2025-03-21T20:25:13.5256247Z   copying backends/mediatek/partitioner.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/mediatek
2025-03-21T20:25:13.5257411Z   copying backends/mediatek/preprocess.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/mediatek
2025-03-21T20:25:13.5258143Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm
2025-03-21T20:25:13.5258891Z   copying backends/qualcomm/qnn_preprocess.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm
2025-03-21T20:25:13.5259644Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms
2025-03-21T20:25:13.5260363Z   copying backends/transforms/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms
2025-03-21T20:25:13.5261973Z   copying backends/transforms/addmm_mm_to_linear.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms
2025-03-21T20:25:13.5263718Z   copying backends/transforms/convert_dtype_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms
2025-03-21T20:25:13.5264700Z   copying backends/transforms/decompose_sdpa.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms
2025-03-21T20:25:13.5265702Z   copying backends/transforms/duplicate_dynamic_quant_chain.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms
2025-03-21T20:25:13.5266723Z   copying backends/transforms/fuse_batch_norm_with_conv.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms
2025-03-21T20:25:13.5267703Z   copying backends/transforms/fuse_conv_with_clamp.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms
2025-03-21T20:25:13.5268649Z   copying backends/transforms/fuse_dequant_linear.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms
2025-03-21T20:25:13.5270241Z   copying backends/transforms/fuse_view_copy.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms
2025-03-21T20:25:13.5271748Z   copying backends/transforms/mean_to_sum_div.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms
2025-03-21T20:25:13.5272688Z   copying backends/transforms/rank_0_to_rank_1.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms
2025-03-21T20:25:13.5273611Z   copying backends/transforms/remove_clone_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms
2025-03-21T20:25:13.5274588Z   copying backends/transforms/replace_scalar_with_tensor.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms
2025-03-21T20:25:13.5275521Z   copying backends/transforms/utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms
2025-03-21T20:25:13.5276498Z   copying backends/transforms/view_copy_to_squeeze_unsqueeze.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms
2025-03-21T20:25:13.5277905Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan
2025-03-21T20:25:13.5279085Z   copying backends/vulkan/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan
2025-03-21T20:25:13.5279979Z   copying backends/vulkan/custom_ops_lib.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan
2025-03-21T20:25:13.5280826Z   copying backends/vulkan/op_registry.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan
2025-03-21T20:25:13.5281633Z   copying backends/vulkan/utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan
2025-03-21T20:25:13.5282474Z   copying backends/vulkan/vulkan_preprocess.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan
2025-03-21T20:25:13.5283204Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack
2025-03-21T20:25:13.5283899Z   copying backends/xnnpack/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack
2025-03-21T20:25:13.5284846Z   copying backends/xnnpack/xnnpack_preprocess.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack
2025-03-21T20:25:13.5286168Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps
2025-03-21T20:25:13.5287630Z   copying backends/apple/mps/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps
2025-03-21T20:25:13.5288526Z   copying backends/apple/mps/mps_preprocess.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps
2025-03-21T20:25:13.5289399Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/coreml/compiler
2025-03-21T20:25:13.5290286Z   copying backends/apple/coreml/compiler/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/coreml/compiler
2025-03-21T20:25:13.5291403Z   copying backends/apple/coreml/compiler/coreml_preprocess.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/coreml/compiler
2025-03-21T20:25:13.5292340Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/coreml/partition
2025-03-21T20:25:13.5293826Z   copying backends/apple/coreml/partition/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/coreml/partition
2025-03-21T20:25:13.5295883Z   copying backends/apple/coreml/partition/coreml_partitioner.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/coreml/partition
2025-03-21T20:25:13.5297610Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/coreml/quantizer
2025-03-21T20:25:13.5298534Z   copying backends/apple/coreml/quantizer/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/coreml/quantizer
2025-03-21T20:25:13.5299648Z   copying backends/apple/coreml/quantizer/coreml_quantizer.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/coreml/quantizer
2025-03-21T20:25:13.5300567Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/coreml/test
2025-03-21T20:25:13.5301469Z   copying backends/apple/coreml/test/test_coreml_partitioner.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/coreml/test
2025-03-21T20:25:13.5302591Z   copying backends/apple/coreml/test/test_coreml_quantizer.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/coreml/test
2025-03-21T20:25:13.5303544Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/coreml/runtime/inmemoryfs
2025-03-21T20:25:13.5305247Z   copying backends/apple/coreml/runtime/inmemoryfs/setup.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/coreml/runtime/inmemoryfs
2025-03-21T20:25:13.5306807Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/coreml/runtime/test
2025-03-21T20:25:13.5307818Z   copying backends/apple/coreml/runtime/test/export_stateful_model.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/coreml/runtime/test
2025-03-21T20:25:13.5308792Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators
2025-03-21T20:25:13.5309648Z   copying backends/apple/mps/operators/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators
2025-03-21T20:25:13.5310724Z   copying backends/apple/mps/operators/activation_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators
2025-03-21T20:25:13.5311818Z   copying backends/apple/mps/operators/binary_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators
2025-03-21T20:25:13.5313591Z   copying backends/apple/mps/operators/clamp_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators
2025-03-21T20:25:13.5315561Z   copying backends/apple/mps/operators/constant_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators
2025-03-21T20:25:13.5317514Z   copying backends/apple/mps/operators/convolution_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators
2025-03-21T20:25:13.5318848Z   copying backends/apple/mps/operators/indexing_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators
2025-03-21T20:25:13.5320070Z   copying backends/apple/mps/operators/linear_algebra_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators
2025-03-21T20:25:13.5321237Z   copying backends/apple/mps/operators/node_visitor.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators
2025-03-21T20:25:13.5322348Z   copying backends/apple/mps/operators/normalization_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators
2025-03-21T20:25:13.5323438Z   copying backends/apple/mps/operators/op_clone.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators
2025-03-21T20:25:13.5324949Z   copying backends/apple/mps/operators/op_getitem.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators
2025-03-21T20:25:13.5326800Z   copying backends/apple/mps/operators/op_quant_dequant.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators
2025-03-21T20:25:13.5327872Z   copying backends/apple/mps/operators/op_skip_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators
2025-03-21T20:25:13.5734074Z   copying backends/apple/mps/operators/pad_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators
2025-03-21T20:25:13.5735164Z   copying backends/apple/mps/operators/pooling_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators
2025-03-21T20:25:13.5736228Z   copying backends/apple/mps/operators/range_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators
2025-03-21T20:25:13.5737670Z   copying backends/apple/mps/operators/reduce_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators
2025-03-21T20:25:13.5739533Z   copying backends/apple/mps/operators/shape_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators
2025-03-21T20:25:13.5740691Z   copying backends/apple/mps/operators/unary_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators
2025-03-21T20:25:13.5741815Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/partition
2025-03-21T20:25:13.5742675Z   copying backends/apple/mps/partition/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/partition
2025-03-21T20:25:13.5743745Z   copying backends/apple/mps/partition/mps_partitioner.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/partition
2025-03-21T20:25:13.5744657Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/serialization
2025-03-21T20:25:13.5745977Z   copying backends/apple/mps/serialization/mps_graph_schema.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/serialization
2025-03-21T20:25:13.5748088Z   copying backends/apple/mps/serialization/mps_graph_serialize.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/serialization
2025-03-21T20:25:13.5749175Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/test
2025-03-21T20:25:13.5750107Z   copying backends/apple/mps/test/test_mps.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/test
2025-03-21T20:25:13.5751203Z   copying backends/apple/mps/test/test_mps_binary_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/test
2025-03-21T20:25:13.5752224Z   copying backends/apple/mps/test/test_mps_indexing_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/test
2025-03-21T20:25:13.5753269Z   copying backends/apple/mps/test/test_mps_linear.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/test
2025-03-21T20:25:13.5754275Z   copying backends/apple/mps/test/test_mps_models.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/test
2025-03-21T20:25:13.5755283Z   copying backends/apple/mps/test/test_mps_unary_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/test
2025-03-21T20:25:13.5756446Z   copying backends/apple/mps/test/test_mps_utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/test
2025-03-21T20:25:13.5757708Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/utils
2025-03-21T20:25:13.5759123Z   copying backends/apple/mps/utils/mps_utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/utils
2025-03-21T20:25:13.5760422Z   copying backends/apple/mps/utils/quant_utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/utils
2025-03-21T20:25:13.5761458Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5762226Z   copying backends/arm/_passes/_debug_passes.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5763220Z   copying backends/arm/_passes/annotate_channels_last_dim_order_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5764281Z   copying backends/arm/_passes/annotate_decomposed_matmul.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5765269Z   copying backends/arm/_passes/arm_pass_manager.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5766188Z   copying backends/arm/_passes/arm_pass_utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5767098Z   copying backends/arm/_passes/cast_int64_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5768205Z   copying backends/arm/_passes/conv1d_unsqueeze_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5770043Z   copying backends/arm/_passes/convert_any_default_dim_dims_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5771400Z   copying backends/arm/_passes/convert_expand_copy_to_repeat.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5772688Z   copying backends/arm/_passes/convert_full_like_to_full_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5773685Z   copying backends/arm/_passes/convert_minmax_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5774640Z   copying backends/arm/_passes/convert_split_to_slice.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5775625Z   copying backends/arm/_passes/convert_squeezes_to_view.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5777236Z   copying backends/arm/_passes/convert_to_clamp.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5778845Z   copying backends/arm/_passes/decompose_batchnorm_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5780083Z   copying backends/arm/_passes/decompose_div_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5781084Z   copying backends/arm/_passes/decompose_layernorm_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5782077Z   copying backends/arm/_passes/decompose_linear_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5783061Z   copying backends/arm/_passes/decompose_meandim_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5784047Z   copying backends/arm/_passes/decompose_select.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5785684Z   copying backends/arm/_passes/decompose_softmax_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5787248Z   copying backends/arm/_passes/decompose_softmax_unstable_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5788778Z   copying backends/arm/_passes/decompose_var_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5789798Z   copying backends/arm/_passes/fold_qdq_with_annotated_qparams_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5790828Z   copying backends/arm/_passes/fuse_batchnorm2d_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5791799Z   copying backends/arm/_passes/fuse_constant_ops_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5792798Z   copying backends/arm/_passes/fuse_quantized_activation_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5793972Z   copying backends/arm/_passes/insert_rescales_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5795613Z   copying backends/arm/_passes/insert_table_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5797017Z   copying backends/arm/_passes/keep_dims_false_to_squeeze_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5798268Z   copying backends/arm/_passes/match_arg_ranks_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5799254Z   copying backends/arm/_passes/meandim_to_averagepool_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5800208Z   copying backends/arm/_passes/mm_to_bmm_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5801120Z   copying backends/arm/_passes/remove_clone_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5802083Z   copying backends/arm/_passes/scalars_to_attribute_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5803079Z   copying backends/arm/_passes/size_adjust_conv2d_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5804189Z   copying backends/arm/_passes/unsqueeze_before_repeat_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5806028Z   copying backends/arm/_passes/unsqueeze_scalar_placeholders_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes
2025-03-21T20:25:13.5807730Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operator_support
2025-03-21T20:25:13.5809470Z   copying backends/arm/operator_support/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operator_support
2025-03-21T20:25:13.6249949Z   copying backends/arm/operator_support/convolution_support.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operator_support
2025-03-21T20:25:13.6251122Z   copying backends/arm/operator_support/minmax_support.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operator_support
2025-03-21T20:25:13.6252221Z   copying backends/arm/operator_support/pool_2d_support.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operator_support
2025-03-21T20:25:13.6253327Z   copying backends/arm/operator_support/reduce_sum_support.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operator_support
2025-03-21T20:25:13.6255168Z   copying backends/arm/operator_support/right_shift_support.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operator_support
2025-03-21T20:25:13.6256725Z   copying backends/arm/operator_support/slice_copy_support.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operator_support
2025-03-21T20:25:13.6257836Z   copying backends/arm/operator_support/to_copy_support.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operator_support
2025-03-21T20:25:13.6259597Z   copying backends/arm/operator_support/tosa_supported_operators.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operator_support
2025-03-21T20:25:13.6260600Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6261453Z   copying backends/arm/operators/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6263106Z   copying backends/arm/operators/node_visitor.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6264479Z   copying backends/arm/operators/op_abs.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6265384Z   copying backends/arm/operators/op_add.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6266288Z   copying backends/arm/operators/op_amax.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6267210Z   copying backends/arm/operators/op_amin.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6268118Z   copying backends/arm/operators/op_any.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6269032Z   copying backends/arm/operators/op_avg_pool2d.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6269956Z   copying backends/arm/operators/op_bmm.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6270852Z   copying backends/arm/operators/op_cat.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6271803Z   copying backends/arm/operators/op_clamp.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6272763Z   copying backends/arm/operators/op_constant_pad_nd.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6274043Z   copying backends/arm/operators/op_conv2d.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6275680Z   copying backends/arm/operators/op_eq.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6276612Z   copying backends/arm/operators/op_exp.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6277546Z   copying backends/arm/operators/op_full.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6278441Z   copying backends/arm/operators/op_ge.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6279353Z   copying backends/arm/operators/op_get_item.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6280270Z   copying backends/arm/operators/op_gt.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6281167Z   copying backends/arm/operators/op_le.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6282068Z   copying backends/arm/operators/op_log.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6282964Z   copying backends/arm/operators/op_lt.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6283990Z   copying backends/arm/operators/op_max_pool2d.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6285717Z   copying backends/arm/operators/op_maximum.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6286813Z   copying backends/arm/operators/op_minimum.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6287739Z   copying backends/arm/operators/op_mul.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6288815Z   copying backends/arm/operators/op_permute.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6289950Z   copying backends/arm/operators/op_reciprocal.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6290910Z   copying backends/arm/operators/op_repeat.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6292007Z   copying backends/arm/operators/op_rescale.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6293684Z   copying backends/arm/operators/op_rshift.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6294781Z   copying backends/arm/operators/op_rsqrt.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6295717Z   copying backends/arm/operators/op_sigmoid.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6296667Z   copying backends/arm/operators/op_slice.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6297583Z   copying backends/arm/operators/op_sub.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6298480Z   copying backends/arm/operators/op_sum.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6299770Z   copying backends/arm/operators/op_table.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6301301Z   copying backends/arm/operators/op_tanh.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6302244Z   copying backends/arm/operators/op_to_copy.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6303212Z   copying backends/arm/operators/op_to_dim_order_copy.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6304208Z   copying backends/arm/operators/op_transpose.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6305210Z   copying backends/arm/operators/op_upsample_nearest2d.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6306191Z   copying backends/arm/operators/op_view.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6307372Z   copying backends/arm/operators/ops_binary.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6309059Z   copying backends/arm/operators/ops_unary.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators
2025-03-21T20:25:13.6309861Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/quantizer
2025-03-21T20:25:13.6310638Z   copying backends/arm/quantizer/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/quantizer
2025-03-21T20:25:13.6311594Z   copying backends/arm/quantizer/arm_quantizer.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/quantizer
2025-03-21T20:25:13.6312588Z   copying backends/arm/quantizer/arm_quantizer_utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/quantizer
2025-03-21T20:25:13.6313631Z   copying backends/arm/quantizer/quantization_annotator.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/quantizer
2025-03-21T20:25:13.6314688Z   copying backends/arm/quantizer/quantization_config.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/quantizer
2025-03-21T20:25:13.6315493Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test
2025-03-21T20:25:13.6316613Z   copying backends/arm/test/common.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test
2025-03-21T20:25:13.6318056Z   copying backends/arm/test/conftest.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test
2025-03-21T20:25:13.6319112Z   copying backends/arm/test/runner_utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test
2025-03-21T20:25:13.6319971Z   copying backends/arm/test/test_model.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test
2025-03-21T20:25:13.6320689Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/util
2025-03-21T20:25:13.6321452Z   copying backends/arm/util/arm_model_evaluator.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/util
2025-03-21T20:25:13.6322211Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/misc
2025-03-21T20:25:13.6775540Z   copying backends/arm/test/misc/test_custom_partition.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/misc
2025-03-21T20:25:13.6776818Z   copying backends/arm/test/misc/test_debug_feats.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/misc
2025-03-21T20:25:13.6777841Z   copying backends/arm/test/misc/test_dim_order_guards.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/misc
2025-03-21T20:25:13.6778859Z   copying backends/arm/test/misc/test_lifted_tensor.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/misc
2025-03-21T20:25:13.6779866Z   copying backends/arm/test/misc/test_model_evaluator.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/misc
2025-03-21T20:25:13.6780898Z   copying backends/arm/test/misc/test_multiple_delegates.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/misc
2025-03-21T20:25:13.6782214Z   copying backends/arm/test/misc/test_multiple_outputs.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/misc
2025-03-21T20:25:13.6784136Z   copying backends/arm/test/misc/test_partition_decomposed_quantized_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/misc
2025-03-21T20:25:13.6785230Z   copying backends/arm/test/misc/test_tosa_spec.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/misc
2025-03-21T20:25:13.6786079Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/models
2025-03-21T20:25:13.6786917Z   copying backends/arm/test/models/test_conformer.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/models
2025-03-21T20:25:13.6787917Z   copying backends/arm/test/models/test_dl3_arm.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/models
2025-03-21T20:25:13.6789242Z   copying backends/arm/test/models/test_llama.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/models
2025-03-21T20:25:13.6790905Z   copying backends/arm/test/models/test_lstm_arm.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/models
2025-03-21T20:25:13.6791949Z   copying backends/arm/test/models/test_mobilenet_v2_arm.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/models
2025-03-21T20:25:13.6792994Z   copying backends/arm/test/models/test_nn_functional.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/models
2025-03-21T20:25:13.6794020Z   copying backends/arm/test/models/test_nn_modules.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/models
2025-03-21T20:25:13.6795054Z   copying backends/arm/test/models/test_torch_functions.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/models
2025-03-21T20:25:13.6796123Z   copying backends/arm/test/models/test_w2l_arm.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/models
2025-03-21T20:25:13.6797566Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6798662Z   copying backends/arm/test/ops/test_abs.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6799563Z   copying backends/arm/test/ops/test_add.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6800623Z   copying backends/arm/test/ops/test_amax.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6801618Z   copying backends/arm/test/ops/test_amin.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6802518Z   copying backends/arm/test/ops/test_any.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6803558Z   copying backends/arm/test/ops/test_avg_pool2d.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6805266Z   copying backends/arm/test/ops/test_batch_norm.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6806410Z   copying backends/arm/test/ops/test_bitwise.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6807328Z   copying backends/arm/test/ops/test_bmm.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6808217Z   copying backends/arm/test/ops/test_cat.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6809119Z   copying backends/arm/test/ops/test_clamp.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6810131Z   copying backends/arm/test/ops/test_clone.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6811358Z   copying backends/arm/test/ops/test_constant_pad_nd.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6813059Z   copying backends/arm/test/ops/test_conv1d.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6813999Z   copying backends/arm/test/ops/test_conv2d.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6814941Z   copying backends/arm/test/ops/test_conv_combos.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6815912Z   copying backends/arm/test/ops/test_depthwise_conv.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6816852Z   copying backends/arm/test/ops/test_div.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6817738Z   copying backends/arm/test/ops/test_eq.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6819304Z   copying backends/arm/test/ops/test_exp.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6820570Z   copying backends/arm/test/ops/test_expand.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6821489Z   copying backends/arm/test/ops/test_floor.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6822391Z   copying backends/arm/test/ops/test_full.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6823287Z   copying backends/arm/test/ops/test_ge.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6824168Z   copying backends/arm/test/ops/test_gt.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6825092Z   copying backends/arm/test/ops/test_hardsigmoid.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6826192Z   copying backends/arm/test/ops/test_hardswish.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6827930Z   copying backends/arm/test/ops/test_hardtanh.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6828982Z   copying backends/arm/test/ops/test_layer_norm.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6829905Z   copying backends/arm/test/ops/test_le.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6831023Z   copying backends/arm/test/ops/test_linear.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6831924Z   copying backends/arm/test/ops/test_log.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6833039Z   copying backends/arm/test/ops/test_logical.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6834375Z   copying backends/arm/test/ops/test_logsoftmax.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6835989Z   copying backends/arm/test/ops/test_lt.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6836912Z   copying backends/arm/test/ops/test_max_pool.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6837846Z   copying backends/arm/test/ops/test_maximum.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6838795Z   copying backends/arm/test/ops/test_mean_dim.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6839717Z   copying backends/arm/test/ops/test_minimum.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6840620Z   copying backends/arm/test/ops/test_mm.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6842097Z   copying backends/arm/test/ops/test_mul.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6843451Z   copying backends/arm/test/ops/test_permute.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6844410Z   copying backends/arm/test/ops/test_reciprocal.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6845349Z   copying backends/arm/test/ops/test_relu.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6846285Z   copying backends/arm/test/ops/test_repeat.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6847200Z   copying backends/arm/test/ops/test_rshift.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.6848145Z   copying backends/arm/test/ops/test_rsqrt.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.7197307Z   copying backends/arm/test/ops/test_scalars.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.7198402Z   copying backends/arm/test/ops/test_select.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.7199343Z   copying backends/arm/test/ops/test_sigmoid.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.7200320Z   copying backends/arm/test/ops/test_sigmoid_16bit.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.7201301Z   copying backends/arm/test/ops/test_sigmoid_32bit.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.7202248Z   copying backends/arm/test/ops/test_slice.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.7203163Z   copying backends/arm/test/ops/test_softmax.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.7204083Z   copying backends/arm/test/ops/test_split.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.7205031Z   copying backends/arm/test/ops/test_squeeze.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.7206573Z   copying backends/arm/test/ops/test_sub.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.7208109Z   copying backends/arm/test/ops/test_sum.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.7209101Z   copying backends/arm/test/ops/test_tanh.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.7210123Z   copying backends/arm/test/ops/test_to_copy.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.7211061Z   copying backends/arm/test/ops/test_unsqueeze.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.7212041Z   copying backends/arm/test/ops/test_upsample_nearest2d.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.7212999Z   copying backends/arm/test/ops/test_var.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.7213894Z   copying backends/arm/test/ops/test_view.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops
2025-03-21T20:25:13.7214681Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/passes
2025-03-21T20:25:13.7215597Z   copying backends/arm/test/passes/test_cast_int64_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/passes
2025-03-21T20:25:13.7217480Z   copying backends/arm/test/passes/test_convert_to_clamp.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/passes
2025-03-21T20:25:13.7218756Z   copying backends/arm/test/passes/test_fold_qdq_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/passes
2025-03-21T20:25:13.7219798Z   copying backends/arm/test/passes/test_fuse_batchnorm_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/passes
2025-03-21T20:25:13.7220893Z   copying backends/arm/test/passes/test_fuse_constant_ops_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/passes
2025-03-21T20:25:13.7221989Z   copying backends/arm/test/passes/test_insert_table_ops_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/passes
2025-03-21T20:25:13.7223095Z   copying backends/arm/test/passes/test_ioquantization_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/passes
2025-03-21T20:25:13.7225049Z   copying backends/arm/test/passes/test_meandim_to_averagepool2d.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/passes
2025-03-21T20:25:13.7226358Z   copying backends/arm/test/passes/test_rescale_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/passes
2025-03-21T20:25:13.7227458Z   copying backends/arm/test/passes/test_unsqueeze_before_repeat_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/passes
2025-03-21T20:25:13.7228370Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/quantizer
2025-03-21T20:25:13.7229262Z   copying backends/arm/test/quantizer/test_generic_annotater.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/quantizer
2025-03-21T20:25:13.7230155Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/tester
2025-03-21T20:25:13.7230950Z   copying backends/arm/test/tester/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/tester
2025-03-21T20:25:13.7232061Z   copying backends/arm/test/tester/analyze_output_utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/tester
2025-03-21T20:25:13.7234100Z   copying backends/arm/test/tester/arm_tester.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/tester
2025-03-21T20:25:13.7235233Z   copying backends/arm/test/tester/test_pipeline.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/tester
2025-03-21T20:25:13.7236071Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/tosautil
2025-03-21T20:25:13.7236882Z   copying backends/arm/test/tosautil/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/tosautil
2025-03-21T20:25:13.7238021Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib
2025-03-21T20:25:13.7239453Z   copying backends/arm/third-party/serialization_lib/setup.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib
2025-03-21T20:25:13.7241287Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/serializer
2025-03-21T20:25:13.7242589Z   copying backends/arm/third-party/serialization_lib/python/serializer/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/serializer
2025-03-21T20:25:13.7244229Z   copying backends/arm/third-party/serialization_lib/python/serializer/tosa_serializer.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/serializer
2025-03-21T20:25:13.7245549Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:13.7247757Z   copying backends/arm/third-party/serialization_lib/python/tosa/ArithmeticRightShiftAttribute.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:13.7249726Z   copying backends/arm/third-party/serialization_lib/python/tosa/Attribute.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:13.7251264Z   copying backends/arm/third-party/serialization_lib/python/tosa/AxisAttribute.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:13.7252846Z   copying backends/arm/third-party/serialization_lib/python/tosa/ClampAttribute.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:13.7255291Z   copying backends/arm/third-party/serialization_lib/python/tosa/CondIfAttribute.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:13.7257109Z   copying backends/arm/third-party/serialization_lib/python/tosa/ConvAttribute.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:13.7258698Z   copying backends/arm/third-party/serialization_lib/python/tosa/CustomAttribute.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:13.7260238Z   copying backends/arm/third-party/serialization_lib/python/tosa/DType.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:13.7262793Z   copying backends/arm/third-party/serialization_lib/python/tosa/FFTAttribute.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:13.7264452Z   copying backends/arm/third-party/serialization_lib/python/tosa/FullyConnectedAttribute.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:13.7266101Z   copying backends/arm/third-party/serialization_lib/python/tosa/MatMulAttribute.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:13.7267675Z   copying backends/arm/third-party/serialization_lib/python/tosa/MulAttribute.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:13.7270291Z   copying backends/arm/third-party/serialization_lib/python/tosa/NegateAttribute.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:13.7271819Z   copying backends/arm/third-party/serialization_lib/python/tosa/Op.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:13.7668831Z   copying backends/arm/third-party/serialization_lib/python/tosa/PadAttribute.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:13.7670901Z   copying backends/arm/third-party/serialization_lib/python/tosa/PoolAttribute.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:13.7673007Z   copying backends/arm/third-party/serialization_lib/python/tosa/RFFTAttribute.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:13.7674802Z   copying backends/arm/third-party/serialization_lib/python/tosa/RescaleAttribute.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:13.7677564Z   copying backends/arm/third-party/serialization_lib/python/tosa/ReshapeAttribute.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:13.7679336Z   copying backends/arm/third-party/serialization_lib/python/tosa/ResizeAttribute.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:13.7680911Z   copying backends/arm/third-party/serialization_lib/python/tosa/ResizeMode.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:13.7683676Z   copying backends/arm/third-party/serialization_lib/python/tosa/SliceAttribute.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:13.7685410Z   copying backends/arm/third-party/serialization_lib/python/tosa/TableAttribute.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:13.7686998Z   copying backends/arm/third-party/serialization_lib/python/tosa/TileAttribute.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:13.7688589Z   copying backends/arm/third-party/serialization_lib/python/tosa/TosaBasicBlock.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:13.7690242Z   copying backends/arm/third-party/serialization_lib/python/tosa/TosaGraph.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:13.7691794Z   copying backends/arm/third-party/serialization_lib/python/tosa/TosaOperator.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:13.7693348Z   copying backends/arm/third-party/serialization_lib/python/tosa/TosaRegion.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:13.7694895Z   copying backends/arm/third-party/serialization_lib/python/tosa/TosaTensor.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:13.7696488Z   copying backends/arm/third-party/serialization_lib/python/tosa/TransposeAttribute.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:13.7698150Z   copying backends/arm/third-party/serialization_lib/python/tosa/TransposeConvAttribute.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:13.7699747Z   copying backends/arm/third-party/serialization_lib/python/tosa/Version.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:13.7701321Z   copying backends/arm/third-party/serialization_lib/python/tosa/WhileLoopAttribute.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:13.7703107Z   copying backends/arm/third-party/serialization_lib/python/tosa/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:13.7704296Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/test/scripts
2025-03-21T20:25:13.7706483Z   copying backends/arm/third-party/serialization_lib/test/scripts/test_npy_fileio.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/test/scripts
2025-03-21T20:25:13.7707996Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/test/scripts/xunit
2025-03-21T20:25:13.7709302Z   copying backends/arm/third-party/serialization_lib/test/scripts/xunit/xunit.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/test/scripts/xunit
2025-03-21T20:25:13.7710423Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot
2025-03-21T20:25:13.7711162Z   copying backends/cadence/aot/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot
2025-03-21T20:25:13.7712450Z   copying backends/cadence/aot/compiler.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot
2025-03-21T20:25:13.7714000Z   copying backends/cadence/aot/compiler_utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot
2025-03-21T20:25:13.7714953Z   copying backends/cadence/aot/export_example.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot
2025-03-21T20:25:13.7715863Z   copying backends/cadence/aot/fuse_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot
2025-03-21T20:25:13.7716771Z   copying backends/cadence/aot/graph_builder.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot
2025-03-21T20:25:13.7717739Z   copying backends/cadence/aot/memory_constraints.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot
2025-03-21T20:25:13.7718706Z   copying backends/cadence/aot/memory_planning.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot
2025-03-21T20:25:13.7720011Z   copying backends/cadence/aot/ops_registrations.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot
2025-03-21T20:25:13.7721628Z   copying backends/cadence/aot/pass_utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot
2025-03-21T20:25:13.7722514Z   copying backends/cadence/aot/passes.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot
2025-03-21T20:25:13.7723451Z   copying backends/cadence/aot/ref_implementations.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot
2025-03-21T20:25:13.7724397Z   copying backends/cadence/aot/remove_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot
2025-03-21T20:25:13.7725318Z   copying backends/cadence/aot/reorder_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot
2025-03-21T20:25:13.7726549Z   copying backends/cadence/aot/replace_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot
2025-03-21T20:25:13.7728153Z   copying backends/cadence/aot/simplify_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot
2025-03-21T20:25:13.7729059Z   copying backends/cadence/aot/utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot
2025-03-21T20:25:13.7729905Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/runtime
2025-03-21T20:25:13.7730704Z   copying backends/cadence/runtime/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/runtime
2025-03-21T20:25:13.7731666Z   copying backends/cadence/runtime/executor.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/runtime
2025-03-21T20:25:13.7732986Z   copying backends/cadence/runtime/runtime.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/runtime
2025-03-21T20:25:13.7734033Z   copying backends/cadence/runtime/utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/runtime
2025-03-21T20:25:13.7734819Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils
2025-03-21T20:25:13.7735595Z   copying backends/cadence/utils/facto_util.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils
2025-03-21T20:25:13.7736537Z   copying backends/cadence/utils/gen_header.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils
2025-03-21T20:25:13.7737516Z   copying backends/cadence/utils/post_compilation.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils
2025-03-21T20:25:13.7738450Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/quantizer
2025-03-21T20:25:13.7740045Z   copying backends/cadence/aot/quantizer/fusion_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/quantizer
2025-03-21T20:25:13.7741504Z   copying backends/cadence/aot/quantizer/patterns.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/quantizer
2025-03-21T20:25:13.7742622Z   copying backends/cadence/aot/quantizer/quantizer.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/quantizer
2025-03-21T20:25:13.7743709Z   copying backends/cadence/aot/quantizer/utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/quantizer
2025-03-21T20:25:13.7999589Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/tests
2025-03-21T20:25:13.8000773Z   copying backends/cadence/aot/tests/test_fusion_ops_passes.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/tests
2025-03-21T20:25:13.8001885Z   copying backends/cadence/aot/tests/test_graph_builder.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/tests
2025-03-21T20:25:13.8002980Z   copying backends/cadence/aot/tests/test_memory_passes.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/tests
2025-03-21T20:25:13.8004040Z   copying backends/cadence/aot/tests/test_pass_filter.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/tests
2025-03-21T20:25:13.8005535Z   copying backends/cadence/aot/tests/test_remove_ops_passes.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/tests
2025-03-21T20:25:13.8007421Z   copying backends/cadence/aot/tests/test_reorder_ops_passes.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/tests
2025-03-21T20:25:13.8008673Z   copying backends/cadence/aot/tests/test_replace_ops_passes.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/tests
2025-03-21T20:25:13.8009903Z   copying backends/cadence/aot/tests/test_simplify_ops_passes.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/tests
2025-03-21T20:25:13.8010805Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO
2025-03-21T20:25:13.8012174Z   copying backends/cadence/utils/FACTO/setup.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO
2025-03-21T20:25:13.8013715Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/calibrator
2025-03-21T20:25:13.8014867Z   copying backends/cadence/utils/FACTO/calibrator/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/calibrator
2025-03-21T20:25:13.8016117Z   copying backends/cadence/utils/FACTO/calibrator/runner.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/calibrator
2025-03-21T20:25:13.8017126Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/examples
2025-03-21T20:25:13.8018526Z   copying backends/cadence/utils/FACTO/examples/example.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/examples
2025-03-21T20:25:13.8020869Z   copying backends/cadence/utils/FACTO/examples/minimal_example.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/examples
2025-03-21T20:25:13.8022180Z   copying backends/cadence/utils/FACTO/examples/random_seed.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/examples
2025-03-21T20:25:13.8023170Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto
2025-03-21T20:25:13.8024112Z   copying backends/cadence/utils/FACTO/facto/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto
2025-03-21T20:25:13.8025608Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen
2025-03-21T20:25:13.8027353Z   copying backends/cadence/utils/FACTO/facto/inputgen/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen
2025-03-21T20:25:13.8028520Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/specdb
2025-03-21T20:25:13.8029554Z   copying backends/cadence/utils/FACTO/facto/specdb/db.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/specdb
2025-03-21T20:25:13.8030824Z   copying backends/cadence/utils/FACTO/facto/specdb/default.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/specdb
2025-03-21T20:25:13.8033322Z   copying backends/cadence/utils/FACTO/facto/specdb/dtypes.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/specdb
2025-03-21T20:25:13.8034960Z   copying backends/cadence/utils/FACTO/facto/specdb/function.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/specdb
2025-03-21T20:25:13.8036082Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/argtuple
2025-03-21T20:25:13.8037308Z   copying backends/cadence/utils/FACTO/facto/inputgen/argtuple/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/argtuple
2025-03-21T20:25:13.8038827Z   copying backends/cadence/utils/FACTO/facto/inputgen/argtuple/engine.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/argtuple
2025-03-21T20:25:13.8040336Z   copying backends/cadence/utils/FACTO/facto/inputgen/argtuple/gen.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/argtuple
2025-03-21T20:25:13.8041532Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/argument
2025-03-21T20:25:13.8042721Z   copying backends/cadence/utils/FACTO/facto/inputgen/argument/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/argument
2025-03-21T20:25:13.8044238Z   copying backends/cadence/utils/FACTO/facto/inputgen/argument/engine.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/argument
2025-03-21T20:25:13.8045752Z   copying backends/cadence/utils/FACTO/facto/inputgen/argument/gen.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/argument
2025-03-21T20:25:13.8047452Z   copying backends/cadence/utils/FACTO/facto/inputgen/argument/type.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/argument
2025-03-21T20:25:13.8049710Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/attribute
2025-03-21T20:25:13.8051183Z   copying backends/cadence/utils/FACTO/facto/inputgen/attribute/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/attribute
2025-03-21T20:25:13.8052741Z   copying backends/cadence/utils/FACTO/facto/inputgen/attribute/engine.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/attribute
2025-03-21T20:25:13.8054549Z   copying backends/cadence/utils/FACTO/facto/inputgen/attribute/model.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/attribute
2025-03-21T20:25:13.8056092Z   copying backends/cadence/utils/FACTO/facto/inputgen/attribute/solve.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/attribute
2025-03-21T20:25:13.8057308Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/specs
2025-03-21T20:25:13.8058458Z   copying backends/cadence/utils/FACTO/facto/inputgen/specs/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/specs
2025-03-21T20:25:13.8060777Z   copying backends/cadence/utils/FACTO/facto/inputgen/specs/model.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/specs
2025-03-21T20:25:13.8062419Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/utils
2025-03-21T20:25:13.8063589Z   copying backends/cadence/utils/FACTO/facto/inputgen/utils/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/utils
2025-03-21T20:25:13.8065638Z   copying backends/cadence/utils/FACTO/facto/inputgen/utils/random_manager.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/utils
2025-03-21T20:25:13.8067574Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/variable
2025-03-21T20:25:13.8068801Z   copying backends/cadence/utils/FACTO/facto/inputgen/variable/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/variable
2025-03-21T20:25:13.8070353Z   copying backends/cadence/utils/FACTO/facto/inputgen/variable/constants.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/variable
2025-03-21T20:25:13.8072745Z   copying backends/cadence/utils/FACTO/facto/inputgen/variable/gen.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/variable
2025-03-21T20:25:13.8074655Z   copying backends/cadence/utils/FACTO/facto/inputgen/variable/solve.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/variable
2025-03-21T20:25:13.8076184Z   copying backends/cadence/utils/FACTO/facto/inputgen/variable/space.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/variable
2025-03-21T20:25:13.8077699Z   copying backends/cadence/utils/FACTO/facto/inputgen/variable/type.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/variable
2025-03-21T20:25:13.8079614Z   copying backends/cadence/utils/FACTO/facto/inputgen/variable/utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/variable
2025-03-21T20:25:13.8426485Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/test/inputgen
2025-03-21T20:25:13.8427812Z   copying backends/cadence/utils/FACTO/test/inputgen/test_argtuple_engine.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/test/inputgen
2025-03-21T20:25:13.8429249Z   copying backends/cadence/utils/FACTO/test/inputgen/test_argtuple_generator.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/test/inputgen
2025-03-21T20:25:13.8430970Z   copying backends/cadence/utils/FACTO/test/inputgen/test_argument_attributes.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/test/inputgen
2025-03-21T20:25:13.8433516Z   copying backends/cadence/utils/FACTO/test/inputgen/test_argument_generator.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/test/inputgen
2025-03-21T20:25:13.8435204Z   copying backends/cadence/utils/FACTO/test/inputgen/test_argument_types.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/test/inputgen
2025-03-21T20:25:13.8437082Z   copying backends/cadence/utils/FACTO/test/inputgen/test_attribute_engine.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/test/inputgen
2025-03-21T20:25:13.8439193Z   copying backends/cadence/utils/FACTO/test/inputgen/test_attribute_solver.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/test/inputgen
2025-03-21T20:25:13.8440608Z   copying backends/cadence/utils/FACTO/test/inputgen/test_constraints.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/test/inputgen
2025-03-21T20:25:13.8442000Z   copying backends/cadence/utils/FACTO/test/inputgen/test_meta_arg_engine.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/test/inputgen
2025-03-21T20:25:13.8444323Z   copying backends/cadence/utils/FACTO/test/inputgen/test_specs.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/test/inputgen
2025-03-21T20:25:13.8445880Z   copying backends/cadence/utils/FACTO/test/inputgen/test_structural_engine.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/test/inputgen
2025-03-21T20:25:13.8447323Z   copying backends/cadence/utils/FACTO/test/inputgen/test_variable_generation.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/test/inputgen
2025-03-21T20:25:13.8448866Z   copying backends/cadence/utils/FACTO/test/inputgen/test_variable_solving.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/test/inputgen
2025-03-21T20:25:13.8451388Z   copying backends/cadence/utils/FACTO/test/inputgen/test_variable_space.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/test/inputgen
2025-03-21T20:25:13.8452812Z   copying backends/cadence/utils/FACTO/test/inputgen/test_variable_types.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/test/inputgen
2025-03-21T20:25:13.8453961Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/example/example_backend_delegate_passes
2025-03-21T20:25:13.8456021Z   copying backends/example/example_backend_delegate_passes/merge_to_dim_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/example/example_backend_delegate_passes
2025-03-21T20:25:13.8457684Z   copying backends/example/example_backend_delegate_passes/permute_memory_formats_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/example/example_backend_delegate_passes
2025-03-21T20:25:13.8458815Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/example/example_operators
2025-03-21T20:25:13.8459842Z   copying backends/example/example_operators/adaptive_avg_pool2d.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/example/example_operators
2025-03-21T20:25:13.8461985Z   copying backends/example/example_operators/add.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/example/example_operators
2025-03-21T20:25:13.8463189Z   copying backends/example/example_operators/conv2d.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/example/example_operators
2025-03-21T20:25:13.8464325Z   copying backends/example/example_operators/conv_relu.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/example/example_operators
2025-03-21T20:25:13.8465465Z   copying backends/example/example_operators/dropout.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/example/example_operators
2025-03-21T20:25:13.8466766Z   copying backends/example/example_operators/flatten.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/example/example_operators
2025-03-21T20:25:13.8468772Z   copying backends/example/example_operators/linear.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/example/example_operators
2025-03-21T20:25:13.8470056Z   copying backends/example/example_operators/op_base.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/example/example_operators
2025-03-21T20:25:13.8471237Z   copying backends/example/example_operators/ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/example/example_operators
2025-03-21T20:25:13.8472357Z   copying backends/example/example_operators/utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/example/example_operators
2025-03-21T20:25:13.8473715Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/mediatek/_passes
2025-03-21T20:25:13.8475118Z   copying backends/mediatek/_passes/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/mediatek/_passes
2025-03-21T20:25:13.8476239Z   copying backends/mediatek/_passes/decompose_scaled_dot_product_attention.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/mediatek/_passes
2025-03-21T20:25:13.8477168Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/mediatek/quantizer
2025-03-21T20:25:13.8478019Z   copying backends/mediatek/quantizer/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/mediatek/quantizer
2025-03-21T20:25:13.8479145Z   copying backends/mediatek/quantizer/annotator.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/mediatek/quantizer
2025-03-21T20:25:13.8481034Z   copying backends/mediatek/quantizer/qconfig.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/mediatek/quantizer
2025-03-21T20:25:13.8482214Z   copying backends/mediatek/quantizer/quantizer.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/mediatek/quantizer
2025-03-21T20:25:13.8483069Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes
2025-03-21T20:25:13.8483873Z   copying backends/qualcomm/_passes/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes
2025-03-21T20:25:13.8484869Z   copying backends/qualcomm/_passes/annotate_decomposed.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes
2025-03-21T20:25:13.8485933Z   copying backends/qualcomm/_passes/annotate_quant_attrs.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes
2025-03-21T20:25:13.8486956Z   copying backends/qualcomm/_passes/build_quant_io.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes
2025-03-21T20:25:13.8487967Z   copying backends/qualcomm/_passes/constant_i64_to_i32.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes
2025-03-21T20:25:13.8489002Z   copying backends/qualcomm/_passes/convert_bmm_to_matmul.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes
2025-03-21T20:25:13.8490247Z   copying backends/qualcomm/_passes/convert_interpolate_with_upsample2d.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes
2025-03-21T20:25:13.8491357Z   copying backends/qualcomm/_passes/convert_to_linear.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes
2025-03-21T20:25:13.8492383Z   copying backends/qualcomm/_passes/decompose_any.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes
2025-03-21T20:25:13.8493809Z   copying backends/qualcomm/_passes/decompose_einsum.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes
2025-03-21T20:25:13.8495754Z   copying backends/qualcomm/_passes/decompose_linalg_vector_norm.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes
2025-03-21T20:25:13.8497557Z   copying backends/qualcomm/_passes/decompose_silu.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes
2025-03-21T20:25:13.8498651Z   copying backends/qualcomm/_passes/expand_broadcast_tensor_shape.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes
2025-03-21T20:25:13.8499701Z   copying backends/qualcomm/_passes/fold_qdq.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes
2025-03-21T20:25:13.8500945Z   copying backends/qualcomm/_passes/fuse_consecutive_transpose.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes
2025-03-21T20:25:13.8501999Z   copying backends/qualcomm/_passes/insert_io_qdq.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes
2025-03-21T20:25:13.8503001Z   copying backends/qualcomm/_passes/insert_requantize.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes
2025-03-21T20:25:13.8504471Z   copying backends/qualcomm/_passes/layout_transform.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes
2025-03-21T20:25:13.8875321Z   copying backends/qualcomm/_passes/lift_constant_scalar_operands.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes
2025-03-21T20:25:13.8876496Z   copying backends/qualcomm/_passes/recompose_pixel_unshuffle.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes
2025-03-21T20:25:13.8877592Z   copying backends/qualcomm/_passes/recompose_prelu.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes
2025-03-21T20:25:13.8878639Z   copying backends/qualcomm/_passes/recompose_rms_norm.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes
2025-03-21T20:25:13.8879873Z   copying backends/qualcomm/_passes/reduce_dynamic_range.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes
2025-03-21T20:25:13.8881745Z   copying backends/qualcomm/_passes/remove_redundancy.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes
2025-03-21T20:25:13.8882913Z   copying backends/qualcomm/_passes/replace_index_put_input.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes
2025-03-21T20:25:13.8883959Z   copying backends/qualcomm/_passes/replace_inf_buffer.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes
2025-03-21T20:25:13.8884992Z   copying backends/qualcomm/_passes/tensor_i64_to_i32.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes
2025-03-21T20:25:13.8885972Z   copying backends/qualcomm/_passes/utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes
2025-03-21T20:25:13.8886773Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8888070Z   copying backends/qualcomm/builders/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8889732Z   copying backends/qualcomm/builders/node_visitor.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8890756Z   copying backends/qualcomm/builders/op_abs.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8891781Z   copying backends/qualcomm/builders/op_adaptive_avg_pool2d.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8892831Z   copying backends/qualcomm/builders/op_add.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8893820Z   copying backends/qualcomm/builders/op_arange.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8895182Z   copying backends/qualcomm/builders/op_argmin.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8896860Z   copying backends/qualcomm/builders/op_avg_pool2d.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8897903Z   copying backends/qualcomm/builders/op_batch_norm.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8898908Z   copying backends/qualcomm/builders/op_bmm.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8900073Z   copying backends/qualcomm/builders/op_cat.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8901124Z   copying backends/qualcomm/builders/op_ceil.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8902167Z   copying backends/qualcomm/builders/op_clamp.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8903963Z   copying backends/qualcomm/builders/op_conv2d.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8905142Z   copying backends/qualcomm/builders/op_cos.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8906159Z   copying backends/qualcomm/builders/op_depth_to_space.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8907208Z   copying backends/qualcomm/builders/op_dequantize.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8908225Z   copying backends/qualcomm/builders/op_div.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8909221Z   copying backends/qualcomm/builders/op_embedding.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8910693Z   copying backends/qualcomm/builders/op_eq.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8912207Z   copying backends/qualcomm/builders/op_expand.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8913208Z   copying backends/qualcomm/builders/op_full.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8914208Z   copying backends/qualcomm/builders/op_full_like.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8915192Z   copying backends/qualcomm/builders/op_ge.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8916170Z   copying backends/qualcomm/builders/op_gelu.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8917183Z   copying backends/qualcomm/builders/op_group_norm.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8918987Z   copying backends/qualcomm/builders/op_gt.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8920179Z   copying backends/qualcomm/builders/op_hardsigmoid.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8921220Z   copying backends/qualcomm/builders/op_hardswish.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8922241Z   copying backends/qualcomm/builders/op_hardtanh.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8923247Z   copying backends/qualcomm/builders/op_index.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8924250Z   copying backends/qualcomm/builders/op_index_put.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8925925Z   copying backends/qualcomm/builders/op_instance_norm.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8927350Z   copying backends/qualcomm/builders/op_layer_norm.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8928344Z   copying backends/qualcomm/builders/op_le.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8929407Z   copying backends/qualcomm/builders/op_linear.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8930517Z   copying backends/qualcomm/builders/op_log.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8931578Z   copying backends/qualcomm/builders/op_log_softmax.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8932810Z   copying backends/qualcomm/builders/op_logical_not.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8934587Z   copying backends/qualcomm/builders/op_lt.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8936037Z   copying backends/qualcomm/builders/op_matmul.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8937042Z   copying backends/qualcomm/builders/op_max.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8938027Z   copying backends/qualcomm/builders/op_max_pool2d.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8939058Z   copying backends/qualcomm/builders/op_mean_dim.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8940042Z   copying backends/qualcomm/builders/op_min.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8941558Z   copying backends/qualcomm/builders/op_mul.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8943056Z   copying backends/qualcomm/builders/op_ne.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8944156Z   copying backends/qualcomm/builders/op_neg.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8945124Z   copying backends/qualcomm/builders/op_or.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8946078Z   copying backends/qualcomm/builders/op_pad.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8947060Z   copying backends/qualcomm/builders/op_pow.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.8948033Z   copying backends/qualcomm/builders/op_prelu.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.9375236Z   copying backends/qualcomm/builders/op_quantize.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.9376432Z   copying backends/qualcomm/builders/op_relu.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.9377431Z   copying backends/qualcomm/builders/op_repeat.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.9378435Z   copying backends/qualcomm/builders/op_reshape.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.9379451Z   copying backends/qualcomm/builders/op_rms_norm.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.9380512Z   copying backends/qualcomm/builders/op_rsqrt.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.9382275Z   copying backends/qualcomm/builders/op_select_copy.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.9384140Z   copying backends/qualcomm/builders/op_sigmoid.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.9385523Z   copying backends/qualcomm/builders/op_sin.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.9386511Z   copying backends/qualcomm/builders/op_skip_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.9387530Z   copying backends/qualcomm/builders/op_slice_copy.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.9388825Z   copying backends/qualcomm/builders/op_softmax.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.9389963Z   copying backends/qualcomm/builders/op_space_to_depth.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.9391865Z   copying backends/qualcomm/builders/op_split_with_sizes.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.9393742Z   copying backends/qualcomm/builders/op_sqrt.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.9394919Z   copying backends/qualcomm/builders/op_squeeze.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.9395911Z   copying backends/qualcomm/builders/op_sub.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.9396918Z   copying backends/qualcomm/builders/op_sum_int_list.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.9397928Z   copying backends/qualcomm/builders/op_tanh.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.9398897Z   copying backends/qualcomm/builders/op_to.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.9399865Z   copying backends/qualcomm/builders/op_topk.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.9400853Z   copying backends/qualcomm/builders/op_transpose.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.9401881Z   copying backends/qualcomm/builders/op_unsqueeze.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.9402951Z   copying backends/qualcomm/builders/op_upsample_bilinear2d.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.9404065Z   copying backends/qualcomm/builders/op_upsample_nearest2d.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.9405111Z   copying backends/qualcomm/builders/op_where.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.9406130Z   copying backends/qualcomm/builders/qnn_constants.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.9407146Z   copying backends/qualcomm/builders/utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders
2025-03-21T20:25:13.9407967Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/debugger
2025-03-21T20:25:13.9408776Z   copying backends/qualcomm/debugger/utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/debugger
2025-03-21T20:25:13.9409713Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/partition
2025-03-21T20:25:13.9410817Z   copying backends/qualcomm/partition/common_defs.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/partition
2025-03-21T20:25:13.9412738Z   copying backends/qualcomm/partition/qnn_partitioner.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/partition
2025-03-21T20:25:13.9424241Z   copying backends/qualcomm/partition/utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/partition
2025-03-21T20:25:13.9425752Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/quantizer
2025-03-21T20:25:13.9426917Z   copying backends/qualcomm/quantizer/annotators.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/quantizer
2025-03-21T20:25:13.9428011Z   copying backends/qualcomm/quantizer/custom_annotation.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/quantizer
2025-03-21T20:25:13.9429210Z   copying backends/qualcomm/quantizer/qconfig.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/quantizer
2025-03-21T20:25:13.9430301Z   copying backends/qualcomm/quantizer/quantizer.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/quantizer
2025-03-21T20:25:13.9431176Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/serialization
2025-03-21T20:25:13.9432087Z   copying backends/qualcomm/serialization/qc_schema.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/serialization
2025-03-21T20:25:13.9433514Z   copying backends/qualcomm/serialization/qc_schema_serialize.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/serialization
2025-03-21T20:25:13.9434620Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/tests
2025-03-21T20:25:13.9436025Z   copying backends/qualcomm/tests/models.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/tests
2025-03-21T20:25:13.9437368Z   copying backends/qualcomm/tests/test_qnn_delegate.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/tests
2025-03-21T20:25:13.9438331Z   copying backends/qualcomm/tests/utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/tests
2025-03-21T20:25:13.9439117Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/utils
2025-03-21T20:25:13.9439933Z   copying backends/qualcomm/utils/constants.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/utils
2025-03-21T20:25:13.9440884Z   copying backends/qualcomm/utils/utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/utils
2025-03-21T20:25:13.9441734Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/quantizer/observers
2025-03-21T20:25:13.9443048Z   copying backends/qualcomm/quantizer/observers/per_channel_param_observer.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/quantizer/observers
2025-03-21T20:25:13.9444903Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms/test
2025-03-21T20:25:13.9446611Z   copying backends/transforms/test/test_create_delete_constant_placeholder.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms/test
2025-03-21T20:25:13.9447906Z   copying backends/transforms/test/test_duplicate_dynamic_quant_chain.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms/test
2025-03-21T20:25:13.9449019Z   copying backends/transforms/test/test_rank_0_to_rank_1.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms/test
2025-03-21T20:25:13.9449947Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/_passes
2025-03-21T20:25:13.9450730Z   copying backends/vulkan/_passes/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/_passes
2025-03-21T20:25:13.9451956Z   copying backends/vulkan/_passes/insert_prepack_nodes.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/_passes
2025-03-21T20:25:13.9453795Z   copying backends/vulkan/_passes/int4_weight_only_quantizer.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/_passes
2025-03-21T20:25:13.9454836Z   copying backends/vulkan/_passes/remove_asserts.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/_passes
2025-03-21T20:25:13.9455862Z   copying backends/vulkan/_passes/remove_local_scalar_dense_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/_passes
2025-03-21T20:25:13.9456914Z   copying backends/vulkan/_passes/remove_redundant_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/_passes
2025-03-21T20:25:13.9457960Z   copying backends/vulkan/_passes/squeeze_unsqueeze_inputs.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/_passes
2025-03-21T20:25:13.9458995Z   copying backends/vulkan/_passes/tag_memory_meta_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/_passes
2025-03-21T20:25:13.9460069Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/partitioner
2025-03-21T20:25:13.9866730Z   copying backends/vulkan/partitioner/vulkan_partitioner.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/partitioner
2025-03-21T20:25:13.9867674Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/quantizer
2025-03-21T20:25:13.9868546Z   copying backends/vulkan/quantizer/vulkan_quantizer.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/quantizer
2025-03-21T20:25:13.9869393Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime
2025-03-21T20:25:13.9870197Z   copying backends/vulkan/runtime/gen_vulkan_spv.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime
2025-03-21T20:25:13.9871189Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/serialization
2025-03-21T20:25:13.9872858Z   copying backends/vulkan/serialization/vulkan_graph_builder.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/serialization
2025-03-21T20:25:13.9874348Z   copying backends/vulkan/serialization/vulkan_graph_schema.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/serialization
2025-03-21T20:25:13.9875551Z   copying backends/vulkan/serialization/vulkan_graph_serialize.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/serialization
2025-03-21T20:25:13.9876453Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/test
2025-03-21T20:25:13.9877253Z   copying backends/vulkan/test/test_serialization.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/test
2025-03-21T20:25:13.9878226Z   copying backends/vulkan/test/test_vulkan_delegate.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/test
2025-03-21T20:25:13.9879238Z   copying backends/vulkan/test/test_vulkan_delegate_header.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/test
2025-03-21T20:25:13.9880110Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/test/op_tests
2025-03-21T20:25:13.9880966Z   copying backends/vulkan/test/op_tests/cases.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/test/op_tests
2025-03-21T20:25:13.9882245Z   copying backends/vulkan/test/op_tests/generate_op_benchmarks.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/test/op_tests
2025-03-21T20:25:13.9884318Z   copying backends/vulkan/test/op_tests/generate_op_correctness_tests.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/test/op_tests
2025-03-21T20:25:13.9885446Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/test/op_tests/utils
2025-03-21T20:25:13.9886395Z   copying backends/vulkan/test/op_tests/utils/aten_types.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/test/op_tests/utils
2025-03-21T20:25:13.9887583Z   copying backends/vulkan/test/op_tests/utils/gen_benchmark_vk.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/test/op_tests/utils
2025-03-21T20:25:13.9888791Z   copying backends/vulkan/test/op_tests/utils/gen_computegraph.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/test/op_tests/utils
2025-03-21T20:25:13.9890097Z   copying backends/vulkan/test/op_tests/utils/gen_correctness_base.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/test/op_tests/utils
2025-03-21T20:25:13.9891324Z   copying backends/vulkan/test/op_tests/utils/gen_correctness_vk.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/test/op_tests/utils
2025-03-21T20:25:13.9893343Z   copying backends/vulkan/test/op_tests/utils/test_suite.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/test/op_tests/utils
2025-03-21T20:25:13.9894598Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/third-party/volk
2025-03-21T20:25:13.9895777Z   copying backends/vulkan/third-party/volk/generate.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/third-party/volk
2025-03-21T20:25:13.9896870Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/third-party/Vulkan-Headers/registry
2025-03-21T20:25:13.9898099Z   copying backends/vulkan/third-party/Vulkan-Headers/registry/apiconventions.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/third-party/Vulkan-Headers/registry
2025-03-21T20:25:13.9900690Z   copying backends/vulkan/third-party/Vulkan-Headers/registry/cgenerator.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/third-party/Vulkan-Headers/registry
2025-03-21T20:25:13.9902365Z   copying backends/vulkan/third-party/Vulkan-Headers/registry/conventions.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/third-party/Vulkan-Headers/registry
2025-03-21T20:25:13.9903869Z   copying backends/vulkan/third-party/Vulkan-Headers/registry/generator.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/third-party/Vulkan-Headers/registry
2025-03-21T20:25:13.9905838Z   copying backends/vulkan/third-party/Vulkan-Headers/registry/genvk.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/third-party/Vulkan-Headers/registry
2025-03-21T20:25:13.9907900Z   copying backends/vulkan/third-party/Vulkan-Headers/registry/reg.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/third-party/Vulkan-Headers/registry
2025-03-21T20:25:13.9909464Z   copying backends/vulkan/third-party/Vulkan-Headers/registry/vkconventions.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/third-party/Vulkan-Headers/registry
2025-03-21T20:25:13.9910726Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/third-party/Vulkan-Headers/registry/spec_tools
2025-03-21T20:25:13.9912025Z   copying backends/vulkan/third-party/Vulkan-Headers/registry/spec_tools/util.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/third-party/Vulkan-Headers/registry/spec_tools
2025-03-21T20:25:13.9914443Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/third-party/VulkanMemoryAllocator/tools/GpuMemDumpVis
2025-03-21T20:25:13.9916105Z   copying backends/vulkan/third-party/VulkanMemoryAllocator/tools/GpuMemDumpVis/GpuMemDumpVis.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/third-party/VulkanMemoryAllocator/tools/GpuMemDumpVis
2025-03-21T20:25:13.9917400Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/_passes
2025-03-21T20:25:13.9918201Z   copying backends/xnnpack/_passes/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/_passes
2025-03-21T20:25:13.9919237Z   copying backends/xnnpack/_passes/channels_last_tagged_reshape_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/_passes
2025-03-21T20:25:13.9920596Z   copying backends/xnnpack/_passes/conv1d_unsqueeze_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/_passes
2025-03-21T20:25:13.9922424Z   copying backends/xnnpack/_passes/convert_to_linear.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/_passes
2025-03-21T20:25:13.9923571Z   copying backends/xnnpack/_passes/convert_to_sdpa.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/_passes
2025-03-21T20:25:13.9924646Z   copying backends/xnnpack/_passes/convert_to_upsample_bilinear2d.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/_passes
2025-03-21T20:25:13.9925704Z   copying backends/xnnpack/_passes/decompose_cat.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/_passes
2025-03-21T20:25:13.9927017Z   copying backends/xnnpack/_passes/fuse_activation_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/_passes
2025-03-21T20:25:13.9928803Z   copying backends/xnnpack/_passes/fuse_batch_norm_with_conv.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/_passes
2025-03-21T20:25:13.9930234Z   copying backends/xnnpack/_passes/prelu_reshape_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/_passes
2025-03-21T20:25:13.9931325Z   copying backends/xnnpack/_passes/remove_getitem_op.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/_passes
2025-03-21T20:25:13.9932542Z   copying backends/xnnpack/_passes/tag_implicit_q_dq_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/_passes
2025-03-21T20:25:13.9933723Z   copying backends/xnnpack/_passes/xnnpack_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/_passes
2025-03-21T20:25:13.9935169Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:13.9936405Z   copying backends/xnnpack/operators/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:13.9937496Z   copying backends/xnnpack/operators/node_visitor.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:13.9938526Z   copying backends/xnnpack/operators/op_abs.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:13.9939500Z   copying backends/xnnpack/operators/op_add.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:13.9941233Z   copying backends/xnnpack/operators/op_addmm.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:13.9942677Z   copying backends/xnnpack/operators/op_avg_pooling2d.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:13.9943786Z   copying backends/xnnpack/operators/op_bmm.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0328991Z   copying backends/xnnpack/operators/op_cat.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0330244Z   copying backends/xnnpack/operators/op_ceiling.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0331265Z   copying backends/xnnpack/operators/op_clamp.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0332431Z   copying backends/xnnpack/operators/op_conv2d.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0333433Z   copying backends/xnnpack/operators/op_div.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0334608Z   copying backends/xnnpack/operators/op_dynamic_dequantize_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0336634Z   copying backends/xnnpack/operators/op_dynamic_quantize_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0338557Z   copying backends/xnnpack/operators/op_elu.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0339770Z   copying backends/xnnpack/operators/op_floor.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0340791Z   copying backends/xnnpack/operators/op_hardswish.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0341825Z   copying backends/xnnpack/operators/op_hardtanh.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0342854Z   copying backends/xnnpack/operators/op_leaky_relu.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0344495Z   copying backends/xnnpack/operators/op_linear.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0345977Z   copying backends/xnnpack/operators/op_matrix_multiplication.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0347222Z   copying backends/xnnpack/operators/op_max_dim.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0348308Z   copying backends/xnnpack/operators/op_max_pool2d.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0349338Z   copying backends/xnnpack/operators/op_maximum.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0350354Z   copying backends/xnnpack/operators/op_mean_dim.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0351367Z   copying backends/xnnpack/operators/op_minimum.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0352395Z   copying backends/xnnpack/operators/op_multiply.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0354195Z   copying backends/xnnpack/operators/op_negate.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0356052Z   copying backends/xnnpack/operators/op_permute.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0357447Z   copying backends/xnnpack/operators/op_prelu.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0358475Z   copying backends/xnnpack/operators/op_quant_dequant.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0359505Z   copying backends/xnnpack/operators/op_relu.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0360496Z   copying backends/xnnpack/operators/op_rsqrt.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0361517Z   copying backends/xnnpack/operators/op_sdpa.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0363360Z   copying backends/xnnpack/operators/op_sigmoid.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0364530Z   copying backends/xnnpack/operators/op_skip_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0365558Z   copying backends/xnnpack/operators/op_slice_copy.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0366568Z   copying backends/xnnpack/operators/op_softmax.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0367575Z   copying backends/xnnpack/operators/op_square.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0368624Z   copying backends/xnnpack/operators/op_square_root.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0370583Z   copying backends/xnnpack/operators/op_squeeze.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0371818Z   copying backends/xnnpack/operators/op_static_constant_pad.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0372943Z   copying backends/xnnpack/operators/op_static_resize_bilinear_2d.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0374003Z   copying backends/xnnpack/operators/op_sub.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0374992Z   copying backends/xnnpack/operators/op_to_copy.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0376592Z   copying backends/xnnpack/operators/quant_params.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators
2025-03-21T20:25:14.0377887Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/partition
2025-03-21T20:25:14.0378866Z   copying backends/xnnpack/partition/configs.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/partition
2025-03-21T20:25:14.0380004Z   copying backends/xnnpack/partition/xnnpack_partitioner.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/partition
2025-03-21T20:25:14.0380890Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/quantizer
2025-03-21T20:25:14.0381775Z   copying backends/xnnpack/quantizer/xnnpack_quantizer.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/quantizer
2025-03-21T20:25:14.0383367Z   copying backends/xnnpack/quantizer/xnnpack_quantizer_utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/quantizer
2025-03-21T20:25:14.0384842Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/serialization
2025-03-21T20:25:14.0385802Z   copying backends/xnnpack/serialization/xnnpack_graph_schema.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/serialization
2025-03-21T20:25:14.0387027Z   copying backends/xnnpack/serialization/xnnpack_graph_serialize.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/serialization
2025-03-21T20:25:14.0387955Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test
2025-03-21T20:25:14.0388767Z   copying backends/xnnpack/test/test_xnnpack_utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test
2025-03-21T20:25:14.0390120Z   copying backends/xnnpack/test/test_xnnpack_utils_classes.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test
2025-03-21T20:25:14.0391659Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party
2025-03-21T20:25:14.0392622Z   copying backends/xnnpack/third-party/generate-cpuinfo-wrappers.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party
2025-03-21T20:25:14.0393548Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/utils
2025-03-21T20:25:14.0394352Z   copying backends/xnnpack/utils/configs.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/utils
2025-03-21T20:25:14.0395300Z   copying backends/xnnpack/utils/quant_utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/utils
2025-03-21T20:25:14.0396232Z   copying backends/xnnpack/utils/utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/utils
2025-03-21T20:25:14.0397785Z   copying backends/xnnpack/utils/xnnpack_constants.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/utils
2025-03-21T20:25:14.0399092Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/partition/config
2025-03-21T20:25:14.0400020Z   copying backends/xnnpack/partition/config/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/partition/config
2025-03-21T20:25:14.0401175Z   copying backends/xnnpack/partition/config/gemm_configs.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/partition/config
2025-03-21T20:25:14.0402415Z   copying backends/xnnpack/partition/config/generic_node_configs.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/partition/config
2025-03-21T20:25:14.0403632Z   copying backends/xnnpack/partition/config/node_configs.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/partition/config
2025-03-21T20:25:14.0405633Z   copying backends/xnnpack/partition/config/quant_affine_configs.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/partition/config
2025-03-21T20:25:14.0799986Z   copying backends/xnnpack/partition/config/xnnpack_config.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/partition/config
2025-03-21T20:25:14.0800992Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/partition/graphs
2025-03-21T20:25:14.0801970Z   copying backends/xnnpack/partition/graphs/bilinear_2d.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/partition/graphs
2025-03-21T20:25:14.0803423Z   copying backends/xnnpack/partition/graphs/sdpa.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/partition/graphs
2025-03-21T20:25:14.0804413Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/models
2025-03-21T20:25:14.0805919Z   copying backends/xnnpack/test/models/deeplab_v3.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/models
2025-03-21T20:25:14.0807352Z   copying backends/xnnpack/test/models/edsr.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/models
2025-03-21T20:25:14.0808401Z   copying backends/xnnpack/test/models/emformer_rnnt.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/models
2025-03-21T20:25:14.0809570Z   copying backends/xnnpack/test/models/inception_v3.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/models
2025-03-21T20:25:14.0810662Z   copying backends/xnnpack/test/models/inception_v4.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/models
2025-03-21T20:25:14.0812155Z   copying backends/xnnpack/test/models/llama2_et_example.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/models
2025-03-21T20:25:14.0813890Z   copying backends/xnnpack/test/models/mobilebert.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/models
2025-03-21T20:25:14.0814982Z   copying backends/xnnpack/test/models/mobilenet_v2.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/models
2025-03-21T20:25:14.0816055Z   copying backends/xnnpack/test/models/mobilenet_v3.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/models
2025-03-21T20:25:14.0817105Z   copying backends/xnnpack/test/models/resnet.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/models
2025-03-21T20:25:14.0818176Z   copying backends/xnnpack/test/models/torchvision_vit.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/models
2025-03-21T20:25:14.0820097Z   copying backends/xnnpack/test/models/very_big_model.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/models
2025-03-21T20:25:14.0821349Z   copying backends/xnnpack/test/models/w2l.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/models
2025-03-21T20:25:14.0822162Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0822986Z   copying backends/xnnpack/test/ops/test_abs.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0824076Z   copying backends/xnnpack/test/ops/test_add.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0825078Z   copying backends/xnnpack/test/ops/test_avgpool2d.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0826126Z   copying backends/xnnpack/test/ops/test_bilinear2d.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0827798Z   copying backends/xnnpack/test/ops/test_bmm.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0829583Z   copying backends/xnnpack/test/ops/test_cat.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0831039Z   copying backends/xnnpack/test/ops/test_ceil.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0832087Z   copying backends/xnnpack/test/ops/test_check_quant_params.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0833323Z   copying backends/xnnpack/test/ops/test_clamp.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0834320Z   copying backends/xnnpack/test/ops/test_conv1d.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0835554Z   copying backends/xnnpack/test/ops/test_conv2d.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0836686Z   copying backends/xnnpack/test/ops/test_div.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0838422Z   copying backends/xnnpack/test/ops/test_elu.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0839577Z   copying backends/xnnpack/test/ops/test_floor.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0840589Z   copying backends/xnnpack/test/ops/test_hardswish.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0841613Z   copying backends/xnnpack/test/ops/test_hardtanh.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0842646Z   copying backends/xnnpack/test/ops/test_leaky_relu.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0843672Z   copying backends/xnnpack/test/ops/test_linear.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0844765Z   copying backends/xnnpack/test/ops/test_lstm.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0846569Z   copying backends/xnnpack/test/ops/test_max_dim.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0847696Z   copying backends/xnnpack/test/ops/test_maximum.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0848714Z   copying backends/xnnpack/test/ops/test_maxpool2d.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0849843Z   copying backends/xnnpack/test/ops/test_mean_dim.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0850869Z   copying backends/xnnpack/test/ops/test_minimum.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0851883Z   copying backends/xnnpack/test/ops/test_multiply.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0852894Z   copying backends/xnnpack/test/ops/test_negate.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0853897Z   copying backends/xnnpack/test/ops/test_permute.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0854885Z   copying backends/xnnpack/test/ops/test_pow.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0855855Z   copying backends/xnnpack/test/ops/test_prelu.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0856904Z   copying backends/xnnpack/test/ops/test_quantize_per_tensor.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0857949Z   copying backends/xnnpack/test/ops/test_relu.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0858935Z   copying backends/xnnpack/test/ops/test_rsqrt.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0859922Z   copying backends/xnnpack/test/ops/test_sdpa.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0861679Z   copying backends/xnnpack/test/ops/test_sigmoid.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0863541Z   copying backends/xnnpack/test/ops/test_slice_copy.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0864975Z   copying backends/xnnpack/test/ops/test_softmax.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0866215Z   copying backends/xnnpack/test/ops/test_sqrt.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0867210Z   copying backends/xnnpack/test/ops/test_square.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0868472Z   copying backends/xnnpack/test/ops/test_static_constant_pad.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0870330Z   copying backends/xnnpack/test/ops/test_sub.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:14.0871170Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/passes
2025-03-21T20:25:14.0872090Z   copying backends/xnnpack/test/passes/test_activation_fusion.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/passes
2025-03-21T20:25:14.0873245Z   copying backends/xnnpack/test/passes/test_batch_norm_fusion.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/passes
2025-03-21T20:25:14.0874413Z   copying backends/xnnpack/test/passes/test_channels_last_tagged_reshape.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/passes
2025-03-21T20:25:14.1045686Z   copying backends/xnnpack/test/passes/test_convert_to_linear.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/passes
2025-03-21T20:25:14.1047737Z   copying backends/xnnpack/test/passes/test_decompose_cat_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/passes
2025-03-21T20:25:14.1049973Z   copying backends/xnnpack/test/passes/test_remove_get_item_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/passes
2025-03-21T20:25:14.1052132Z   copying backends/xnnpack/test/passes/test_tag_implicit_q_dq_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/passes
2025-03-21T20:25:14.1053870Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/quantizer
2025-03-21T20:25:14.1055648Z   copying backends/xnnpack/test/quantizer/test_pt2e_quantization.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/quantizer
2025-03-21T20:25:14.1057199Z   copying backends/xnnpack/test/quantizer/test_representation.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/quantizer
2025-03-21T20:25:14.1058405Z   copying backends/xnnpack/test/quantizer/test_xnnpack_quantizer.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/quantizer
2025-03-21T20:25:14.1059374Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/serialization
2025-03-21T20:25:14.1060375Z   copying backends/xnnpack/test/serialization/test_serialization.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/serialization
2025-03-21T20:25:14.1061632Z   copying backends/xnnpack/test/serialization/test_xnnheader.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/serialization
2025-03-21T20:25:14.1062587Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/tester
2025-03-21T20:25:14.1063427Z   copying backends/xnnpack/test/tester/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/tester
2025-03-21T20:25:14.1064440Z   copying backends/xnnpack/test/tester/tester.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/tester
2025-03-21T20:25:14.1065316Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/FP16
2025-03-21T20:25:14.1066254Z   copying backends/xnnpack/third-party/FP16/configure.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/FP16
2025-03-21T20:25:14.1067184Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/FXdiv
2025-03-21T20:25:14.1068301Z   copying backends/xnnpack/third-party/FXdiv/configure.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/FXdiv
2025-03-21T20:25:14.1069346Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/cpuinfo
2025-03-21T20:25:14.1070336Z   copying backends/xnnpack/third-party/cpuinfo/configure.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/cpuinfo
2025-03-21T20:25:14.1071341Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/pthreadpool
2025-03-21T20:25:14.1072390Z   copying backends/xnnpack/third-party/pthreadpool/configure.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/pthreadpool
2025-03-21T20:25:14.1073466Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/FP16/include/fp16
2025-03-21T20:25:14.1074552Z   copying backends/xnnpack/third-party/FP16/include/fp16/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/FP16/include/fp16
2025-03-21T20:25:14.1075896Z   copying backends/xnnpack/third-party/FP16/include/fp16/avx.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/FP16/include/fp16
2025-03-21T20:25:14.1077229Z   copying backends/xnnpack/third-party/FP16/include/fp16/avx2.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/FP16/include/fp16
2025-03-21T20:25:14.1078318Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/FP16/test/peachpy
2025-03-21T20:25:14.1079422Z   copying backends/xnnpack/third-party/FP16/test/peachpy/stubs.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/FP16/test/peachpy
2025-03-21T20:25:14.1080508Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/scripts
2025-03-21T20:25:14.1081606Z   copying backends/xnnpack/third-party/XNNPACK/scripts/check_config.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/scripts
2025-03-21T20:25:14.1083062Z   copying backends/xnnpack/third-party/XNNPACK/scripts/check_files_changed.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/scripts
2025-03-21T20:25:14.1084535Z   copying backends/xnnpack/third-party/XNNPACK/scripts/generate-build-identifier.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/scripts
2025-03-21T20:25:14.1085990Z   copying backends/xnnpack/third-party/XNNPACK/scripts/sort-filenames.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/scripts
2025-03-21T20:25:14.1087091Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:14.1088232Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-argmaxpool-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:14.1089785Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-conv-hwc-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:14.1091248Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-conv-hwc2chw-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:14.1092751Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-dwconv-multipass-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:14.1094270Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-dwconv-unipass-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:14.1095759Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-dwconv2d-chw-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:14.1097279Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-gemm-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:14.1098775Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-ibilinear-chw-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:14.1100232Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-ibilinear-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:14.1101674Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-lut-norm-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:14.1103081Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-lut-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:14.1104541Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-raddexpminusmax-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:14.1106030Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-raddextexp-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:14.1107550Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-raddstoreexpminusmax-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:14.1109063Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-rdsum-benchmark.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:14.1110502Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-rdsum-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:14.1111911Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-reduce-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:14.1113317Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-spmm-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:14.1114710Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-vbinary-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:14.1116147Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-vmulcaddc-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:14.1617879Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-vscaleexpminusmax-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:14.1619456Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-vscaleextexp-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:14.1620919Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-vunary-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:14.1622279Z   copying backends/xnnpack/third-party/XNNPACK/tools/primes.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:14.1623945Z   copying backends/xnnpack/third-party/XNNPACK/tools/update-microkernels.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:14.1626104Z   copying backends/xnnpack/third-party/XNNPACK/tools/xngen.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:14.1627578Z   copying backends/xnnpack/third-party/XNNPACK/tools/xnncommon.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:14.1628739Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/cpuinfo/scripts
2025-03-21T20:25:14.1629873Z   copying backends/xnnpack/third-party/cpuinfo/scripts/android-device-dump.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/cpuinfo/scripts
2025-03-21T20:25:14.1632166Z   copying backends/xnnpack/third-party/cpuinfo/scripts/arm-linux-filesystem-dump.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/cpuinfo/scripts
2025-03-21T20:25:14.1634127Z   copying backends/xnnpack/third-party/cpuinfo/scripts/parse-x86-cpuid-dump.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/cpuinfo/scripts
2025-03-21T20:25:14.1635315Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/cpuinfo/deps/clog
2025-03-21T20:25:14.1636460Z   copying backends/xnnpack/third-party/cpuinfo/deps/clog/configure.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/cpuinfo/deps/clog
2025-03-21T20:25:14.1637430Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/codegen
2025-03-21T20:25:14.1638005Z   copying codegen/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/codegen
2025-03-21T20:25:14.1638611Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/codegen/tools
2025-03-21T20:25:14.1639258Z   copying codegen/tools/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/codegen/tools
2025-03-21T20:25:14.1640040Z   copying codegen/tools/gen_all_oplist.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/codegen/tools
2025-03-21T20:25:14.1640831Z   copying codegen/tools/gen_oplist.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/codegen/tools
2025-03-21T20:25:14.1641600Z   copying codegen/tools/gen_ops_def.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/codegen/tools
2025-03-21T20:25:14.1642433Z   copying codegen/tools/gen_selected_op_variants.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/codegen/tools
2025-03-21T20:25:14.1643273Z   copying codegen/tools/merge_yaml.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/codegen/tools
2025-03-21T20:25:14.1644042Z   copying codegen/tools/yaml_util.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/codegen/tools
2025-03-21T20:25:14.1644713Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/codegen/tools/test
2025-03-21T20:25:14.1645479Z   copying codegen/tools/test/test_gen_all_oplist.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/codegen/tools/test
2025-03-21T20:25:14.1646457Z   copying codegen/tools/test/test_gen_oplist.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/codegen/tools/test
2025-03-21T20:25:14.1648138Z   copying codegen/tools/test/test_gen_oplist_real_model.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/codegen/tools/test
2025-03-21T20:25:14.1649539Z   copying codegen/tools/test/test_gen_selected_op_variants.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/codegen/tools/test
2025-03-21T20:25:14.1650398Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/apple/coreml/llama
2025-03-21T20:25:14.1651250Z   copying examples/apple/coreml/llama/export.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/apple/coreml/llama
2025-03-21T20:25:14.1652302Z   copying examples/apple/coreml/llama/llama_transformer.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/apple/coreml/llama
2025-03-21T20:25:14.1653338Z   copying examples/apple/coreml/llama/run.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/apple/coreml/llama
2025-03-21T20:25:14.1654325Z   copying examples/apple/coreml/llama/test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/apple/coreml/llama
2025-03-21T20:25:14.1655317Z   copying examples/apple/coreml/llama/utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/apple/coreml/llama
2025-03-21T20:25:14.1656500Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/llm_pte_finetuning
2025-03-21T20:25:14.1658265Z   copying examples/llm_pte_finetuning/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/llm_pte_finetuning
2025-03-21T20:25:14.1659286Z   copying examples/llm_pte_finetuning/model_exporter.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/llm_pte_finetuning
2025-03-21T20:25:14.1660313Z   copying examples/llm_pte_finetuning/model_loading_lib.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/llm_pte_finetuning
2025-03-21T20:25:14.1661322Z   copying examples/llm_pte_finetuning/runner.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/llm_pte_finetuning
2025-03-21T20:25:14.1662309Z   copying examples/llm_pte_finetuning/training_lib.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/llm_pte_finetuning
2025-03-21T20:25:14.1663644Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models
2025-03-21T20:25:14.1664835Z   copying examples/models/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models
2025-03-21T20:25:14.1665663Z   copying examples/models/checkpoint.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models
2025-03-21T20:25:14.1666487Z   copying examples/models/model_base.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models
2025-03-21T20:25:14.1667299Z   copying examples/models/model_factory.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models
2025-03-21T20:25:14.1668049Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/deeplab_v3
2025-03-21T20:25:14.1668864Z   copying examples/models/deeplab_v3/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/deeplab_v3
2025-03-21T20:25:14.1670348Z   copying examples/models/deeplab_v3/model.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/deeplab_v3
2025-03-21T20:25:14.1671632Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/edsr
2025-03-21T20:25:14.1672400Z   copying examples/models/edsr/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/edsr
2025-03-21T20:25:14.1673266Z   copying examples/models/edsr/model.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/edsr
2025-03-21T20:25:14.1674025Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/efficient_sam
2025-03-21T20:25:14.1674880Z   copying examples/models/efficient_sam/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/efficient_sam
2025-03-21T20:25:14.1675897Z   copying examples/models/efficient_sam/model.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/efficient_sam
2025-03-21T20:25:14.1676909Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/emformer_rnnt
2025-03-21T20:25:14.1678452Z   copying examples/models/emformer_rnnt/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/emformer_rnnt
2025-03-21T20:25:14.1679647Z   copying examples/models/emformer_rnnt/model.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/emformer_rnnt
2025-03-21T20:25:14.1680498Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/inception_v3
2025-03-21T20:25:14.1681321Z   copying examples/models/inception_v3/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/inception_v3
2025-03-21T20:25:14.1682310Z   copying examples/models/inception_v3/model.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/inception_v3
2025-03-21T20:25:14.1683136Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/inception_v4
2025-03-21T20:25:14.1683964Z   copying examples/models/inception_v4/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/inception_v4
2025-03-21T20:25:14.1685399Z   copying examples/models/inception_v4/model.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/inception_v4
2025-03-21T20:25:14.1686898Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama
2025-03-21T20:25:14.1687727Z   copying examples/models/llama/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama
2025-03-21T20:25:14.1688648Z   copying examples/models/llama/attention.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama
2025-03-21T20:25:14.1689694Z   copying examples/models/llama/eval_llama.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama
2025-03-21T20:25:14.2044925Z   copying examples/models/llama/eval_llama_lib.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama
2025-03-21T20:25:14.2046109Z   copying examples/models/llama/export_llama.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama
2025-03-21T20:25:14.2047076Z   copying examples/models/llama/export_llama_lib.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama
2025-03-21T20:25:14.2048042Z   copying examples/models/llama/fairseq2.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama
2025-03-21T20:25:14.2049055Z   copying examples/models/llama/install_requirement_helper.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama
2025-03-21T20:25:14.2050539Z   copying examples/models/llama/llama_test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama
2025-03-21T20:25:14.2052205Z   copying examples/models/llama/llama_transformer.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama
2025-03-21T20:25:14.2053148Z   copying examples/models/llama/model.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama
2025-03-21T20:25:14.2054057Z   copying examples/models/llama/model_args.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama
2025-03-21T20:25:14.2054964Z   copying examples/models/llama/norm.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama
2025-03-21T20:25:14.2055856Z   copying examples/models/llama/rope.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama
2025-03-21T20:25:14.2056781Z   copying examples/models/llama/static_attention.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama
2025-03-21T20:25:14.2057625Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision
2025-03-21T20:25:14.2059011Z   copying examples/models/llama3_2_vision/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision
2025-03-21T20:25:14.2060481Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llava
2025-03-21T20:25:14.2061856Z   copying examples/models/llava/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llava
2025-03-21T20:25:14.2062931Z   copying examples/models/llava/export_llava.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llava
2025-03-21T20:25:14.2063874Z   copying examples/models/llava/image_util.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llava
2025-03-21T20:25:14.2064777Z   copying examples/models/llava/model.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llava
2025-03-21T20:25:14.2065525Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/lstm
2025-03-21T20:25:14.2066399Z   copying examples/models/lstm/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/lstm
2025-03-21T20:25:14.2067949Z   copying examples/models/lstm/model.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/lstm
2025-03-21T20:25:14.2068912Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/mobilebert
2025-03-21T20:25:14.2069741Z   copying examples/models/mobilebert/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/mobilebert
2025-03-21T20:25:14.2070719Z   copying examples/models/mobilebert/model.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/mobilebert
2025-03-21T20:25:14.2071790Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/mobilenet_v2
2025-03-21T20:25:14.2072624Z   copying examples/models/mobilenet_v2/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/mobilenet_v2
2025-03-21T20:25:14.2073782Z   copying examples/models/mobilenet_v2/model.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/mobilenet_v2
2025-03-21T20:25:14.2075272Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/mobilenet_v3
2025-03-21T20:25:14.2076348Z   copying examples/models/mobilenet_v3/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/mobilenet_v3
2025-03-21T20:25:14.2077342Z   copying examples/models/mobilenet_v3/model.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/mobilenet_v3
2025-03-21T20:25:14.2078194Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/phi-3-mini-lora
2025-03-21T20:25:14.2079118Z   copying examples/models/phi-3-mini-lora/export_model.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/phi-3-mini-lora
2025-03-21T20:25:14.2080000Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/phi-3-mini
2025-03-21T20:25:14.2080808Z   copying examples/models/phi-3-mini/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/phi-3-mini
2025-03-21T20:25:14.2081876Z   copying examples/models/phi-3-mini/eager.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/phi-3-mini
2025-03-21T20:25:14.2083699Z   copying examples/models/phi-3-mini/export_phi-3-mini.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/phi-3-mini
2025-03-21T20:25:14.2084860Z   copying examples/models/phi-3-mini/phi_3_mini.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/phi-3-mini
2025-03-21T20:25:14.2085863Z   copying examples/models/phi-3-mini/static_cache.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/phi-3-mini
2025-03-21T20:25:14.2086716Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/phi-4-mini
2025-03-21T20:25:14.2087527Z   copying examples/models/phi-4-mini/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/phi-4-mini
2025-03-21T20:25:14.2088530Z   copying examples/models/phi-4-mini/convert_weights.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/phi-4-mini
2025-03-21T20:25:14.2089478Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/qwen2_5
2025-03-21T20:25:14.2090267Z   copying examples/models/qwen2_5/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/qwen2_5
2025-03-21T20:25:14.2091635Z   copying examples/models/qwen2_5/convert_weights.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/qwen2_5
2025-03-21T20:25:14.2093089Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/resnet
2025-03-21T20:25:14.2094535Z   copying examples/models/resnet/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/resnet
2025-03-21T20:25:14.2095732Z   copying examples/models/resnet/model.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/resnet
2025-03-21T20:25:14.2096492Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/test
2025-03-21T20:25:14.2097231Z   copying examples/models/test/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/test
2025-03-21T20:25:14.2098120Z   copying examples/models/test/test_export.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/test
2025-03-21T20:25:14.2099233Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/torchvision_vit
2025-03-21T20:25:14.2100807Z   copying examples/models/torchvision_vit/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/torchvision_vit
2025-03-21T20:25:14.2102005Z   copying examples/models/torchvision_vit/model.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/torchvision_vit
2025-03-21T20:25:14.2102975Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/toy_model
2025-03-21T20:25:14.2103760Z   copying examples/models/toy_model/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/toy_model
2025-03-21T20:25:14.2104698Z   copying examples/models/toy_model/model.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/toy_model
2025-03-21T20:25:14.2105498Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/wav2letter
2025-03-21T20:25:14.2106326Z   copying examples/models/wav2letter/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/wav2letter
2025-03-21T20:25:14.2108061Z   copying examples/models/wav2letter/model.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/wav2letter
2025-03-21T20:25:14.2109309Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/efficient_sam/efficient_sam_core
2025-03-21T20:25:14.2110486Z   copying examples/models/efficient_sam/efficient_sam_core/build_efficient_sam.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/efficient_sam/efficient_sam_core
2025-03-21T20:25:14.2111926Z   copying examples/models/efficient_sam/efficient_sam_core/efficient_sam.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/efficient_sam/efficient_sam_core
2025-03-21T20:25:14.2113353Z   copying examples/models/efficient_sam/efficient_sam_core/efficient_sam_decoder.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/efficient_sam/efficient_sam_core
2025-03-21T20:25:14.2114821Z   copying examples/models/efficient_sam/efficient_sam_core/efficient_sam_encoder.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/efficient_sam/efficient_sam_core
2025-03-21T20:25:14.2116963Z   copying examples/models/efficient_sam/efficient_sam_core/mlp.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/efficient_sam/efficient_sam_core
2025-03-21T20:25:14.2119540Z   copying examples/models/efficient_sam/efficient_sam_core/two_way_transformer.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/efficient_sam/efficient_sam_core
2025-03-21T20:25:14.2121541Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/evaluate
2025-03-21T20:25:14.2394728Z   copying examples/models/llama/evaluate/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/evaluate
2025-03-21T20:25:14.2396027Z   copying examples/models/llama/evaluate/eager_eval.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/evaluate
2025-03-21T20:25:14.2396951Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/experimental
2025-03-21T20:25:14.2397928Z   copying examples/models/llama/experimental/generate.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/experimental
2025-03-21T20:25:14.2399147Z   copying examples/models/llama/experimental/load_gguf_q4_0.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/experimental
2025-03-21T20:25:14.2400944Z   copying examples/models/llama/experimental/subclass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/experimental
2025-03-21T20:25:14.2402647Z   copying examples/models/llama/experimental/test_subclass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/experimental
2025-03-21T20:25:14.2403595Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/runner
2025-03-21T20:25:14.2404456Z   copying examples/models/llama/runner/eager.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/runner
2025-03-21T20:25:14.2405512Z   copying examples/models/llama/runner/generation.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/runner
2025-03-21T20:25:14.2406736Z   copying examples/models/llama/runner/native.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/runner
2025-03-21T20:25:14.2407750Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/source_transformation
2025-03-21T20:25:14.2409682Z   copying examples/models/llama/source_transformation/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/source_transformation
2025-03-21T20:25:14.2412147Z   copying examples/models/llama/source_transformation/apply_spin_quant_r1_r2.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/source_transformation
2025-03-21T20:25:14.2413602Z   copying examples/models/llama/source_transformation/attention.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/source_transformation
2025-03-21T20:25:14.2414953Z   copying examples/models/llama/source_transformation/attention_sink.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/source_transformation
2025-03-21T20:25:14.2416282Z   copying examples/models/llama/source_transformation/lora.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/source_transformation
2025-03-21T20:25:14.2417606Z   copying examples/models/llama/source_transformation/pre_quantization.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/source_transformation
2025-03-21T20:25:14.2419033Z   copying examples/models/llama/source_transformation/prune_vocab.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/source_transformation
2025-03-21T20:25:14.2421461Z   copying examples/models/llama/source_transformation/quantize.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/source_transformation
2025-03-21T20:25:14.2423522Z   copying examples/models/llama/source_transformation/quantized_kv_cache.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/source_transformation
2025-03-21T20:25:14.2424872Z   copying examples/models/llama/source_transformation/rms_norm.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/source_transformation
2025-03-21T20:25:14.2426164Z   copying examples/models/llama/source_transformation/rope.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/source_transformation
2025-03-21T20:25:14.2427560Z   copying examples/models/llama/source_transformation/sdpa.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/source_transformation
2025-03-21T20:25:14.2429726Z   copying examples/models/llama/source_transformation/spin_quant.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/source_transformation
2025-03-21T20:25:14.2431090Z   copying examples/models/llama/source_transformation/test_attention_sink.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/source_transformation
2025-03-21T20:25:14.2432698Z   copying examples/models/llama/source_transformation/test_quantized_kv_cache.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/source_transformation
2025-03-21T20:25:14.2434161Z   copying examples/models/llama/source_transformation/test_sdpa_with_quantized_kv_cache.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/source_transformation
2025-03-21T20:25:14.2436166Z   copying examples/models/llama/source_transformation/vulkan_rope.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/source_transformation
2025-03-21T20:25:14.2437593Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/tests
2025-03-21T20:25:14.2438539Z   copying examples/models/llama/tests/test_pre_quantization_transforms.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/tests
2025-03-21T20:25:14.2439695Z   copying examples/models/llama/tests/test_simple_sdpa.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/tests
2025-03-21T20:25:14.2440954Z   copying examples/models/llama/tests/test_static_attention.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/tests
2025-03-21T20:25:14.2441940Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/tokenizer
2025-03-21T20:25:14.2443454Z   copying examples/models/llama/tokenizer/tiktoken.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/tokenizer
2025-03-21T20:25:14.2444871Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/preprocess
2025-03-21T20:25:14.2445906Z   copying examples/models/llama3_2_vision/preprocess/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/preprocess
2025-03-21T20:25:14.2447201Z   copying examples/models/llama3_2_vision/preprocess/export_preprocess.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/preprocess
2025-03-21T20:25:14.2448486Z   copying examples/models/llama3_2_vision/preprocess/model.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/preprocess
2025-03-21T20:25:14.2449916Z   copying examples/models/llama3_2_vision/preprocess/test_preprocess.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/preprocess
2025-03-21T20:25:14.2451811Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/runner
2025-03-21T20:25:14.2452964Z   copying examples/models/llama3_2_vision/runner/eager.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/runner
2025-03-21T20:25:14.2454150Z   copying examples/models/llama3_2_vision/runner/exported.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/runner
2025-03-21T20:25:14.2455355Z   copying examples/models/llama3_2_vision/runner/generation.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/runner
2025-03-21T20:25:14.2456554Z   copying examples/models/llama3_2_vision/runner/native.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/runner
2025-03-21T20:25:14.2458033Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/text_decoder
2025-03-21T20:25:14.2459587Z   copying examples/models/llama3_2_vision/text_decoder/model.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/text_decoder
2025-03-21T20:25:14.2460648Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/vision_encoder
2025-03-21T20:25:14.2461719Z   copying examples/models/llama3_2_vision/vision_encoder/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/vision_encoder
2025-03-21T20:25:14.2463021Z   copying examples/models/llama3_2_vision/vision_encoder/model.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/vision_encoder
2025-03-21T20:25:14.2464100Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/text_decoder/test
2025-03-21T20:25:14.2465711Z   copying examples/models/llama3_2_vision/text_decoder/test/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/text_decoder/test
2025-03-21T20:25:14.2467636Z   copying examples/models/llama3_2_vision/text_decoder/test/test_text_decoder.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/text_decoder/test
2025-03-21T20:25:14.2468808Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/vision_encoder/test
2025-03-21T20:25:14.2469930Z   copying examples/models/llama3_2_vision/vision_encoder/test/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/vision_encoder/test
2025-03-21T20:25:14.2471365Z   copying examples/models/llama3_2_vision/vision_encoder/test/test_vision_encoder.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/vision_encoder/test
2025-03-21T20:25:14.3021521Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llava/test
2025-03-21T20:25:14.3022879Z   copying examples/models/llava/test/test_llava.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llava/test
2025-03-21T20:25:14.3023898Z   copying examples/models/llava/test/test_pte.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llava/test
2025-03-21T20:25:14.3024708Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/moshi/mimi
2025-03-21T20:25:14.3025613Z   copying examples/models/moshi/mimi/test_mimi.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/moshi/mimi
2025-03-21T20:25:14.3026889Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/exir
2025-03-21T20:25:14.3027847Z   copying exir/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir
2025-03-21T20:25:14.3028609Z   copying exir/_warnings.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir
2025-03-21T20:25:14.3029243Z   copying exir/common.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir
2025-03-21T20:25:14.3029876Z   copying exir/control_flow.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir
2025-03-21T20:25:14.3030513Z   copying exir/delegate.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir
2025-03-21T20:25:14.3031142Z   copying exir/dim_order_utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir
2025-03-21T20:25:14.3031806Z   copying exir/dynamic_shape.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir
2025-03-21T20:25:14.3032630Z   copying exir/error.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir
2025-03-21T20:25:14.3033234Z   copying exir/graph.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir
2025-03-21T20:25:14.3034248Z   copying exir/graph_module.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir
2025-03-21T20:25:14.3035488Z   copying exir/lowered_backend_module.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir
2025-03-21T20:25:14.3036289Z   copying exir/memory.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir
2025-03-21T20:25:14.3036936Z   copying exir/memory_planning.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir
2025-03-21T20:25:14.3037586Z   copying exir/pass_base.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir
2025-03-21T20:25:14.3038217Z   copying exir/pass_manager.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir
2025-03-21T20:25:14.3038866Z   copying exir/print_program.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir
2025-03-21T20:25:14.3039517Z   copying exir/scalar_type.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir
2025-03-21T20:25:14.3040128Z   copying exir/schema.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir
2025-03-21T20:25:14.3040737Z   copying exir/sym_util.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir
2025-03-21T20:25:14.3041363Z   copying exir/tensor.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir
2025-03-21T20:25:14.3042415Z   copying exir/tracer.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir
2025-03-21T20:25:14.3043485Z   copying exir/types.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir
2025-03-21T20:25:14.3044186Z   copying exir/version.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir
2025-03-21T20:25:14.3044806Z   copying exir/wrap.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir
2025-03-21T20:25:14.3045393Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/exir/_serialize
2025-03-21T20:25:14.3046072Z   copying exir/_serialize/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/_serialize
2025-03-21T20:25:14.3046835Z   copying exir/_serialize/_cord.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/_serialize
2025-03-21T20:25:14.3047595Z   copying exir/_serialize/_dataclass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/_serialize
2025-03-21T20:25:14.3048397Z   copying exir/_serialize/_flatbuffer.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/_serialize
2025-03-21T20:25:14.3049930Z   copying exir/_serialize/_named_data_store.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/_serialize
2025-03-21T20:25:14.3051375Z   copying exir/_serialize/_program.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/_serialize
2025-03-21T20:25:14.3052262Z   copying exir/_serialize/_serialize.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/_serialize
2025-03-21T20:25:14.3053087Z   copying exir/_serialize/data_serializer.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/_serialize
2025-03-21T20:25:14.3053889Z   copying exir/_serialize/padding.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/_serialize
2025-03-21T20:25:14.3054564Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend
2025-03-21T20:25:14.3055238Z   copying exir/backend/backend_api.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend
2025-03-21T20:25:14.3056043Z   copying exir/backend/backend_details.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend
2025-03-21T20:25:14.3057505Z   copying exir/backend/compile_spec_schema.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend
2025-03-21T20:25:14.3058743Z   copying exir/backend/operator_support.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend
2025-03-21T20:25:14.3059569Z   copying exir/backend/partitioner.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend
2025-03-21T20:25:14.3060317Z   copying exir/backend/utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend
2025-03-21T20:25:14.3060965Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/exir/capture
2025-03-21T20:25:14.3061612Z   copying exir/capture/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/capture
2025-03-21T20:25:14.3062346Z   copying exir/capture/_capture.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/capture
2025-03-21T20:25:14.3063092Z   copying exir/capture/_config.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/capture
2025-03-21T20:25:14.3063944Z   copying exir/capture/_unlift.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/capture
2025-03-21T20:25:14.3065096Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects
2025-03-21T20:25:14.3066120Z   copying exir/dialects/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects
2025-03-21T20:25:14.3066861Z   copying exir/dialects/_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects
2025-03-21T20:25:14.3067493Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/exir/emit
2025-03-21T20:25:14.3068091Z   copying exir/emit/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/emit
2025-03-21T20:25:14.3068788Z   copying exir/emit/_emit_program.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/emit
2025-03-21T20:25:14.3069479Z   copying exir/emit/_emitter.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/emit
2025-03-21T20:25:14.3070123Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/exir/operator
2025-03-21T20:25:14.3070790Z   copying exir/operator/convert.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/operator
2025-03-21T20:25:14.3071971Z   copying exir/operator/manip.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/operator
2025-03-21T20:25:14.3073288Z   copying exir/operator/util.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/operator
2025-03-21T20:25:14.3073948Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes
2025-03-21T20:25:14.3074580Z   copying exir/passes/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes
2025-03-21T20:25:14.3075401Z   copying exir/passes/_quant_patterns_and_replacements.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes
2025-03-21T20:25:14.3076263Z   copying exir/passes/const_prop_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes
2025-03-21T20:25:14.3077496Z   copying exir/passes/constant_prop_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes
2025-03-21T20:25:14.3078508Z   copying exir/passes/debug_handle_generator_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes
2025-03-21T20:25:14.3080053Z   copying exir/passes/dim_order_ops_registry.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes
2025-03-21T20:25:14.3081229Z   copying exir/passes/dynamic_shape_prop_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes
2025-03-21T20:25:14.3082103Z   copying exir/passes/executorch_prim_ops_registry.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes
2025-03-21T20:25:14.3082993Z   copying exir/passes/external_constants_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes
2025-03-21T20:25:14.3083830Z   copying exir/passes/init_mutable_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes
2025-03-21T20:25:14.3084711Z   copying exir/passes/insert_write_back_for_buffers_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes
2025-03-21T20:25:14.3085602Z   copying exir/passes/memory_format_ops_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes
2025-03-21T20:25:14.3086438Z   copying exir/passes/memory_planning_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes
2025-03-21T20:25:14.3087904Z   copying exir/passes/normalize_transpose_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes
2025-03-21T20:25:14.3089279Z   copying exir/passes/normalize_view_copy_base_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes
2025-03-21T20:25:14.3090145Z   copying exir/passes/pass_registry.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes
2025-03-21T20:25:14.3090975Z   copying exir/passes/prune_empty_tensors_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes
2025-03-21T20:25:14.3091812Z   copying exir/passes/quant_fusion_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes
2025-03-21T20:25:14.3092627Z   copying exir/passes/quantize_io_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes
2025-03-21T20:25:14.3093464Z   copying exir/passes/remove_graph_asserts_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes
2025-03-21T20:25:14.3604174Z   copying exir/passes/remove_mixed_type_operators.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes
2025-03-21T20:25:14.3605463Z   copying exir/passes/remove_noop_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes
2025-03-21T20:25:14.3606316Z   copying exir/passes/replace_aten_with_edge_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes
2025-03-21T20:25:14.3607253Z   copying exir/passes/replace_broken_ops_with_function_ops_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes
2025-03-21T20:25:14.3608208Z   copying exir/passes/replace_edge_with_backend_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes
2025-03-21T20:25:14.3609664Z   copying exir/passes/replace_sym_size_op_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes
2025-03-21T20:25:14.3611183Z   copying exir/passes/replace_view_copy_with_view_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes
2025-03-21T20:25:14.3612081Z   copying exir/passes/scalar_to_tensor_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes
2025-03-21T20:25:14.3612877Z   copying exir/passes/spec_prop_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes
2025-03-21T20:25:14.3613676Z   copying exir/passes/sym_shape_eval_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes
2025-03-21T20:25:14.3614483Z   copying exir/passes/sym_to_tensor_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes
2025-03-21T20:25:14.3615312Z   copying exir/passes/weights_to_outputs_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes
2025-03-21T20:25:14.3616226Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/exir/program
2025-03-21T20:25:14.3617511Z   copying exir/program/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/program
2025-03-21T20:25:14.3618706Z   copying exir/program/_fake_program.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/program
2025-03-21T20:25:14.3619470Z   copying exir/program/_program.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/program
2025-03-21T20:25:14.3620117Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/exir/serde
2025-03-21T20:25:14.3620736Z   copying exir/serde/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/serde
2025-03-21T20:25:14.3621479Z   copying exir/serde/export_serialize.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/serde
2025-03-21T20:25:14.3622222Z   copying exir/serde/schema.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/serde
2025-03-21T20:25:14.3622944Z   copying exir/serde/schema_check.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/serde
2025-03-21T20:25:14.3623687Z   copying exir/serde/serialize.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/serde
2025-03-21T20:25:14.3624401Z   copying exir/serde/union.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/serde
2025-03-21T20:25:14.3625232Z   copying exir/serde/upgrade.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/serde
2025-03-21T20:25:14.3625898Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests
2025-03-21T20:25:14.3626531Z   copying exir/tests/asr_joiner.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests
2025-03-21T20:25:14.3627243Z   copying exir/tests/common.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests
2025-03-21T20:25:14.3627996Z   copying exir/tests/control_flow_models.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests
2025-03-21T20:25:14.3628792Z   copying exir/tests/dynamic_shape_models.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests
2025-03-21T20:25:14.3629800Z   copying exir/tests/models.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests
2025-03-21T20:25:14.3631122Z   copying exir/tests/test_arg_validator.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests
2025-03-21T20:25:14.3632161Z   copying exir/tests/test_capture.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests
2025-03-21T20:25:14.3633090Z   copying exir/tests/test_common.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests
2025-03-21T20:25:14.3633837Z   copying exir/tests/test_delegate.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests
2025-03-21T20:25:14.3634614Z   copying exir/tests/test_dim_order_utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests
2025-03-21T20:25:14.3635453Z   copying exir/tests/test_dynamic_shape_propagation.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests
2025-03-21T20:25:14.3636275Z   copying exir/tests/test_error.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests
2025-03-21T20:25:14.3637040Z   copying exir/tests/test_joint_graph.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests
2025-03-21T20:25:14.3637860Z   copying exir/tests/test_memory_format_ops_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests
2025-03-21T20:25:14.3638738Z   copying exir/tests/test_memory_format_ops_pass_aten.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests
2025-03-21T20:25:14.3639637Z   copying exir/tests/test_memory_format_ops_pass_utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests
2025-03-21T20:25:14.3640979Z   copying exir/tests/test_memory_planning.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests
2025-03-21T20:25:14.3642342Z   copying exir/tests/test_op_convert.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests
2025-03-21T20:25:14.3643127Z   copying exir/tests/test_pass_infra.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests
2025-03-21T20:25:14.3644111Z   copying exir/tests/test_passes.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests
2025-03-21T20:25:14.3644953Z   copying exir/tests/test_print_program.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests
2025-03-21T20:25:14.3645794Z   copying exir/tests/test_prune_empty_tensors_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests
2025-03-21T20:25:14.3646648Z   copying exir/tests/test_quant_fusion_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests
2025-03-21T20:25:14.3647445Z   copying exir/tests/test_quantization.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests
2025-03-21T20:25:14.3648355Z   copying exir/tests/test_quantize_io_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests
2025-03-21T20:25:14.3649890Z   copying exir/tests/test_remove_view_copy.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests
2025-03-21T20:25:14.3650987Z   copying exir/tests/test_serde.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests
2025-03-21T20:25:14.3651737Z   copying exir/tests/test_tensor.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests
2025-03-21T20:25:14.3652465Z   copying exir/tests/test_tracer.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests
2025-03-21T20:25:14.3653229Z   copying exir/tests/test_verification.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests
2025-03-21T20:25:14.3653988Z   copying exir/tests/test_warnings.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests
2025-03-21T20:25:14.3654740Z   copying exir/tests/transformer.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests
2025-03-21T20:25:14.3655413Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/exir/verification
2025-03-21T20:25:14.3656153Z   copying exir/verification/arg_validator.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/verification
2025-03-21T20:25:14.3657007Z   copying exir/verification/dev_html.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/verification
2025-03-21T20:25:14.3657876Z   copying exir/verification/interpreter.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/verification
2025-03-21T20:25:14.3658729Z   copying exir/verification/verifier.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/verification
2025-03-21T20:25:14.3659461Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/exir/_serialize/test
2025-03-21T20:25:14.3660188Z   copying exir/_serialize/test/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/_serialize/test
2025-03-21T20:25:14.3661038Z   copying exir/_serialize/test/test_cord.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/_serialize/test
2025-03-21T20:25:14.3661931Z   copying exir/_serialize/test/test_flatbuffer.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/_serialize/test
2025-03-21T20:25:14.3662877Z   copying exir/_serialize/test/test_named_data_store.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/_serialize/test
2025-03-21T20:25:14.3663806Z   copying exir/_serialize/test/test_program.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/_serialize/test
2025-03-21T20:25:14.3664926Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/canonical_partitioners
2025-03-21T20:25:14.3666694Z   copying exir/backend/canonical_partitioners/config_partitioner.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/canonical_partitioners
2025-03-21T20:25:14.3667999Z   copying exir/backend/canonical_partitioners/duplicate_constant_node_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/canonical_partitioners
2025-03-21T20:25:14.3669318Z   copying exir/backend/canonical_partitioners/duplicate_dequant_node_pass.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/canonical_partitioners
2025-03-21T20:25:14.3670655Z   copying exir/backend/canonical_partitioners/pattern_op_partitioner.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/canonical_partitioners
2025-03-21T20:25:14.3671794Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test
2025-03-21T20:25:14.3672590Z   copying exir/backend/test/backend_with_compiler_demo.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test
2025-03-21T20:25:14.3673603Z   copying exir/backend/test/backend_with_delegate_mapping_demo.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test
2025-03-21T20:25:14.4085125Z   copying exir/backend/test/backend_with_named_data_map.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test
2025-03-21T20:25:14.4086137Z   copying exir/backend/test/hta_partitioner_demo.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test
2025-03-21T20:25:14.4087077Z   copying exir/backend/test/op_partitioner_demo.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test
2025-03-21T20:25:14.4087989Z   copying exir/backend/test/qnn_backend_demo.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test
2025-03-21T20:25:14.4088964Z   copying exir/backend/test/test_backend_with_named_data_map.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test
2025-03-21T20:25:14.4090015Z   copying exir/backend/test/test_backends.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test
2025-03-21T20:25:14.4090921Z   copying exir/backend/test/test_backends_lifted.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test
2025-03-21T20:25:14.4091858Z   copying exir/backend/test/test_backends_nested.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test
2025-03-21T20:25:14.4092777Z   copying exir/backend/test/test_compatibility.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test
2025-03-21T20:25:14.4093709Z   copying exir/backend/test/test_debug_handle_map.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test
2025-03-21T20:25:14.4094658Z   copying exir/backend/test/test_delegate_map_builder.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test
2025-03-21T20:25:14.4095615Z   copying exir/backend/test/test_graph_partition.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test
2025-03-21T20:25:14.4096571Z   copying exir/backend/test/test_lowered_backend_module.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test
2025-03-21T20:25:14.4097516Z   copying exir/backend/test/test_partitioner.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test
2025-03-21T20:25:14.4098401Z   copying exir/backend/test/test_passes.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test
2025-03-21T20:25:14.4099235Z   copying exir/backend/test/test_utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test
2025-03-21T20:25:14.4099973Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test/demos
2025-03-21T20:25:14.4100824Z   copying exir/backend/test/demos/test_delegate_aten_mode.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test/demos
2025-03-21T20:25:14.4101881Z   copying exir/backend/test/demos/test_xnnpack_qnnpack.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test/demos
2025-03-21T20:25:14.4102736Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test/demos/rpc
2025-03-21T20:25:14.4103673Z   copying exir/backend/test/demos/rpc/executor_backend_partitioner.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test/demos/rpc
2025-03-21T20:25:14.4104870Z   copying exir/backend/test/demos/rpc/executor_backend_preprocess.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test/demos/rpc
2025-03-21T20:25:14.4105962Z   copying exir/backend/test/demos/rpc/test_rpc.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test/demos/rpc
2025-03-21T20:25:14.4106771Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/backend
2025-03-21T20:25:14.4107507Z   copying exir/dialects/backend/_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/backend
2025-03-21T20:25:14.4108479Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/edge
2025-03-21T20:25:14.4109214Z   copying exir/dialects/edge/_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/edge
2025-03-21T20:25:14.4109917Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/test
2025-03-21T20:25:14.4110698Z   copying exir/dialects/test/test_exir_dialect_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/test
2025-03-21T20:25:14.4111508Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/backend/test
2025-03-21T20:25:14.4112364Z   copying exir/dialects/backend/test/test_backend_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/backend/test
2025-03-21T20:25:14.4113211Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/edge/arg
2025-03-21T20:25:14.4113981Z   copying exir/dialects/edge/arg/model.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/edge/arg
2025-03-21T20:25:14.4114892Z   copying exir/dialects/edge/arg/type.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/edge/arg
2025-03-21T20:25:14.4115662Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/edge/dtype
2025-03-21T20:25:14.4116471Z   copying exir/dialects/edge/dtype/runner.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/edge/dtype
2025-03-21T20:25:14.4117440Z   copying exir/dialects/edge/dtype/supported.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/edge/dtype
2025-03-21T20:25:14.4118418Z   copying exir/dialects/edge/dtype/utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/edge/dtype
2025-03-21T20:25:14.4119201Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/edge/op
2025-03-21T20:25:14.4119952Z   copying exir/dialects/edge/op/api.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/edge/op
2025-03-21T20:25:14.4120858Z   copying exir/dialects/edge/op/sample_input.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/edge/op
2025-03-21T20:25:14.4121643Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/edge/spec
2025-03-21T20:25:14.4122408Z   copying exir/dialects/edge/spec/gen.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/edge/spec
2025-03-21T20:25:14.4123307Z   copying exir/dialects/edge/spec/utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/edge/spec
2025-03-21T20:25:14.4124116Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/edge/test
2025-03-21T20:25:14.4125439Z   copying exir/dialects/edge/test/test_edge_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/edge/test
2025-03-21T20:25:14.4127200Z   copying exir/dialects/edge/test/test_edge_yaml.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/edge/test
2025-03-21T20:25:14.4128720Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/edge/op/test
2025-03-21T20:25:14.4130351Z   copying exir/dialects/edge/op/test/test_api.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/edge/op/test
2025-03-21T20:25:14.4131426Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/exir/emit/test
2025-03-21T20:25:14.4132104Z   copying exir/emit/test/test_emit.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/emit/test
2025-03-21T20:25:14.4133093Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/exir/operator/test
2025-03-21T20:25:14.4133853Z   copying exir/operator/test/test_operator.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/operator/test
2025-03-21T20:25:14.4134608Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/exir/program/test
2025-03-21T20:25:14.4135321Z   copying exir/program/test/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/program/test
2025-03-21T20:25:14.4136765Z   copying exir/program/test/test_fake_program.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/program/test
2025-03-21T20:25:14.4138346Z   copying exir/program/test/test_program.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/program/test
2025-03-21T20:25:14.4139125Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/exir/verification/test
2025-03-21T20:25:14.4139939Z   copying exir/verification/test/test_verifier.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/verification/test
2025-03-21T20:25:14.4140748Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/android_test
2025-03-21T20:25:14.4141527Z   copying extension/android_test/add_model.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/android_test
2025-03-21T20:25:14.4142294Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/export_util
2025-03-21T20:25:14.4143045Z   copying extension/export_util/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/export_util
2025-03-21T20:25:14.4144352Z   copying extension/export_util/utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/export_util
2025-03-21T20:25:14.4145694Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/flat_tensor
2025-03-21T20:25:14.4147060Z   copying extension/flat_tensor/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/flat_tensor
2025-03-21T20:25:14.4148112Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/gguf_util
2025-03-21T20:25:14.4148868Z   copying extension/gguf_util/convert_main.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/gguf_util
2025-03-21T20:25:14.4149741Z   copying extension/gguf_util/converter.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/gguf_util
2025-03-21T20:25:14.4150583Z   copying extension/gguf_util/load_gguf.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/gguf_util
2025-03-21T20:25:14.4151313Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/pybindings
2025-03-21T20:25:14.4152106Z   copying extension/pybindings/portable_lib.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/pybindings
2025-03-21T20:25:14.4153444Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/pytree
2025-03-21T20:25:14.4154670Z   copying extension/pytree/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/pytree
2025-03-21T20:25:14.4155958Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/training
2025-03-21T20:25:14.4454096Z   copying extension/training/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/training
2025-03-21T20:25:14.4455109Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/flat_tensor/serialize
2025-03-21T20:25:14.4455981Z   copying extension/flat_tensor/serialize/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/flat_tensor/serialize
2025-03-21T20:25:14.4457096Z   copying extension/flat_tensor/serialize/flat_tensor_schema.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/flat_tensor/serialize
2025-03-21T20:25:14.4458223Z   copying extension/flat_tensor/serialize/serialize.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/flat_tensor/serialize
2025-03-21T20:25:14.4459095Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/flat_tensor/test
2025-03-21T20:25:14.4459944Z   copying extension/flat_tensor/test/test_serialize.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/flat_tensor/test
2025-03-21T20:25:14.4460796Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/gguf_util/converters
2025-03-21T20:25:14.4461700Z   copying extension/gguf_util/converters/llama_converter.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/gguf_util/converters
2025-03-21T20:25:14.4462559Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/custom_ops
2025-03-21T20:25:14.4463350Z   copying extension/llm/custom_ops/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/custom_ops
2025-03-21T20:25:14.4464531Z   copying extension/llm/custom_ops/custom_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/custom_ops
2025-03-21T20:25:14.4465509Z   copying extension/llm/custom_ops/model_sharding.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/custom_ops
2025-03-21T20:25:14.4466504Z   copying extension/llm/custom_ops/op_tile_crop_aot.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/custom_ops
2025-03-21T20:25:14.4467523Z   copying extension/llm/custom_ops/preprocess_custom_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/custom_ops
2025-03-21T20:25:14.4468592Z   copying extension/llm/custom_ops/test_preprocess_custom_ops.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/custom_ops
2025-03-21T20:25:14.4469661Z   copying extension/llm/custom_ops/test_sdpa_with_kv_cache.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/custom_ops
2025-03-21T20:25:14.4470684Z   copying extension/llm/custom_ops/test_update_cache.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/custom_ops
2025-03-21T20:25:14.4471499Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/export
2025-03-21T20:25:14.4472238Z   copying extension/llm/export/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/export
2025-03-21T20:25:14.4473114Z   copying extension/llm/export/builder.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/export
2025-03-21T20:25:14.4474026Z   copying extension/llm/export/export_passes.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/export
2025-03-21T20:25:14.4474977Z   copying extension/llm/export/partitioner_lib.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/export
2025-03-21T20:25:14.4475920Z   copying extension/llm/export/quantizer_lib.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/export
2025-03-21T20:25:14.4476859Z   copying extension/llm/export/test_export_passes.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/export
2025-03-21T20:25:14.4477654Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/modules
2025-03-21T20:25:14.4478402Z   copying extension/llm/modules/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/modules
2025-03-21T20:25:14.4479340Z   copying extension/llm/modules/_position_embeddings.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/modules
2025-03-21T20:25:14.4480297Z   copying extension/llm/modules/attention.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/modules
2025-03-21T20:25:14.4481203Z   copying extension/llm/modules/kv_cache.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/modules
2025-03-21T20:25:14.4481957Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizer
2025-03-21T20:25:14.4482741Z   copying extension/llm/tokenizer/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizer
2025-03-21T20:25:14.4483691Z   copying extension/llm/tokenizer/hf_tokenizer.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizer
2025-03-21T20:25:14.4484665Z   copying extension/llm/tokenizer/tokenizer.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizer
2025-03-21T20:25:14.4485610Z   copying extension/llm/tokenizer/utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizer
2025-03-21T20:25:14.4486393Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers
2025-03-21T20:25:14.4487190Z   copying extension/llm/tokenizers/setup.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers
2025-03-21T20:25:14.4488015Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/custom_ops/spinquant
2025-03-21T20:25:14.4489071Z   copying extension/llm/custom_ops/spinquant/special_hadamard_code_gen.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/custom_ops/spinquant
2025-03-21T20:25:14.4490336Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/custom_ops/spinquant/third-party/FFHT
2025-03-21T20:25:14.4491509Z   copying extension/llm/custom_ops/spinquant/third-party/FFHT/example.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/custom_ops/spinquant/third-party/FFHT
2025-03-21T20:25:14.4492936Z   copying extension/llm/custom_ops/spinquant/third-party/FFHT/gen.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/custom_ops/spinquant/third-party/FFHT
2025-03-21T20:25:14.4493961Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/modules/test
2025-03-21T20:25:14.4494781Z   copying extension/llm/modules/test/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/modules/test
2025-03-21T20:25:14.4495792Z   copying extension/llm/modules/test/test_attention.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/modules/test
2025-03-21T20:25:14.4496825Z   copying extension/llm/modules/test/test_kv_cache.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/modules/test
2025-03-21T20:25:14.4497903Z   copying extension/llm/modules/test/test_position_embeddings.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/modules/test
2025-03-21T20:25:14.4498796Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizer/test
2025-03-21T20:25:14.4499679Z   copying extension/llm/tokenizer/test/test_tokenizer.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizer/test
2025-03-21T20:25:14.4500638Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/pytorch_tokenizers
2025-03-21T20:25:14.4501699Z   copying extension/llm/tokenizers/pytorch_tokenizers/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/pytorch_tokenizers
2025-03-21T20:25:14.4503428Z   copying extension/llm/tokenizers/pytorch_tokenizers/hf_tokenizer.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/pytorch_tokenizers
2025-03-21T20:25:14.4505818Z   copying extension/llm/tokenizers/pytorch_tokenizers/llama2c.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/pytorch_tokenizers
2025-03-21T20:25:14.4507807Z   copying extension/llm/tokenizers/pytorch_tokenizers/tiktoken.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/pytorch_tokenizers
2025-03-21T20:25:14.4508959Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/pytorch_tokenizers/tools/llama2c
2025-03-21T20:25:14.4510222Z   copying extension/llm/tokenizers/pytorch_tokenizers/tools/llama2c/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/pytorch_tokenizers/tools/llama2c
2025-03-21T20:25:14.4512087Z   copying extension/llm/tokenizers/pytorch_tokenizers/tools/llama2c/convert.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/pytorch_tokenizers/tools/llama2c
2025-03-21T20:25:14.4513375Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/abseil-cpp
2025-03-21T20:25:14.4514624Z   copying extension/llm/tokenizers/third-party/abseil-cpp/conanfile.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/abseil-cpp
2025-03-21T20:25:14.4516192Z   copying extension/llm/tokenizers/third-party/abseil-cpp/create_lts.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/abseil-cpp
2025-03-21T20:25:14.4517450Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/abseil-cpp/absl
2025-03-21T20:25:14.4518779Z   copying extension/llm/tokenizers/third-party/abseil-cpp/absl/abseil.podspec.gen.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/abseil-cpp/absl
2025-03-21T20:25:14.4520353Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/abseil-cpp/absl/copts
2025-03-21T20:25:14.4728194Z   copying extension/llm/tokenizers/third-party/abseil-cpp/absl/copts/copts.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/abseil-cpp/absl/copts
2025-03-21T20:25:14.4731162Z   copying extension/llm/tokenizers/third-party/abseil-cpp/absl/copts/generate_copts.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/abseil-cpp/absl/copts
2025-03-21T20:25:14.4732762Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/json/docs/mkdocs/scripts
2025-03-21T20:25:14.4734148Z   copying extension/llm/tokenizers/third-party/json/docs/mkdocs/scripts/check_structure.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/json/docs/mkdocs/scripts
2025-03-21T20:25:14.4735536Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/json/tests/thirdparty/imapdl
2025-03-21T20:25:14.4736946Z   copying extension/llm/tokenizers/third-party/json/tests/thirdparty/imapdl/filterbr.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/json/tests/thirdparty/imapdl
2025-03-21T20:25:14.4738601Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/json/tools/amalgamate
2025-03-21T20:25:14.4740993Z   copying extension/llm/tokenizers/third-party/json/tools/amalgamate/amalgamate.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/json/tools/amalgamate
2025-03-21T20:25:14.4743381Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/json/tools/gdb_pretty_printer
2025-03-21T20:25:14.4745315Z   copying extension/llm/tokenizers/third-party/json/tools/gdb_pretty_printer/nlohmann-json.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/json/tools/gdb_pretty_printer
2025-03-21T20:25:14.4746741Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/json/tools/generate_natvis
2025-03-21T20:25:14.4748127Z   copying extension/llm/tokenizers/third-party/json/tools/generate_natvis/generate_natvis.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/json/tools/generate_natvis
2025-03-21T20:25:14.4749493Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/json/tools/serve_header
2025-03-21T20:25:14.4750809Z   copying extension/llm/tokenizers/third-party/json/tools/serve_header/serve_header.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/json/tools/serve_header
2025-03-21T20:25:14.4752920Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/re2/benchlog
2025-03-21T20:25:14.4754994Z   copying extension/llm/tokenizers/third-party/re2/benchlog/benchplot.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/re2/benchlog
2025-03-21T20:25:14.4756646Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/re2/python
2025-03-21T20:25:14.4757774Z   copying extension/llm/tokenizers/third-party/re2/python/re2.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/re2/python
2025-03-21T20:25:14.4759150Z   copying extension/llm/tokenizers/third-party/re2/python/re2_test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/re2/python
2025-03-21T20:25:14.4760538Z   copying extension/llm/tokenizers/third-party/re2/python/setup.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/re2/python
2025-03-21T20:25:14.4762309Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/re2/re2
2025-03-21T20:25:14.4764087Z   copying extension/llm/tokenizers/third-party/re2/re2/make_unicode_casefold.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/re2/re2
2025-03-21T20:25:14.4765611Z   copying extension/llm/tokenizers/third-party/re2/re2/make_unicode_groups.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/re2/re2
2025-03-21T20:25:14.4766981Z   copying extension/llm/tokenizers/third-party/re2/re2/unicode.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/re2/re2
2025-03-21T20:25:14.4768133Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/re2/python/toolchains
2025-03-21T20:25:14.4770005Z   copying extension/llm/tokenizers/third-party/re2/python/toolchains/generate.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/re2/python/toolchains
2025-03-21T20:25:14.4772313Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/sentencepiece/python
2025-03-21T20:25:14.4774417Z   copying extension/llm/tokenizers/third-party/sentencepiece/python/setup.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/sentencepiece/python
2025-03-21T20:25:14.4775744Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/sentencepiece/python/test
2025-03-21T20:25:14.4777092Z   copying extension/llm/tokenizers/third-party/sentencepiece/python/test/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/sentencepiece/python/test
2025-03-21T20:25:14.4778836Z   copying extension/llm/tokenizers/third-party/sentencepiece/python/test/sentencepiece_test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/sentencepiece/python/test
2025-03-21T20:25:14.4780817Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/sentencepiece/python/src/sentencepiece
2025-03-21T20:25:14.4783016Z   copying extension/llm/tokenizers/third-party/sentencepiece/python/src/sentencepiece/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/sentencepiece/python/src/sentencepiece
2025-03-21T20:25:14.4784978Z   copying extension/llm/tokenizers/third-party/sentencepiece/python/src/sentencepiece/_version.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/sentencepiece/python/src/sentencepiece
2025-03-21T20:25:14.4787012Z   copying extension/llm/tokenizers/third-party/sentencepiece/python/src/sentencepiece/sentencepiece_model_pb2.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/sentencepiece/python/src/sentencepiece
2025-03-21T20:25:14.4789919Z   copying extension/llm/tokenizers/third-party/sentencepiece/python/src/sentencepiece/sentencepiece_pb2.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/sentencepiece/python/src/sentencepiece
2025-03-21T20:25:14.4791806Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/tools/llama2c
2025-03-21T20:25:14.4792831Z   copying extension/llm/tokenizers/tools/llama2c/convert.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/tools/llama2c
2025-03-21T20:25:14.4793784Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/pybindings/test
2025-03-21T20:25:14.4794617Z   copying extension/pybindings/test/make_test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/pybindings/test
2025-03-21T20:25:14.4795666Z   copying extension/pybindings/test/test_backend_pybinding.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/pybindings/test
2025-03-21T20:25:14.4797548Z   copying extension/pybindings/test/test_pybindings.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/pybindings/test
2025-03-21T20:25:14.4798973Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/pytree/test
2025-03-21T20:25:14.4800557Z   copying extension/pytree/test/test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/pytree/test
2025-03-21T20:25:14.4801450Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/training/pybindings
2025-03-21T20:25:14.4802365Z   copying extension/training/pybindings/_training_module.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/training/pybindings
2025-03-21T20:25:14.4803279Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/training/examples/XOR
2025-03-21T20:25:14.4804207Z   copying extension/training/examples/XOR/export_model.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/training/examples/XOR
2025-03-21T20:25:14.4805315Z   copying extension/training/examples/XOR/model.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/training/examples/XOR
2025-03-21T20:25:14.4806862Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/training/examples/XOR/test
2025-03-21T20:25:14.4808379Z   copying extension/training/examples/XOR/test/test_export.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/training/examples/XOR/test
2025-03-21T20:25:14.4809483Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/extension/training/pybindings/test
2025-03-21T20:25:14.4810440Z   copying extension/training/pybindings/test/test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/training/pybindings/test
2025-03-21T20:25:14.4811311Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/kernels/quantized
2025-03-21T20:25:14.5095983Z   copying kernels/quantized/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/kernels/quantized
2025-03-21T20:25:14.5097300Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/kernels/quantized/test
2025-03-21T20:25:14.5098295Z   copying kernels/quantized/test/test_out_variants.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/kernels/quantized/test
2025-03-21T20:25:14.5099474Z   copying kernels/quantized/test/test_quant_dequant_per_token.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/kernels/quantized/test
2025-03-21T20:25:14.5100294Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/devtools
2025-03-21T20:25:14.5100900Z   copying devtools/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools
2025-03-21T20:25:14.5101555Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/backend_debug
2025-03-21T20:25:14.5102334Z   copying devtools/backend_debug/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/backend_debug
2025-03-21T20:25:14.5103907Z   copying devtools/backend_debug/delegation_info.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/backend_debug
2025-03-21T20:25:14.5105397Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program
2025-03-21T20:25:14.5106848Z   copying devtools/bundled_program/config.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program
2025-03-21T20:25:14.5108537Z   copying devtools/bundled_program/core.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program
2025-03-21T20:25:14.5110148Z   copying devtools/bundled_program/version.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program
2025-03-21T20:25:14.5111505Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/debug_format
2025-03-21T20:25:14.5112303Z   copying devtools/debug_format/base_schema.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/debug_format
2025-03-21T20:25:14.5113350Z   copying devtools/debug_format/et_schema.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/debug_format
2025-03-21T20:25:14.5114096Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/etdump
2025-03-21T20:25:14.5114806Z   copying devtools/etdump/schema_flatcc.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/etdump
2025-03-21T20:25:14.5115647Z   copying devtools/etdump/serialize.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/etdump
2025-03-21T20:25:14.5116602Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/etrecord
2025-03-21T20:25:14.5117545Z   copying devtools/etrecord/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/etrecord
2025-03-21T20:25:14.5118977Z   copying devtools/etrecord/_etrecord.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/etrecord
2025-03-21T20:25:14.5120303Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/inspector
2025-03-21T20:25:14.5121623Z   copying devtools/inspector/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/inspector
2025-03-21T20:25:14.5123188Z   copying devtools/inspector/_inspector.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/inspector
2025-03-21T20:25:14.5124847Z   copying devtools/inspector/_inspector_utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/inspector
2025-03-21T20:25:14.5126562Z   copying devtools/inspector/inspector_cli.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/inspector
2025-03-21T20:25:14.5128030Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/size_analysis_tool
2025-03-21T20:25:14.5129724Z   copying devtools/size_analysis_tool/size_analysis_tool.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/size_analysis_tool
2025-03-21T20:25:14.5131737Z   copying devtools/size_analysis_tool/size_analysis_tool_test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/size_analysis_tool
2025-03-21T20:25:14.5133418Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/visualization
2025-03-21T20:25:14.5134766Z   copying devtools/visualization/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/visualization
2025-03-21T20:25:14.5136147Z   copying devtools/visualization/visualization_utils.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/visualization
2025-03-21T20:25:14.5137324Z   copying devtools/visualization/visualization_utils_test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/visualization
2025-03-21T20:25:14.5138209Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/backend_debug/tests
2025-03-21T20:25:14.5139105Z   copying devtools/backend_debug/tests/test_delegation_info.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/backend_debug/tests
2025-03-21T20:25:14.5140011Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/schema
2025-03-21T20:25:14.5140890Z   copying devtools/bundled_program/schema/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/schema
2025-03-21T20:25:14.5142757Z   copying devtools/bundled_program/schema/bundled_program_schema.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/schema
2025-03-21T20:25:14.5144216Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/serialize
2025-03-21T20:25:14.5145232Z   copying devtools/bundled_program/serialize/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/serialize
2025-03-21T20:25:14.5146198Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/test
2025-03-21T20:25:14.5147095Z   copying devtools/bundled_program/test/test_bundle_data.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/test
2025-03-21T20:25:14.5148165Z   copying devtools/bundled_program/test/test_config.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/test
2025-03-21T20:25:14.5149223Z   copying devtools/bundled_program/test/test_end2end.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/test
2025-03-21T20:25:14.5150085Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/util
2025-03-21T20:25:14.5151373Z   copying devtools/bundled_program/util/test_util.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/util
2025-03-21T20:25:14.5153206Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/schema/test
2025-03-21T20:25:14.5154276Z   copying devtools/bundled_program/schema/test/test_schema.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/schema/test
2025-03-21T20:25:14.5155407Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/serialize/test
2025-03-21T20:25:14.5156443Z   copying devtools/bundled_program/serialize/test/test_serialize.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/serialize/test
2025-03-21T20:25:14.5157391Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/etdump/tests
2025-03-21T20:25:14.5158180Z   copying devtools/etdump/tests/serialize_test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/etdump/tests
2025-03-21T20:25:14.5159137Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/etrecord/tests
2025-03-21T20:25:14.5160623Z   copying devtools/etrecord/tests/etrecord_test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/etrecord/tests
2025-03-21T20:25:14.5162187Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/inspector/tests
2025-03-21T20:25:14.5163792Z   copying devtools/inspector/tests/event_blocks_test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/inspector/tests
2025-03-21T20:25:14.5165785Z   copying devtools/inspector/tests/inspector_test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/inspector/tests
2025-03-21T20:25:14.5167818Z   copying devtools/inspector/tests/inspector_utils_test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/inspector/tests
2025-03-21T20:25:14.5169811Z   copying devtools/bundled_program/config.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program
2025-03-21T20:25:14.5171582Z   copying devtools/bundled_program/core.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program
2025-03-21T20:25:14.5173363Z   copying devtools/bundled_program/version.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program
2025-03-21T20:25:14.5175250Z   copying devtools/bundled_program/schema/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/schema
2025-03-21T20:25:14.5177398Z   copying devtools/bundled_program/schema/bundled_program_schema.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/schema
2025-03-21T20:25:14.5179604Z   copying devtools/bundled_program/serialize/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/serialize
2025-03-21T20:25:14.5181714Z   copying devtools/bundled_program/test/test_bundle_data.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/test
2025-03-21T20:25:14.5183780Z   copying devtools/bundled_program/test/test_config.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/test
2025-03-21T20:25:14.5185813Z   copying devtools/bundled_program/test/test_end2end.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/test
2025-03-21T20:25:14.5187837Z   copying devtools/bundled_program/util/test_util.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/util
2025-03-21T20:25:14.5189982Z   copying devtools/bundled_program/schema/test/test_schema.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/schema/test
2025-03-21T20:25:15.3203221Z   copying devtools/bundled_program/serialize/test/test_serialize.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/serialize/test
2025-03-21T20:25:15.3204170Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/runtime
2025-03-21T20:25:15.3204765Z   copying runtime/__init__.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/runtime
2025-03-21T20:25:15.3205378Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/runtime/test
2025-03-21T20:25:15.3206297Z   copying runtime/test/test_runtime.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/runtime/test
2025-03-21T20:25:15.3207082Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/util
2025-03-21T20:25:15.3207724Z   copying util/activation_memory_profiler.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/util
2025-03-21T20:25:15.3208435Z   copying util/collect_env.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/util
2025-03-21T20:25:15.3209094Z   copying util/python_profiler.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/util
2025-03-21T20:25:15.3209675Z   running egg_info
2025-03-21T20:25:15.3209949Z   creating executorch.egg-info
2025-03-21T20:25:15.3210279Z   writing executorch.egg-info/PKG-INFO
2025-03-21T20:25:15.3210736Z   writing dependency_links to executorch.egg-info/dependency_links.txt
2025-03-21T20:25:15.3211278Z   writing entry points to executorch.egg-info/entry_points.txt
2025-03-21T20:25:15.3211758Z   writing requirements to executorch.egg-info/requires.txt
2025-03-21T20:25:15.3212255Z   writing top-level names to executorch.egg-info/top_level.txt
2025-03-21T20:25:15.3212748Z   writing manifest file 'executorch.egg-info/SOURCES.txt'
2025-03-21T20:25:15.3213216Z   reading manifest file 'executorch.egg-info/SOURCES.txt'
2025-03-21T20:25:15.3213617Z   adding license file 'LICENSE'
2025-03-21T20:25:15.3213980Z   writing manifest file 'executorch.egg-info/SOURCES.txt'
2025-03-21T20:25:15.3214740Z   copying backends/apple/coreml/executorchcoreml.pyi -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/coreml
2025-03-21T20:25:15.3215841Z   copying backends/apple/mps/serialization/schema.fbs -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/serialization
2025-03-21T20:25:15.3216857Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/schema
2025-03-21T20:25:15.3217995Z   copying backends/arm/third-party/serialization_lib/schema/tosa.fbs -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/schema
2025-03-21T20:25:15.3219173Z   copying backends/cadence/aot/functions.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot
2025-03-21T20:25:15.3220143Z   copying backends/cadence/aot/functions_fusion_g3.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot
2025-03-21T20:25:15.3221109Z   copying backends/cadence/aot/functions_hifi.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot
2025-03-21T20:25:15.3222183Z   copying backends/qualcomm/serialization/qc_compiler_spec.fbs -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/serialization
2025-03-21T20:25:15.3223085Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/aot/ir
2025-03-21T20:25:15.3223878Z   copying backends/qualcomm/aot/ir/qcir.fbs -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/aot/ir
2025-03-21T20:25:15.3224880Z   copying backends/vulkan/serialization/schema.fbs -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/serialization
2025-03-21T20:25:15.3225804Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3226863Z   copying backends/vulkan/runtime/graph/ops/glsl/addmm_naive_buffer.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3228199Z   copying backends/vulkan/runtime/graph/ops/glsl/addmm_naive_texture3d.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3229538Z   copying backends/vulkan/runtime/graph/ops/glsl/addmm_optimized.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3230828Z   copying backends/vulkan/runtime/graph/ops/glsl/arange.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3232180Z   copying backends/vulkan/runtime/graph/ops/glsl/avg_pool2d.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3233739Z   copying backends/vulkan/runtime/graph/ops/glsl/batchnorm.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3235016Z   copying backends/vulkan/runtime/graph/ops/glsl/binary_op.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3236374Z   copying backends/vulkan/runtime/graph/ops/glsl/bitw8_image_to_nchw_nobitw8buffer.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3237756Z   copying backends/vulkan/runtime/graph/ops/glsl/buffer_to_buffer.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3239059Z   copying backends/vulkan/runtime/graph/ops/glsl/buffer_to_nchw.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3240325Z   copying backends/vulkan/runtime/graph/ops/glsl/clone.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3241568Z   copying backends/vulkan/runtime/graph/ops/glsl/conv1d.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3242810Z   copying backends/vulkan/runtime/graph/ops/glsl/conv2d.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3244063Z   copying backends/vulkan/runtime/graph/ops/glsl/conv2d_dw.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3245365Z   copying backends/vulkan/runtime/graph/ops/glsl/conv2d_dw_output_tile.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3246741Z   copying backends/vulkan/runtime/graph/ops/glsl/conv2d_dw_prepack_weights.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3248132Z   copying backends/vulkan/runtime/graph/ops/glsl/conv2d_dw_sned_output_tile.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3249571Z   copying backends/vulkan/runtime/graph/ops/glsl/conv2d_prepack_weights.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3250890Z   copying backends/vulkan/runtime/graph/ops/glsl/conv2d_pw.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3252170Z   copying backends/vulkan/runtime/graph/ops/glsl/conv_transpose2d.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3253568Z   copying backends/vulkan/runtime/graph/ops/glsl/conv_transpose2d_prepack_weights.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3254972Z   copying backends/vulkan/runtime/graph/ops/glsl/copy_channel_offset.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3256289Z   copying backends/vulkan/runtime/graph/ops/glsl/copy_offset.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3257604Z   copying backends/vulkan/runtime/graph/ops/glsl/copy_packed_dim_offset.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3258927Z   copying backends/vulkan/runtime/graph/ops/glsl/embedding.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3260185Z   copying backends/vulkan/runtime/graph/ops/glsl/flip.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3261495Z   copying backends/vulkan/runtime/graph/ops/glsl/full.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3262817Z   copying backends/vulkan/runtime/graph/ops/glsl/grid_priors.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3264093Z   copying backends/vulkan/runtime/graph/ops/glsl/image_to_nchw.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3265383Z   copying backends/vulkan/runtime/graph/ops/glsl/index_select.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3266708Z   copying backends/vulkan/runtime/graph/ops/glsl/index_select_channel.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3268041Z   copying backends/vulkan/runtime/graph/ops/glsl/kv_cache_update.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3269326Z   copying backends/vulkan/runtime/graph/ops/glsl/max_pool2d.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3544135Z   copying backends/vulkan/runtime/graph/ops/glsl/native_layer_norm.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3545720Z   copying backends/vulkan/runtime/graph/ops/glsl/nchw_to_bitw8_image_nobitw8buffer.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3547202Z   copying backends/vulkan/runtime/graph/ops/glsl/nchw_to_buffer.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3548522Z   copying backends/vulkan/runtime/graph/ops/glsl/nchw_to_image.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3549897Z   copying backends/vulkan/runtime/graph/ops/glsl/no_op.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3551225Z   copying backends/vulkan/runtime/graph/ops/glsl/pad_channel.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3552565Z   copying backends/vulkan/runtime/graph/ops/glsl/pad_height_width.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3553938Z   copying backends/vulkan/runtime/graph/ops/glsl/permute.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3555293Z   copying backends/vulkan/runtime/graph/ops/glsl/q_4w_linear.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3556550Z   copying backends/vulkan/runtime/graph/ops/glsl/q_8w_linear.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3557977Z   copying backends/vulkan/runtime/graph/ops/glsl/q_8w_linear_optimized.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3559372Z   copying backends/vulkan/runtime/graph/ops/glsl/reduce.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3560775Z   copying backends/vulkan/runtime/graph/ops/glsl/repeat_channel.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3562186Z   copying backends/vulkan/runtime/graph/ops/glsl/repeat_interleave.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3563613Z   copying backends/vulkan/runtime/graph/ops/glsl/rotary_embedding.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3565394Z   copying backends/vulkan/runtime/graph/ops/glsl/sdpa_attn_weight_scale_and_mask.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3566805Z   copying backends/vulkan/runtime/graph/ops/glsl/select_batch_4d.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3568180Z   copying backends/vulkan/runtime/graph/ops/glsl/select_channel_3d.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3569716Z   copying backends/vulkan/runtime/graph/ops/glsl/select_channel_4d.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3571120Z   copying backends/vulkan/runtime/graph/ops/glsl/select_height_3d.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3572441Z   copying backends/vulkan/runtime/graph/ops/glsl/select_height_4d.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3573878Z   copying backends/vulkan/runtime/graph/ops/glsl/select_width_3d.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3575276Z   copying backends/vulkan/runtime/graph/ops/glsl/select_width_4d.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3576575Z   copying backends/vulkan/runtime/graph/ops/glsl/slice_packed_dim.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3578024Z   copying backends/vulkan/runtime/graph/ops/glsl/slice_unpacked_dim.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3579442Z   copying backends/vulkan/runtime/graph/ops/glsl/softmax.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3580712Z   copying backends/vulkan/runtime/graph/ops/glsl/unary_op.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3582130Z   copying backends/vulkan/runtime/graph/ops/glsl/upsample_nearest2d.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3583423Z   copying backends/vulkan/runtime/graph/ops/glsl/view.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.3584466Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/test/glsl
2025-03-21T20:25:15.3585317Z   copying backends/vulkan/test/glsl/all_shaders.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/test/glsl
2025-03-21T20:25:15.3586311Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/tools/gpuinfo/glsl
2025-03-21T20:25:15.3587293Z   copying backends/vulkan/tools/gpuinfo/glsl/buf_bandwidth.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/tools/gpuinfo/glsl
2025-03-21T20:25:15.3588538Z   copying backends/vulkan/tools/gpuinfo/glsl/buf_cacheline_size.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/tools/gpuinfo/glsl
2025-03-21T20:25:15.3589856Z   copying backends/vulkan/tools/gpuinfo/glsl/reg_count.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/tools/gpuinfo/glsl
2025-03-21T20:25:15.3591183Z   copying backends/vulkan/tools/gpuinfo/glsl/tex_bandwidth.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/tools/gpuinfo/glsl
2025-03-21T20:25:15.3592447Z   copying backends/vulkan/tools/gpuinfo/glsl/tex_cacheline_concurr.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/tools/gpuinfo/glsl
2025-03-21T20:25:15.3593791Z   copying backends/vulkan/tools/gpuinfo/glsl/warp_size.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/tools/gpuinfo/glsl
2025-03-21T20:25:15.3595192Z   copying backends/xnnpack/serialization/runtime_schema.fbs -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/serialization
2025-03-21T20:25:15.3596382Z   copying backends/xnnpack/serialization/schema.fbs -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/serialization
2025-03-21T20:25:15.3597631Z   copying backends/xnnpack/third-party/generate-cpuinfo-wrappers.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party
2025-03-21T20:25:15.3598815Z   copying backends/xnnpack/third-party/FP16/confu.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/FP16
2025-03-21T20:25:15.3600088Z   copying backends/xnnpack/third-party/FXdiv/confu.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/FXdiv
2025-03-21T20:25:15.3601451Z   copying backends/xnnpack/third-party/cpuinfo/confu.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/cpuinfo
2025-03-21T20:25:15.3602700Z   copying backends/xnnpack/third-party/pthreadpool/confu.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/pthreadpool
2025-03-21T20:25:15.3604201Z   copying backends/xnnpack/third-party/XNNPACK/scripts/generate-build-identifier.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/scripts
2025-03-21T20:25:15.3605795Z   copying backends/xnnpack/third-party/XNNPACK/scripts/sort-filenames.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/scripts
2025-03-21T20:25:15.3606906Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3608081Z   copying backends/xnnpack/third-party/XNNPACK/test/bf16-gemm-minmax.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3609597Z   copying backends/xnnpack/third-party/XNNPACK/test/f16-conv-hwc2chw.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3611022Z   copying backends/xnnpack/third-party/XNNPACK/test/f16-dwconv2d-chw.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3612529Z   copying backends/xnnpack/third-party/XNNPACK/test/f16-f32acc-gemm-minmax.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3614079Z   copying backends/xnnpack/third-party/XNNPACK/test/f16-f32acc-igemm-minmax.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3646529Z   copying backends/xnnpack/third-party/XNNPACK/test/f16-f32acc-rdsum.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3648232Z   copying backends/xnnpack/third-party/XNNPACK/test/f16-f32acc-rsum.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3650088Z   copying backends/xnnpack/third-party/XNNPACK/test/f16-gemm-minmax.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3651579Z   copying backends/xnnpack/third-party/XNNPACK/test/f16-ibilinear-chw.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3653043Z   copying backends/xnnpack/third-party/XNNPACK/test/f16-ibilinear.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3654534Z   copying backends/xnnpack/third-party/XNNPACK/test/f16-igemm-minmax.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3656502Z   copying backends/xnnpack/third-party/XNNPACK/test/f16-raddstoreexpminusmax.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3658443Z   copying backends/xnnpack/third-party/XNNPACK/test/f16-rmax.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3660103Z   copying backends/xnnpack/third-party/XNNPACK/test/f16-rmin.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3661666Z   copying backends/xnnpack/third-party/XNNPACK/test/f16-rminmax.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3663275Z   copying backends/xnnpack/third-party/XNNPACK/test/f16-rsum.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3664793Z   copying backends/xnnpack/third-party/XNNPACK/test/f16-spmm-minmax.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3666485Z   copying backends/xnnpack/third-party/XNNPACK/test/f16-vmulcaddc-minmax.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3667946Z   copying backends/xnnpack/third-party/XNNPACK/test/f32-argmaxpool.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3669493Z   copying backends/xnnpack/third-party/XNNPACK/test/f32-conv-hwc.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3671072Z   copying backends/xnnpack/third-party/XNNPACK/test/f32-conv-hwc2chw.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3672581Z   copying backends/xnnpack/third-party/XNNPACK/test/f32-dwconv2d-chw.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3674241Z   copying backends/xnnpack/third-party/XNNPACK/test/f32-gemm-goi-minmax.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3675809Z   copying backends/xnnpack/third-party/XNNPACK/test/f32-gemm-minmax.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3677449Z   copying backends/xnnpack/third-party/XNNPACK/test/f32-gemm-relu.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3678848Z   copying backends/xnnpack/third-party/XNNPACK/test/f32-gemm.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3680367Z   copying backends/xnnpack/third-party/XNNPACK/test/f32-gemminc-minmax.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3682099Z   copying backends/xnnpack/third-party/XNNPACK/test/f32-ibilinear-chw.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3683742Z   copying backends/xnnpack/third-party/XNNPACK/test/f32-ibilinear.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3685202Z   copying backends/xnnpack/third-party/XNNPACK/test/f32-igemm-minmax.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3686942Z   copying backends/xnnpack/third-party/XNNPACK/test/f32-igemm-relu.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3688576Z   copying backends/xnnpack/third-party/XNNPACK/test/f32-igemm.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3690449Z   copying backends/xnnpack/third-party/XNNPACK/test/f32-ppmm-minmax.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3692424Z   copying backends/xnnpack/third-party/XNNPACK/test/f32-qc4w-gemm-minmax.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3694500Z   copying backends/xnnpack/third-party/XNNPACK/test/f32-qc8w-gemm-minmax.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3697029Z   copying backends/xnnpack/third-party/XNNPACK/test/f32-qc8w-gemm-relu.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3699597Z   copying backends/xnnpack/third-party/XNNPACK/test/f32-qc8w-gemm.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3702185Z   copying backends/xnnpack/third-party/XNNPACK/test/f32-raddexpminusmax.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3704821Z   copying backends/xnnpack/third-party/XNNPACK/test/f32-raddextexp.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3707222Z   copying backends/xnnpack/third-party/XNNPACK/test/f32-raddstoreexpminusmax.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3709723Z   copying backends/xnnpack/third-party/XNNPACK/test/f32-rdsum.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3712090Z   copying backends/xnnpack/third-party/XNNPACK/test/f32-rmax.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3714456Z   copying backends/xnnpack/third-party/XNNPACK/test/f32-rmin.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3716858Z   copying backends/xnnpack/third-party/XNNPACK/test/f32-rminmax.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3719208Z   copying backends/xnnpack/third-party/XNNPACK/test/f32-rsum.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3721602Z   copying backends/xnnpack/third-party/XNNPACK/test/f32-spmm-minmax.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3724079Z   copying backends/xnnpack/third-party/XNNPACK/test/f32-vmulcaddc-minmax.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3726347Z   copying backends/xnnpack/third-party/XNNPACK/test/f32-vscaleexpminusmax.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3729002Z   copying backends/xnnpack/third-party/XNNPACK/test/f32-vscaleextexp.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3731511Z   copying backends/xnnpack/third-party/XNNPACK/test/qd8-f16-qb4w-gemm-minmax.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3734389Z   copying backends/xnnpack/third-party/XNNPACK/test/qd8-f16-qc4w-gemm-minmax.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3736946Z   copying backends/xnnpack/third-party/XNNPACK/test/qd8-f16-qc8w-gemm-minmax.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3739225Z   copying backends/xnnpack/third-party/XNNPACK/test/qd8-f16-qc8w-igemm-minmax.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3741976Z   copying backends/xnnpack/third-party/XNNPACK/test/qd8-f32-qb4w-gemm-minmax.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3755518Z   copying backends/xnnpack/third-party/XNNPACK/test/qd8-f32-qc4w-gemm-minmax.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3757205Z   copying backends/xnnpack/third-party/XNNPACK/test/qd8-f32-qc8w-gemm-minmax.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3758650Z   copying backends/xnnpack/third-party/XNNPACK/test/qd8-f32-qc8w-igemm-minmax.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3760092Z   copying backends/xnnpack/third-party/XNNPACK/test/qp8-f32-qb4w-gemm-minmax.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3761538Z   copying backends/xnnpack/third-party/XNNPACK/test/qp8-f32-qc4w-gemm-minmax.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3764005Z   copying backends/xnnpack/third-party/XNNPACK/test/qs8-qc8w-gemm-minmax-fp32.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3765467Z   copying backends/xnnpack/third-party/XNNPACK/test/qs8-qc8w-igemm-minmax-fp32.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3766940Z   copying backends/xnnpack/third-party/XNNPACK/test/qs8-rdsum-minmax-fp32.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3768289Z   copying backends/xnnpack/third-party/XNNPACK/test/qs8-rsum.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3770260Z   copying backends/xnnpack/third-party/XNNPACK/test/qu8-gemm-minmax-fp32.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3772458Z   copying backends/xnnpack/third-party/XNNPACK/test/qu8-gemm-minmax-rndnu.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3773888Z   copying backends/xnnpack/third-party/XNNPACK/test/qu8-igemm-minmax-fp32.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3775309Z   copying backends/xnnpack/third-party/XNNPACK/test/qu8-igemm-minmax-rndnu.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3776681Z   copying backends/xnnpack/third-party/XNNPACK/test/qu8-rdsum.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3778495Z   copying backends/xnnpack/third-party/XNNPACK/test/qu8-rsum.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3780966Z   copying backends/xnnpack/third-party/XNNPACK/test/s8-ibilinear.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3782611Z   copying backends/xnnpack/third-party/XNNPACK/test/u8-ibilinear.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3783940Z   copying backends/xnnpack/third-party/XNNPACK/test/u8-lut32norm.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3785252Z   copying backends/xnnpack/third-party/XNNPACK/test/u8-rmax.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3786526Z   copying backends/xnnpack/third-party/XNNPACK/test/x8-lut.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.3788960Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-argmaxpool-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.3791801Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-conv-hwc-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.3793840Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-conv-hwc2chw-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.3795361Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-dwconv-multipass-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.3796882Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-dwconv-unipass-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.3798389Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-dwconv2d-chw-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.3799843Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-gemm-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.3801283Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-ibilinear-chw-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.3802764Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-ibilinear-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.3804211Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-lut-norm-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.3805623Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-lut-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.3807084Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-raddexpminusmax-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.3808580Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-raddextexp-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.3810801Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-raddstoreexpminusmax-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.3812819Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-rdsum-benchmark.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.3814276Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-rdsum-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.3815696Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-reduce-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.3817088Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-spmm-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.3818983Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-vbinary-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.3821690Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-vmulcaddc-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.3824471Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-vscaleexpminusmax-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.3827198Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-vscaleextexp-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.3829557Z   copying backends/xnnpack/third-party/XNNPACK/tools/generate-vunary-test.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.3830993Z   copying backends/xnnpack/third-party/XNNPACK/tools/update-microkernels.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.3832691Z   copying backends/xnnpack/third-party/cpuinfo/scripts/android-device-dump.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/cpuinfo/scripts
2025-03-21T20:25:15.3834500Z   copying backends/xnnpack/third-party/cpuinfo/scripts/arm-linux-filesystem-dump.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/cpuinfo/scripts
2025-03-21T20:25:15.3836815Z   copying backends/xnnpack/third-party/cpuinfo/scripts/parse-x86-cpuid-dump.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/cpuinfo/scripts
2025-03-21T20:25:15.4565793Z   copying backends/xnnpack/third-party/cpuinfo/deps/clog/confu.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/cpuinfo/deps/clog
2025-03-21T20:25:15.4567178Z   copying examples/llm_pte_finetuning/phi3_alpaca_code_config.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/llm_pte_finetuning
2025-03-21T20:25:15.4568438Z   copying examples/llm_pte_finetuning/phi3_config.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/llm_pte_finetuning
2025-03-21T20:25:15.4569652Z   copying examples/llm_pte_finetuning/qwen_05b_config.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/llm_pte_finetuning
2025-03-21T20:25:15.4570893Z   copying examples/models/phi-3-mini/export_phi-3-mini.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/phi-3-mini
2025-03-21T20:25:15.4571916Z   copying exir/delegate.pyi -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir
2025-03-21T20:25:15.4572745Z   copying exir/_serialize/program.fbs -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/_serialize
2025-03-21T20:25:15.4573557Z   copying exir/_serialize/scalar_type.fbs -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/_serialize
2025-03-21T20:25:15.4574590Z   copying exir/dialects/edge/edge.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/edge
2025-03-21T20:25:15.4575485Z   copying extension/pybindings/pybindings.pyi -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/pybindings
2025-03-21T20:25:15.4576613Z   copying extension/flat_tensor/serialize/flat_tensor.fbs -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/flat_tensor/serialize
2025-03-21T20:25:15.4577923Z   copying extension/flat_tensor/serialize/scalar_type.fbs -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/flat_tensor/serialize
2025-03-21T20:25:15.4579339Z   copying extension/llm/tokenizers/third-party/abseil-cpp/absl/abseil.podspec.gen.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/abseil-cpp/absl
2025-03-21T20:25:15.4581094Z   copying extension/llm/tokenizers/third-party/json/tools/gdb_pretty_printer/nlohmann-json.py -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/json/tools/gdb_pretty_printer
2025-03-21T20:25:15.4582743Z   copying extension/training/pybindings/_training_lib.pyi -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/training/pybindings
2025-03-21T20:25:15.4583837Z   copying kernels/quantized/quantized.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/kernels/quantized
2025-03-21T20:25:15.4584920Z   copying kernels/quantized/test/supported_features_def.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/kernels/quantized/test
2025-03-21T20:25:15.4586141Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/schema
2025-03-21T20:25:15.4586769Z   copying schema/program.fbs -> pip-out/lib.linux-x86_64-cpython-310/executorch/schema
2025-03-21T20:25:15.4587506Z   copying schema/scalar_type.fbs -> pip-out/lib.linux-x86_64-cpython-310/executorch/schema
2025-03-21T20:25:15.4588418Z   copying devtools/etdump/etdump_schema_flatcc.fbs -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/etdump
2025-03-21T20:25:15.4589450Z   copying devtools/etdump/scalar_type.fbs -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/etdump
2025-03-21T20:25:15.4590572Z   copying devtools/bundled_program/schema/bundled_program_schema.fbs -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/schema
2025-03-21T20:25:15.4591733Z   copying devtools/bundled_program/schema/scalar_type.fbs -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/schema
2025-03-21T20:25:15.4593099Z   copying devtools/bundled_program/schema/bundled_program_schema.fbs -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/schema
2025-03-21T20:25:15.4594358Z   copying devtools/bundled_program/schema/scalar_type.fbs -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/schema
2025-03-21T20:25:15.4595223Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/runtime/kernel/test
2025-03-21T20:25:15.4596210Z   copying runtime/kernel/test/functions.yaml -> pip-out/lib.linux-x86_64-cpython-310/executorch/runtime/kernel/test
2025-03-21T20:25:15.4597294Z   copying devtools/bundled_program/schema/bundled_program_schema.fbs -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/serialize
2025-03-21T20:25:15.4598656Z   copying devtools/bundled_program/schema/scalar_type.fbs -> pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/serialize
2025-03-21T20:25:15.4599509Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/share/cmake
2025-03-21T20:25:15.4600594Z   copying tools/cmake/executorch-wheel-config.cmake -> pip-out/lib.linux-x86_64-cpython-310/executorch/share/cmake/executorch-config.cmake
2025-03-21T20:25:15.4601511Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core
2025-03-21T20:25:15.4602418Z   copying runtime/core/array_ref.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core
2025-03-21T20:25:15.4603333Z   copying runtime/core/data_loader.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core
2025-03-21T20:25:15.4604456Z   copying runtime/core/defines.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core
2025-03-21T20:25:15.4605344Z   copying runtime/core/error.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core
2025-03-21T20:25:15.4606317Z   copying runtime/core/evalue.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core
2025-03-21T20:25:15.4607228Z   copying runtime/core/event_tracer.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core
2025-03-21T20:25:15.4608373Z   copying runtime/core/event_tracer_hooks.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core
2025-03-21T20:25:15.4609493Z   copying runtime/core/event_tracer_hooks_delegate.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core
2025-03-21T20:25:15.4610576Z   copying runtime/core/freeable_buffer.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core
2025-03-21T20:25:15.4611636Z   copying runtime/core/hierarchical_allocator.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core
2025-03-21T20:25:15.4612849Z   copying runtime/core/memory_allocator.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core
2025-03-21T20:25:15.4614148Z   copying runtime/core/named_data_map.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core
2025-03-21T20:25:15.4615313Z   copying runtime/core/result.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core
2025-03-21T20:25:15.4616176Z   copying runtime/core/span.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core
2025-03-21T20:25:15.4617351Z   copying runtime/core/tag.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core
2025-03-21T20:25:15.4618323Z   copying runtime/core/tensor_layout.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core
2025-03-21T20:25:15.4619379Z   copying runtime/core/tensor_shape_dynamism.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core
2025-03-21T20:25:15.4620378Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/exec_aten
2025-03-21T20:25:15.4621480Z   copying runtime/core/exec_aten/exec_aten.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/exec_aten
2025-03-21T20:25:15.4622618Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/exec_aten/testing_util
2025-03-21T20:25:15.4623748Z   copying runtime/core/exec_aten/testing_util/tensor_factory.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/exec_aten/testing_util
2025-03-21T20:25:15.4625086Z   copying runtime/core/exec_aten/testing_util/tensor_util.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/exec_aten/testing_util
2025-03-21T20:25:15.4626170Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/exec_aten/util
2025-03-21T20:25:15.4627187Z   copying runtime/core/exec_aten/util/dim_order_util.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/exec_aten/util
2025-03-21T20:25:15.4628395Z   copying runtime/core/exec_aten/util/scalar_type_util.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/exec_aten/util
2025-03-21T20:25:15.4629893Z   copying runtime/core/exec_aten/util/tensor_dimension_limit.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/exec_aten/util
2025-03-21T20:25:15.4631336Z   copying runtime/core/exec_aten/util/tensor_shape_to_c_string.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/exec_aten/util
2025-03-21T20:25:15.4632920Z   copying runtime/core/exec_aten/util/tensor_util.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/exec_aten/util
2025-03-21T20:25:15.4633930Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type
2025-03-21T20:25:15.4634990Z   copying runtime/core/portable_type/bfloat16.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type
2025-03-21T20:25:15.4692357Z   copying runtime/core/portable_type/bfloat16_math.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type
2025-03-21T20:25:15.4693710Z   copying runtime/core/portable_type/bits_types.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type
2025-03-21T20:25:15.4694880Z   copying runtime/core/portable_type/complex.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type
2025-03-21T20:25:15.4696035Z   copying runtime/core/portable_type/device.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type
2025-03-21T20:25:15.4697163Z   copying runtime/core/portable_type/half.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type
2025-03-21T20:25:15.4698309Z   copying runtime/core/portable_type/optional.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type
2025-03-21T20:25:15.4699647Z   copying runtime/core/portable_type/qint_types.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type
2025-03-21T20:25:15.4700870Z   copying runtime/core/portable_type/scalar.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type
2025-03-21T20:25:15.4702033Z   copying runtime/core/portable_type/scalar_type.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type
2025-03-21T20:25:15.4703215Z   copying runtime/core/portable_type/string_view.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type
2025-03-21T20:25:15.4704375Z   copying runtime/core/portable_type/tensor.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type
2025-03-21T20:25:15.4705537Z   copying runtime/core/portable_type/tensor_impl.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type
2025-03-21T20:25:15.4706737Z   copying runtime/core/portable_type/tensor_options.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type
2025-03-21T20:25:15.4707832Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/c10/c10/macros
2025-03-21T20:25:15.4709038Z   copying runtime/core/portable_type/c10/c10/macros/Export.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/c10/c10/macros
2025-03-21T20:25:15.4710460Z   copying runtime/core/portable_type/c10/c10/macros/Macros.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/c10/c10/macros
2025-03-21T20:25:15.4711642Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/c10/c10/util
2025-03-21T20:25:15.4712847Z   copying runtime/core/portable_type/c10/c10/util/BFloat16-inl.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/c10/c10/util
2025-03-21T20:25:15.4714288Z   copying runtime/core/portable_type/c10/c10/util/BFloat16-math.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/c10/c10/util
2025-03-21T20:25:15.4715715Z   copying runtime/core/portable_type/c10/c10/util/BFloat16.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/c10/c10/util
2025-03-21T20:25:15.4717114Z   copying runtime/core/portable_type/c10/c10/util/Half-inl.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/c10/c10/util
2025-03-21T20:25:15.4718484Z   copying runtime/core/portable_type/c10/c10/util/Half.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/c10/c10/util
2025-03-21T20:25:15.4719911Z   copying runtime/core/portable_type/c10/c10/util/TypeSafeSignMath.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/c10/c10/util
2025-03-21T20:25:15.4721350Z   copying runtime/core/portable_type/c10/c10/util/bit_cast.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/c10/c10/util
2025-03-21T20:25:15.4722782Z   copying runtime/core/portable_type/c10/c10/util/floating_point_utils.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/c10/c10/util
2025-03-21T20:25:15.4724199Z   copying runtime/core/portable_type/c10/c10/util/irange.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/c10/c10/util
2025-03-21T20:25:15.4725287Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/kernel
2025-03-21T20:25:15.4726151Z   copying runtime/kernel/kernel_includes.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/kernel
2025-03-21T20:25:15.4727242Z   copying runtime/kernel/kernel_runtime_context.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/kernel
2025-03-21T20:25:15.4728334Z   copying runtime/kernel/operator_registry.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/kernel
2025-03-21T20:25:15.4729470Z   copying runtime/kernel/thread_parallel_interface.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/kernel
2025-03-21T20:25:15.4730398Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/kernel/test
2025-03-21T20:25:15.4731298Z   copying runtime/kernel/test/test_util.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/kernel/test
2025-03-21T20:25:15.4732189Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/platform
2025-03-21T20:25:15.4733490Z   copying runtime/platform/abort.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/platform
2025-03-21T20:25:15.4734683Z   copying runtime/platform/assert.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/platform
2025-03-21T20:25:15.4735655Z   copying runtime/platform/clock.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/platform
2025-03-21T20:25:15.4736964Z   copying runtime/platform/compat_unistd.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/platform
2025-03-21T20:25:15.4738051Z   copying runtime/platform/compiler.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/platform
2025-03-21T20:25:15.4739301Z   copying runtime/platform/log.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/platform
2025-03-21T20:25:15.4740460Z   copying runtime/platform/platform.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/platform
2025-03-21T20:25:15.4741666Z   copying runtime/platform/profiler.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/platform
2025-03-21T20:25:15.4742741Z   copying runtime/platform/runtime.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/platform
2025-03-21T20:25:15.4743781Z   copying runtime/platform/system.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/platform
2025-03-21T20:25:15.4744745Z   copying runtime/platform/types.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/platform
2025-03-21T20:25:15.4745620Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/platform/test
2025-03-21T20:25:15.4746580Z   copying runtime/platform/test/stub_platform.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/platform/test
2025-03-21T20:25:15.4747534Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/extension/kernel_util
2025-03-21T20:25:15.4748599Z   copying extension/kernel_util/make_boxed_from_unboxed_functor.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/extension/kernel_util
2025-03-21T20:25:15.4749784Z   copying extension/kernel_util/meta_programming.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/extension/kernel_util
2025-03-21T20:25:15.4750945Z   copying extension/kernel_util/type_list.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/extension/kernel_util
2025-03-21T20:25:15.4751845Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/extension/tensor
2025-03-21T20:25:15.4752756Z   copying extension/tensor/tensor.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/extension/tensor
2025-03-21T20:25:15.4753767Z   copying extension/tensor/tensor_accessor.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/extension/tensor
2025-03-21T20:25:15.4754916Z   copying extension/tensor/tensor_ptr.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/extension/tensor
2025-03-21T20:25:15.4756501Z   copying extension/tensor/tensor_ptr_maker.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/extension/tensor
2025-03-21T20:25:15.4757830Z   creating pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/extension/threadpool
2025-03-21T20:25:15.4759023Z   copying extension/threadpool/cpuinfo_utils.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/extension/threadpool
2025-03-21T20:25:15.4760459Z   copying extension/threadpool/threadpool.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/extension/threadpool
2025-03-21T20:25:15.5172389Z   copying extension/threadpool/threadpool_guard.h -> pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/extension/threadpool
2025-03-21T20:25:15.5173306Z   running build_ext
2025-03-21T20:25:15.5173763Z   creating /pytorch/executorch/pip-out/lib.linux-x86_64-cpython-310/executorch/data/bin
2025-03-21T20:25:15.5174771Z   creating /pytorch/executorch/pip-out/lib.linux-x86_64-cpython-310/executorch/data/bin
2025-03-21T20:25:15.5176212Z   copying /pytorch/executorch/pip-out/temp.linux-x86_64-cpython-310/cmake-out/third-party/flatbuffers/flatc -> /pytorch/executorch/pip-out/lib.linux-x86_64-cpython-310/executorch/data/bin
2025-03-21T20:25:15.5177792Z   copying tools/wheel/pip_data_bin_init.py.in -> /pytorch/executorch/pip-out/lib.linux-x86_64-cpython-310/executorch/data/bin/__init__.py
2025-03-21T20:25:15.5179500Z   copying /pytorch/executorch/pip-out/temp.linux-x86_64-cpython-310/cmake-out/extension/llm/custom_ops/libcustom_ops_aot_lib.so -> /pytorch/executorch/pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/custom_ops
2025-03-21T20:25:15.5181596Z   copying /pytorch/executorch/pip-out/temp.linux-x86_64-cpython-310/cmake-out/kernels/quantized/libquantized_ops_aot_lib.so -> /pytorch/executorch/pip-out/lib.linux-x86_64-cpython-310/executorch/kernels/quantized
2025-03-21T20:25:15.5183516Z   copying /pytorch/executorch/pip-out/temp.linux-x86_64-cpython-310/cmake-out/_portable_lib.cpython-310-x86_64-linux-gnu.so -> pip-out/lib.linux-x86_64-cpython-310/executorch/extension/pybindings
2025-03-21T20:25:15.5184723Z   installing to pip-out/bdist.linux-x86_64/wheel
2025-03-21T20:25:15.5185149Z   running install
2025-03-21T20:25:15.5185396Z   running install_lib
2025-03-21T20:25:15.5185887Z   creating pip-out/bdist.linux-x86_64/wheel
2025-03-21T20:25:15.5186322Z   creating pip-out/bdist.linux-x86_64/wheel/executorch
2025-03-21T20:25:15.5186850Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends
2025-03-21T20:25:15.5187631Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/arm
2025-03-21T20:25:15.5188556Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/arm_backend.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm
2025-03-21T20:25:15.5189987Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/arm_vela.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm
2025-03-21T20:25:15.5191368Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/ethosu_backend.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm
2025-03-21T20:25:15.5192868Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/ethosu_partitioner.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm
2025-03-21T20:25:15.5194363Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/process_node.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm
2025-03-21T20:25:15.5195811Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/tosa_backend.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm
2025-03-21T20:25:15.5197187Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/tosa_mapping.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm
2025-03-21T20:25:15.5198665Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/tosa_partitioner.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm
2025-03-21T20:25:15.5200280Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/tosa_quant_utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm
2025-03-21T20:25:15.5202113Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/tosa_specification.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm
2025-03-21T20:25:15.5203383Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/tosa_utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm
2025-03-21T20:25:15.5204388Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/arm/_passes
2025-03-21T20:25:15.5205504Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/_debug_passes.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5207109Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/annotate_channels_last_dim_order_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5208864Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/annotate_decomposed_matmul.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5210551Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/arm_pass_manager.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5212054Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/arm_pass_utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5213807Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/cast_int64_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5215355Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/conv1d_unsqueeze_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5217057Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/convert_any_default_dim_dims_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5218681Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/convert_expand_copy_to_repeat.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5220304Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/convert_full_like_to_full_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5221950Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/convert_minmax_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5223586Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/convert_split_to_slice.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5225286Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/convert_squeezes_to_view.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5226945Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/convert_to_clamp.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5228858Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/decompose_batchnorm_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5230589Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/decompose_div_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5232437Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/decompose_layernorm_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5234290Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/decompose_linear_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5235883Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/decompose_meandim_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5237491Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/decompose_select.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5239084Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/decompose_softmax_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5240611Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/decompose_softmax_unstable_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5242171Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/decompose_var_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5243730Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/fold_qdq_with_annotated_qparams_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5245302Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/fuse_batchnorm2d_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5246822Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/fuse_constant_ops_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5248601Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/fuse_quantized_activation_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5250804Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/insert_rescales_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5252169Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/insert_table_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5253640Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/keep_dims_false_to_squeeze_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5255131Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/match_arg_ranks_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5256669Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/meandim_to_averagepool_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5258134Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/mm_to_bmm_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5259721Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/remove_clone_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5261244Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/scalars_to_attribute_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5262780Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/size_adjust_conv2d_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5264341Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/unsqueeze_before_repeat_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5266203Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/_passes/unsqueeze_scalar_placeholders_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/_passes
2025-03-21T20:25:15.5267577Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/arm/operator_support
2025-03-21T20:25:15.5268836Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operator_support/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operator_support
2025-03-21T20:25:15.5270584Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operator_support/convolution_support.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operator_support
2025-03-21T20:25:15.5272263Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operator_support/minmax_support.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operator_support
2025-03-21T20:25:15.5273990Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operator_support/pool_2d_support.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operator_support
2025-03-21T20:25:15.5275644Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operator_support/reduce_sum_support.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operator_support
2025-03-21T20:25:15.5277303Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operator_support/right_shift_support.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operator_support
2025-03-21T20:25:15.5278969Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operator_support/slice_copy_support.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operator_support
2025-03-21T20:25:15.5280606Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operator_support/to_copy_support.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operator_support
2025-03-21T20:25:15.5282307Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operator_support/tosa_supported_operators.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operator_support
2025-03-21T20:25:15.5283525Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/arm/operators
2025-03-21T20:25:15.5284652Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5286099Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/node_visitor.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5287587Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_abs.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5289149Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_add.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5290779Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_amax.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5292327Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_amin.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5293831Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_any.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5295387Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_avg_pool2d.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5296918Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_bmm.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5298836Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_cat.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5300447Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_clamp.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5302218Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_constant_pad_nd.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5303902Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_conv2d.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5305441Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_eq.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5307254Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_exp.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5309027Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_full.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5310680Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_ge.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5312412Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_get_item.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5314044Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_gt.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5315732Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_le.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5317385Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_log.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5318886Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_lt.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5320425Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_max_pool2d.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5321982Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_maximum.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5323663Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_minimum.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5325334Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_mul.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5329982Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_permute.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5332396Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_reciprocal.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5333944Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_repeat.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5335537Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_rescale.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5337541Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_rshift.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5339302Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_rsqrt.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5340967Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_sigmoid.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5342582Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_slice.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5344157Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_sub.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5345737Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_sum.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5347318Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_table.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5348974Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_tanh.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5350631Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_to_copy.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5352330Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_to_dim_order_copy.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5354059Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_transpose.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5355784Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_upsample_nearest2d.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5357426Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/op_view.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5359079Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/ops_binary.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5360702Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/operators/ops_unary.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/operators
2025-03-21T20:25:15.5361906Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/arm/quantizer
2025-03-21T20:25:15.5363124Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/quantizer/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/quantizer
2025-03-21T20:25:15.5364834Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/quantizer/arm_quantizer.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/quantizer
2025-03-21T20:25:15.5366564Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/quantizer/arm_quantizer_utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/quantizer
2025-03-21T20:25:15.5368396Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/quantizer/quantization_annotator.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/quantizer
2025-03-21T20:25:15.5370251Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/quantizer/quantization_config.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/quantizer
2025-03-21T20:25:15.5371740Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/arm/test
2025-03-21T20:25:15.5372901Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/common.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test
2025-03-21T20:25:15.5374477Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/conftest.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test
2025-03-21T20:25:15.5376026Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/runner_utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test
2025-03-21T20:25:15.5377555Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/test_model.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test
2025-03-21T20:25:15.5378743Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/arm/test/misc
2025-03-21T20:25:15.5379950Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/misc/test_custom_partition.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/misc
2025-03-21T20:25:15.5381734Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/misc/test_debug_feats.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/misc
2025-03-21T20:25:15.5383410Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/misc/test_dim_order_guards.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/misc
2025-03-21T20:25:15.5385097Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/misc/test_lifted_tensor.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/misc
2025-03-21T20:25:15.5386852Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/misc/test_model_evaluator.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/misc
2025-03-21T20:25:15.5388703Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/misc/test_multiple_delegates.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/misc
2025-03-21T20:25:15.5390452Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/misc/test_multiple_outputs.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/misc
2025-03-21T20:25:15.5392258Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/misc/test_partition_decomposed_quantized_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/misc
2025-03-21T20:25:15.5394005Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/misc/test_tosa_spec.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/misc
2025-03-21T20:25:15.5395222Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/arm/test/models
2025-03-21T20:25:15.5396440Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/models/test_conformer.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/models
2025-03-21T20:25:15.5398159Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/models/test_dl3_arm.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/models
2025-03-21T20:25:15.5399863Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/models/test_llama.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/models
2025-03-21T20:25:15.5401991Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/models/test_lstm_arm.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/models
2025-03-21T20:25:15.5403923Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/models/test_mobilenet_v2_arm.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/models
2025-03-21T20:25:15.5405675Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/models/test_nn_functional.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/models
2025-03-21T20:25:15.5407507Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/models/test_nn_modules.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/models
2025-03-21T20:25:15.5409160Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/models/test_torch_functions.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/models
2025-03-21T20:25:15.5411050Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/models/test_w2l_arm.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/models
2025-03-21T20:25:15.5412171Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/arm/test/ops
2025-03-21T20:25:15.5413330Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_abs.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5414845Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_add.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5416358Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_amax.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5417834Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_amin.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5419258Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_any.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5420750Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_avg_pool2d.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5422234Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_batch_norm.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5423754Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_bitwise.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5425191Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_bmm.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5426506Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_cat.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5427954Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_clamp.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5429584Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_clone.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5431323Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_constant_pad_nd.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5433209Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_conv1d.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5434855Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_conv2d.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5436439Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_conv_combos.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5438041Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_depthwise_conv.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5439841Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_div.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5441358Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_eq.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5442852Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_exp.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5444363Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_expand.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5445984Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_floor.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5447560Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_full.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5449153Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_ge.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5450787Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_gt.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5452408Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_hardsigmoid.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5453985Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_hardswish.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5455599Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_hardtanh.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5457171Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_layer_norm.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5458701Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_le.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5460227Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_linear.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5461708Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_log.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5463293Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_logical.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5464911Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_logsoftmax.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5466409Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_lt.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5467960Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_max_pool.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5469580Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_maximum.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5471222Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_mean_dim.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5472989Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_minimum.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5474576Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_mm.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5476123Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_mul.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5477821Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_permute.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5480257Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_reciprocal.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5481882Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_relu.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5483360Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_repeat.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5484825Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_rshift.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5486323Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_rsqrt.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5487771Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_scalars.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5489370Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_select.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5490838Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_sigmoid.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5492330Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_sigmoid_16bit.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5493845Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_sigmoid_32bit.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5495330Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_slice.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5496726Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_softmax.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5498176Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_split.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5499678Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_squeeze.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5501123Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_sub.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5502550Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_sum.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5503954Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_tanh.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5505666Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_to_copy.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5507383Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_unsqueeze.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5509046Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_upsample_nearest2d.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5510615Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_var.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5512069Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/ops/test_view.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/ops
2025-03-21T20:25:15.5513118Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/arm/test/passes
2025-03-21T20:25:15.5514348Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/passes/test_cast_int64_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/passes
2025-03-21T20:25:15.5516054Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/passes/test_convert_to_clamp.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/passes
2025-03-21T20:25:15.5517754Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/passes/test_fold_qdq_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/passes
2025-03-21T20:25:15.5519345Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/passes/test_fuse_batchnorm_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/passes
2025-03-21T20:25:15.5521082Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/passes/test_fuse_constant_ops_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/passes
2025-03-21T20:25:15.5522891Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/passes/test_insert_table_ops_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/passes
2025-03-21T20:25:15.5524568Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/passes/test_ioquantization_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/passes
2025-03-21T20:25:15.5526271Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/passes/test_meandim_to_averagepool2d.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/passes
2025-03-21T20:25:15.5527997Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/passes/test_rescale_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/passes
2025-03-21T20:25:15.5529900Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/passes/test_unsqueeze_before_repeat_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/passes
2025-03-21T20:25:15.5531244Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/arm/test/quantizer
2025-03-21T20:25:15.5532790Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/quantizer/test_generic_annotater.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/quantizer
2025-03-21T20:25:15.5534194Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/arm/test/tester
2025-03-21T20:25:15.5535199Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/tester/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/tester
2025-03-21T20:25:15.5536805Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/tester/analyze_output_utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/tester
2025-03-21T20:25:15.5538840Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/tester/arm_tester.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/tester
2025-03-21T20:25:15.5541135Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/tester/test_pipeline.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/tester
2025-03-21T20:25:15.5542425Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/arm/test/tosautil
2025-03-21T20:25:15.5543645Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/test/tosautil/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/test/tosautil
2025-03-21T20:25:15.5544812Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/arm/util
2025-03-21T20:25:15.5546007Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/util/arm_model_evaluator.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/util
2025-03-21T20:25:15.5547174Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/arm/third-party
2025-03-21T20:25:15.5547952Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/arm/third-party/serialization_lib
2025-03-21T20:25:15.5549335Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/setup.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib
2025-03-21T20:25:15.5550743Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/arm/third-party/serialization_lib/python
2025-03-21T20:25:15.5551869Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/arm/third-party/serialization_lib/python/serializer
2025-03-21T20:25:15.5553540Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/serializer/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/python/serializer
2025-03-21T20:25:15.5555914Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/serializer/tosa_serializer.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/python/serializer
2025-03-21T20:25:15.5557707Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:15.5559480Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa/ArithmeticRightShiftAttribute.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:15.5561842Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa/Attribute.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:15.5564065Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa/AxisAttribute.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:15.5566469Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa/ClampAttribute.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:15.5568817Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa/CondIfAttribute.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:15.5571180Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa/ConvAttribute.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:15.5573624Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa/CustomAttribute.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:15.5575931Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa/DType.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:15.5578241Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa/FFTAttribute.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:15.5580515Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa/FullyConnectedAttribute.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:15.5582909Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa/MatMulAttribute.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:15.5585129Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa/MulAttribute.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:15.5587452Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa/NegateAttribute.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:15.5589587Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa/Op.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:15.5591824Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa/PadAttribute.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:15.5594057Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa/PoolAttribute.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:15.5596410Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa/RFFTAttribute.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:15.5598919Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa/RescaleAttribute.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:15.5601232Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa/ReshapeAttribute.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:15.5603532Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa/ResizeAttribute.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:15.5605871Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa/ResizeMode.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:15.5608070Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa/SliceAttribute.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:15.5610599Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa/TableAttribute.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:15.5612895Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa/TileAttribute.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:15.5615591Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa/TosaBasicBlock.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:15.5617981Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa/TosaGraph.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:15.5620160Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa/TosaOperator.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:15.5622313Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa/TosaRegion.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:15.5624460Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa/TosaTensor.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:15.5626546Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa/TransposeAttribute.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:15.5628678Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa/TransposeConvAttribute.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:15.5630791Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa/Version.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:15.5632947Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa/WhileLoopAttribute.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:15.5635359Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/python/tosa/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/python/tosa
2025-03-21T20:25:15.5637151Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/arm/third-party/serialization_lib/test
2025-03-21T20:25:15.5638195Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/arm/third-party/serialization_lib/test/scripts
2025-03-21T20:25:15.5640019Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/test/scripts/test_npy_fileio.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/test/scripts
2025-03-21T20:25:15.5641899Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/arm/third-party/serialization_lib/test/scripts/xunit
2025-03-21T20:25:15.5643716Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/test/scripts/xunit/xunit.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/test/scripts/xunit
2025-03-21T20:25:15.5645702Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/arm/third-party/serialization_lib/schema
2025-03-21T20:25:15.5647601Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/arm/third-party/serialization_lib/schema/tosa.fbs -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/arm/third-party/serialization_lib/schema
2025-03-21T20:25:15.5649048Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/example
2025-03-21T20:25:15.5650456Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/example/example_backend.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/example
2025-03-21T20:25:15.5652240Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/example/example_partitioner.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/example
2025-03-21T20:25:15.5666442Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/example/example_quantizer.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/example
2025-03-21T20:25:15.5668134Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/example/test_example_delegate.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/example
2025-03-21T20:25:15.5669540Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/example/example_backend_delegate_passes
2025-03-21T20:25:15.5671083Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/example/example_backend_delegate_passes/merge_to_dim_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/example/example_backend_delegate_passes
2025-03-21T20:25:15.5673327Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/example/example_backend_delegate_passes/permute_memory_formats_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/example/example_backend_delegate_passes
2025-03-21T20:25:15.5675021Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/example/example_operators
2025-03-21T20:25:15.5676480Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/example/example_operators/adaptive_avg_pool2d.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/example/example_operators
2025-03-21T20:25:15.5678509Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/example/example_operators/add.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/example/example_operators
2025-03-21T20:25:15.5680470Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/example/example_operators/conv2d.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/example/example_operators
2025-03-21T20:25:15.5682364Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/example/example_operators/conv_relu.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/example/example_operators
2025-03-21T20:25:15.5684229Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/example/example_operators/dropout.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/example/example_operators
2025-03-21T20:25:15.5686501Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/example/example_operators/flatten.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/example/example_operators
2025-03-21T20:25:15.5688497Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/example/example_operators/linear.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/example/example_operators
2025-03-21T20:25:15.5690469Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/example/example_operators/op_base.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/example/example_operators
2025-03-21T20:25:15.5692386Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/example/example_operators/ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/example/example_operators
2025-03-21T20:25:15.5694453Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/example/example_operators/utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/example/example_operators
2025-03-21T20:25:15.5695916Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/mediatek
2025-03-21T20:25:15.5697124Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/mediatek/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/mediatek
2025-03-21T20:25:15.5698675Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/mediatek/partitioner.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/mediatek
2025-03-21T20:25:15.5700182Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/mediatek/preprocess.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/mediatek
2025-03-21T20:25:15.5701350Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/mediatek/_passes
2025-03-21T20:25:15.5702531Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/mediatek/_passes/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/mediatek/_passes
2025-03-21T20:25:15.5704211Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/mediatek/_passes/decompose_scaled_dot_product_attention.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/mediatek/_passes
2025-03-21T20:25:15.5705492Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/mediatek/quantizer
2025-03-21T20:25:15.5706785Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/mediatek/quantizer/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/mediatek/quantizer
2025-03-21T20:25:15.5708600Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/mediatek/quantizer/annotator.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/mediatek/quantizer
2025-03-21T20:25:15.5710412Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/mediatek/quantizer/qconfig.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/mediatek/quantizer
2025-03-21T20:25:15.5712228Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/mediatek/quantizer/quantizer.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/mediatek/quantizer
2025-03-21T20:25:15.5713549Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/qualcomm
2025-03-21T20:25:15.5714659Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/qnn_preprocess.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm
2025-03-21T20:25:15.5715826Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/qualcomm/_passes
2025-03-21T20:25:15.5717068Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/_passes
2025-03-21T20:25:15.5718806Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes/annotate_decomposed.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/_passes
2025-03-21T20:25:15.5720630Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes/annotate_quant_attrs.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/_passes
2025-03-21T20:25:15.5722421Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes/build_quant_io.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/_passes
2025-03-21T20:25:15.5724209Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes/constant_i64_to_i32.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/_passes
2025-03-21T20:25:15.5726044Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes/convert_bmm_to_matmul.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/_passes
2025-03-21T20:25:15.5727879Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes/convert_interpolate_with_upsample2d.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/_passes
2025-03-21T20:25:15.5729999Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes/convert_to_linear.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/_passes
2025-03-21T20:25:15.5731817Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes/decompose_any.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/_passes
2025-03-21T20:25:15.5733661Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes/decompose_einsum.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/_passes
2025-03-21T20:25:15.5735490Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes/decompose_linalg_vector_norm.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/_passes
2025-03-21T20:25:15.5737365Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes/decompose_silu.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/_passes
2025-03-21T20:25:15.5739193Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes/expand_broadcast_tensor_shape.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/_passes
2025-03-21T20:25:15.5740968Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes/fold_qdq.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/_passes
2025-03-21T20:25:15.5742856Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes/fuse_consecutive_transpose.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/_passes
2025-03-21T20:25:15.5744747Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes/insert_io_qdq.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/_passes
2025-03-21T20:25:15.5746513Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes/insert_requantize.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/_passes
2025-03-21T20:25:15.5748289Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes/layout_transform.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/_passes
2025-03-21T20:25:15.5750196Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes/lift_constant_scalar_operands.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/_passes
2025-03-21T20:25:15.5752135Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes/recompose_pixel_unshuffle.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/_passes
2025-03-21T20:25:15.5753952Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes/recompose_prelu.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/_passes
2025-03-21T20:25:15.5755746Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes/recompose_rms_norm.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/_passes
2025-03-21T20:25:15.5757619Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes/reduce_dynamic_range.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/_passes
2025-03-21T20:25:15.5759428Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes/remove_redundancy.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/_passes
2025-03-21T20:25:15.5761193Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes/replace_index_put_input.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/_passes
2025-03-21T20:25:15.5762935Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes/replace_inf_buffer.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/_passes
2025-03-21T20:25:15.5764714Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes/tensor_i64_to_i32.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/_passes
2025-03-21T20:25:15.5766562Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/_passes/utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/_passes
2025-03-21T20:25:15.5767867Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5769164Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5771011Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/node_visitor.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5772936Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_abs.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5774843Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_adaptive_avg_pool2d.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5776724Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_add.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5778495Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_arange.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5780268Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_argmin.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5781954Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_avg_pool2d.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5783822Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_batch_norm.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5785421Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_bmm.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5786987Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_cat.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5788577Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_ceil.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5790157Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_clamp.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5791759Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_conv2d.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5793352Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_cos.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5795010Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_depth_to_space.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5796676Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_dequantize.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5798419Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_div.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5800071Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_embedding.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5801726Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_eq.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5803452Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_expand.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5805151Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_full.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5806739Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_full_like.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5808248Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_ge.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5809896Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_gelu.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5811844Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_group_norm.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5813768Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_gt.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5815463Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_hardsigmoid.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5817262Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_hardswish.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5819006Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_hardtanh.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5820648Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_index.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5822353Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_index_put.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5824051Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_instance_norm.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5825770Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_layer_norm.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5827412Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_le.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5829005Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_linear.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5830637Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_log.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5832430Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_log_softmax.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5834348Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_logical_not.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5836080Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_lt.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5838076Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_matmul.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5839800Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_max.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5841440Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_max_pool2d.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5843156Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_mean_dim.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5844762Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_min.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5846334Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_mul.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5848066Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_ne.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5849877Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_neg.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5851576Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_or.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5853310Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_pad.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5855045Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_pow.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5856827Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_prelu.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5858599Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_quantize.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5860433Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_relu.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5862233Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_repeat.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5864155Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_reshape.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5865941Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_rms_norm.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5867705Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_rsqrt.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5869741Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_select_copy.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5871600Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_sigmoid.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5873331Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_sin.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5874982Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_skip_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5876862Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_slice_copy.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5878677Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_softmax.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5880404Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_space_to_depth.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5882353Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_split_with_sizes.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5884209Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_sqrt.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5886069Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_squeeze.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5887776Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_sub.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5889683Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_sum_int_list.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5891499Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_tanh.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5893134Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_to.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5894775Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_topk.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5896386Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_transpose.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5898010Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_unsqueeze.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5899804Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_upsample_bilinear2d.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5901770Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_upsample_nearest2d.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5903715Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/op_where.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5905868Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/qnn_constants.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5907516Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/builders/utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/builders
2025-03-21T20:25:15.5908652Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/qualcomm/debugger
2025-03-21T20:25:15.5909832Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/debugger/utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/debugger
2025-03-21T20:25:15.5910987Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/qualcomm/partition
2025-03-21T20:25:15.5912190Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/partition/common_defs.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/partition
2025-03-21T20:25:15.5913801Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/partition/qnn_partitioner.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/partition
2025-03-21T20:25:15.5915424Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/partition/utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/partition
2025-03-21T20:25:15.5916560Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/qualcomm/quantizer
2025-03-21T20:25:15.5917726Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/quantizer/annotators.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/quantizer
2025-03-21T20:25:15.5919433Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/quantizer/custom_annotation.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/quantizer
2025-03-21T20:25:15.5921091Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/quantizer/qconfig.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/quantizer
2025-03-21T20:25:15.5922702Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/quantizer/quantizer.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/quantizer
2025-03-21T20:25:15.5924163Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/qualcomm/quantizer/observers
2025-03-21T20:25:15.5925802Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/quantizer/observers/per_channel_param_observer.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/quantizer/observers
2025-03-21T20:25:15.5927446Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/qualcomm/serialization
2025-03-21T20:25:15.5928828Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/serialization/qc_schema.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/serialization
2025-03-21T20:25:15.5930852Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/serialization/qc_schema_serialize.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/serialization
2025-03-21T20:25:15.5932767Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/serialization/qc_compiler_spec.fbs -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/serialization
2025-03-21T20:25:15.5934093Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/qualcomm/tests
2025-03-21T20:25:15.5935252Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/tests/models.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/tests
2025-03-21T20:25:15.5936904Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/tests/test_qnn_delegate.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/tests
2025-03-21T20:25:15.5938644Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/tests/utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/tests
2025-03-21T20:25:15.5939840Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/qualcomm/utils
2025-03-21T20:25:15.5940946Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/utils/constants.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/utils
2025-03-21T20:25:15.5942774Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/utils/utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/utils
2025-03-21T20:25:15.5943905Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/qualcomm/aot
2025-03-21T20:25:15.5944580Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/qualcomm/aot/ir
2025-03-21T20:25:15.5945754Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/qualcomm/aot/ir/qcir.fbs -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/qualcomm/aot/ir
2025-03-21T20:25:15.5946905Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/transforms
2025-03-21T20:25:15.5947908Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/transforms
2025-03-21T20:25:15.5949591Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms/addmm_mm_to_linear.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/transforms
2025-03-21T20:25:15.5951082Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms/convert_dtype_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/transforms
2025-03-21T20:25:15.5952791Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms/decompose_sdpa.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/transforms
2025-03-21T20:25:15.5954313Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms/duplicate_dynamic_quant_chain.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/transforms
2025-03-21T20:25:15.5955856Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms/fuse_batch_norm_with_conv.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/transforms
2025-03-21T20:25:15.5957592Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms/fuse_conv_with_clamp.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/transforms
2025-03-21T20:25:15.5959349Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms/fuse_dequant_linear.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/transforms
2025-03-21T20:25:15.5961015Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms/fuse_view_copy.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/transforms
2025-03-21T20:25:15.5962716Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms/mean_to_sum_div.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/transforms
2025-03-21T20:25:15.5964541Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms/rank_0_to_rank_1.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/transforms
2025-03-21T20:25:15.5966276Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms/remove_clone_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/transforms
2025-03-21T20:25:15.5968130Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms/replace_scalar_with_tensor.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/transforms
2025-03-21T20:25:15.5969822Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms/utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/transforms
2025-03-21T20:25:15.5971377Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms/view_copy_to_squeeze_unsqueeze.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/transforms
2025-03-21T20:25:15.5972728Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/transforms/test
2025-03-21T20:25:15.5973980Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms/test/test_create_delete_constant_placeholder.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/transforms/test
2025-03-21T20:25:15.5975826Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms/test/test_duplicate_dynamic_quant_chain.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/transforms/test
2025-03-21T20:25:15.5977744Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/transforms/test/test_rank_0_to_rank_1.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/transforms/test
2025-03-21T20:25:15.5978882Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/vulkan
2025-03-21T20:25:15.5979956Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan
2025-03-21T20:25:15.5981555Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/custom_ops_lib.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan
2025-03-21T20:25:15.5983226Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/op_registry.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan
2025-03-21T20:25:15.5984811Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan
2025-03-21T20:25:15.5986518Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/vulkan_preprocess.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan
2025-03-21T20:25:15.5987871Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/vulkan/_passes
2025-03-21T20:25:15.5989206Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/_passes/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/_passes
2025-03-21T20:25:15.5990874Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/_passes/insert_prepack_nodes.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/_passes
2025-03-21T20:25:15.5992587Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/_passes/int4_weight_only_quantizer.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/_passes
2025-03-21T20:25:15.5994217Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/_passes/remove_asserts.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/_passes
2025-03-21T20:25:15.5995922Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/_passes/remove_local_scalar_dense_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/_passes
2025-03-21T20:25:15.5997663Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/_passes/remove_redundant_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/_passes
2025-03-21T20:25:15.5999419Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/_passes/squeeze_unsqueeze_inputs.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/_passes
2025-03-21T20:25:15.6001228Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/_passes/tag_memory_meta_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/_passes
2025-03-21T20:25:15.6002412Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/vulkan/partitioner
2025-03-21T20:25:15.6003899Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/partitioner/vulkan_partitioner.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/partitioner
2025-03-21T20:25:15.6005259Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/vulkan/quantizer
2025-03-21T20:25:15.6006664Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/quantizer/vulkan_quantizer.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/quantizer
2025-03-21T20:25:15.6007991Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/vulkan/runtime
2025-03-21T20:25:15.6009289Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/gen_vulkan_spv.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime
2025-03-21T20:25:15.6010509Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/vulkan/runtime/graph
2025-03-21T20:25:15.6011216Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/vulkan/runtime/graph/ops
2025-03-21T20:25:15.6012037Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6013440Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/addmm_naive_buffer.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6015345Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/addmm_naive_texture3d.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6017287Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/addmm_optimized.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6019120Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/arange.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6021165Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/avg_pool2d.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6023130Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/batchnorm.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6025069Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/binary_op.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6027270Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/bitw8_image_to_nchw_nobitw8buffer.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6029436Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/buffer_to_buffer.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6031355Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/buffer_to_nchw.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6033561Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/clone.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6035548Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/conv1d.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6037680Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/conv2d.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6039630Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/conv2d_dw.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6041755Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/conv2d_dw_output_tile.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6044245Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/conv2d_dw_prepack_weights.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6046607Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/conv2d_dw_sned_output_tile.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6048902Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/conv2d_prepack_weights.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6051040Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/conv2d_pw.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6052902Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/conv_transpose2d.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6055227Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/conv_transpose2d_prepack_weights.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6057200Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/copy_channel_offset.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6059347Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/copy_offset.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6061254Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/copy_packed_dim_offset.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6063431Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/embedding.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6065388Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/flip.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6067543Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/full.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6069702Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/grid_priors.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6071988Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/image_to_nchw.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6074201Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/index_select.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6076293Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/index_select_channel.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6078388Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/kv_cache_update.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6080469Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/max_pool2d.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6082821Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/native_layer_norm.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6085098Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/nchw_to_bitw8_image_nobitw8buffer.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6087390Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/nchw_to_buffer.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6089576Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/nchw_to_image.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6091485Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/no_op.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6093498Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/pad_channel.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6095590Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/pad_height_width.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6097583Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/permute.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6099740Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/q_4w_linear.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6101931Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/q_8w_linear.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6103982Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/q_8w_linear_optimized.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6106313Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/reduce.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6108203Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/repeat_channel.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6110316Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/repeat_interleave.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6112380Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/rotary_embedding.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6114529Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/sdpa_attn_weight_scale_and_mask.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6117075Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/select_batch_4d.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6119353Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/select_channel_3d.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6121448Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/select_channel_4d.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6123719Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/select_height_3d.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6125805Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/select_height_4d.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6128077Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/select_width_3d.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6130213Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/select_width_4d.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6132448Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/slice_packed_dim.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6134408Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/slice_unpacked_dim.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6136356Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/softmax.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6138318Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/unary_op.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6140176Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/upsample_nearest2d.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6142035Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/runtime/graph/ops/glsl/view.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/runtime/graph/ops/glsl
2025-03-21T20:25:15.6143431Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/vulkan/serialization
2025-03-21T20:25:15.6144738Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/serialization/vulkan_graph_builder.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/serialization
2025-03-21T20:25:15.6146555Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/serialization/vulkan_graph_schema.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/serialization
2025-03-21T20:25:15.6148401Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/serialization/vulkan_graph_serialize.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/serialization
2025-03-21T20:25:15.6150132Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/serialization/schema.fbs -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/serialization
2025-03-21T20:25:15.6151355Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/vulkan/test
2025-03-21T20:25:15.6152737Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/test/test_serialization.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/test
2025-03-21T20:25:15.6154307Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/test/test_vulkan_delegate.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/test
2025-03-21T20:25:15.6155875Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/test/test_vulkan_delegate_header.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/test
2025-03-21T20:25:15.6157015Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/vulkan/test/op_tests
2025-03-21T20:25:15.6158192Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/test/op_tests/cases.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/test/op_tests
2025-03-21T20:25:15.6159939Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/test/op_tests/generate_op_benchmarks.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/test/op_tests
2025-03-21T20:25:15.6161687Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/test/op_tests/generate_op_correctness_tests.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/test/op_tests
2025-03-21T20:25:15.6162839Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/vulkan/test/op_tests/utils
2025-03-21T20:25:15.6164116Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/test/op_tests/utils/aten_types.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/test/op_tests/utils
2025-03-21T20:25:15.6165881Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/test/op_tests/utils/gen_benchmark_vk.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/test/op_tests/utils
2025-03-21T20:25:15.6167771Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/test/op_tests/utils/gen_computegraph.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/test/op_tests/utils
2025-03-21T20:25:15.6169717Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/test/op_tests/utils/gen_correctness_base.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/test/op_tests/utils
2025-03-21T20:25:15.6171615Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/test/op_tests/utils/gen_correctness_vk.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/test/op_tests/utils
2025-03-21T20:25:15.6173611Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/test/op_tests/utils/test_suite.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/test/op_tests/utils
2025-03-21T20:25:15.6174729Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/vulkan/test/glsl
2025-03-21T20:25:15.6175916Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/test/glsl/all_shaders.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/test/glsl
2025-03-21T20:25:15.6177121Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/vulkan/third-party
2025-03-21T20:25:15.6177868Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/vulkan/third-party/volk
2025-03-21T20:25:15.6179184Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/third-party/volk/generate.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/third-party/volk
2025-03-21T20:25:15.6180597Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/vulkan/third-party/Vulkan-Headers
2025-03-21T20:25:15.6181577Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/vulkan/third-party/Vulkan-Headers/registry
2025-03-21T20:25:15.6183380Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/third-party/Vulkan-Headers/registry/apiconventions.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/third-party/Vulkan-Headers/registry
2025-03-21T20:25:15.6185585Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/third-party/Vulkan-Headers/registry/cgenerator.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/third-party/Vulkan-Headers/registry
2025-03-21T20:25:15.6187725Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/third-party/Vulkan-Headers/registry/conventions.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/third-party/Vulkan-Headers/registry
2025-03-21T20:25:15.6189881Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/third-party/Vulkan-Headers/registry/generator.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/third-party/Vulkan-Headers/registry
2025-03-21T20:25:15.6191970Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/third-party/Vulkan-Headers/registry/genvk.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/third-party/Vulkan-Headers/registry
2025-03-21T20:25:15.6194640Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/third-party/Vulkan-Headers/registry/reg.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/third-party/Vulkan-Headers/registry
2025-03-21T20:25:15.6197085Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/third-party/Vulkan-Headers/registry/vkconventions.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/third-party/Vulkan-Headers/registry
2025-03-21T20:25:15.6198652Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/vulkan/third-party/Vulkan-Headers/registry/spec_tools
2025-03-21T20:25:15.6200301Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/third-party/Vulkan-Headers/registry/spec_tools/util.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/third-party/Vulkan-Headers/registry/spec_tools
2025-03-21T20:25:15.6201847Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/vulkan/third-party/VulkanMemoryAllocator
2025-03-21T20:25:15.6202953Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/vulkan/third-party/VulkanMemoryAllocator/tools
2025-03-21T20:25:15.6204048Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/vulkan/third-party/VulkanMemoryAllocator/tools/GpuMemDumpVis
2025-03-21T20:25:15.6205869Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/third-party/VulkanMemoryAllocator/tools/GpuMemDumpVis/GpuMemDumpVis.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/third-party/VulkanMemoryAllocator/tools/GpuMemDumpVis
2025-03-21T20:25:15.6207444Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/vulkan/tools
2025-03-21T20:25:15.6208191Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/vulkan/tools/gpuinfo
2025-03-21T20:25:15.6208941Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/vulkan/tools/gpuinfo/glsl
2025-03-21T20:25:15.6210267Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/tools/gpuinfo/glsl/buf_bandwidth.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/tools/gpuinfo/glsl
2025-03-21T20:25:15.6212129Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/tools/gpuinfo/glsl/buf_cacheline_size.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/tools/gpuinfo/glsl
2025-03-21T20:25:15.6214031Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/tools/gpuinfo/glsl/reg_count.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/tools/gpuinfo/glsl
2025-03-21T20:25:15.6215900Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/tools/gpuinfo/glsl/tex_bandwidth.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/tools/gpuinfo/glsl
2025-03-21T20:25:15.6217811Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/tools/gpuinfo/glsl/tex_cacheline_concurr.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/tools/gpuinfo/glsl
2025-03-21T20:25:15.6219831Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/vulkan/tools/gpuinfo/glsl/warp_size.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/vulkan/tools/gpuinfo/glsl
2025-03-21T20:25:15.6221064Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/xnnpack
2025-03-21T20:25:15.6222081Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack
2025-03-21T20:25:15.6223549Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/xnnpack_preprocess.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack
2025-03-21T20:25:15.6224659Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/xnnpack/_passes
2025-03-21T20:25:15.6225684Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/_passes/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/_passes
2025-03-21T20:25:15.6227432Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/_passes/channels_last_tagged_reshape_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/_passes
2025-03-21T20:25:15.6229051Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/_passes/conv1d_unsqueeze_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/_passes
2025-03-21T20:25:15.6230752Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/_passes/convert_to_linear.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/_passes
2025-03-21T20:25:15.6232552Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/_passes/convert_to_sdpa.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/_passes
2025-03-21T20:25:15.6234322Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/_passes/convert_to_upsample_bilinear2d.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/_passes
2025-03-21T20:25:15.6236056Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/_passes/decompose_cat.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/_passes
2025-03-21T20:25:15.6237762Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/_passes/fuse_activation_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/_passes
2025-03-21T20:25:15.6239409Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/_passes/fuse_batch_norm_with_conv.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/_passes
2025-03-21T20:25:15.6241101Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/_passes/prelu_reshape_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/_passes
2025-03-21T20:25:15.6242665Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/_passes/remove_getitem_op.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/_passes
2025-03-21T20:25:15.6244416Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/_passes/tag_implicit_q_dq_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/_passes
2025-03-21T20:25:15.6246196Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/_passes/xnnpack_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/_passes
2025-03-21T20:25:15.6247643Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6248790Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6250721Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/node_visitor.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6252588Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_abs.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6254379Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_add.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6255980Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_addmm.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6257704Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_avg_pooling2d.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6259250Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_bmm.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6260869Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_cat.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6262490Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_ceiling.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6264348Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_clamp.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6266372Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_conv2d.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6267900Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_div.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6269492Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_dynamic_dequantize_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6271187Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_dynamic_quantize_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6272865Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_elu.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6274512Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_floor.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6276065Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_hardswish.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6277846Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_hardtanh.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6279542Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_leaky_relu.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6281363Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_linear.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6283048Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_matrix_multiplication.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6285007Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_max_dim.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6286643Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_max_pool2d.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6288210Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_maximum.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6289826Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_mean_dim.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6291380Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_minimum.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6292945Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_multiply.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6294472Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_negate.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6296123Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_permute.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6297627Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_prelu.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6299283Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_quant_dequant.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6301012Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_relu.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6302807Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_rsqrt.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6304396Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_sdpa.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6306149Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_sigmoid.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6307725Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_skip_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6309389Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_slice_copy.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6311022Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_softmax.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6312625Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_square.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6314229Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_square_root.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6315964Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_squeeze.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6317685Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_static_constant_pad.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6319501Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_static_resize_bilinear_2d.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6321181Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_sub.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6322788Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/op_to_copy.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6324366Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/operators/quant_params.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/operators
2025-03-21T20:25:15.6325665Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/xnnpack/partition
2025-03-21T20:25:15.6326865Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/partition/configs.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/partition
2025-03-21T20:25:15.6328498Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/partition/xnnpack_partitioner.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/partition
2025-03-21T20:25:15.6329901Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/xnnpack/partition/config
2025-03-21T20:25:15.6331175Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/partition/config/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/partition/config
2025-03-21T20:25:15.6333143Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/partition/config/gemm_configs.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/partition/config
2025-03-21T20:25:15.6334933Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/partition/config/generic_node_configs.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/partition/config
2025-03-21T20:25:15.6337012Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/partition/config/node_configs.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/partition/config
2025-03-21T20:25:15.6338895Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/partition/config/quant_affine_configs.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/partition/config
2025-03-21T20:25:15.6340696Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/partition/config/xnnpack_config.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/partition/config
2025-03-21T20:25:15.6342640Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/xnnpack/partition/graphs
2025-03-21T20:25:15.6343652Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/partition/graphs/bilinear_2d.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/partition/graphs
2025-03-21T20:25:15.6344443Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/partition/graphs/sdpa.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/partition/graphs
2025-03-21T20:25:15.6344733Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/xnnpack/quantizer
2025-03-21T20:25:15.6345616Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/quantizer/xnnpack_quantizer.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/quantizer
2025-03-21T20:25:15.6346427Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/quantizer/xnnpack_quantizer_utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/quantizer
2025-03-21T20:25:15.6346754Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/xnnpack/serialization
2025-03-21T20:25:15.6347896Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/serialization/xnnpack_graph_schema.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/serialization
2025-03-21T20:25:15.6348772Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/serialization/xnnpack_graph_serialize.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/serialization
2025-03-21T20:25:15.6349615Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/serialization/runtime_schema.fbs -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/serialization
2025-03-21T20:25:15.6350477Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/serialization/schema.fbs -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/serialization
2025-03-21T20:25:15.6350824Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/xnnpack/test
2025-03-21T20:25:15.6351545Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/test_xnnpack_utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test
2025-03-21T20:25:15.6352280Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/test_xnnpack_utils_classes.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test
2025-03-21T20:25:15.6352612Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/xnnpack/test/models
2025-03-21T20:25:15.6353355Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/models/deeplab_v3.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/models
2025-03-21T20:25:15.6354201Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/models/edsr.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/models
2025-03-21T20:25:15.6354963Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/models/emformer_rnnt.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/models
2025-03-21T20:25:15.6355928Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/models/inception_v3.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/models
2025-03-21T20:25:15.6356675Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/models/inception_v4.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/models
2025-03-21T20:25:15.6357555Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/models/llama2_et_example.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/models
2025-03-21T20:25:15.6358305Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/models/mobilebert.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/models
2025-03-21T20:25:15.6359229Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/models/mobilenet_v2.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/models
2025-03-21T20:25:15.6359995Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/models/mobilenet_v3.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/models
2025-03-21T20:25:15.6360781Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/models/resnet.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/models
2025-03-21T20:25:15.6361559Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/models/torchvision_vit.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/models
2025-03-21T20:25:15.6362389Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/models/very_big_model.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/models
2025-03-21T20:25:15.6363361Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/models/w2l.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/models
2025-03-21T20:25:15.6363785Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6364556Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_abs.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6365295Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_add.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6366185Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_avgpool2d.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6367006Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_bilinear2d.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6367733Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_bmm.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6368443Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_cat.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6369395Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_ceil.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6370189Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_check_quant_params.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6370971Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_clamp.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6371691Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_conv1d.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6372602Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_conv2d.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6373302Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_div.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6374194Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_elu.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6374893Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_floor.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6375787Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_hardswish.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6376497Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_hardtanh.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6377317Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_leaky_relu.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6378011Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_linear.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6378806Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_lstm.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6379764Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_max_dim.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6380542Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_maximum.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6381348Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_maxpool2d.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6382150Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_mean_dim.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6382974Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_minimum.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6383714Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_multiply.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6384619Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_negate.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6385383Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_permute.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6386195Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_pow.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6386893Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_prelu.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6387726Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_quantize_per_tensor.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6388466Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_relu.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6389235Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_rsqrt.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6389974Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_sdpa.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6390882Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_sigmoid.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6391586Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_slice_copy.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6392509Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_softmax.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6393199Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_sqrt.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6394020Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_square.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6394724Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_static_constant_pad.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6395707Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/ops/test_sub.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/ops
2025-03-21T20:25:15.6395990Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/xnnpack/test/passes
2025-03-21T20:25:15.6396944Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/passes/test_activation_fusion.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/passes
2025-03-21T20:25:15.6397739Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/passes/test_batch_norm_fusion.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/passes
2025-03-21T20:25:15.6398694Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/passes/test_channels_last_tagged_reshape.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/passes
2025-03-21T20:25:15.6399424Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/passes/test_convert_to_linear.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/passes
2025-03-21T20:25:15.6400382Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/passes/test_decompose_cat_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/passes
2025-03-21T20:25:15.6401138Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/passes/test_remove_get_item_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/passes
2025-03-21T20:25:15.6401997Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/passes/test_tag_implicit_q_dq_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/passes
2025-03-21T20:25:15.6402456Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/xnnpack/test/quantizer
2025-03-21T20:25:15.6403544Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/quantizer/test_pt2e_quantization.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/quantizer
2025-03-21T20:25:15.6404404Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/quantizer/test_representation.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/quantizer
2025-03-21T20:25:15.6405298Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/quantizer/test_xnnpack_quantizer.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/quantizer
2025-03-21T20:25:15.6405775Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/xnnpack/test/serialization
2025-03-21T20:25:15.6406671Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/serialization/test_serialization.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/serialization
2025-03-21T20:25:15.6407647Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/serialization/test_xnnheader.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/serialization
2025-03-21T20:25:15.6408056Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/xnnpack/test/tester
2025-03-21T20:25:15.6408817Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/tester/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/tester
2025-03-21T20:25:15.6409664Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/test/tester/tester.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/test/tester
2025-03-21T20:25:15.6409983Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/xnnpack/third-party
2025-03-21T20:25:15.6410329Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/xnnpack/third-party/FP16
2025-03-21T20:25:15.6411240Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/FP16/configure.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/FP16
2025-03-21T20:25:15.6411740Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/xnnpack/third-party/FP16/include
2025-03-21T20:25:15.6412150Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/xnnpack/third-party/FP16/include/fp16
2025-03-21T20:25:15.6413081Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/FP16/include/fp16/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/FP16/include/fp16
2025-03-21T20:25:15.6414055Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/FP16/include/fp16/avx.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/FP16/include/fp16
2025-03-21T20:25:15.6415031Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/FP16/include/fp16/avx2.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/FP16/include/fp16
2025-03-21T20:25:15.6415424Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/xnnpack/third-party/FP16/test
2025-03-21T20:25:15.6415914Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/xnnpack/third-party/FP16/test/peachpy
2025-03-21T20:25:15.6416880Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/FP16/test/peachpy/stubs.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/FP16/test/peachpy
2025-03-21T20:25:15.6417827Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/FP16/confu.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/FP16
2025-03-21T20:25:15.6418192Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/xnnpack/third-party/FXdiv
2025-03-21T20:25:15.6419138Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/FXdiv/configure.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/FXdiv
2025-03-21T20:25:15.6420037Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/FXdiv/confu.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/FXdiv
2025-03-21T20:25:15.6420405Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/xnnpack/third-party/cpuinfo
2025-03-21T20:25:15.6421410Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/cpuinfo/configure.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/cpuinfo
2025-03-21T20:25:15.6421786Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/xnnpack/third-party/cpuinfo/scripts
2025-03-21T20:25:15.6422897Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/cpuinfo/scripts/android-device-dump.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/cpuinfo/scripts
2025-03-21T20:25:15.6423937Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/cpuinfo/scripts/arm-linux-filesystem-dump.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/cpuinfo/scripts
2025-03-21T20:25:15.6425042Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/cpuinfo/scripts/parse-x86-cpuid-dump.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/cpuinfo/scripts
2025-03-21T20:25:15.6425459Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/xnnpack/third-party/cpuinfo/deps
2025-03-21T20:25:15.6425933Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/xnnpack/third-party/cpuinfo/deps/clog
2025-03-21T20:25:15.6426954Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/cpuinfo/deps/clog/configure.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/cpuinfo/deps/clog
2025-03-21T20:25:15.6428038Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/cpuinfo/deps/clog/confu.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/cpuinfo/deps/clog
2025-03-21T20:25:15.6429050Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/cpuinfo/confu.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/cpuinfo
2025-03-21T20:25:15.6429440Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/xnnpack/third-party/pthreadpool
2025-03-21T20:25:15.6430374Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/pthreadpool/configure.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/pthreadpool
2025-03-21T20:25:15.6431244Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/pthreadpool/confu.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/pthreadpool
2025-03-21T20:25:15.6431580Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/xnnpack/third-party/XNNPACK
2025-03-21T20:25:15.6431988Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/xnnpack/third-party/XNNPACK/scripts
2025-03-21T20:25:15.6433109Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/scripts/check_config.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/scripts
2025-03-21T20:25:15.6434109Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/scripts/check_files_changed.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/scripts
2025-03-21T20:25:15.6435423Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/scripts/generate-build-identifier.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/scripts
2025-03-21T20:25:15.6436497Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/scripts/sort-filenames.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/scripts
2025-03-21T20:25:15.6436986Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.6437942Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools/primes.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.6438821Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools/xngen.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.6439963Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools/xnncommon.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.6440981Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-argmaxpool-test.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.6441943Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-conv-hwc-test.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.6443071Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-conv-hwc2chw-test.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.6444248Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-dwconv-multipass-test.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.6445654Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-dwconv-unipass-test.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.6446700Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-dwconv2d-chw-test.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.6447853Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-gemm-test.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.6449015Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-ibilinear-chw-test.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.6450082Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-ibilinear-test.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.6451153Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-lut-norm-test.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.6452118Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-lut-test.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.6453079Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-raddexpminusmax-test.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.6454021Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-raddextexp-test.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.6455074Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-raddstoreexpminusmax-test.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.6456069Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-rdsum-benchmark.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.6457031Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-rdsum-test.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.6457948Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-reduce-test.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.6458918Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-spmm-test.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.6459959Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-vbinary-test.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.6460825Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-vmulcaddc-test.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.6462063Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-vscaleexpminusmax-test.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.6463518Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-vscaleextexp-test.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.6464634Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-vunary-test.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.6465740Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/tools/update-microkernels.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/tools
2025-03-21T20:25:15.6466182Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6467212Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/bf16-gemm-minmax.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6468196Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f16-conv-hwc2chw.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6469306Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f16-dwconv2d-chw.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6470316Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f16-f32acc-gemm-minmax.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6471329Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f16-f32acc-igemm-minmax.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6472458Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f16-f32acc-rdsum.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6473397Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f16-f32acc-rsum.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6474440Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f16-gemm-minmax.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6475543Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f16-ibilinear-chw.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6476529Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f16-ibilinear.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6477589Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f16-igemm-minmax.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6478588Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f16-raddstoreexpminusmax.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6479727Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f16-rmax.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6480665Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f16-rmin.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6481660Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f16-rminmax.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6482647Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f16-rsum.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6483596Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f16-spmm-minmax.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6484812Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f16-vmulcaddc-minmax.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6485709Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f32-argmaxpool.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6486752Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f32-conv-hwc.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6487743Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f32-conv-hwc2chw.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6488717Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f32-dwconv2d-chw.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6489716Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f32-gemm-goi-minmax.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6490762Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f32-gemm-minmax.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6491634Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f32-gemm-relu.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6492631Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f32-gemm.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6493549Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f32-gemminc-minmax.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6494529Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f32-ibilinear-chw.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6495608Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f32-ibilinear.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6496692Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f32-igemm-minmax.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6497727Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f32-igemm-relu.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6498703Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f32-igemm.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6499715Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f32-ppmm-minmax.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6500664Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f32-qc4w-gemm-minmax.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6501700Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f32-qc8w-gemm-minmax.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6502678Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f32-qc8w-gemm-relu.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6503483Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f32-qc8w-gemm.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6504467Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f32-raddexpminusmax.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6505534Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f32-raddextexp.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6506570Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f32-raddstoreexpminusmax.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6507522Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f32-rdsum.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6508533Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f32-rmax.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6509418Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f32-rmin.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6510580Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f32-rminmax.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6511626Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f32-rsum.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6534101Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f32-spmm-minmax.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6534976Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f32-vmulcaddc-minmax.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6536364Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f32-vscaleexpminusmax.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6537535Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/f32-vscaleextexp.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6538598Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/qd8-f16-qb4w-gemm-minmax.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6539578Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/qd8-f16-qc4w-gemm-minmax.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6540747Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/qd8-f16-qc8w-gemm-minmax.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6541817Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/qd8-f16-qc8w-igemm-minmax.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6542786Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/qd8-f32-qb4w-gemm-minmax.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6543754Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/qd8-f32-qc4w-gemm-minmax.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6544715Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/qd8-f32-qc8w-gemm-minmax.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6545692Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/qd8-f32-qc8w-igemm-minmax.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6546715Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/qp8-f32-qb4w-gemm-minmax.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6547710Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/qp8-f32-qc4w-gemm-minmax.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6548813Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/qs8-qc8w-gemm-minmax-fp32.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6549830Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/qs8-qc8w-igemm-minmax-fp32.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6550757Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/qs8-rdsum-minmax-fp32.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6551790Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/qs8-rsum.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6552840Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/qu8-gemm-minmax-fp32.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6553936Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/qu8-gemm-minmax-rndnu.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6554888Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/qu8-igemm-minmax-fp32.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6555931Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/qu8-igemm-minmax-rndnu.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6556945Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/qu8-rdsum.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6558010Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/qu8-rsum.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6558956Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/s8-ibilinear.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6559936Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/u8-ibilinear.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6560892Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/u8-lut32norm.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6561902Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/u8-rmax.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6562871Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/XNNPACK/test/x8-lut.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party/XNNPACK/test
2025-03-21T20:25:15.6563671Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/third-party/generate-cpuinfo-wrappers.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/third-party
2025-03-21T20:25:15.6564015Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/xnnpack/utils
2025-03-21T20:25:15.6564837Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/utils/configs.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/utils
2025-03-21T20:25:15.6565493Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/utils/quant_utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/utils
2025-03-21T20:25:15.6566300Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/utils/utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/utils
2025-03-21T20:25:15.6566972Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/xnnpack/utils/xnnpack_constants.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/xnnpack/utils
2025-03-21T20:25:15.6567267Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/apple
2025-03-21T20:25:15.6567630Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/apple/mps
2025-03-21T20:25:15.6568269Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/mps
2025-03-21T20:25:15.6569014Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/mps_preprocess.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/mps
2025-03-21T20:25:15.6569595Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/apple/mps/operators
2025-03-21T20:25:15.6570277Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/mps/operators
2025-03-21T20:25:15.6571118Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators/activation_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/mps/operators
2025-03-21T20:25:15.6617327Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators/binary_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/mps/operators
2025-03-21T20:25:15.6618033Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators/clamp_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/mps/operators
2025-03-21T20:25:15.6618800Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators/constant_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/mps/operators
2025-03-21T20:25:15.6619512Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators/convolution_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/mps/operators
2025-03-21T20:25:15.6620435Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators/indexing_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/mps/operators
2025-03-21T20:25:15.6621160Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators/linear_algebra_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/mps/operators
2025-03-21T20:25:15.6622050Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators/node_visitor.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/mps/operators
2025-03-21T20:25:15.6622847Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators/normalization_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/mps/operators
2025-03-21T20:25:15.6623589Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators/op_clone.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/mps/operators
2025-03-21T20:25:15.6624279Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators/op_getitem.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/mps/operators
2025-03-21T20:25:15.6625188Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators/op_quant_dequant.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/mps/operators
2025-03-21T20:25:15.6625926Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators/op_skip_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/mps/operators
2025-03-21T20:25:15.6626793Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators/pad_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/mps/operators
2025-03-21T20:25:15.6627551Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators/pooling_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/mps/operators
2025-03-21T20:25:15.6628344Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators/range_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/mps/operators
2025-03-21T20:25:15.6629140Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators/reduce_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/mps/operators
2025-03-21T20:25:15.6629975Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators/shape_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/mps/operators
2025-03-21T20:25:15.6630755Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/operators/unary_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/mps/operators
2025-03-21T20:25:15.6631089Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/apple/mps/partition
2025-03-21T20:25:15.6631771Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/partition/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/mps/partition
2025-03-21T20:25:15.6632737Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/partition/mps_partitioner.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/mps/partition
2025-03-21T20:25:15.6633149Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/apple/mps/serialization
2025-03-21T20:25:15.6633901Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/serialization/mps_graph_schema.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/mps/serialization
2025-03-21T20:25:15.6634717Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/serialization/mps_graph_serialize.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/mps/serialization
2025-03-21T20:25:15.6635522Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/serialization/schema.fbs -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/mps/serialization
2025-03-21T20:25:15.6635819Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/apple/mps/test
2025-03-21T20:25:15.6636608Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/test/test_mps.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/mps/test
2025-03-21T20:25:15.6637290Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/test/test_mps_binary_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/mps/test
2025-03-21T20:25:15.6638094Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/test/test_mps_indexing_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/mps/test
2025-03-21T20:25:15.6638813Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/test/test_mps_linear.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/mps/test
2025-03-21T20:25:15.6639565Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/test/test_mps_models.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/mps/test
2025-03-21T20:25:15.6640335Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/test/test_mps_unary_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/mps/test
2025-03-21T20:25:15.6641009Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/test/test_mps_utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/mps/test
2025-03-21T20:25:15.6641357Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/apple/mps/utils
2025-03-21T20:25:15.6642083Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/utils/mps_utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/mps/utils
2025-03-21T20:25:15.6642890Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/mps/utils/quant_utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/mps/utils
2025-03-21T20:25:15.6643160Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/apple/coreml
2025-03-21T20:25:15.6643539Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/apple/coreml/compiler
2025-03-21T20:25:15.6644352Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/coreml/compiler/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/coreml/compiler
2025-03-21T20:25:15.6645449Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/coreml/compiler/coreml_preprocess.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/coreml/compiler
2025-03-21T20:25:15.6645781Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/apple/coreml/partition
2025-03-21T20:25:15.6646634Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/coreml/partition/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/coreml/partition
2025-03-21T20:25:15.6647401Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/coreml/partition/coreml_partitioner.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/coreml/partition
2025-03-21T20:25:15.6647782Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/apple/coreml/quantizer
2025-03-21T20:25:15.6648569Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/coreml/quantizer/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/coreml/quantizer
2025-03-21T20:25:15.6649407Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/coreml/quantizer/coreml_quantizer.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/coreml/quantizer
2025-03-21T20:25:15.6649688Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/apple/coreml/test
2025-03-21T20:25:15.6650579Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/coreml/test/test_coreml_partitioner.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/coreml/test
2025-03-21T20:25:15.6651302Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/coreml/test/test_coreml_quantizer.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/coreml/test
2025-03-21T20:25:15.6651624Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/apple/coreml/runtime
2025-03-21T20:25:15.6652113Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/apple/coreml/runtime/inmemoryfs
2025-03-21T20:25:15.6699487Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/coreml/runtime/inmemoryfs/setup.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/coreml/runtime/inmemoryfs
2025-03-21T20:25:15.6699848Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/apple/coreml/runtime/test
2025-03-21T20:25:15.6700840Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/coreml/runtime/test/export_stateful_model.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/coreml/runtime/test
2025-03-21T20:25:15.6701578Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/apple/coreml/executorchcoreml.pyi -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/apple/coreml
2025-03-21T20:25:15.6701887Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/cadence
2025-03-21T20:25:15.6702172Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/cadence/aot
2025-03-21T20:25:15.6702860Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/aot
2025-03-21T20:25:15.6703565Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/compiler.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/aot
2025-03-21T20:25:15.6704197Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/compiler_utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/aot
2025-03-21T20:25:15.6704942Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/export_example.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/aot
2025-03-21T20:25:15.6705603Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/fuse_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/aot
2025-03-21T20:25:15.6706578Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/graph_builder.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/aot
2025-03-21T20:25:15.6707293Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/memory_constraints.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/aot
2025-03-21T20:25:15.6708118Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/memory_planning.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/aot
2025-03-21T20:25:15.6708806Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/ops_registrations.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/aot
2025-03-21T20:25:15.6709643Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/pass_utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/aot
2025-03-21T20:25:15.6710259Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/passes.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/aot
2025-03-21T20:25:15.6711130Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/ref_implementations.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/aot
2025-03-21T20:25:15.6711743Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/remove_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/aot
2025-03-21T20:25:15.6712529Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/reorder_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/aot
2025-03-21T20:25:15.6713179Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/replace_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/aot
2025-03-21T20:25:15.6714015Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/simplify_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/aot
2025-03-21T20:25:15.6714622Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/aot
2025-03-21T20:25:15.6714955Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/cadence/aot/quantizer
2025-03-21T20:25:15.6715855Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/quantizer/fusion_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/aot/quantizer
2025-03-21T20:25:15.6716552Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/quantizer/patterns.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/aot/quantizer
2025-03-21T20:25:15.6717481Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/quantizer/quantizer.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/aot/quantizer
2025-03-21T20:25:15.6718173Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/quantizer/utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/aot/quantizer
2025-03-21T20:25:15.6718445Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/cadence/aot/tests
2025-03-21T20:25:15.6719345Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/tests/test_fusion_ops_passes.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/aot/tests
2025-03-21T20:25:15.6720060Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/tests/test_graph_builder.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/aot/tests
2025-03-21T20:25:15.6720935Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/tests/test_memory_passes.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/aot/tests
2025-03-21T20:25:15.6721687Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/tests/test_pass_filter.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/aot/tests
2025-03-21T20:25:15.6722594Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/tests/test_remove_ops_passes.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/aot/tests
2025-03-21T20:25:15.6723305Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/tests/test_reorder_ops_passes.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/aot/tests
2025-03-21T20:25:15.6724204Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/tests/test_replace_ops_passes.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/aot/tests
2025-03-21T20:25:15.6724913Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/tests/test_simplify_ops_passes.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/aot/tests
2025-03-21T20:25:15.6725664Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/functions.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/aot
2025-03-21T20:25:15.6726448Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/functions_fusion_g3.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/aot
2025-03-21T20:25:15.6727259Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/aot/functions_hifi.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/aot
2025-03-21T20:25:15.6727516Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/cadence/runtime
2025-03-21T20:25:15.6728196Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/runtime/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/runtime
2025-03-21T20:25:15.6729024Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/runtime/executor.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/runtime
2025-03-21T20:25:15.6729838Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/runtime/runtime.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/runtime
2025-03-21T20:25:15.6730591Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/runtime/utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/runtime
2025-03-21T20:25:15.6730915Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/cadence/utils
2025-03-21T20:25:15.6731619Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/facto_util.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils
2025-03-21T20:25:15.6732527Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/gen_header.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils
2025-03-21T20:25:15.6733262Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/post_compilation.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils
2025-03-21T20:25:15.6733600Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/cadence/utils/FACTO
2025-03-21T20:25:15.6734356Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/setup.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO
2025-03-21T20:25:15.6734732Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/cadence/utils/FACTO/calibrator
2025-03-21T20:25:15.6769329Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/calibrator/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/calibrator
2025-03-21T20:25:15.6770332Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/calibrator/runner.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/calibrator
2025-03-21T20:25:15.6771186Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/cadence/utils/FACTO/examples
2025-03-21T20:25:15.6772311Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/examples/example.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/examples
2025-03-21T20:25:15.6773476Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/examples/minimal_example.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/examples
2025-03-21T20:25:15.6774424Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/examples/random_seed.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/examples
2025-03-21T20:25:15.6774903Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/cadence/utils/FACTO/facto
2025-03-21T20:25:15.6775748Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/facto
2025-03-21T20:25:15.6776219Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/cadence/utils/FACTO/facto/inputgen
2025-03-21T20:25:15.6777321Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/facto/inputgen
2025-03-21T20:25:15.6777799Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/cadence/utils/FACTO/facto/inputgen/argtuple
2025-03-21T20:25:15.6779068Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/argtuple/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/facto/inputgen/argtuple
2025-03-21T20:25:15.6780310Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/argtuple/engine.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/facto/inputgen/argtuple
2025-03-21T20:25:15.6781456Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/argtuple/gen.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/facto/inputgen/argtuple
2025-03-21T20:25:15.6782024Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/cadence/utils/FACTO/facto/inputgen/argument
2025-03-21T20:25:15.6783127Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/argument/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/facto/inputgen/argument
2025-03-21T20:25:15.6784188Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/argument/engine.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/facto/inputgen/argument
2025-03-21T20:25:15.6785411Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/argument/gen.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/facto/inputgen/argument
2025-03-21T20:25:15.6786596Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/argument/type.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/facto/inputgen/argument
2025-03-21T20:25:15.6787059Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/cadence/utils/FACTO/facto/inputgen/attribute
2025-03-21T20:25:15.6788266Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/attribute/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/facto/inputgen/attribute
2025-03-21T20:25:15.6789597Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/attribute/engine.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/facto/inputgen/attribute
2025-03-21T20:25:15.6790840Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/attribute/model.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/facto/inputgen/attribute
2025-03-21T20:25:15.6791896Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/attribute/solve.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/facto/inputgen/attribute
2025-03-21T20:25:15.6792504Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/cadence/utils/FACTO/facto/inputgen/specs
2025-03-21T20:25:15.6793517Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/specs/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/facto/inputgen/specs
2025-03-21T20:25:15.6794676Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/specs/model.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/facto/inputgen/specs
2025-03-21T20:25:15.6795138Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/cadence/utils/FACTO/facto/inputgen/utils
2025-03-21T20:25:15.6796221Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/utils/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/facto/inputgen/utils
2025-03-21T20:25:15.6797427Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/utils/random_manager.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/facto/inputgen/utils
2025-03-21T20:25:15.6797933Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/cadence/utils/FACTO/facto/inputgen/variable
2025-03-21T20:25:15.6799062Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/variable/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/facto/inputgen/variable
2025-03-21T20:25:15.6800283Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/variable/constants.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/facto/inputgen/variable
2025-03-21T20:25:15.6801462Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/variable/gen.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/facto/inputgen/variable
2025-03-21T20:25:15.6802548Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/variable/solve.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/facto/inputgen/variable
2025-03-21T20:25:15.6803648Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/variable/space.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/facto/inputgen/variable
2025-03-21T20:25:15.6804865Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/variable/type.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/facto/inputgen/variable
2025-03-21T20:25:15.6805972Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/inputgen/variable/utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/facto/inputgen/variable
2025-03-21T20:25:15.6806373Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/cadence/utils/FACTO/facto/specdb
2025-03-21T20:25:15.6807411Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/specdb/db.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/facto/specdb
2025-03-21T20:25:15.6808613Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/specdb/default.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/facto/specdb
2025-03-21T20:25:15.6809647Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/specdb/dtypes.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/facto/specdb
2025-03-21T20:25:15.6810682Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/facto/specdb/function.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/facto/specdb
2025-03-21T20:25:15.6841870Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/cadence/utils/FACTO/test
2025-03-21T20:25:15.6842436Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/backends/cadence/utils/FACTO/test/inputgen
2025-03-21T20:25:15.6843518Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/test/inputgen/test_argtuple_engine.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/test/inputgen
2025-03-21T20:25:15.6844581Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/test/inputgen/test_argtuple_generator.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/test/inputgen
2025-03-21T20:25:15.6845629Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/test/inputgen/test_argument_attributes.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/test/inputgen
2025-03-21T20:25:15.6846579Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/test/inputgen/test_argument_generator.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/test/inputgen
2025-03-21T20:25:15.6847520Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/test/inputgen/test_argument_types.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/test/inputgen
2025-03-21T20:25:15.6848431Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/test/inputgen/test_attribute_engine.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/test/inputgen
2025-03-21T20:25:15.6849490Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/test/inputgen/test_attribute_solver.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/test/inputgen
2025-03-21T20:25:15.6850442Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/test/inputgen/test_constraints.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/test/inputgen
2025-03-21T20:25:15.6851346Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/test/inputgen/test_meta_arg_engine.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/test/inputgen
2025-03-21T20:25:15.6852306Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/test/inputgen/test_specs.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/test/inputgen
2025-03-21T20:25:15.6853366Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/test/inputgen/test_structural_engine.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/test/inputgen
2025-03-21T20:25:15.6854404Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/test/inputgen/test_variable_generation.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/test/inputgen
2025-03-21T20:25:15.6855550Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/test/inputgen/test_variable_solving.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/test/inputgen
2025-03-21T20:25:15.6856632Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/test/inputgen/test_variable_space.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/test/inputgen
2025-03-21T20:25:15.6857641Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/backends/cadence/utils/FACTO/test/inputgen/test_variable_types.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/backends/cadence/utils/FACTO/test/inputgen
2025-03-21T20:25:15.6857906Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/codegen
2025-03-21T20:25:15.6858528Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/codegen/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/codegen
2025-03-21T20:25:15.6858803Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/codegen/tools
2025-03-21T20:25:15.6859425Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/codegen/tools/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/codegen/tools
2025-03-21T20:25:15.6860082Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/codegen/tools/gen_all_oplist.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/codegen/tools
2025-03-21T20:25:15.6860736Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/codegen/tools/gen_oplist.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/codegen/tools
2025-03-21T20:25:15.6861417Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/codegen/tools/gen_ops_def.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/codegen/tools
2025-03-21T20:25:15.6862031Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/codegen/tools/gen_selected_op_variants.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/codegen/tools
2025-03-21T20:25:15.6862809Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/codegen/tools/merge_yaml.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/codegen/tools
2025-03-21T20:25:15.6863380Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/codegen/tools/yaml_util.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/codegen/tools
2025-03-21T20:25:15.6863679Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/codegen/tools/test
2025-03-21T20:25:15.6864408Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/codegen/tools/test/test_gen_all_oplist.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/codegen/tools/test
2025-03-21T20:25:15.6865158Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/codegen/tools/test/test_gen_oplist.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/codegen/tools/test
2025-03-21T20:25:15.6865967Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/codegen/tools/test/test_gen_oplist_real_model.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/codegen/tools/test
2025-03-21T20:25:15.6866761Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/codegen/tools/test/test_gen_selected_op_variants.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/codegen/tools/test
2025-03-21T20:25:15.6866988Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples
2025-03-21T20:25:15.6867292Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/apple
2025-03-21T20:25:15.6867666Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/apple/coreml
2025-03-21T20:25:15.6867962Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/apple/coreml/llama
2025-03-21T20:25:15.6868693Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/apple/coreml/llama/export.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/apple/coreml/llama
2025-03-21T20:25:15.6869574Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/apple/coreml/llama/llama_transformer.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/apple/coreml/llama
2025-03-21T20:25:15.6870277Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/apple/coreml/llama/run.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/apple/coreml/llama
2025-03-21T20:25:15.6871253Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/apple/coreml/llama/test.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/apple/coreml/llama
2025-03-21T20:25:15.6871967Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/apple/coreml/llama/utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/apple/coreml/llama
2025-03-21T20:25:15.6872290Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/llm_pte_finetuning
2025-03-21T20:25:15.6872964Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/llm_pte_finetuning/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/llm_pte_finetuning
2025-03-21T20:25:15.6873705Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/llm_pte_finetuning/model_exporter.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/llm_pte_finetuning
2025-03-21T20:25:15.6874526Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/llm_pte_finetuning/model_loading_lib.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/llm_pte_finetuning
2025-03-21T20:25:15.6875231Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/llm_pte_finetuning/runner.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/llm_pte_finetuning
2025-03-21T20:25:15.6875978Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/llm_pte_finetuning/training_lib.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/llm_pte_finetuning
2025-03-21T20:25:15.6876753Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/llm_pte_finetuning/phi3_alpaca_code_config.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/llm_pte_finetuning
2025-03-21T20:25:15.6877570Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/llm_pte_finetuning/phi3_config.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/llm_pte_finetuning
2025-03-21T20:25:15.6922402Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/llm_pte_finetuning/qwen_05b_config.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/llm_pte_finetuning
2025-03-21T20:25:15.6922773Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models
2025-03-21T20:25:15.6923568Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models
2025-03-21T20:25:15.6924306Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/checkpoint.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models
2025-03-21T20:25:15.6925197Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/model_base.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models
2025-03-21T20:25:15.6925952Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/model_factory.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models
2025-03-21T20:25:15.6926367Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/deeplab_v3
2025-03-21T20:25:15.6927149Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/deeplab_v3/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/deeplab_v3
2025-03-21T20:25:15.6927992Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/deeplab_v3/model.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/deeplab_v3
2025-03-21T20:25:15.6928262Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/edsr
2025-03-21T20:25:15.6928992Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/edsr/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/edsr
2025-03-21T20:25:15.6929712Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/edsr/model.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/edsr
2025-03-21T20:25:15.6930049Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/efficient_sam
2025-03-21T20:25:15.6930987Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/efficient_sam/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/efficient_sam
2025-03-21T20:25:15.6931742Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/efficient_sam/model.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/efficient_sam
2025-03-21T20:25:15.6932126Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/efficient_sam/efficient_sam_core
2025-03-21T20:25:15.6933359Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/efficient_sam/efficient_sam_core/build_efficient_sam.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/efficient_sam/efficient_sam_core
2025-03-21T20:25:15.6934291Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/efficient_sam/efficient_sam_core/efficient_sam.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/efficient_sam/efficient_sam_core
2025-03-21T20:25:15.6935443Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/efficient_sam/efficient_sam_core/efficient_sam_decoder.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/efficient_sam/efficient_sam_core
2025-03-21T20:25:15.6936464Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/efficient_sam/efficient_sam_core/efficient_sam_encoder.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/efficient_sam/efficient_sam_core
2025-03-21T20:25:15.6937337Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/efficient_sam/efficient_sam_core/mlp.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/efficient_sam/efficient_sam_core
2025-03-21T20:25:15.6938503Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/efficient_sam/efficient_sam_core/two_way_transformer.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/efficient_sam/efficient_sam_core
2025-03-21T20:25:15.6938794Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/emformer_rnnt
2025-03-21T20:25:15.6939614Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/emformer_rnnt/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/emformer_rnnt
2025-03-21T20:25:15.6940390Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/emformer_rnnt/model.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/emformer_rnnt
2025-03-21T20:25:15.6940681Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/inception_v3
2025-03-21T20:25:15.6941681Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/inception_v3/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/inception_v3
2025-03-21T20:25:15.6942494Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/inception_v3/model.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/inception_v3
2025-03-21T20:25:15.6942932Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/inception_v4
2025-03-21T20:25:15.6943655Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/inception_v4/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/inception_v4
2025-03-21T20:25:15.6944503Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/inception_v4/model.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/inception_v4
2025-03-21T20:25:15.6944760Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/llama
2025-03-21T20:25:15.6945400Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama
2025-03-21T20:25:15.6946361Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/attention.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama
2025-03-21T20:25:15.6947282Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/eval_llama.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama
2025-03-21T20:25:15.6948037Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/eval_llama_lib.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama
2025-03-21T20:25:15.6948676Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/export_llama.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama
2025-03-21T20:25:15.6949365Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/export_llama_lib.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama
2025-03-21T20:25:15.6950006Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/fairseq2.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama
2025-03-21T20:25:15.6950714Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/install_requirement_helper.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama
2025-03-21T20:25:15.6951395Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/llama_test.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama
2025-03-21T20:25:15.6952038Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/llama_transformer.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama
2025-03-21T20:25:15.6952713Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/model.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama
2025-03-21T20:25:15.6953320Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/model_args.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama
2025-03-21T20:25:15.6954005Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/norm.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama
2025-03-21T20:25:15.6954591Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/rope.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama
2025-03-21T20:25:15.6955394Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/static_attention.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama
2025-03-21T20:25:15.6955743Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/llama/evaluate
2025-03-21T20:25:15.6956586Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/evaluate/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama/evaluate
2025-03-21T20:25:15.6957346Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/evaluate/eager_eval.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama/evaluate
2025-03-21T20:25:15.6957665Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/llama/experimental
2025-03-21T20:25:15.6958633Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/experimental/generate.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama/experimental
2025-03-21T20:25:15.6993444Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/experimental/load_gguf_q4_0.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama/experimental
2025-03-21T20:25:15.6994437Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/experimental/subclass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama/experimental
2025-03-21T20:25:15.6995331Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/experimental/test_subclass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama/experimental
2025-03-21T20:25:15.6995887Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/llama/runner
2025-03-21T20:25:15.6996583Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/runner/eager.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama/runner
2025-03-21T20:25:15.6997410Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/runner/generation.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama/runner
2025-03-21T20:25:15.6998126Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/runner/native.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama/runner
2025-03-21T20:25:15.6998475Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/llama/source_transformation
2025-03-21T20:25:15.6999410Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/source_transformation/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama/source_transformation
2025-03-21T20:25:15.7000319Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/source_transformation/apply_spin_quant_r1_r2.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama/source_transformation
2025-03-21T20:25:15.7001226Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/source_transformation/attention.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama/source_transformation
2025-03-21T20:25:15.7002180Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/source_transformation/attention_sink.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama/source_transformation
2025-03-21T20:25:15.7003153Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/source_transformation/lora.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama/source_transformation
2025-03-21T20:25:15.7004087Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/source_transformation/pre_quantization.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama/source_transformation
2025-03-21T20:25:15.7004989Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/source_transformation/prune_vocab.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama/source_transformation
2025-03-21T20:25:15.7005923Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/source_transformation/quantize.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama/source_transformation
2025-03-21T20:25:15.7006821Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/source_transformation/quantized_kv_cache.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama/source_transformation
2025-03-21T20:25:15.7007804Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/source_transformation/rms_norm.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama/source_transformation
2025-03-21T20:25:15.7008729Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/source_transformation/rope.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama/source_transformation
2025-03-21T20:25:15.7009646Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/source_transformation/sdpa.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama/source_transformation
2025-03-21T20:25:15.7010591Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/source_transformation/spin_quant.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama/source_transformation
2025-03-21T20:25:15.7011601Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/source_transformation/test_attention_sink.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama/source_transformation
2025-03-21T20:25:15.7012759Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/source_transformation/test_quantized_kv_cache.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama/source_transformation
2025-03-21T20:25:15.7013824Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/source_transformation/test_sdpa_with_quantized_kv_cache.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama/source_transformation
2025-03-21T20:25:15.7014776Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/source_transformation/vulkan_rope.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama/source_transformation
2025-03-21T20:25:15.7015103Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/llama/tests
2025-03-21T20:25:15.7016008Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/tests/test_pre_quantization_transforms.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama/tests
2025-03-21T20:25:15.7016710Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/tests/test_simple_sdpa.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama/tests
2025-03-21T20:25:15.7017522Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/tests/test_static_attention.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama/tests
2025-03-21T20:25:15.7017881Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/llama/tokenizer
2025-03-21T20:25:15.7018726Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama/tokenizer/tiktoken.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama/tokenizer
2025-03-21T20:25:15.7019080Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/llama3_2_vision
2025-03-21T20:25:15.7019916Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama3_2_vision
2025-03-21T20:25:15.7020313Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/llama3_2_vision/preprocess
2025-03-21T20:25:15.7021291Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/preprocess/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama3_2_vision/preprocess
2025-03-21T20:25:15.7022303Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/preprocess/export_preprocess.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama3_2_vision/preprocess
2025-03-21T20:25:15.7023248Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/preprocess/model.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama3_2_vision/preprocess
2025-03-21T20:25:15.7024314Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/preprocess/test_preprocess.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama3_2_vision/preprocess
2025-03-21T20:25:15.7024677Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/llama3_2_vision/runner
2025-03-21T20:25:15.7025537Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/runner/eager.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama3_2_vision/runner
2025-03-21T20:25:15.7026385Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/runner/exported.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama3_2_vision/runner
2025-03-21T20:25:15.7027367Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/runner/generation.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama3_2_vision/runner
2025-03-21T20:25:15.7028323Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/runner/native.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama3_2_vision/runner
2025-03-21T20:25:15.7028834Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/llama3_2_vision/text_decoder
2025-03-21T20:25:15.7081838Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/text_decoder/model.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama3_2_vision/text_decoder
2025-03-21T20:25:15.7082266Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/llama3_2_vision/text_decoder/test
2025-03-21T20:25:15.7083095Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/text_decoder/test/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama3_2_vision/text_decoder/test
2025-03-21T20:25:15.7084189Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/text_decoder/test/test_text_decoder.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama3_2_vision/text_decoder/test
2025-03-21T20:25:15.7084546Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/llama3_2_vision/vision_encoder
2025-03-21T20:25:15.7085574Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/vision_encoder/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama3_2_vision/vision_encoder
2025-03-21T20:25:15.7086491Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/vision_encoder/model.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama3_2_vision/vision_encoder
2025-03-21T20:25:15.7086971Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/llama3_2_vision/vision_encoder/test
2025-03-21T20:25:15.7088096Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/vision_encoder/test/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama3_2_vision/vision_encoder/test
2025-03-21T20:25:15.7089115Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llama3_2_vision/vision_encoder/test/test_vision_encoder.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llama3_2_vision/vision_encoder/test
2025-03-21T20:25:15.7089542Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/llava
2025-03-21T20:25:15.7090157Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llava/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llava
2025-03-21T20:25:15.7090830Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llava/export_llava.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llava
2025-03-21T20:25:15.7091579Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llava/image_util.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llava
2025-03-21T20:25:15.7092176Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llava/model.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llava
2025-03-21T20:25:15.7092439Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/llava/test
2025-03-21T20:25:15.7093230Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llava/test/test_llava.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llava/test
2025-03-21T20:25:15.7093986Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/llava/test/test_pte.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/llava/test
2025-03-21T20:25:15.7094245Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/lstm
2025-03-21T20:25:15.7095237Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/lstm/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/lstm
2025-03-21T20:25:15.7095847Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/lstm/model.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/lstm
2025-03-21T20:25:15.7096109Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/mobilebert
2025-03-21T20:25:15.7096922Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/mobilebert/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/mobilebert
2025-03-21T20:25:15.7097570Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/mobilebert/model.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/mobilebert
2025-03-21T20:25:15.7097856Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/mobilenet_v2
2025-03-21T20:25:15.7098730Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/mobilenet_v2/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/mobilenet_v2
2025-03-21T20:25:15.7099461Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/mobilenet_v2/model.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/mobilenet_v2
2025-03-21T20:25:15.7099811Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/mobilenet_v3
2025-03-21T20:25:15.7100554Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/mobilenet_v3/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/mobilenet_v3
2025-03-21T20:25:15.7101357Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/mobilenet_v3/model.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/mobilenet_v3
2025-03-21T20:25:15.7101705Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/phi-3-mini-lora
2025-03-21T20:25:15.7102430Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/phi-3-mini-lora/export_model.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/phi-3-mini-lora
2025-03-21T20:25:15.7102807Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/phi-3-mini
2025-03-21T20:25:15.7103615Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/phi-3-mini/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/phi-3-mini
2025-03-21T20:25:15.7104359Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/phi-3-mini/eager.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/phi-3-mini
2025-03-21T20:25:15.7105167Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/phi-3-mini/phi_3_mini.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/phi-3-mini
2025-03-21T20:25:15.7106017Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/phi-3-mini/static_cache.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/phi-3-mini
2025-03-21T20:25:15.7106774Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/phi-3-mini/export_phi-3-mini.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/phi-3-mini
2025-03-21T20:25:15.7107057Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/phi-4-mini
2025-03-21T20:25:15.7107870Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/phi-4-mini/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/phi-4-mini
2025-03-21T20:25:15.7108619Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/phi-4-mini/convert_weights.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/phi-4-mini
2025-03-21T20:25:15.7108974Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/qwen2_5
2025-03-21T20:25:15.7109737Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/qwen2_5/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/qwen2_5
2025-03-21T20:25:15.7110702Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/qwen2_5/convert_weights.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/qwen2_5
2025-03-21T20:25:15.7110963Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/resnet
2025-03-21T20:25:15.7111704Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/resnet/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/resnet
2025-03-21T20:25:15.7112480Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/resnet/model.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/resnet
2025-03-21T20:25:15.7112777Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/test
2025-03-21T20:25:15.7113569Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/test/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/test
2025-03-21T20:25:15.7114279Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/test/test_export.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/test
2025-03-21T20:25:15.7114638Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/torchvision_vit
2025-03-21T20:25:15.7115495Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/torchvision_vit/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/torchvision_vit
2025-03-21T20:25:15.7116327Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/torchvision_vit/model.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/torchvision_vit
2025-03-21T20:25:15.7116680Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/toy_model
2025-03-21T20:25:15.7173513Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/toy_model/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/toy_model
2025-03-21T20:25:15.7174214Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/toy_model/model.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/toy_model
2025-03-21T20:25:15.7174560Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/wav2letter
2025-03-21T20:25:15.7175396Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/wav2letter/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/wav2letter
2025-03-21T20:25:15.7176133Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/wav2letter/model.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/wav2letter
2025-03-21T20:25:15.7176512Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/moshi
2025-03-21T20:25:15.7176870Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/examples/models/moshi/mimi
2025-03-21T20:25:15.7177779Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/examples/models/moshi/mimi/test_mimi.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/examples/models/moshi/mimi
2025-03-21T20:25:15.7178080Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/exir
2025-03-21T20:25:15.7178598Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir
2025-03-21T20:25:15.7179104Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/_warnings.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir
2025-03-21T20:25:15.7179773Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/common.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir
2025-03-21T20:25:15.7180304Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/control_flow.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir
2025-03-21T20:25:15.7181160Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/delegate.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir
2025-03-21T20:25:15.7181773Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dim_order_utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir
2025-03-21T20:25:15.7182452Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dynamic_shape.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir
2025-03-21T20:25:15.7182977Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/error.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir
2025-03-21T20:25:15.7183447Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/graph.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir
2025-03-21T20:25:15.7184151Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/graph_module.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir
2025-03-21T20:25:15.7184729Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/lowered_backend_module.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir
2025-03-21T20:25:15.7185314Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/memory.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir
2025-03-21T20:25:15.7185962Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/memory_planning.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir
2025-03-21T20:25:15.7186498Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/pass_base.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir
2025-03-21T20:25:15.7187053Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/pass_manager.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir
2025-03-21T20:25:15.7187651Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/print_program.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir
2025-03-21T20:25:15.7188196Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/scalar_type.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir
2025-03-21T20:25:15.7188848Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/schema.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir
2025-03-21T20:25:15.7189355Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/sym_util.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir
2025-03-21T20:25:15.7189998Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tensor.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir
2025-03-21T20:25:15.7190525Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tracer.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir
2025-03-21T20:25:15.7191144Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/types.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir
2025-03-21T20:25:15.7191770Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/version.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir
2025-03-21T20:25:15.7192297Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/wrap.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir
2025-03-21T20:25:15.7192644Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/exir/_serialize
2025-03-21T20:25:15.7193290Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/_serialize/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/_serialize
2025-03-21T20:25:15.7193970Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/_serialize/_cord.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/_serialize
2025-03-21T20:25:15.7194668Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/_serialize/_dataclass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/_serialize
2025-03-21T20:25:15.7195433Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/_serialize/_flatbuffer.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/_serialize
2025-03-21T20:25:15.7196127Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/_serialize/_named_data_store.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/_serialize
2025-03-21T20:25:15.7197126Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/_serialize/_program.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/_serialize
2025-03-21T20:25:15.7197740Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/_serialize/_serialize.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/_serialize
2025-03-21T20:25:15.7198563Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/_serialize/data_serializer.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/_serialize
2025-03-21T20:25:15.7199173Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/_serialize/padding.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/_serialize
2025-03-21T20:25:15.7199580Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/exir/_serialize/test
2025-03-21T20:25:15.7200266Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/_serialize/test/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/_serialize/test
2025-03-21T20:25:15.7201062Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/_serialize/test/test_cord.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/_serialize/test
2025-03-21T20:25:15.7201765Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/_serialize/test/test_flatbuffer.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/_serialize/test
2025-03-21T20:25:15.7202654Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/_serialize/test/test_named_data_store.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/_serialize/test
2025-03-21T20:25:15.7203382Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/_serialize/test/test_program.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/_serialize/test
2025-03-21T20:25:15.7204085Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/_serialize/program.fbs -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/_serialize
2025-03-21T20:25:15.7204758Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/_serialize/scalar_type.fbs -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/_serialize
2025-03-21T20:25:15.7205104Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/exir/backend
2025-03-21T20:25:15.7205750Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/backend_api.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/backend
2025-03-21T20:25:15.7206463Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/backend_details.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/backend
2025-03-21T20:25:15.7207163Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/compile_spec_schema.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/backend
2025-03-21T20:25:15.7207886Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/operator_support.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/backend
2025-03-21T20:25:15.7208567Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/partitioner.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/backend
2025-03-21T20:25:15.7209094Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/backend
2025-03-21T20:25:15.7209525Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/exir/backend/canonical_partitioners
2025-03-21T20:25:15.7259883Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/canonical_partitioners/config_partitioner.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/backend/canonical_partitioners
2025-03-21T20:25:15.7260851Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/canonical_partitioners/duplicate_constant_node_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/backend/canonical_partitioners
2025-03-21T20:25:15.7261983Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/canonical_partitioners/duplicate_dequant_node_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/backend/canonical_partitioners
2025-03-21T20:25:15.7263293Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/canonical_partitioners/pattern_op_partitioner.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/backend/canonical_partitioners
2025-03-21T20:25:15.7263728Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/exir/backend/test
2025-03-21T20:25:15.7264793Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test/backend_with_compiler_demo.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/backend/test
2025-03-21T20:25:15.7265728Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test/backend_with_delegate_mapping_demo.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/backend/test
2025-03-21T20:25:15.7266423Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test/backend_with_named_data_map.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/backend/test
2025-03-21T20:25:15.7267254Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test/hta_partitioner_demo.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/backend/test
2025-03-21T20:25:15.7267971Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test/op_partitioner_demo.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/backend/test
2025-03-21T20:25:15.7268774Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test/qnn_backend_demo.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/backend/test
2025-03-21T20:25:15.7269512Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test/test_backend_with_named_data_map.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/backend/test
2025-03-21T20:25:15.7270190Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test/test_backends.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/backend/test
2025-03-21T20:25:15.7270998Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test/test_backends_lifted.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/backend/test
2025-03-21T20:25:15.7271909Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test/test_backends_nested.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/backend/test
2025-03-21T20:25:15.7272573Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test/test_compatibility.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/backend/test
2025-03-21T20:25:15.7273441Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test/test_debug_handle_map.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/backend/test
2025-03-21T20:25:15.7274144Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test/test_delegate_map_builder.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/backend/test
2025-03-21T20:25:15.7275013Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test/test_graph_partition.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/backend/test
2025-03-21T20:25:15.7275704Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test/test_lowered_backend_module.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/backend/test
2025-03-21T20:25:15.7276451Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test/test_partitioner.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/backend/test
2025-03-21T20:25:15.7277105Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test/test_passes.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/backend/test
2025-03-21T20:25:15.7277812Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test/test_utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/backend/test
2025-03-21T20:25:15.7278072Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/exir/backend/test/demos
2025-03-21T20:25:15.7279013Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test/demos/test_delegate_aten_mode.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/backend/test/demos
2025-03-21T20:25:15.7279797Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test/demos/test_xnnpack_qnnpack.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/backend/test/demos
2025-03-21T20:25:15.7280197Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/exir/backend/test/demos/rpc
2025-03-21T20:25:15.7281004Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test/demos/rpc/executor_backend_partitioner.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/backend/test/demos/rpc
2025-03-21T20:25:15.7282020Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test/demos/rpc/executor_backend_preprocess.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/backend/test/demos/rpc
2025-03-21T20:25:15.7282827Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/backend/test/demos/rpc/test_rpc.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/backend/test/demos/rpc
2025-03-21T20:25:15.7283094Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/exir/capture
2025-03-21T20:25:15.7283677Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/capture/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/capture
2025-03-21T20:25:15.7284309Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/capture/_capture.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/capture
2025-03-21T20:25:15.7284985Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/capture/_config.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/capture
2025-03-21T20:25:15.7285542Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/capture/_unlift.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/capture
2025-03-21T20:25:15.7285756Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/exir/dialects
2025-03-21T20:25:15.7286404Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/dialects
2025-03-21T20:25:15.7286993Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/dialects
2025-03-21T20:25:15.7287235Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/exir/dialects/backend
2025-03-21T20:25:15.7287965Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/backend/_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/dialects/backend
2025-03-21T20:25:15.7288226Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/exir/dialects/backend/test
2025-03-21T20:25:15.7288957Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/backend/test/test_backend_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/dialects/backend/test
2025-03-21T20:25:15.7289311Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/exir/dialects/edge
2025-03-21T20:25:15.7289967Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/edge/_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/dialects/edge
2025-03-21T20:25:15.7290274Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/exir/dialects/edge/arg
2025-03-21T20:25:15.7290942Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/edge/arg/model.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/dialects/edge/arg
2025-03-21T20:25:15.7291673Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/edge/arg/type.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/dialects/edge/arg
2025-03-21T20:25:15.7291930Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/exir/dialects/edge/dtype
2025-03-21T20:25:15.7292607Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/edge/dtype/runner.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/dialects/edge/dtype
2025-03-21T20:25:15.7293588Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/edge/dtype/supported.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/dialects/edge/dtype
2025-03-21T20:25:15.7294278Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/edge/dtype/utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/dialects/edge/dtype
2025-03-21T20:25:15.7294572Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/exir/dialects/edge/op
2025-03-21T20:25:15.7295392Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/edge/op/api.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/dialects/edge/op
2025-03-21T20:25:15.7296034Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/edge/op/sample_input.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/dialects/edge/op
2025-03-21T20:25:15.7348797Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/exir/dialects/edge/op/test
2025-03-21T20:25:15.7349963Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/edge/op/test/test_api.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/dialects/edge/op/test
2025-03-21T20:25:15.7350234Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/exir/dialects/edge/spec
2025-03-21T20:25:15.7350937Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/edge/spec/gen.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/dialects/edge/spec
2025-03-21T20:25:15.7351610Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/edge/spec/utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/dialects/edge/spec
2025-03-21T20:25:15.7351862Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/exir/dialects/edge/test
2025-03-21T20:25:15.7352630Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/edge/test/test_edge_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/dialects/edge/test
2025-03-21T20:25:15.7353444Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/edge/test/test_edge_yaml.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/dialects/edge/test
2025-03-21T20:25:15.7354207Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/edge/edge.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/dialects/edge
2025-03-21T20:25:15.7354525Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/exir/dialects/test
2025-03-21T20:25:15.7355209Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/dialects/test/test_exir_dialect_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/dialects/test
2025-03-21T20:25:15.7355459Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/exir/emit
2025-03-21T20:25:15.7356099Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/emit/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/emit
2025-03-21T20:25:15.7356632Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/emit/_emit_program.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/emit
2025-03-21T20:25:15.7357346Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/emit/_emitter.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/emit
2025-03-21T20:25:15.7357580Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/exir/emit/test
2025-03-21T20:25:15.7358196Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/emit/test/test_emit.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/emit/test
2025-03-21T20:25:15.7358483Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/exir/operator
2025-03-21T20:25:15.7359124Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/operator/convert.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/operator
2025-03-21T20:25:15.7359755Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/operator/manip.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/operator
2025-03-21T20:25:15.7360575Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/operator/util.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/operator
2025-03-21T20:25:15.7360939Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/exir/operator/test
2025-03-21T20:25:15.7361761Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/operator/test/test_operator.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/operator/test
2025-03-21T20:25:15.7361973Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/exir/passes
2025-03-21T20:25:15.7374771Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/passes
2025-03-21T20:25:15.7375594Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes/_quant_patterns_and_replacements.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/passes
2025-03-21T20:25:15.7376266Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes/const_prop_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/passes
2025-03-21T20:25:15.7376937Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes/constant_prop_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/passes
2025-03-21T20:25:15.7377590Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes/debug_handle_generator_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/passes
2025-03-21T20:25:15.7378331Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes/dim_order_ops_registry.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/passes
2025-03-21T20:25:15.7378927Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes/dynamic_shape_prop_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/passes
2025-03-21T20:25:15.7379718Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes/executorch_prim_ops_registry.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/passes
2025-03-21T20:25:15.7380302Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes/external_constants_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/passes
2025-03-21T20:25:15.7380921Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes/init_mutable_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/passes
2025-03-21T20:25:15.7381637Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes/insert_write_back_for_buffers_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/passes
2025-03-21T20:25:15.7382254Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes/memory_format_ops_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/passes
2025-03-21T20:25:15.7382907Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes/memory_planning_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/passes
2025-03-21T20:25:15.7383532Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes/normalize_transpose_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/passes
2025-03-21T20:25:15.7384315Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes/normalize_view_copy_base_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/passes
2025-03-21T20:25:15.7384904Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes/pass_registry.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/passes
2025-03-21T20:25:15.7385604Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes/prune_empty_tensors_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/passes
2025-03-21T20:25:15.7386215Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes/quant_fusion_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/passes
2025-03-21T20:25:15.7386762Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes/quantize_io_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/passes
2025-03-21T20:25:15.7387610Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes/remove_graph_asserts_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/passes
2025-03-21T20:25:15.7388306Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes/remove_mixed_type_operators.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/passes
2025-03-21T20:25:15.7388935Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes/remove_noop_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/passes
2025-03-21T20:25:15.7389615Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes/replace_aten_with_edge_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/passes
2025-03-21T20:25:15.7390370Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes/replace_broken_ops_with_function_ops_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/passes
2025-03-21T20:25:15.7391077Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes/replace_edge_with_backend_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/passes
2025-03-21T20:25:15.7391715Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes/replace_sym_size_op_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/passes
2025-03-21T20:25:15.7392467Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes/replace_view_copy_with_view_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/passes
2025-03-21T20:25:15.7393071Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes/scalar_to_tensor_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/passes
2025-03-21T20:25:15.7393704Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes/spec_prop_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/passes
2025-03-21T20:25:15.7394323Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes/sym_shape_eval_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/passes
2025-03-21T20:25:15.7394883Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes/sym_to_tensor_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/passes
2025-03-21T20:25:15.7395615Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/passes/weights_to_outputs_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/passes
2025-03-21T20:25:15.7395847Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/exir/program
2025-03-21T20:25:15.7445107Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/program/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/program
2025-03-21T20:25:15.7445969Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/program/_fake_program.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/program
2025-03-21T20:25:15.7446592Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/program/_program.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/program
2025-03-21T20:25:15.7446878Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/exir/program/test
2025-03-21T20:25:15.7447570Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/program/test/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/program/test
2025-03-21T20:25:15.7448206Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/program/test/test_fake_program.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/program/test
2025-03-21T20:25:15.7448939Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/program/test/test_program.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/program/test
2025-03-21T20:25:15.7449296Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/exir/serde
2025-03-21T20:25:15.7449820Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/serde/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/serde
2025-03-21T20:25:15.7450503Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/serde/export_serialize.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/serde
2025-03-21T20:25:15.7451294Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/serde/schema.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/serde
2025-03-21T20:25:15.7452121Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/serde/schema_check.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/serde
2025-03-21T20:25:15.7452712Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/serde/serialize.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/serde
2025-03-21T20:25:15.7453393Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/serde/union.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/serde
2025-03-21T20:25:15.7453962Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/serde/upgrade.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/serde
2025-03-21T20:25:15.7454222Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/exir/tests
2025-03-21T20:25:15.7454915Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests/asr_joiner.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/tests
2025-03-21T20:25:15.7455409Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests/common.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/tests
2025-03-21T20:25:15.7456023Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests/control_flow_models.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/tests
2025-03-21T20:25:15.7456640Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests/dynamic_shape_models.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/tests
2025-03-21T20:25:15.7457140Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests/models.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/tests
2025-03-21T20:25:15.7457785Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests/test_arg_validator.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/tests
2025-03-21T20:25:15.7458482Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests/test_capture.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/tests
2025-03-21T20:25:15.7459099Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests/test_common.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/tests
2025-03-21T20:25:15.7459717Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests/test_delegate.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/tests
2025-03-21T20:25:15.7460338Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests/test_dim_order_utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/tests
2025-03-21T20:25:15.7461156Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests/test_dynamic_shape_propagation.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/tests
2025-03-21T20:25:15.7461735Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests/test_error.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/tests
2025-03-21T20:25:15.7462455Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests/test_joint_graph.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/tests
2025-03-21T20:25:15.7463132Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests/test_memory_format_ops_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/tests
2025-03-21T20:25:15.7463717Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests/test_memory_format_ops_pass_aten.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/tests
2025-03-21T20:25:15.7464592Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests/test_memory_format_ops_pass_utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/tests
2025-03-21T20:25:15.7465222Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests/test_memory_planning.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/tests
2025-03-21T20:25:15.7465974Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests/test_op_convert.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/tests
2025-03-21T20:25:15.7466694Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests/test_pass_infra.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/tests
2025-03-21T20:25:15.7467268Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests/test_passes.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/tests
2025-03-21T20:25:15.7467962Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests/test_print_program.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/tests
2025-03-21T20:25:15.7468757Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests/test_prune_empty_tensors_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/tests
2025-03-21T20:25:15.7469305Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests/test_quant_fusion_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/tests
2025-03-21T20:25:15.7469963Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests/test_quantization.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/tests
2025-03-21T20:25:15.7470700Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests/test_quantize_io_pass.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/tests
2025-03-21T20:25:15.7471305Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests/test_remove_view_copy.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/tests
2025-03-21T20:25:15.7471995Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests/test_serde.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/tests
2025-03-21T20:25:15.7472496Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests/test_tensor.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/tests
2025-03-21T20:25:15.7473073Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests/test_tracer.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/tests
2025-03-21T20:25:15.7473793Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests/test_verification.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/tests
2025-03-21T20:25:15.7474315Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests/test_warnings.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/tests
2025-03-21T20:25:15.7474999Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/tests/transformer.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/tests
2025-03-21T20:25:15.7475297Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/exir/verification
2025-03-21T20:25:15.7475885Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/verification/arg_validator.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/verification
2025-03-21T20:25:15.7476630Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/verification/dev_html.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/verification
2025-03-21T20:25:15.7477353Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/verification/interpreter.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/verification
2025-03-21T20:25:15.7478076Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/verification/verifier.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/verification
2025-03-21T20:25:15.7478398Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/exir/verification/test
2025-03-21T20:25:15.7479098Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/verification/test/test_verifier.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir/verification/test
2025-03-21T20:25:15.7479594Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/exir/delegate.pyi -> pip-out/bdist.linux-x86_64/wheel/./executorch/exir
2025-03-21T20:25:15.7479794Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension
2025-03-21T20:25:15.7480053Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/android_test
2025-03-21T20:25:15.7641147Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/android_test/add_model.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/android_test
2025-03-21T20:25:15.7641499Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/export_util
2025-03-21T20:25:15.7642132Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/export_util/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/export_util
2025-03-21T20:25:15.7642865Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/export_util/utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/export_util
2025-03-21T20:25:15.7643137Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/flat_tensor
2025-03-21T20:25:15.7643787Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/flat_tensor/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/flat_tensor
2025-03-21T20:25:15.7644071Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/flat_tensor/serialize
2025-03-21T20:25:15.7644914Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/flat_tensor/serialize/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/flat_tensor/serialize
2025-03-21T20:25:15.7645672Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/flat_tensor/serialize/flat_tensor_schema.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/flat_tensor/serialize
2025-03-21T20:25:15.7646639Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/flat_tensor/serialize/serialize.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/flat_tensor/serialize
2025-03-21T20:25:15.7647404Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/flat_tensor/serialize/flat_tensor.fbs -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/flat_tensor/serialize
2025-03-21T20:25:15.7648328Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/flat_tensor/serialize/scalar_type.fbs -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/flat_tensor/serialize
2025-03-21T20:25:15.7648653Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/flat_tensor/test
2025-03-21T20:25:15.7649419Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/flat_tensor/test/test_serialize.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/flat_tensor/test
2025-03-21T20:25:15.7649656Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/gguf_util
2025-03-21T20:25:15.7650254Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/gguf_util/convert_main.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/gguf_util
2025-03-21T20:25:15.7650830Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/gguf_util/converter.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/gguf_util
2025-03-21T20:25:15.7651413Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/gguf_util/load_gguf.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/gguf_util
2025-03-21T20:25:15.7651693Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/gguf_util/converters
2025-03-21T20:25:15.7652386Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/gguf_util/converters/llama_converter.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/gguf_util/converters
2025-03-21T20:25:15.7652638Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/pybindings
2025-03-21T20:25:15.7653256Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/pybindings/portable_lib.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/pybindings
2025-03-21T20:25:15.7653523Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/pybindings/test
2025-03-21T20:25:15.7654167Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/pybindings/test/make_test.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/pybindings/test
2025-03-21T20:25:15.7655068Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/pybindings/test/test_backend_pybinding.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/pybindings/test
2025-03-21T20:25:15.7655737Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/pybindings/test/test_pybindings.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/pybindings/test
2025-03-21T20:25:15.7656376Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/pybindings/pybindings.pyi -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/pybindings
2025-03-21T20:25:15.7657094Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/pybindings/_portable_lib.cpython-310-x86_64-linux-gnu.so -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/pybindings
2025-03-21T20:25:15.7657338Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/pytree
2025-03-21T20:25:15.7657890Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/pytree/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/pytree
2025-03-21T20:25:15.7658146Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/pytree/test
2025-03-21T20:25:15.7658728Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/pytree/test/test.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/pytree/test
2025-03-21T20:25:15.7658959Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/training
2025-03-21T20:25:15.7659528Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/training/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/training
2025-03-21T20:25:15.7659802Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/training/pybindings
2025-03-21T20:25:15.7660518Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/training/pybindings/_training_module.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/training/pybindings
2025-03-21T20:25:15.7660823Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/training/pybindings/test
2025-03-21T20:25:15.7661547Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/training/pybindings/test/test.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/training/pybindings/test
2025-03-21T20:25:15.7662239Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/training/pybindings/_training_lib.pyi -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/training/pybindings
2025-03-21T20:25:15.7662514Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/training/examples
2025-03-21T20:25:15.7662791Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/training/examples/XOR
2025-03-21T20:25:15.7663519Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/training/examples/XOR/export_model.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/training/examples/XOR
2025-03-21T20:25:15.7664207Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/training/examples/XOR/model.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/training/examples/XOR
2025-03-21T20:25:15.7664533Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/training/examples/XOR/test
2025-03-21T20:25:15.7665537Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/training/examples/XOR/test/test_export.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/training/examples/XOR/test
2025-03-21T20:25:15.7665800Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm
2025-03-21T20:25:15.7666124Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/custom_ops
2025-03-21T20:25:15.7666798Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/custom_ops/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/custom_ops
2025-03-21T20:25:15.7667717Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/custom_ops/custom_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/custom_ops
2025-03-21T20:25:15.7669660Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/custom_ops/model_sharding.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/custom_ops
2025-03-21T20:25:15.7671739Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/custom_ops/op_tile_crop_aot.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/custom_ops
2025-03-21T20:25:15.7673376Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/custom_ops/preprocess_custom_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/custom_ops
2025-03-21T20:25:15.7675173Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/custom_ops/test_preprocess_custom_ops.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/custom_ops
2025-03-21T20:25:15.7676899Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/custom_ops/test_sdpa_with_kv_cache.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/custom_ops
2025-03-21T20:25:15.7678561Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/custom_ops/test_update_cache.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/custom_ops
2025-03-21T20:25:15.7679734Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/custom_ops/spinquant
2025-03-21T20:25:15.7744940Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/custom_ops/spinquant/special_hadamard_code_gen.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/custom_ops/spinquant
2025-03-21T20:25:15.7746628Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/custom_ops/spinquant/third-party
2025-03-21T20:25:15.7747490Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/custom_ops/spinquant/third-party/FFHT
2025-03-21T20:25:15.7749057Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/custom_ops/spinquant/third-party/FFHT/example.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/custom_ops/spinquant/third-party/FFHT
2025-03-21T20:25:15.7751118Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/custom_ops/spinquant/third-party/FFHT/gen.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/custom_ops/spinquant/third-party/FFHT
2025-03-21T20:25:15.7752967Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/custom_ops/libcustom_ops_aot_lib.so -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/custom_ops
2025-03-21T20:25:15.7754051Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/export
2025-03-21T20:25:15.7755172Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/export/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/export
2025-03-21T20:25:15.7756627Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/export/builder.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/export
2025-03-21T20:25:15.7758138Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/export/export_passes.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/export
2025-03-21T20:25:15.7759643Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/export/partitioner_lib.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/export
2025-03-21T20:25:15.7761185Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/export/quantizer_lib.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/export
2025-03-21T20:25:15.7762666Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/export/test_export_passes.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/export
2025-03-21T20:25:15.7763781Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/modules
2025-03-21T20:25:15.7765065Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/modules/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/modules
2025-03-21T20:25:15.7766686Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/modules/_position_embeddings.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/modules
2025-03-21T20:25:15.7768230Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/modules/attention.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/modules
2025-03-21T20:25:15.7769798Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/modules/kv_cache.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/modules
2025-03-21T20:25:15.7770935Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/modules/test
2025-03-21T20:25:15.7772057Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/modules/test/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/modules/test
2025-03-21T20:25:15.7773656Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/modules/test/test_attention.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/modules/test
2025-03-21T20:25:15.7775285Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/modules/test/test_kv_cache.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/modules/test
2025-03-21T20:25:15.7777013Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/modules/test/test_position_embeddings.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/modules/test
2025-03-21T20:25:15.7778278Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/tokenizer
2025-03-21T20:25:15.7779371Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizer/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizer
2025-03-21T20:25:15.7780897Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizer/hf_tokenizer.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizer
2025-03-21T20:25:15.7782475Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizer/tokenizer.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizer
2025-03-21T20:25:15.7784008Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizer/utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizer
2025-03-21T20:25:15.7785163Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/tokenizer/test
2025-03-21T20:25:15.7786319Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizer/test/test_tokenizer.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizer/test
2025-03-21T20:25:15.7787503Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/tokenizers
2025-03-21T20:25:15.7788656Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/setup.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizers
2025-03-21T20:25:15.7789876Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/tokenizers/pytorch_tokenizers
2025-03-21T20:25:15.7791251Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/pytorch_tokenizers/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizers/pytorch_tokenizers
2025-03-21T20:25:15.7793201Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/pytorch_tokenizers/hf_tokenizer.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizers/pytorch_tokenizers
2025-03-21T20:25:15.7795099Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/pytorch_tokenizers/llama2c.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizers/pytorch_tokenizers
2025-03-21T20:25:15.7797082Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/pytorch_tokenizers/tiktoken.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizers/pytorch_tokenizers
2025-03-21T20:25:15.7798614Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/tokenizers/pytorch_tokenizers/tools
2025-03-21T20:25:15.7799715Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/tokenizers/pytorch_tokenizers/tools/llama2c
2025-03-21T20:25:15.7801483Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/pytorch_tokenizers/tools/llama2c/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizers/pytorch_tokenizers/tools/llama2c
2025-03-21T20:25:15.7803725Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/pytorch_tokenizers/tools/llama2c/convert.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizers/pytorch_tokenizers/tools/llama2c
2025-03-21T20:25:15.7805250Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/tokenizers/third-party
2025-03-21T20:25:15.7806219Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/tokenizers/third-party/abseil-cpp
2025-03-21T20:25:15.7807693Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/abseil-cpp/conanfile.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizers/third-party/abseil-cpp
2025-03-21T20:25:15.7809774Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/abseil-cpp/create_lts.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizers/third-party/abseil-cpp
2025-03-21T20:25:15.7811314Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/tokenizers/third-party/abseil-cpp/absl
2025-03-21T20:25:15.7812423Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/tokenizers/third-party/abseil-cpp/absl/copts
2025-03-21T20:25:15.7814061Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/abseil-cpp/absl/copts/copts.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizers/third-party/abseil-cpp/absl/copts
2025-03-21T20:25:15.7816307Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/abseil-cpp/absl/copts/generate_copts.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizers/third-party/abseil-cpp/absl/copts
2025-03-21T20:25:15.7818629Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/abseil-cpp/absl/abseil.podspec.gen.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizers/third-party/abseil-cpp/absl
2025-03-21T20:25:15.7820196Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/tokenizers/third-party/json
2025-03-21T20:25:15.7822981Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/tokenizers/third-party/json/docs
2025-03-21T20:25:15.7824219Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/tokenizers/third-party/json/docs/mkdocs
2025-03-21T20:25:15.7825256Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/tokenizers/third-party/json/docs/mkdocs/scripts
2025-03-21T20:25:15.7826929Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/json/docs/mkdocs/scripts/check_structure.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizers/third-party/json/docs/mkdocs/scripts
2025-03-21T20:25:15.7828693Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/tokenizers/third-party/json/tests
2025-03-21T20:25:15.7829626Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/tokenizers/third-party/json/tests/thirdparty
2025-03-21T20:25:15.7830786Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/tokenizers/third-party/json/tests/thirdparty/imapdl
2025-03-21T20:25:15.7832856Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/json/tests/thirdparty/imapdl/filterbr.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizers/third-party/json/tests/thirdparty/imapdl
2025-03-21T20:25:15.7834685Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/tokenizers/third-party/json/tools
2025-03-21T20:25:15.7835715Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/tokenizers/third-party/json/tools/amalgamate
2025-03-21T20:25:15.7837393Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/json/tools/amalgamate/amalgamate.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizers/third-party/json/tools/amalgamate
2025-03-21T20:25:15.7839204Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/tokenizers/third-party/json/tools/gdb_pretty_printer
2025-03-21T20:25:15.7841079Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/json/tools/gdb_pretty_printer/nlohmann-json.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizers/third-party/json/tools/gdb_pretty_printer
2025-03-21T20:25:15.7842840Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/tokenizers/third-party/json/tools/generate_natvis
2025-03-21T20:25:15.7844573Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/json/tools/generate_natvis/generate_natvis.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizers/third-party/json/tools/generate_natvis
2025-03-21T20:25:15.7846304Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/tokenizers/third-party/json/tools/serve_header
2025-03-21T20:25:15.7848035Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/json/tools/serve_header/serve_header.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizers/third-party/json/tools/serve_header
2025-03-21T20:25:15.7849709Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/tokenizers/third-party/re2
2025-03-21T20:25:15.7850658Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/tokenizers/third-party/re2/benchlog
2025-03-21T20:25:15.7852195Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/re2/benchlog/benchplot.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizers/third-party/re2/benchlog
2025-03-21T20:25:15.7853720Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/tokenizers/third-party/re2/python
2025-03-21T20:25:15.7855217Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/re2/python/re2.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizers/third-party/re2/python
2025-03-21T20:25:15.7857239Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/re2/python/re2_test.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizers/third-party/re2/python
2025-03-21T20:25:15.7859295Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/re2/python/setup.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizers/third-party/re2/python
2025-03-21T20:25:15.7860821Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/tokenizers/third-party/re2/python/toolchains
2025-03-21T20:25:15.7862498Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/re2/python/toolchains/generate.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizers/third-party/re2/python/toolchains
2025-03-21T20:25:15.7864140Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/tokenizers/third-party/re2/re2
2025-03-21T20:25:15.7865871Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/re2/re2/make_unicode_casefold.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizers/third-party/re2/re2
2025-03-21T20:25:15.7868046Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/re2/re2/make_unicode_groups.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizers/third-party/re2/re2
2025-03-21T20:25:15.7870066Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/re2/re2/unicode.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizers/third-party/re2/re2
2025-03-21T20:25:15.7871599Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/tokenizers/third-party/sentencepiece
2025-03-21T20:25:15.7872693Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/tokenizers/third-party/sentencepiece/python
2025-03-21T20:25:15.7874411Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/sentencepiece/python/setup.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizers/third-party/sentencepiece/python
2025-03-21T20:25:15.7876180Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/tokenizers/third-party/sentencepiece/python/test
2025-03-21T20:25:15.7877995Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/sentencepiece/python/test/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizers/third-party/sentencepiece/python/test
2025-03-21T20:25:15.7880490Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/sentencepiece/python/test/sentencepiece_test.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizers/third-party/sentencepiece/python/test
2025-03-21T20:25:15.7882370Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/tokenizers/third-party/sentencepiece/python/src
2025-03-21T20:25:15.7883712Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/tokenizers/third-party/sentencepiece/python/src/sentencepiece
2025-03-21T20:25:15.7885780Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/sentencepiece/python/src/sentencepiece/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizers/third-party/sentencepiece/python/src/sentencepiece
2025-03-21T20:25:15.7888524Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/sentencepiece/python/src/sentencepiece/_version.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizers/third-party/sentencepiece/python/src/sentencepiece
2025-03-21T20:25:15.7891521Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/sentencepiece/python/src/sentencepiece/sentencepiece_model_pb2.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizers/third-party/sentencepiece/python/src/sentencepiece
2025-03-21T20:25:15.7894361Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/third-party/sentencepiece/python/src/sentencepiece/sentencepiece_pb2.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizers/third-party/sentencepiece/python/src/sentencepiece
2025-03-21T20:25:15.7896435Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/tokenizers/tools
2025-03-21T20:25:15.7897331Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/extension/llm/tokenizers/tools/llama2c
2025-03-21T20:25:15.7898846Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/extension/llm/tokenizers/tools/llama2c/convert.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/extension/llm/tokenizers/tools/llama2c
2025-03-21T20:25:15.7900135Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/kernels
2025-03-21T20:25:15.7900727Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/kernels/quantized
2025-03-21T20:25:15.7901886Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/kernels/quantized/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/kernels/quantized
2025-03-21T20:25:15.7903018Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/kernels/quantized/test
2025-03-21T20:25:15.7909740Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/kernels/quantized/test/test_out_variants.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/kernels/quantized/test
2025-03-21T20:25:15.7911613Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/kernels/quantized/test/test_quant_dequant_per_token.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/kernels/quantized/test
2025-03-21T20:25:15.7913214Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/kernels/quantized/test/supported_features_def.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/kernels/quantized/test
2025-03-21T20:25:15.7914762Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/kernels/quantized/quantized.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/kernels/quantized
2025-03-21T20:25:15.7916239Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/kernels/quantized/libquantized_ops_aot_lib.so -> pip-out/bdist.linux-x86_64/wheel/./executorch/kernels/quantized
2025-03-21T20:25:15.7917432Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/devtools
2025-03-21T20:25:15.7918406Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools
2025-03-21T20:25:15.7919407Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/devtools/backend_debug
2025-03-21T20:25:15.7920509Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/backend_debug/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/backend_debug
2025-03-21T20:25:15.7922113Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/backend_debug/delegation_info.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/backend_debug
2025-03-21T20:25:15.7923372Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/devtools/backend_debug/tests
2025-03-21T20:25:15.7924695Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/backend_debug/tests/test_delegation_info.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/backend_debug/tests
2025-03-21T20:25:15.7925929Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/devtools/bundled_program
2025-03-21T20:25:15.7926636Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/devtools/bundled_program/schema
2025-03-21T20:25:15.7927452Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/devtools/bundled_program/schema/test
2025-03-21T20:25:15.7928796Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/schema/test/test_schema.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/bundled_program/schema/test
2025-03-21T20:25:15.7930826Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/schema/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/bundled_program/schema
2025-03-21T20:25:15.7932771Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/schema/bundled_program_schema.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/bundled_program/schema
2025-03-21T20:25:15.7934639Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/schema/bundled_program_schema.fbs -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/bundled_program/schema
2025-03-21T20:25:15.7936442Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/schema/scalar_type.fbs -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/bundled_program/schema
2025-03-21T20:25:15.7937705Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/devtools/bundled_program/serialize
2025-03-21T20:25:15.7938564Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/devtools/bundled_program/serialize/test
2025-03-21T20:25:15.7940151Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/serialize/test/test_serialize.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/bundled_program/serialize/test
2025-03-21T20:25:15.7942218Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/serialize/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/bundled_program/serialize
2025-03-21T20:25:15.7944093Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/serialize/bundled_program_schema.fbs -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/bundled_program/serialize
2025-03-21T20:25:15.7946000Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/serialize/scalar_type.fbs -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/bundled_program/serialize
2025-03-21T20:25:15.7947367Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/devtools/bundled_program/test
2025-03-21T20:25:15.7948691Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/test/test_bundle_data.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/bundled_program/test
2025-03-21T20:25:15.7950449Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/test/test_config.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/bundled_program/test
2025-03-21T20:25:15.7952226Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/test/test_end2end.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/bundled_program/test
2025-03-21T20:25:15.7953489Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/devtools/bundled_program/util
2025-03-21T20:25:15.7954751Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/util/test_util.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/bundled_program/util
2025-03-21T20:25:15.7956399Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/config.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/bundled_program
2025-03-21T20:25:15.7958065Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/core.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/bundled_program
2025-03-21T20:25:15.7959569Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/bundled_program/version.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/bundled_program
2025-03-21T20:25:15.7960735Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/devtools/debug_format
2025-03-21T20:25:15.7961818Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/debug_format/base_schema.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/debug_format
2025-03-21T20:25:15.7963318Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/debug_format/et_schema.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/debug_format
2025-03-21T20:25:15.7964380Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/devtools/etdump
2025-03-21T20:25:15.7965488Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/etdump/schema_flatcc.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/etdump
2025-03-21T20:25:15.7967013Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/etdump/serialize.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/etdump
2025-03-21T20:25:15.7968212Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/devtools/etdump/tests
2025-03-21T20:25:15.7969557Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/etdump/tests/serialize_test.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/etdump/tests
2025-03-21T20:25:15.7971125Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/etdump/etdump_schema_flatcc.fbs -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/etdump
2025-03-21T20:25:15.7972714Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/etdump/scalar_type.fbs -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/etdump
2025-03-21T20:25:15.7973871Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/devtools/etrecord
2025-03-21T20:25:15.7974910Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/etrecord/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/etrecord
2025-03-21T20:25:15.7976444Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/etrecord/_etrecord.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/etrecord
2025-03-21T20:25:15.7977510Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/devtools/etrecord/tests
2025-03-21T20:25:15.7978808Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/etrecord/tests/etrecord_test.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/etrecord/tests
2025-03-21T20:25:15.7979922Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/devtools/inspector
2025-03-21T20:25:15.7980923Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/inspector/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/inspector
2025-03-21T20:25:15.7982467Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/inspector/_inspector.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/inspector
2025-03-21T20:25:15.7983972Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/inspector/_inspector_utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/inspector
2025-03-21T20:25:15.7985556Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/inspector/inspector_cli.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/inspector
2025-03-21T20:25:15.7986758Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/devtools/inspector/tests
2025-03-21T20:25:15.7997995Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/inspector/tests/event_blocks_test.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/inspector/tests
2025-03-21T20:25:15.8000813Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/inspector/tests/inspector_test.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/inspector/tests
2025-03-21T20:25:15.8003530Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/inspector/tests/inspector_utils_test.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/inspector/tests
2025-03-21T20:25:15.8005511Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/devtools/size_analysis_tool
2025-03-21T20:25:15.8007467Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/size_analysis_tool/size_analysis_tool.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/size_analysis_tool
2025-03-21T20:25:15.8010319Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/size_analysis_tool/size_analysis_tool_test.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/size_analysis_tool
2025-03-21T20:25:15.8012278Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/devtools/visualization
2025-03-21T20:25:15.8014104Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/visualization/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/visualization
2025-03-21T20:25:15.8016700Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/visualization/visualization_utils.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/visualization
2025-03-21T20:25:15.8019467Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/devtools/visualization/visualization_utils_test.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/devtools/visualization
2025-03-21T20:25:15.8021321Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/runtime
2025-03-21T20:25:15.8022704Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/runtime/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/runtime
2025-03-21T20:25:15.8024154Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/runtime/test
2025-03-21T20:25:15.8025884Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/runtime/test/test_runtime.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/runtime/test
2025-03-21T20:25:15.8027562Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/runtime/kernel
2025-03-21T20:25:15.8028710Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/runtime/kernel/test
2025-03-21T20:25:15.8030461Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/runtime/kernel/test/functions.yaml -> pip-out/bdist.linux-x86_64/wheel/./executorch/runtime/kernel/test
2025-03-21T20:25:15.8032136Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/util
2025-03-21T20:25:15.8033853Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/util/activation_memory_profiler.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/util
2025-03-21T20:25:15.8035885Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/util/collect_env.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/util
2025-03-21T20:25:15.8037838Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/util/python_profiler.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/util
2025-03-21T20:25:15.8039279Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/schema
2025-03-21T20:25:15.8040658Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/schema/program.fbs -> pip-out/bdist.linux-x86_64/wheel/./executorch/schema
2025-03-21T20:25:15.8042606Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/schema/scalar_type.fbs -> pip-out/bdist.linux-x86_64/wheel/./executorch/schema
2025-03-21T20:25:15.8044439Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/version.py -> pip-out/bdist.linux-x86_64/wheel/./executorch
2025-03-21T20:25:15.8045741Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/share
2025-03-21T20:25:15.8046628Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/share/cmake
2025-03-21T20:25:15.8048277Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/share/cmake/executorch-config.cmake -> pip-out/bdist.linux-x86_64/wheel/./executorch/share/cmake
2025-03-21T20:25:15.8050024Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/include
2025-03-21T20:25:15.8050997Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/include/executorch
2025-03-21T20:25:15.8052061Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/include/executorch/runtime
2025-03-21T20:25:15.8053262Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/include/executorch/runtime/core
2025-03-21T20:25:15.8055289Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/array_ref.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core
2025-03-21T20:25:15.8058116Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/data_loader.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core
2025-03-21T20:25:15.8060968Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/defines.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core
2025-03-21T20:25:15.8063774Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/error.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core
2025-03-21T20:25:15.8066566Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/evalue.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core
2025-03-21T20:25:15.8069366Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/event_tracer.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core
2025-03-21T20:25:15.8072258Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/event_tracer_hooks.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core
2025-03-21T20:25:15.8075491Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/event_tracer_hooks_delegate.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core
2025-03-21T20:25:15.8079013Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/freeable_buffer.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core
2025-03-21T20:25:15.8082038Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/hierarchical_allocator.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core
2025-03-21T20:25:15.8085059Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/memory_allocator.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core
2025-03-21T20:25:15.8087951Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/named_data_map.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core
2025-03-21T20:25:15.8090895Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/result.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core
2025-03-21T20:25:15.8093662Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/span.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core
2025-03-21T20:25:15.8096400Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/tag.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core
2025-03-21T20:25:15.8099197Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/tensor_layout.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core
2025-03-21T20:25:15.8102157Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/tensor_shape_dynamism.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core
2025-03-21T20:25:15.8104388Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/include/executorch/runtime/core/exec_aten
2025-03-21T20:25:15.8106634Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/exec_aten/exec_aten.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core/exec_aten
2025-03-21T20:25:15.8109036Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/include/executorch/runtime/core/exec_aten/testing_util
2025-03-21T20:25:15.8111720Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/exec_aten/testing_util/tensor_factory.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core/exec_aten/testing_util
2025-03-21T20:25:15.8115381Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/exec_aten/testing_util/tensor_util.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core/exec_aten/testing_util
2025-03-21T20:25:15.8117967Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/include/executorch/runtime/core/exec_aten/util
2025-03-21T20:25:15.8120424Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/exec_aten/util/dim_order_util.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core/exec_aten/util
2025-03-21T20:25:15.8123824Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/exec_aten/util/scalar_type_util.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core/exec_aten/util
2025-03-21T20:25:15.8127283Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/exec_aten/util/tensor_dimension_limit.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core/exec_aten/util
2025-03-21T20:25:15.8130922Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/exec_aten/util/tensor_shape_to_c_string.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core/exec_aten/util
2025-03-21T20:25:15.8133038Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/exec_aten/util/tensor_util.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core/exec_aten/util
2025-03-21T20:25:15.8134341Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/include/executorch/runtime/core/portable_type
2025-03-21T20:25:15.8135627Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/bfloat16.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core/portable_type
2025-03-21T20:25:15.8137400Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/bfloat16_math.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core/portable_type
2025-03-21T20:25:15.8139176Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/bits_types.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core/portable_type
2025-03-21T20:25:15.8140923Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/complex.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core/portable_type
2025-03-21T20:25:15.8142656Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/device.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core/portable_type
2025-03-21T20:25:15.8144391Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/half.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core/portable_type
2025-03-21T20:25:15.8146123Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/optional.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core/portable_type
2025-03-21T20:25:15.8147878Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/qint_types.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core/portable_type
2025-03-21T20:25:15.8149619Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/scalar.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core/portable_type
2025-03-21T20:25:15.8151375Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/scalar_type.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core/portable_type
2025-03-21T20:25:15.8153148Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/string_view.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core/portable_type
2025-03-21T20:25:15.8154906Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/tensor.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core/portable_type
2025-03-21T20:25:15.8156658Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/tensor_impl.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core/portable_type
2025-03-21T20:25:15.8158439Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/tensor_options.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core/portable_type
2025-03-21T20:25:15.8159763Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/include/executorch/runtime/core/portable_type/c10
2025-03-21T20:25:15.8160647Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/include/executorch/runtime/core/portable_type/c10/c10
2025-03-21T20:25:15.8161783Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/include/executorch/runtime/core/portable_type/c10/c10/macros
2025-03-21T20:25:15.8163284Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/c10/c10/macros/Export.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core/portable_type/c10/c10/macros
2025-03-21T20:25:15.8165305Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/c10/c10/macros/Macros.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core/portable_type/c10/c10/macros
2025-03-21T20:25:15.8166784Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/include/executorch/runtime/core/portable_type/c10/c10/util
2025-03-21T20:25:15.8168283Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/c10/c10/util/BFloat16-inl.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core/portable_type/c10/c10/util
2025-03-21T20:25:15.8170403Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/c10/c10/util/BFloat16-math.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core/portable_type/c10/c10/util
2025-03-21T20:25:15.8172820Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/c10/c10/util/BFloat16.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core/portable_type/c10/c10/util
2025-03-21T20:25:15.8176243Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/c10/c10/util/Half-inl.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core/portable_type/c10/c10/util
2025-03-21T20:25:15.8178539Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/c10/c10/util/Half.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core/portable_type/c10/c10/util
2025-03-21T20:25:15.8180566Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/c10/c10/util/TypeSafeSignMath.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core/portable_type/c10/c10/util
2025-03-21T20:25:15.8182603Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/c10/c10/util/bit_cast.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core/portable_type/c10/c10/util
2025-03-21T20:25:15.8184631Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/c10/c10/util/floating_point_utils.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core/portable_type/c10/c10/util
2025-03-21T20:25:15.8186665Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/core/portable_type/c10/c10/util/irange.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/core/portable_type/c10/c10/util
2025-03-21T20:25:15.8188007Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/include/executorch/runtime/kernel
2025-03-21T20:25:15.8189170Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/kernel/kernel_includes.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/kernel
2025-03-21T20:25:15.8190813Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/kernel/kernel_runtime_context.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/kernel
2025-03-21T20:25:15.8192450Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/kernel/operator_registry.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/kernel
2025-03-21T20:25:15.8194224Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/kernel/thread_parallel_interface.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/kernel
2025-03-21T20:25:15.8195510Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/include/executorch/runtime/kernel/test
2025-03-21T20:25:15.8196709Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/kernel/test/test_util.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/kernel/test
2025-03-21T20:25:15.8438060Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/include/executorch/runtime/platform
2025-03-21T20:25:15.8440121Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/platform/abort.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/platform
2025-03-21T20:25:15.8442491Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/platform/assert.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/platform
2025-03-21T20:25:15.8444152Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/platform/clock.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/platform
2025-03-21T20:25:15.8445737Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/platform/compat_unistd.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/platform
2025-03-21T20:25:15.8447345Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/platform/compiler.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/platform
2025-03-21T20:25:15.8448906Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/platform/log.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/platform
2025-03-21T20:25:15.8450561Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/platform/platform.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/platform
2025-03-21T20:25:15.8452324Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/platform/profiler.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/platform
2025-03-21T20:25:15.8454841Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/platform/runtime.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/platform
2025-03-21T20:25:15.8456706Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/platform/system.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/platform
2025-03-21T20:25:15.8459454Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/platform/types.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/platform
2025-03-21T20:25:15.8461356Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/include/executorch/runtime/platform/test
2025-03-21T20:25:15.8462635Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/runtime/platform/test/stub_platform.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/runtime/platform/test
2025-03-21T20:25:15.8464011Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/include/executorch/extension
2025-03-21T20:25:15.8465313Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/include/executorch/extension/kernel_util
2025-03-21T20:25:15.8466898Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/extension/kernel_util/make_boxed_from_unboxed_functor.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/extension/kernel_util
2025-03-21T20:25:15.8469871Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/extension/kernel_util/meta_programming.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/extension/kernel_util
2025-03-21T20:25:15.8472593Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/extension/kernel_util/type_list.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/extension/kernel_util
2025-03-21T20:25:15.8474476Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/include/executorch/extension/tensor
2025-03-21T20:25:15.8476324Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/extension/tensor/tensor.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/extension/tensor
2025-03-21T20:25:15.8479343Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/extension/tensor/tensor_accessor.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/extension/tensor
2025-03-21T20:25:15.8481607Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/extension/tensor/tensor_ptr.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/extension/tensor
2025-03-21T20:25:15.8483964Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/extension/tensor/tensor_ptr_maker.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/extension/tensor
2025-03-21T20:25:15.8485983Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/include/executorch/extension/threadpool
2025-03-21T20:25:15.8487248Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/extension/threadpool/cpuinfo_utils.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/extension/threadpool
2025-03-21T20:25:15.8489136Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/extension/threadpool/threadpool.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/extension/threadpool
2025-03-21T20:25:15.8491071Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/include/executorch/extension/threadpool/threadpool_guard.h -> pip-out/bdist.linux-x86_64/wheel/./executorch/include/executorch/extension/threadpool
2025-03-21T20:25:15.8492197Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/data
2025-03-21T20:25:15.8492863Z   creating pip-out/bdist.linux-x86_64/wheel/executorch/data/bin
2025-03-21T20:25:15.8493632Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/data/bin/flatc -> pip-out/bdist.linux-x86_64/wheel/./executorch/data/bin
2025-03-21T20:25:15.8494666Z   copying pip-out/lib.linux-x86_64-cpython-310/executorch/data/bin/__init__.py -> pip-out/bdist.linux-x86_64/wheel/./executorch/data/bin
2025-03-21T20:25:15.8495502Z   running install_egg_info
2025-03-21T20:25:15.8496071Z   Copying executorch.egg-info to pip-out/bdist.linux-x86_64/wheel/./executorch-0.6.0a0+be92d7d-py3.10.egg-info
2025-03-21T20:25:15.8496668Z   running install_scripts
2025-03-21T20:25:15.8497131Z   creating pip-out/bdist.linux-x86_64/wheel/executorch-0.6.0a0+be92d7d.dist-info/WHEEL
2025-03-21T20:25:15.8498238Z   creating '/tmp/pip-wheel-owuqeinv/.tmp-gi8iedtb/executorch-0.6.0a0+be92d7d-cp310-cp310-linux_x86_64.whl' and adding 'pip-out/bdist.linux-x86_64/wheel' to it
2025-03-21T20:25:15.8499056Z   adding 'executorch/version.py'
2025-03-21T20:25:15.8499465Z   adding 'executorch/backends/apple/coreml/executorchcoreml.pyi'
2025-03-21T20:25:15.8499986Z   adding 'executorch/backends/apple/coreml/compiler/__init__.py'
2025-03-21T20:25:15.8500559Z   adding 'executorch/backends/apple/coreml/compiler/coreml_preprocess.py'
2025-03-21T20:25:15.8501293Z   adding 'executorch/backends/apple/coreml/partition/__init__.py'
2025-03-21T20:25:15.8501873Z   adding 'executorch/backends/apple/coreml/partition/coreml_partitioner.py'
2025-03-21T20:25:15.8502441Z   adding 'executorch/backends/apple/coreml/quantizer/__init__.py'
2025-03-21T20:25:15.8503003Z   adding 'executorch/backends/apple/coreml/quantizer/coreml_quantizer.py'
2025-03-21T20:25:15.8503597Z   adding 'executorch/backends/apple/coreml/runtime/inmemoryfs/setup.py'
2025-03-21T20:25:15.8504230Z   adding 'executorch/backends/apple/coreml/runtime/test/export_stateful_model.py'
2025-03-21T20:25:15.8505261Z   adding 'executorch/backends/apple/coreml/test/test_coreml_partitioner.py'
2025-03-21T20:25:15.8505874Z   adding 'executorch/backends/apple/coreml/test/test_coreml_quantizer.py'
2025-03-21T20:25:15.8506371Z   adding 'executorch/backends/apple/mps/__init__.py'
2025-03-21T20:25:15.8506816Z   adding 'executorch/backends/apple/mps/mps_preprocess.py'
2025-03-21T20:25:15.8507300Z   adding 'executorch/backends/apple/mps/operators/__init__.py'
2025-03-21T20:25:15.8507949Z   adding 'executorch/backends/apple/mps/operators/activation_ops.py'
2025-03-21T20:25:15.8508487Z   adding 'executorch/backends/apple/mps/operators/binary_ops.py'
2025-03-21T20:25:15.8508985Z   adding 'executorch/backends/apple/mps/operators/clamp_ops.py'
2025-03-21T20:25:15.8509507Z   adding 'executorch/backends/apple/mps/operators/constant_ops.py'
2025-03-21T20:25:15.8510061Z   adding 'executorch/backends/apple/mps/operators/convolution_ops.py'
2025-03-21T20:25:15.8510616Z   adding 'executorch/backends/apple/mps/operators/indexing_ops.py'
2025-03-21T20:25:15.8511339Z   adding 'executorch/backends/apple/mps/operators/linear_algebra_ops.py'
2025-03-21T20:25:15.8511931Z   adding 'executorch/backends/apple/mps/operators/node_visitor.py'
2025-03-21T20:25:15.8512485Z   adding 'executorch/backends/apple/mps/operators/normalization_ops.py'
2025-03-21T20:25:15.8513030Z   adding 'executorch/backends/apple/mps/operators/op_clone.py'
2025-03-21T20:25:15.8513644Z   adding 'executorch/backends/apple/mps/operators/op_getitem.py'
2025-03-21T20:25:15.8514203Z   adding 'executorch/backends/apple/mps/operators/op_quant_dequant.py'
2025-03-21T20:25:15.8514760Z   adding 'executorch/backends/apple/mps/operators/op_skip_ops.py'
2025-03-21T20:25:15.8515271Z   adding 'executorch/backends/apple/mps/operators/pad_ops.py'
2025-03-21T20:25:15.8515774Z   adding 'executorch/backends/apple/mps/operators/pooling_ops.py'
2025-03-21T20:25:15.8516297Z   adding 'executorch/backends/apple/mps/operators/range_ops.py'
2025-03-21T20:25:15.8516823Z   adding 'executorch/backends/apple/mps/operators/reduce_ops.py'
2025-03-21T20:25:15.8517514Z   adding 'executorch/backends/apple/mps/operators/shape_ops.py'
2025-03-21T20:25:15.8518026Z   adding 'executorch/backends/apple/mps/operators/unary_ops.py'
2025-03-21T20:25:15.8518516Z   adding 'executorch/backends/apple/mps/partition/__init__.py'
2025-03-21T20:25:15.8519051Z   adding 'executorch/backends/apple/mps/partition/mps_partitioner.py'
2025-03-21T20:25:15.8519662Z   adding 'executorch/backends/apple/mps/serialization/mps_graph_schema.py'
2025-03-21T20:25:15.8790568Z   adding 'executorch/backends/apple/mps/serialization/mps_graph_serialize.py'
2025-03-21T20:25:15.8791629Z   adding 'executorch/backends/apple/mps/serialization/schema.fbs'
2025-03-21T20:25:15.8792522Z   adding 'executorch/backends/apple/mps/test/test_mps.py'
2025-03-21T20:25:15.8793367Z   adding 'executorch/backends/apple/mps/test/test_mps_binary_ops.py'
2025-03-21T20:25:15.8794345Z   adding 'executorch/backends/apple/mps/test/test_mps_indexing_ops.py'
2025-03-21T20:25:15.8795319Z   adding 'executorch/backends/apple/mps/test/test_mps_linear.py'
2025-03-21T20:25:15.8796234Z   adding 'executorch/backends/apple/mps/test/test_mps_models.py'
2025-03-21T20:25:15.8797138Z   adding 'executorch/backends/apple/mps/test/test_mps_unary_ops.py'
2025-03-21T20:25:15.8798068Z   adding 'executorch/backends/apple/mps/test/test_mps_utils.py'
2025-03-21T20:25:15.8798902Z   adding 'executorch/backends/apple/mps/utils/mps_utils.py'
2025-03-21T20:25:15.8799749Z   adding 'executorch/backends/apple/mps/utils/quant_utils.py'
2025-03-21T20:25:15.8800494Z   adding 'executorch/backends/arm/arm_backend.py'
2025-03-21T20:25:15.8801177Z   adding 'executorch/backends/arm/arm_vela.py'
2025-03-21T20:25:15.8801852Z   adding 'executorch/backends/arm/ethosu_backend.py'
2025-03-21T20:25:15.8802608Z   adding 'executorch/backends/arm/ethosu_partitioner.py'
2025-03-21T20:25:15.8803365Z   adding 'executorch/backends/arm/process_node.py'
2025-03-21T20:25:15.8804046Z   adding 'executorch/backends/arm/tosa_backend.py'
2025-03-21T20:25:15.8805084Z   adding 'executorch/backends/arm/tosa_mapping.py'
2025-03-21T20:25:15.8805803Z   adding 'executorch/backends/arm/tosa_partitioner.py'
2025-03-21T20:25:15.8806553Z   adding 'executorch/backends/arm/tosa_quant_utils.py'
2025-03-21T20:25:15.8807264Z   adding 'executorch/backends/arm/tosa_specification.py'
2025-03-21T20:25:15.8808002Z   adding 'executorch/backends/arm/tosa_utils.py'
2025-03-21T20:25:15.8808738Z   adding 'executorch/backends/arm/_passes/_debug_passes.py'
2025-03-21T20:25:15.8809830Z   adding 'executorch/backends/arm/_passes/annotate_channels_last_dim_order_pass.py'
2025-03-21T20:25:15.8810941Z   adding 'executorch/backends/arm/_passes/annotate_decomposed_matmul.py'
2025-03-21T20:25:15.8811879Z   adding 'executorch/backends/arm/_passes/arm_pass_manager.py'
2025-03-21T20:25:15.8812739Z   adding 'executorch/backends/arm/_passes/arm_pass_utils.py'
2025-03-21T20:25:15.8813556Z   adding 'executorch/backends/arm/_passes/cast_int64_pass.py'
2025-03-21T20:25:15.8814522Z   adding 'executorch/backends/arm/_passes/conv1d_unsqueeze_pass.py'
2025-03-21T20:25:15.8815566Z   adding 'executorch/backends/arm/_passes/convert_any_default_dim_dims_pass.py'
2025-03-21T20:25:15.8816659Z   adding 'executorch/backends/arm/_passes/convert_expand_copy_to_repeat.py'
2025-03-21T20:25:15.8817747Z   adding 'executorch/backends/arm/_passes/convert_full_like_to_full_pass.py'
2025-03-21T20:25:15.8818741Z   adding 'executorch/backends/arm/_passes/convert_minmax_pass.py'
2025-03-21T20:25:15.8819688Z   adding 'executorch/backends/arm/_passes/convert_split_to_slice.py'
2025-03-21T20:25:15.8820680Z   adding 'executorch/backends/arm/_passes/convert_squeezes_to_view.py'
2025-03-21T20:25:15.8821599Z   adding 'executorch/backends/arm/_passes/convert_to_clamp.py'
2025-03-21T20:25:15.8822539Z   adding 'executorch/backends/arm/_passes/decompose_batchnorm_pass.py'
2025-03-21T20:25:15.8823474Z   adding 'executorch/backends/arm/_passes/decompose_div_pass.py'
2025-03-21T20:25:15.8824414Z   adding 'executorch/backends/arm/_passes/decompose_layernorm_pass.py'
2025-03-21T20:25:15.8825397Z   adding 'executorch/backends/arm/_passes/decompose_linear_pass.py'
2025-03-21T20:25:15.8826360Z   adding 'executorch/backends/arm/_passes/decompose_meandim_pass.py'
2025-03-21T20:25:15.8827265Z   adding 'executorch/backends/arm/_passes/decompose_select.py'
2025-03-21T20:25:15.8828185Z   adding 'executorch/backends/arm/_passes/decompose_softmax_pass.py'
2025-03-21T20:25:15.8829206Z   adding 'executorch/backends/arm/_passes/decompose_softmax_unstable_pass.py'
2025-03-21T20:25:15.8830214Z   adding 'executorch/backends/arm/_passes/decompose_var_pass.py'
2025-03-21T20:25:15.8831224Z   adding 'executorch/backends/arm/_passes/fold_qdq_with_annotated_qparams_pass.py'
2025-03-21T20:25:15.8832550Z   adding 'executorch/backends/arm/_passes/fuse_batchnorm2d_pass.py'
2025-03-21T20:25:15.8833521Z   adding 'executorch/backends/arm/_passes/fuse_constant_ops_pass.py'
2025-03-21T20:25:15.8834523Z   adding 'executorch/backends/arm/_passes/fuse_quantized_activation_pass.py'
2025-03-21T20:25:15.8835540Z   adding 'executorch/backends/arm/_passes/insert_rescales_pass.py'
2025-03-21T20:25:15.8836418Z   adding 'executorch/backends/arm/_passes/insert_table_ops.py'
2025-03-21T20:25:15.8837409Z   adding 'executorch/backends/arm/_passes/keep_dims_false_to_squeeze_pass.py'
2025-03-21T20:25:15.8838402Z   adding 'executorch/backends/arm/_passes/match_arg_ranks_pass.py'
2025-03-21T20:25:15.8839390Z   adding 'executorch/backends/arm/_passes/meandim_to_averagepool_pass.py'
2025-03-21T20:25:15.8840332Z   adding 'executorch/backends/arm/_passes/mm_to_bmm_pass.py'
2025-03-21T20:25:15.8841180Z   adding 'executorch/backends/arm/_passes/remove_clone_pass.py'
2025-03-21T20:25:15.8842102Z   adding 'executorch/backends/arm/_passes/scalars_to_attribute_pass.py'
2025-03-21T20:25:15.8843096Z   adding 'executorch/backends/arm/_passes/size_adjust_conv2d_pass.py'
2025-03-21T20:25:15.8844122Z   adding 'executorch/backends/arm/_passes/unsqueeze_before_repeat_pass.py'
2025-03-21T20:25:15.8845516Z   adding 'executorch/backends/arm/_passes/unsqueeze_scalar_placeholders_pass.py'
2025-03-21T20:25:15.8846542Z   adding 'executorch/backends/arm/operator_support/__init__.py'
2025-03-21T20:25:15.8847500Z   adding 'executorch/backends/arm/operator_support/convolution_support.py'
2025-03-21T20:25:15.8848548Z   adding 'executorch/backends/arm/operator_support/minmax_support.py'
2025-03-21T20:25:15.8849655Z   adding 'executorch/backends/arm/operator_support/pool_2d_support.py'
2025-03-21T20:25:15.8850674Z   adding 'executorch/backends/arm/operator_support/reduce_sum_support.py'
2025-03-21T20:25:15.8851746Z   adding 'executorch/backends/arm/operator_support/right_shift_support.py'
2025-03-21T20:25:15.8852789Z   adding 'executorch/backends/arm/operator_support/slice_copy_support.py'
2025-03-21T20:25:15.8853827Z   adding 'executorch/backends/arm/operator_support/to_copy_support.py'
2025-03-21T20:25:15.8854913Z   adding 'executorch/backends/arm/operator_support/tosa_supported_operators.py'
2025-03-21T20:25:15.8855932Z   adding 'executorch/backends/arm/operators/__init__.py'
2025-03-21T20:25:15.8856743Z   adding 'executorch/backends/arm/operators/node_visitor.py'
2025-03-21T20:25:15.8857560Z   adding 'executorch/backends/arm/operators/op_abs.py'
2025-03-21T20:25:15.8858302Z   adding 'executorch/backends/arm/operators/op_add.py'
2025-03-21T20:25:15.8859047Z   adding 'executorch/backends/arm/operators/op_amax.py'
2025-03-21T20:25:15.8859821Z   adding 'executorch/backends/arm/operators/op_amin.py'
2025-03-21T20:25:15.8860574Z   adding 'executorch/backends/arm/operators/op_any.py'
2025-03-21T20:25:15.8861379Z   adding 'executorch/backends/arm/operators/op_avg_pool2d.py'
2025-03-21T20:25:15.8862167Z   adding 'executorch/backends/arm/operators/op_bmm.py'
2025-03-21T20:25:15.8862907Z   adding 'executorch/backends/arm/operators/op_cat.py'
2025-03-21T20:25:15.8863676Z   adding 'executorch/backends/arm/operators/op_clamp.py'
2025-03-21T20:25:15.8864526Z   adding 'executorch/backends/arm/operators/op_constant_pad_nd.py'
2025-03-21T20:25:15.8865429Z   adding 'executorch/backends/arm/operators/op_conv2d.py'
2025-03-21T20:25:15.8866200Z   adding 'executorch/backends/arm/operators/op_eq.py'
2025-03-21T20:25:15.8866916Z   adding 'executorch/backends/arm/operators/op_exp.py'
2025-03-21T20:25:15.8867673Z   adding 'executorch/backends/arm/operators/op_full.py'
2025-03-21T20:25:15.8868413Z   adding 'executorch/backends/arm/operators/op_ge.py'
2025-03-21T20:25:15.8869168Z   adding 'executorch/backends/arm/operators/op_get_item.py'
2025-03-21T20:25:15.8869947Z   adding 'executorch/backends/arm/operators/op_gt.py'
2025-03-21T20:25:15.8870656Z   adding 'executorch/backends/arm/operators/op_le.py'
2025-03-21T20:25:15.8871401Z   adding 'executorch/backends/arm/operators/op_log.py'
2025-03-21T20:25:15.8872127Z   adding 'executorch/backends/arm/operators/op_lt.py'
2025-03-21T20:25:15.8872909Z   adding 'executorch/backends/arm/operators/op_max_pool2d.py'
2025-03-21T20:25:15.8873739Z   adding 'executorch/backends/arm/operators/op_maximum.py'
2025-03-21T20:25:15.8874577Z   adding 'executorch/backends/arm/operators/op_minimum.py'
2025-03-21T20:25:15.8875369Z   adding 'executorch/backends/arm/operators/op_mul.py'
2025-03-21T20:25:15.8876147Z   adding 'executorch/backends/arm/operators/op_permute.py'
2025-03-21T20:25:15.8876967Z   adding 'executorch/backends/arm/operators/op_reciprocal.py'
2025-03-21T20:25:15.8877801Z   adding 'executorch/backends/arm/operators/op_repeat.py'
2025-03-21T20:25:15.8878602Z   adding 'executorch/backends/arm/operators/op_rescale.py'
2025-03-21T20:25:15.8879407Z   adding 'executorch/backends/arm/operators/op_rshift.py'
2025-03-21T20:25:15.8880198Z   adding 'executorch/backends/arm/operators/op_rsqrt.py'
2025-03-21T20:25:15.8881000Z   adding 'executorch/backends/arm/operators/op_sigmoid.py'
2025-03-21T20:25:15.8881776Z   adding 'executorch/backends/arm/operators/op_slice.py'
2025-03-21T20:25:15.8882529Z   adding 'executorch/backends/arm/operators/op_sub.py'
2025-03-21T20:25:15.8883243Z   adding 'executorch/backends/arm/operators/op_sum.py'
2025-03-21T20:25:15.8884234Z   adding 'executorch/backends/arm/operators/op_table.py'
2025-03-21T20:25:15.8885012Z   adding 'executorch/backends/arm/operators/op_tanh.py'
2025-03-21T20:25:15.8885806Z   adding 'executorch/backends/arm/operators/op_to_copy.py'
2025-03-21T20:25:15.8886664Z   adding 'executorch/backends/arm/operators/op_to_dim_order_copy.py'
2025-03-21T20:25:15.8887570Z   adding 'executorch/backends/arm/operators/op_transpose.py'
2025-03-21T20:25:15.8888465Z   adding 'executorch/backends/arm/operators/op_upsample_nearest2d.py'
2025-03-21T20:25:15.8889456Z   adding 'executorch/backends/arm/operators/op_view.py'
2025-03-21T20:25:15.8890248Z   adding 'executorch/backends/arm/operators/ops_binary.py'
2025-03-21T20:25:15.8891053Z   adding 'executorch/backends/arm/operators/ops_unary.py'
2025-03-21T20:25:15.8891816Z   adding 'executorch/backends/arm/quantizer/__init__.py'
2025-03-21T20:25:15.8892611Z   adding 'executorch/backends/arm/quantizer/arm_quantizer.py'
2025-03-21T20:25:15.8893542Z   adding 'executorch/backends/arm/quantizer/arm_quantizer_utils.py'
2025-03-21T20:25:15.8894541Z   adding 'executorch/backends/arm/quantizer/quantization_annotator.py'
2025-03-21T20:25:15.8895530Z   adding 'executorch/backends/arm/quantizer/quantization_config.py'
2025-03-21T20:25:15.8896360Z   adding 'executorch/backends/arm/test/common.py'
2025-03-21T20:25:15.8897042Z   adding 'executorch/backends/arm/test/conftest.py'
2025-03-21T20:25:15.8897774Z   adding 'executorch/backends/arm/test/runner_utils.py'
2025-03-21T20:25:15.8898498Z   adding 'executorch/backends/arm/test/test_model.py'
2025-03-21T20:25:15.8899339Z   adding 'executorch/backends/arm/test/misc/test_custom_partition.py'
2025-03-21T20:25:15.8900281Z   adding 'executorch/backends/arm/test/misc/test_debug_feats.py'
2025-03-21T20:25:15.8901234Z   adding 'executorch/backends/arm/test/misc/test_dim_order_guards.py'
2025-03-21T20:25:15.8902160Z   adding 'executorch/backends/arm/test/misc/test_lifted_tensor.py'
2025-03-21T20:25:15.8903131Z   adding 'executorch/backends/arm/test/misc/test_model_evaluator.py'
2025-03-21T20:25:15.8904124Z   adding 'executorch/backends/arm/test/misc/test_multiple_delegates.py'
2025-03-21T20:25:15.9122106Z   adding 'executorch/backends/arm/test/misc/test_multiple_outputs.py'
2025-03-21T20:25:15.9123286Z   adding 'executorch/backends/arm/test/misc/test_partition_decomposed_quantized_ops.py'
2025-03-21T20:25:15.9124132Z   adding 'executorch/backends/arm/test/misc/test_tosa_spec.py'
2025-03-21T20:25:15.9124650Z   adding 'executorch/backends/arm/test/models/test_conformer.py'
2025-03-21T20:25:15.9125159Z   adding 'executorch/backends/arm/test/models/test_dl3_arm.py'
2025-03-21T20:25:15.9125628Z   adding 'executorch/backends/arm/test/models/test_llama.py'
2025-03-21T20:25:15.9126204Z   adding 'executorch/backends/arm/test/models/test_lstm_arm.py'
2025-03-21T20:25:15.9126891Z   adding 'executorch/backends/arm/test/models/test_mobilenet_v2_arm.py'
2025-03-21T20:25:15.9127787Z   adding 'executorch/backends/arm/test/models/test_nn_functional.py'
2025-03-21T20:25:15.9128712Z   adding 'executorch/backends/arm/test/models/test_nn_modules.py'
2025-03-21T20:25:15.9129693Z   adding 'executorch/backends/arm/test/models/test_torch_functions.py'
2025-03-21T20:25:15.9130609Z   adding 'executorch/backends/arm/test/models/test_w2l_arm.py'
2025-03-21T20:25:15.9131438Z   adding 'executorch/backends/arm/test/ops/test_abs.py'
2025-03-21T20:25:15.9132183Z   adding 'executorch/backends/arm/test/ops/test_add.py'
2025-03-21T20:25:15.9133143Z   adding 'executorch/backends/arm/test/ops/test_amax.py'
2025-03-21T20:25:15.9133916Z   adding 'executorch/backends/arm/test/ops/test_amin.py'
2025-03-21T20:25:15.9134654Z   adding 'executorch/backends/arm/test/ops/test_any.py'
2025-03-21T20:25:15.9135478Z   adding 'executorch/backends/arm/test/ops/test_avg_pool2d.py'
2025-03-21T20:25:15.9136343Z   adding 'executorch/backends/arm/test/ops/test_batch_norm.py'
2025-03-21T20:25:15.9137209Z   adding 'executorch/backends/arm/test/ops/test_bitwise.py'
2025-03-21T20:25:15.9138357Z   adding 'executorch/backends/arm/test/ops/test_bmm.py'
2025-03-21T20:25:15.9138940Z   adding 'executorch/backends/arm/test/ops/test_cat.py'
2025-03-21T20:25:15.9139704Z   adding 'executorch/backends/arm/test/ops/test_clamp.py'
2025-03-21T20:25:15.9140500Z   adding 'executorch/backends/arm/test/ops/test_clone.py'
2025-03-21T20:25:15.9141359Z   adding 'executorch/backends/arm/test/ops/test_constant_pad_nd.py'
2025-03-21T20:25:15.9142263Z   adding 'executorch/backends/arm/test/ops/test_conv1d.py'
2025-03-21T20:25:15.9143052Z   adding 'executorch/backends/arm/test/ops/test_conv2d.py'
2025-03-21T20:25:15.9143918Z   adding 'executorch/backends/arm/test/ops/test_conv_combos.py'
2025-03-21T20:25:15.9144833Z   adding 'executorch/backends/arm/test/ops/test_depthwise_conv.py'
2025-03-21T20:25:15.9145692Z   adding 'executorch/backends/arm/test/ops/test_div.py'
2025-03-21T20:25:15.9146463Z   adding 'executorch/backends/arm/test/ops/test_eq.py'
2025-03-21T20:25:15.9147068Z   adding 'executorch/backends/arm/test/ops/test_exp.py'
2025-03-21T20:25:15.9147526Z   adding 'executorch/backends/arm/test/ops/test_expand.py'
2025-03-21T20:25:15.9148309Z   adding 'executorch/backends/arm/test/ops/test_floor.py'
2025-03-21T20:25:15.9149102Z   adding 'executorch/backends/arm/test/ops/test_full.py'
2025-03-21T20:25:15.9149788Z   adding 'executorch/backends/arm/test/ops/test_ge.py'
2025-03-21T20:25:15.9150223Z   adding 'executorch/backends/arm/test/ops/test_gt.py'
2025-03-21T20:25:15.9150678Z   adding 'executorch/backends/arm/test/ops/test_hardsigmoid.py'
2025-03-21T20:25:15.9150877Z   adding 'executorch/backends/arm/test/ops/test_hardswish.py'
2025-03-21T20:25:15.9151169Z   adding 'executorch/backends/arm/test/ops/test_hardtanh.py'
2025-03-21T20:25:15.9151514Z   adding 'executorch/backends/arm/test/ops/test_layer_norm.py'
2025-03-21T20:25:15.9151784Z   adding 'executorch/backends/arm/test/ops/test_le.py'
2025-03-21T20:25:15.9152114Z   adding 'executorch/backends/arm/test/ops/test_linear.py'
2025-03-21T20:25:15.9152405Z   adding 'executorch/backends/arm/test/ops/test_log.py'
2025-03-21T20:25:15.9152720Z   adding 'executorch/backends/arm/test/ops/test_logical.py'
2025-03-21T20:25:15.9153052Z   adding 'executorch/backends/arm/test/ops/test_logsoftmax.py'
2025-03-21T20:25:15.9153233Z   adding 'executorch/backends/arm/test/ops/test_lt.py'
2025-03-21T20:25:15.9153431Z   adding 'executorch/backends/arm/test/ops/test_max_pool.py'
2025-03-21T20:25:15.9153610Z   adding 'executorch/backends/arm/test/ops/test_maximum.py'
2025-03-21T20:25:15.9153831Z   adding 'executorch/backends/arm/test/ops/test_mean_dim.py'
2025-03-21T20:25:15.9154129Z   adding 'executorch/backends/arm/test/ops/test_minimum.py'
2025-03-21T20:25:15.9154398Z   adding 'executorch/backends/arm/test/ops/test_mm.py'
2025-03-21T20:25:15.9154687Z   adding 'executorch/backends/arm/test/ops/test_mul.py'
2025-03-21T20:25:15.9155004Z   adding 'executorch/backends/arm/test/ops/test_permute.py'
2025-03-21T20:25:15.9155347Z   adding 'executorch/backends/arm/test/ops/test_reciprocal.py'
2025-03-21T20:25:15.9155654Z   adding 'executorch/backends/arm/test/ops/test_relu.py'
2025-03-21T20:25:15.9155951Z   adding 'executorch/backends/arm/test/ops/test_repeat.py'
2025-03-21T20:25:15.9156126Z   adding 'executorch/backends/arm/test/ops/test_rshift.py'
2025-03-21T20:25:15.9156299Z   adding 'executorch/backends/arm/test/ops/test_rsqrt.py'
2025-03-21T20:25:15.9156489Z   adding 'executorch/backends/arm/test/ops/test_scalars.py'
2025-03-21T20:25:15.9156662Z   adding 'executorch/backends/arm/test/ops/test_select.py'
2025-03-21T20:25:15.9156853Z   adding 'executorch/backends/arm/test/ops/test_sigmoid.py'
2025-03-21T20:25:15.9157053Z   adding 'executorch/backends/arm/test/ops/test_sigmoid_16bit.py'
2025-03-21T20:25:15.9157266Z   adding 'executorch/backends/arm/test/ops/test_sigmoid_32bit.py'
2025-03-21T20:25:15.9157469Z   adding 'executorch/backends/arm/test/ops/test_slice.py'
2025-03-21T20:25:15.9157766Z   adding 'executorch/backends/arm/test/ops/test_softmax.py'
2025-03-21T20:25:15.9158071Z   adding 'executorch/backends/arm/test/ops/test_split.py'
2025-03-21T20:25:15.9158598Z   adding 'executorch/backends/arm/test/ops/test_squeeze.py'
2025-03-21T20:25:15.9158899Z   adding 'executorch/backends/arm/test/ops/test_sub.py'
2025-03-21T20:25:15.9159172Z   adding 'executorch/backends/arm/test/ops/test_sum.py'
2025-03-21T20:25:15.9159441Z   adding 'executorch/backends/arm/test/ops/test_tanh.py'
2025-03-21T20:25:15.9159700Z   adding 'executorch/backends/arm/test/ops/test_to_copy.py'
2025-03-21T20:25:15.9159924Z   adding 'executorch/backends/arm/test/ops/test_unsqueeze.py'
2025-03-21T20:25:15.9160329Z   adding 'executorch/backends/arm/test/ops/test_upsample_nearest2d.py'
2025-03-21T20:25:15.9160607Z   adding 'executorch/backends/arm/test/ops/test_var.py'
2025-03-21T20:25:15.9160908Z   adding 'executorch/backends/arm/test/ops/test_view.py'
2025-03-21T20:25:15.9161314Z   adding 'executorch/backends/arm/test/passes/test_cast_int64_pass.py'
2025-03-21T20:25:15.9161716Z   adding 'executorch/backends/arm/test/passes/test_convert_to_clamp.py'
2025-03-21T20:25:15.9162061Z   adding 'executorch/backends/arm/test/passes/test_fold_qdq_pass.py'
2025-03-21T20:25:15.9162307Z   adding 'executorch/backends/arm/test/passes/test_fuse_batchnorm_pass.py'
2025-03-21T20:25:15.9162576Z   adding 'executorch/backends/arm/test/passes/test_fuse_constant_ops_pass.py'
2025-03-21T20:25:15.9162827Z   adding 'executorch/backends/arm/test/passes/test_insert_table_ops_pass.py'
2025-03-21T20:25:15.9163082Z   adding 'executorch/backends/arm/test/passes/test_ioquantization_pass.py'
2025-03-21T20:25:15.9163348Z   adding 'executorch/backends/arm/test/passes/test_meandim_to_averagepool2d.py'
2025-03-21T20:25:15.9163563Z   adding 'executorch/backends/arm/test/passes/test_rescale_pass.py'
2025-03-21T20:25:15.9163860Z   adding 'executorch/backends/arm/test/passes/test_unsqueeze_before_repeat_pass.py'
2025-03-21T20:25:15.9164276Z   adding 'executorch/backends/arm/test/quantizer/test_generic_annotater.py'
2025-03-21T20:25:15.9164584Z   adding 'executorch/backends/arm/test/tester/__init__.py'
2025-03-21T20:25:15.9165004Z   adding 'executorch/backends/arm/test/tester/analyze_output_utils.py'
2025-03-21T20:25:15.9165341Z   adding 'executorch/backends/arm/test/tester/arm_tester.py'
2025-03-21T20:25:15.9165684Z   adding 'executorch/backends/arm/test/tester/test_pipeline.py'
2025-03-21T20:25:15.9165993Z   adding 'executorch/backends/arm/test/tosautil/__init__.py'
2025-03-21T20:25:15.9166261Z   adding 'executorch/backends/arm/third-party/serialization_lib/setup.py'
2025-03-21T20:25:15.9166596Z   adding 'executorch/backends/arm/third-party/serialization_lib/python/serializer/__init__.py'
2025-03-21T20:25:15.9166975Z   adding 'executorch/backends/arm/third-party/serialization_lib/python/serializer/tosa_serializer.py'
2025-03-21T20:25:15.9167399Z   adding 'executorch/backends/arm/third-party/serialization_lib/python/tosa/ArithmeticRightShiftAttribute.py'
2025-03-21T20:25:15.9167714Z   adding 'executorch/backends/arm/third-party/serialization_lib/python/tosa/Attribute.py'
2025-03-21T20:25:15.9168050Z   adding 'executorch/backends/arm/third-party/serialization_lib/python/tosa/AxisAttribute.py'
2025-03-21T20:25:15.9168392Z   adding 'executorch/backends/arm/third-party/serialization_lib/python/tosa/ClampAttribute.py'
2025-03-21T20:25:15.9168750Z   adding 'executorch/backends/arm/third-party/serialization_lib/python/tosa/CondIfAttribute.py'
2025-03-21T20:25:15.9169399Z   adding 'executorch/backends/arm/third-party/serialization_lib/python/tosa/ConvAttribute.py'
2025-03-21T20:25:15.9170017Z   adding 'executorch/backends/arm/third-party/serialization_lib/python/tosa/CustomAttribute.py'
2025-03-21T20:25:15.9170535Z   adding 'executorch/backends/arm/third-party/serialization_lib/python/tosa/DType.py'
2025-03-21T20:25:15.9171062Z   adding 'executorch/backends/arm/third-party/serialization_lib/python/tosa/FFTAttribute.py'
2025-03-21T20:25:15.9171445Z   adding 'executorch/backends/arm/third-party/serialization_lib/python/tosa/FullyConnectedAttribute.py'
2025-03-21T20:25:15.9172154Z   adding 'executorch/backends/arm/third-party/serialization_lib/python/tosa/MatMulAttribute.py'
2025-03-21T20:25:15.9172822Z   adding 'executorch/backends/arm/third-party/serialization_lib/python/tosa/MulAttribute.py'
2025-03-21T20:25:15.9173440Z   adding 'executorch/backends/arm/third-party/serialization_lib/python/tosa/NegateAttribute.py'
2025-03-21T20:25:15.9173813Z   adding 'executorch/backends/arm/third-party/serialization_lib/python/tosa/Op.py'
2025-03-21T20:25:15.9174138Z   adding 'executorch/backends/arm/third-party/serialization_lib/python/tosa/PadAttribute.py'
2025-03-21T20:25:15.9174512Z   adding 'executorch/backends/arm/third-party/serialization_lib/python/tosa/PoolAttribute.py'
2025-03-21T20:25:15.9175085Z   adding 'executorch/backends/arm/third-party/serialization_lib/python/tosa/RFFTAttribute.py'
2025-03-21T20:25:15.9175733Z   adding 'executorch/backends/arm/third-party/serialization_lib/python/tosa/RescaleAttribute.py'
2025-03-21T20:25:15.9176343Z   adding 'executorch/backends/arm/third-party/serialization_lib/python/tosa/ReshapeAttribute.py'
2025-03-21T20:25:15.9176777Z   adding 'executorch/backends/arm/third-party/serialization_lib/python/tosa/ResizeAttribute.py'
2025-03-21T20:25:15.9177123Z   adding 'executorch/backends/arm/third-party/serialization_lib/python/tosa/ResizeMode.py'
2025-03-21T20:25:15.9177725Z   adding 'executorch/backends/arm/third-party/serialization_lib/python/tosa/SliceAttribute.py'
2025-03-21T20:25:15.9511103Z   adding 'executorch/backends/arm/third-party/serialization_lib/python/tosa/TableAttribute.py'
2025-03-21T20:25:15.9511799Z   adding 'executorch/backends/arm/third-party/serialization_lib/python/tosa/TileAttribute.py'
2025-03-21T20:25:15.9512239Z   adding 'executorch/backends/arm/third-party/serialization_lib/python/tosa/TosaBasicBlock.py'
2025-03-21T20:25:15.9512560Z   adding 'executorch/backends/arm/third-party/serialization_lib/python/tosa/TosaGraph.py'
2025-03-21T20:25:15.9513063Z   adding 'executorch/backends/arm/third-party/serialization_lib/python/tosa/TosaOperator.py'
2025-03-21T20:25:15.9513416Z   adding 'executorch/backends/arm/third-party/serialization_lib/python/tosa/TosaRegion.py'
2025-03-21T20:25:15.9513852Z   adding 'executorch/backends/arm/third-party/serialization_lib/python/tosa/TosaTensor.py'
2025-03-21T20:25:15.9514215Z   adding 'executorch/backends/arm/third-party/serialization_lib/python/tosa/TransposeAttribute.py'
2025-03-21T20:25:15.9514602Z   adding 'executorch/backends/arm/third-party/serialization_lib/python/tosa/TransposeConvAttribute.py'
2025-03-21T20:25:15.9514900Z   adding 'executorch/backends/arm/third-party/serialization_lib/python/tosa/Version.py'
2025-03-21T20:25:15.9515268Z   adding 'executorch/backends/arm/third-party/serialization_lib/python/tosa/WhileLoopAttribute.py'
2025-03-21T20:25:15.9515615Z   adding 'executorch/backends/arm/third-party/serialization_lib/python/tosa/__init__.py'
2025-03-21T20:25:15.9515961Z   adding 'executorch/backends/arm/third-party/serialization_lib/schema/tosa.fbs'
2025-03-21T20:25:15.9516332Z   adding 'executorch/backends/arm/third-party/serialization_lib/test/scripts/test_npy_fileio.py'
2025-03-21T20:25:15.9516742Z   adding 'executorch/backends/arm/third-party/serialization_lib/test/scripts/xunit/xunit.py'
2025-03-21T20:25:15.9516958Z   adding 'executorch/backends/arm/util/arm_model_evaluator.py'
2025-03-21T20:25:15.9517199Z   adding 'executorch/backends/cadence/aot/__init__.py'
2025-03-21T20:25:15.9517381Z   adding 'executorch/backends/cadence/aot/compiler.py'
2025-03-21T20:25:15.9517573Z   adding 'executorch/backends/cadence/aot/compiler_utils.py'
2025-03-21T20:25:15.9517862Z   adding 'executorch/backends/cadence/aot/export_example.py'
2025-03-21T20:25:15.9518041Z   adding 'executorch/backends/cadence/aot/functions.yaml'
2025-03-21T20:25:15.9518268Z   adding 'executorch/backends/cadence/aot/functions_fusion_g3.yaml'
2025-03-21T20:25:15.9518456Z   adding 'executorch/backends/cadence/aot/functions_hifi.yaml'
2025-03-21T20:25:15.9518611Z   adding 'executorch/backends/cadence/aot/fuse_ops.py'
2025-03-21T20:25:15.9518943Z   adding 'executorch/backends/cadence/aot/graph_builder.py'
2025-03-21T20:25:15.9519225Z   adding 'executorch/backends/cadence/aot/memory_constraints.py'
2025-03-21T20:25:15.9519430Z   adding 'executorch/backends/cadence/aot/memory_planning.py'
2025-03-21T20:25:15.9519739Z   adding 'executorch/backends/cadence/aot/ops_registrations.py'
2025-03-21T20:25:15.9519911Z   adding 'executorch/backends/cadence/aot/pass_utils.py'
2025-03-21T20:25:15.9520076Z   adding 'executorch/backends/cadence/aot/passes.py'
2025-03-21T20:25:15.9520281Z   adding 'executorch/backends/cadence/aot/ref_implementations.py'
2025-03-21T20:25:15.9520460Z   adding 'executorch/backends/cadence/aot/remove_ops.py'
2025-03-21T20:25:15.9520626Z   adding 'executorch/backends/cadence/aot/reorder_ops.py'
2025-03-21T20:25:15.9520806Z   adding 'executorch/backends/cadence/aot/replace_ops.py'
2025-03-21T20:25:15.9520979Z   adding 'executorch/backends/cadence/aot/simplify_ops.py'
2025-03-21T20:25:15.9521124Z   adding 'executorch/backends/cadence/aot/utils.py'
2025-03-21T20:25:15.9521361Z   adding 'executorch/backends/cadence/aot/quantizer/fusion_pass.py'
2025-03-21T20:25:15.9521560Z   adding 'executorch/backends/cadence/aot/quantizer/patterns.py'
2025-03-21T20:25:15.9521852Z   adding 'executorch/backends/cadence/aot/quantizer/quantizer.py'
2025-03-21T20:25:15.9522124Z   adding 'executorch/backends/cadence/aot/quantizer/utils.py'
2025-03-21T20:25:15.9522385Z   adding 'executorch/backends/cadence/aot/tests/test_fusion_ops_passes.py'
2025-03-21T20:25:15.9522608Z   adding 'executorch/backends/cadence/aot/tests/test_graph_builder.py'
2025-03-21T20:25:15.9522907Z   adding 'executorch/backends/cadence/aot/tests/test_memory_passes.py'
2025-03-21T20:25:15.9523136Z   adding 'executorch/backends/cadence/aot/tests/test_pass_filter.py'
2025-03-21T20:25:15.9523376Z   adding 'executorch/backends/cadence/aot/tests/test_remove_ops_passes.py'
2025-03-21T20:25:15.9523631Z   adding 'executorch/backends/cadence/aot/tests/test_reorder_ops_passes.py'
2025-03-21T20:25:15.9523880Z   adding 'executorch/backends/cadence/aot/tests/test_replace_ops_passes.py'
2025-03-21T20:25:15.9524145Z   adding 'executorch/backends/cadence/aot/tests/test_simplify_ops_passes.py'
2025-03-21T20:25:15.9524321Z   adding 'executorch/backends/cadence/runtime/__init__.py'
2025-03-21T20:25:15.9524521Z   adding 'executorch/backends/cadence/runtime/executor.py'
2025-03-21T20:25:15.9524790Z   adding 'executorch/backends/cadence/runtime/runtime.py'
2025-03-21T20:25:15.9524954Z   adding 'executorch/backends/cadence/runtime/utils.py'
2025-03-21T20:25:15.9525144Z   adding 'executorch/backends/cadence/utils/facto_util.py'
2025-03-21T20:25:15.9525350Z   adding 'executorch/backends/cadence/utils/gen_header.py'
2025-03-21T20:25:15.9525563Z   adding 'executorch/backends/cadence/utils/post_compilation.py'
2025-03-21T20:25:15.9525737Z   adding 'executorch/backends/cadence/utils/FACTO/setup.py'
2025-03-21T20:25:15.9525975Z   adding 'executorch/backends/cadence/utils/FACTO/calibrator/__init__.py'
2025-03-21T20:25:15.9526330Z   adding 'executorch/backends/cadence/utils/FACTO/calibrator/runner.py'
2025-03-21T20:25:15.9526568Z   adding 'executorch/backends/cadence/utils/FACTO/examples/example.py'
2025-03-21T20:25:15.9527006Z   adding 'executorch/backends/cadence/utils/FACTO/examples/minimal_example.py'
2025-03-21T20:25:15.9527314Z   adding 'executorch/backends/cadence/utils/FACTO/examples/random_seed.py'
2025-03-21T20:25:15.9527645Z   adding 'executorch/backends/cadence/utils/FACTO/facto/__init__.py'
2025-03-21T20:25:15.9527989Z   adding 'executorch/backends/cadence/utils/FACTO/facto/inputgen/__init__.py'
2025-03-21T20:25:15.9528292Z   adding 'executorch/backends/cadence/utils/FACTO/facto/inputgen/argtuple/__init__.py'
2025-03-21T20:25:15.9528707Z   adding 'executorch/backends/cadence/utils/FACTO/facto/inputgen/argtuple/engine.py'
2025-03-21T20:25:15.9528987Z   adding 'executorch/backends/cadence/utils/FACTO/facto/inputgen/argtuple/gen.py'
2025-03-21T20:25:15.9529398Z   adding 'executorch/backends/cadence/utils/FACTO/facto/inputgen/argument/__init__.py'
2025-03-21T20:25:15.9529864Z   adding 'executorch/backends/cadence/utils/FACTO/facto/inputgen/argument/engine.py'
2025-03-21T20:25:15.9530152Z   adding 'executorch/backends/cadence/utils/FACTO/facto/inputgen/argument/gen.py'
2025-03-21T20:25:15.9530432Z   adding 'executorch/backends/cadence/utils/FACTO/facto/inputgen/argument/type.py'
2025-03-21T20:25:15.9530749Z   adding 'executorch/backends/cadence/utils/FACTO/facto/inputgen/attribute/__init__.py'
2025-03-21T20:25:15.9531091Z   adding 'executorch/backends/cadence/utils/FACTO/facto/inputgen/attribute/engine.py'
2025-03-21T20:25:15.9531513Z   adding 'executorch/backends/cadence/utils/FACTO/facto/inputgen/attribute/model.py'
2025-03-21T20:25:15.9531823Z   adding 'executorch/backends/cadence/utils/FACTO/facto/inputgen/attribute/solve.py'
2025-03-21T20:25:15.9532108Z   adding 'executorch/backends/cadence/utils/FACTO/facto/inputgen/specs/__init__.py'
2025-03-21T20:25:15.9532557Z   adding 'executorch/backends/cadence/utils/FACTO/facto/inputgen/specs/model.py'
2025-03-21T20:25:15.9532923Z   adding 'executorch/backends/cadence/utils/FACTO/facto/inputgen/utils/__init__.py'
2025-03-21T20:25:15.9533355Z   adding 'executorch/backends/cadence/utils/FACTO/facto/inputgen/utils/random_manager.py'
2025-03-21T20:25:15.9533657Z   adding 'executorch/backends/cadence/utils/FACTO/facto/inputgen/variable/__init__.py'
2025-03-21T20:25:15.9533961Z   adding 'executorch/backends/cadence/utils/FACTO/facto/inputgen/variable/constants.py'
2025-03-21T20:25:15.9534246Z   adding 'executorch/backends/cadence/utils/FACTO/facto/inputgen/variable/gen.py'
2025-03-21T20:25:15.9534533Z   adding 'executorch/backends/cadence/utils/FACTO/facto/inputgen/variable/solve.py'
2025-03-21T20:25:15.9534829Z   adding 'executorch/backends/cadence/utils/FACTO/facto/inputgen/variable/space.py'
2025-03-21T20:25:15.9535163Z   adding 'executorch/backends/cadence/utils/FACTO/facto/inputgen/variable/type.py'
2025-03-21T20:25:15.9535668Z   adding 'executorch/backends/cadence/utils/FACTO/facto/inputgen/variable/utils.py'
2025-03-21T20:25:15.9536061Z   adding 'executorch/backends/cadence/utils/FACTO/facto/specdb/db.py'
2025-03-21T20:25:15.9536491Z   adding 'executorch/backends/cadence/utils/FACTO/facto/specdb/default.py'
2025-03-21T20:25:15.9536890Z   adding 'executorch/backends/cadence/utils/FACTO/facto/specdb/dtypes.py'
2025-03-21T20:25:15.9537172Z   adding 'executorch/backends/cadence/utils/FACTO/facto/specdb/function.py'
2025-03-21T20:25:15.9537496Z   adding 'executorch/backends/cadence/utils/FACTO/test/inputgen/test_argtuple_engine.py'
2025-03-21T20:25:15.9537822Z   adding 'executorch/backends/cadence/utils/FACTO/test/inputgen/test_argtuple_generator.py'
2025-03-21T20:25:15.9538163Z   adding 'executorch/backends/cadence/utils/FACTO/test/inputgen/test_argument_attributes.py'
2025-03-21T20:25:15.9538486Z   adding 'executorch/backends/cadence/utils/FACTO/test/inputgen/test_argument_generator.py'
2025-03-21T20:25:15.9538800Z   adding 'executorch/backends/cadence/utils/FACTO/test/inputgen/test_argument_types.py'
2025-03-21T20:25:15.9539120Z   adding 'executorch/backends/cadence/utils/FACTO/test/inputgen/test_attribute_engine.py'
2025-03-21T20:25:15.9539431Z   adding 'executorch/backends/cadence/utils/FACTO/test/inputgen/test_attribute_solver.py'
2025-03-21T20:25:15.9539755Z   adding 'executorch/backends/cadence/utils/FACTO/test/inputgen/test_constraints.py'
2025-03-21T20:25:15.9540125Z   adding 'executorch/backends/cadence/utils/FACTO/test/inputgen/test_meta_arg_engine.py'
2025-03-21T20:25:15.9540553Z   adding 'executorch/backends/cadence/utils/FACTO/test/inputgen/test_specs.py'
2025-03-21T20:25:15.9541062Z   adding 'executorch/backends/cadence/utils/FACTO/test/inputgen/test_structural_engine.py'
2025-03-21T20:25:15.9541613Z   adding 'executorch/backends/cadence/utils/FACTO/test/inputgen/test_variable_generation.py'
2025-03-21T20:25:15.9542170Z   adding 'executorch/backends/cadence/utils/FACTO/test/inputgen/test_variable_solving.py'
2025-03-21T20:25:15.9542702Z   adding 'executorch/backends/cadence/utils/FACTO/test/inputgen/test_variable_space.py'
2025-03-21T20:25:15.9543555Z   adding 'executorch/backends/cadence/utils/FACTO/test/inputgen/test_variable_types.py'
2025-03-21T20:25:15.9543884Z   adding 'executorch/backends/example/example_backend.py'
2025-03-21T20:25:15.9544234Z   adding 'executorch/backends/example/example_partitioner.py'
2025-03-21T20:25:15.9544548Z   adding 'executorch/backends/example/example_quantizer.py'
2025-03-21T20:25:15.9823595Z   adding 'executorch/backends/example/test_example_delegate.py'
2025-03-21T20:25:15.9824102Z   adding 'executorch/backends/example/example_backend_delegate_passes/merge_to_dim_pass.py'
2025-03-21T20:25:15.9824771Z   adding 'executorch/backends/example/example_backend_delegate_passes/permute_memory_formats_pass.py'
2025-03-21T20:25:15.9825244Z   adding 'executorch/backends/example/example_operators/adaptive_avg_pool2d.py'
2025-03-21T20:25:15.9825532Z   adding 'executorch/backends/example/example_operators/add.py'
2025-03-21T20:25:15.9825860Z   adding 'executorch/backends/example/example_operators/conv2d.py'
2025-03-21T20:25:15.9826136Z   adding 'executorch/backends/example/example_operators/conv_relu.py'
2025-03-21T20:25:15.9826395Z   adding 'executorch/backends/example/example_operators/dropout.py'
2025-03-21T20:25:15.9826625Z   adding 'executorch/backends/example/example_operators/flatten.py'
2025-03-21T20:25:15.9826831Z   adding 'executorch/backends/example/example_operators/linear.py'
2025-03-21T20:25:15.9827040Z   adding 'executorch/backends/example/example_operators/op_base.py'
2025-03-21T20:25:15.9827248Z   adding 'executorch/backends/example/example_operators/ops.py'
2025-03-21T20:25:15.9827450Z   adding 'executorch/backends/example/example_operators/utils.py'
2025-03-21T20:25:15.9827609Z   adding 'executorch/backends/mediatek/__init__.py'
2025-03-21T20:25:15.9827792Z   adding 'executorch/backends/mediatek/partitioner.py'
2025-03-21T20:25:15.9827988Z   adding 'executorch/backends/mediatek/preprocess.py'
2025-03-21T20:25:15.9828194Z   adding 'executorch/backends/mediatek/_passes/__init__.py'
2025-03-21T20:25:15.9828635Z   adding 'executorch/backends/mediatek/_passes/decompose_scaled_dot_product_attention.py'
2025-03-21T20:25:15.9828839Z   adding 'executorch/backends/mediatek/quantizer/__init__.py'
2025-03-21T20:25:15.9829033Z   adding 'executorch/backends/mediatek/quantizer/annotator.py'
2025-03-21T20:25:15.9829269Z   adding 'executorch/backends/mediatek/quantizer/qconfig.py'
2025-03-21T20:25:15.9829461Z   adding 'executorch/backends/mediatek/quantizer/quantizer.py'
2025-03-21T20:25:15.9829647Z   adding 'executorch/backends/qualcomm/qnn_preprocess.py'
2025-03-21T20:25:15.9829819Z   adding 'executorch/backends/qualcomm/_passes/__init__.py'
2025-03-21T20:25:15.9830094Z   adding 'executorch/backends/qualcomm/_passes/annotate_decomposed.py'
2025-03-21T20:25:15.9830447Z   adding 'executorch/backends/qualcomm/_passes/annotate_quant_attrs.py'
2025-03-21T20:25:15.9830760Z   adding 'executorch/backends/qualcomm/_passes/build_quant_io.py'
2025-03-21T20:25:15.9831001Z   adding 'executorch/backends/qualcomm/_passes/constant_i64_to_i32.py'
2025-03-21T20:25:15.9831270Z   adding 'executorch/backends/qualcomm/_passes/convert_bmm_to_matmul.py'
2025-03-21T20:25:15.9831579Z   adding 'executorch/backends/qualcomm/_passes/convert_interpolate_with_upsample2d.py'
2025-03-21T20:25:15.9831789Z   adding 'executorch/backends/qualcomm/_passes/convert_to_linear.py'
2025-03-21T20:25:15.9831985Z   adding 'executorch/backends/qualcomm/_passes/decompose_any.py'
2025-03-21T20:25:15.9832443Z   adding 'executorch/backends/qualcomm/_passes/decompose_einsum.py'
2025-03-21T20:25:15.9832849Z   adding 'executorch/backends/qualcomm/_passes/decompose_linalg_vector_norm.py'
2025-03-21T20:25:15.9833173Z   adding 'executorch/backends/qualcomm/_passes/decompose_silu.py'
2025-03-21T20:25:15.9833446Z   adding 'executorch/backends/qualcomm/_passes/expand_broadcast_tensor_shape.py'
2025-03-21T20:25:15.9833683Z   adding 'executorch/backends/qualcomm/_passes/fold_qdq.py'
2025-03-21T20:25:15.9833946Z   adding 'executorch/backends/qualcomm/_passes/fuse_consecutive_transpose.py'
2025-03-21T20:25:15.9834390Z   adding 'executorch/backends/qualcomm/_passes/insert_io_qdq.py'
2025-03-21T20:25:15.9834612Z   adding 'executorch/backends/qualcomm/_passes/insert_requantize.py'
2025-03-21T20:25:15.9834824Z   adding 'executorch/backends/qualcomm/_passes/layout_transform.py'
2025-03-21T20:25:15.9835106Z   adding 'executorch/backends/qualcomm/_passes/lift_constant_scalar_operands.py'
2025-03-21T20:25:15.9835360Z   adding 'executorch/backends/qualcomm/_passes/recompose_pixel_unshuffle.py'
2025-03-21T20:25:15.9835583Z   adding 'executorch/backends/qualcomm/_passes/recompose_prelu.py'
2025-03-21T20:25:15.9835805Z   adding 'executorch/backends/qualcomm/_passes/recompose_rms_norm.py'
2025-03-21T20:25:15.9836092Z   adding 'executorch/backends/qualcomm/_passes/reduce_dynamic_range.py'
2025-03-21T20:25:15.9836361Z   adding 'executorch/backends/qualcomm/_passes/remove_redundancy.py'
2025-03-21T20:25:15.9836719Z   adding 'executorch/backends/qualcomm/_passes/replace_index_put_input.py'
2025-03-21T20:25:15.9836968Z   adding 'executorch/backends/qualcomm/_passes/replace_inf_buffer.py'
2025-03-21T20:25:15.9837213Z   adding 'executorch/backends/qualcomm/_passes/tensor_i64_to_i32.py'
2025-03-21T20:25:15.9837411Z   adding 'executorch/backends/qualcomm/_passes/utils.py'
2025-03-21T20:25:15.9837578Z   adding 'executorch/backends/qualcomm/aot/ir/qcir.fbs'
2025-03-21T20:25:15.9837770Z   adding 'executorch/backends/qualcomm/builders/__init__.py'
2025-03-21T20:25:15.9837967Z   adding 'executorch/backends/qualcomm/builders/node_visitor.py'
2025-03-21T20:25:15.9838139Z   adding 'executorch/backends/qualcomm/builders/op_abs.py'
2025-03-21T20:25:15.9838395Z   adding 'executorch/backends/qualcomm/builders/op_adaptive_avg_pool2d.py'
2025-03-21T20:25:15.9838565Z   adding 'executorch/backends/qualcomm/builders/op_add.py'
2025-03-21T20:25:15.9838795Z   adding 'executorch/backends/qualcomm/builders/op_arange.py'
2025-03-21T20:25:15.9839031Z   adding 'executorch/backends/qualcomm/builders/op_argmin.py'
2025-03-21T20:25:15.9839359Z   adding 'executorch/backends/qualcomm/builders/op_avg_pool2d.py'
2025-03-21T20:25:15.9839634Z   adding 'executorch/backends/qualcomm/builders/op_batch_norm.py'
2025-03-21T20:25:15.9839813Z   adding 'executorch/backends/qualcomm/builders/op_bmm.py'
2025-03-21T20:25:15.9840023Z   adding 'executorch/backends/qualcomm/builders/op_cat.py'
2025-03-21T20:25:15.9840217Z   adding 'executorch/backends/qualcomm/builders/op_ceil.py'
2025-03-21T20:25:15.9840410Z   adding 'executorch/backends/qualcomm/builders/op_clamp.py'
2025-03-21T20:25:15.9840592Z   adding 'executorch/backends/qualcomm/builders/op_conv2d.py'
2025-03-21T20:25:15.9840764Z   adding 'executorch/backends/qualcomm/builders/op_cos.py'
2025-03-21T20:25:15.9840995Z   adding 'executorch/backends/qualcomm/builders/op_depth_to_space.py'
2025-03-21T20:25:15.9841199Z   adding 'executorch/backends/qualcomm/builders/op_dequantize.py'
2025-03-21T20:25:15.9841382Z   adding 'executorch/backends/qualcomm/builders/op_div.py'
2025-03-21T20:25:15.9841587Z   adding 'executorch/backends/qualcomm/builders/op_embedding.py'
2025-03-21T20:25:15.9841770Z   adding 'executorch/backends/qualcomm/builders/op_eq.py'
2025-03-21T20:25:15.9841960Z   adding 'executorch/backends/qualcomm/builders/op_expand.py'
2025-03-21T20:25:15.9842171Z   adding 'executorch/backends/qualcomm/builders/op_full.py'
2025-03-21T20:25:15.9842385Z   adding 'executorch/backends/qualcomm/builders/op_full_like.py'
2025-03-21T20:25:15.9842606Z   adding 'executorch/backends/qualcomm/builders/op_ge.py'
2025-03-21T20:25:15.9842902Z   adding 'executorch/backends/qualcomm/builders/op_gelu.py'
2025-03-21T20:25:15.9843110Z   adding 'executorch/backends/qualcomm/builders/op_group_norm.py'
2025-03-21T20:25:15.9843290Z   adding 'executorch/backends/qualcomm/builders/op_gt.py'
2025-03-21T20:25:15.9843545Z   adding 'executorch/backends/qualcomm/builders/op_hardsigmoid.py'
2025-03-21T20:25:15.9843744Z   adding 'executorch/backends/qualcomm/builders/op_hardswish.py'
2025-03-21T20:25:15.9844084Z   adding 'executorch/backends/qualcomm/builders/op_hardtanh.py'
2025-03-21T20:25:15.9844263Z   adding 'executorch/backends/qualcomm/builders/op_index.py'
2025-03-21T20:25:15.9844474Z   adding 'executorch/backends/qualcomm/builders/op_index_put.py'
2025-03-21T20:25:15.9844729Z   adding 'executorch/backends/qualcomm/builders/op_instance_norm.py'
2025-03-21T20:25:15.9844984Z   adding 'executorch/backends/qualcomm/builders/op_layer_norm.py'
2025-03-21T20:25:15.9845212Z   adding 'executorch/backends/qualcomm/builders/op_le.py'
2025-03-21T20:25:15.9845453Z   adding 'executorch/backends/qualcomm/builders/op_linear.py'
2025-03-21T20:25:15.9845640Z   adding 'executorch/backends/qualcomm/builders/op_log.py'
2025-03-21T20:25:15.9845886Z   adding 'executorch/backends/qualcomm/builders/op_log_softmax.py'
2025-03-21T20:25:15.9846111Z   adding 'executorch/backends/qualcomm/builders/op_logical_not.py'
2025-03-21T20:25:15.9846281Z   adding 'executorch/backends/qualcomm/builders/op_lt.py'
2025-03-21T20:25:15.9846479Z   adding 'executorch/backends/qualcomm/builders/op_matmul.py'
2025-03-21T20:25:15.9846653Z   adding 'executorch/backends/qualcomm/builders/op_max.py'
2025-03-21T20:25:15.9846856Z   adding 'executorch/backends/qualcomm/builders/op_max_pool2d.py'
2025-03-21T20:25:15.9847057Z   adding 'executorch/backends/qualcomm/builders/op_mean_dim.py'
2025-03-21T20:25:15.9847225Z   adding 'executorch/backends/qualcomm/builders/op_min.py'
2025-03-21T20:25:15.9847409Z   adding 'executorch/backends/qualcomm/builders/op_mul.py'
2025-03-21T20:25:15.9847575Z   adding 'executorch/backends/qualcomm/builders/op_ne.py'
2025-03-21T20:25:15.9847798Z   adding 'executorch/backends/qualcomm/builders/op_neg.py'
2025-03-21T20:25:15.9847980Z   adding 'executorch/backends/qualcomm/builders/op_or.py'
2025-03-21T20:25:15.9848244Z   adding 'executorch/backends/qualcomm/builders/op_pad.py'
2025-03-21T20:25:15.9848503Z   adding 'executorch/backends/qualcomm/builders/op_pow.py'
2025-03-21T20:25:15.9848684Z   adding 'executorch/backends/qualcomm/builders/op_prelu.py'
2025-03-21T20:25:15.9848910Z   adding 'executorch/backends/qualcomm/builders/op_quantize.py'
2025-03-21T20:25:15.9849118Z   adding 'executorch/backends/qualcomm/builders/op_relu.py'
2025-03-21T20:25:15.9849402Z   adding 'executorch/backends/qualcomm/builders/op_repeat.py'
2025-03-21T20:25:15.9849593Z   adding 'executorch/backends/qualcomm/builders/op_reshape.py'
2025-03-21T20:25:15.9849795Z   adding 'executorch/backends/qualcomm/builders/op_rms_norm.py'
2025-03-21T20:25:15.9850033Z   adding 'executorch/backends/qualcomm/builders/op_rsqrt.py'
2025-03-21T20:25:15.9850347Z   adding 'executorch/backends/qualcomm/builders/op_select_copy.py'
2025-03-21T20:25:15.9850652Z   adding 'executorch/backends/qualcomm/builders/op_sigmoid.py'
2025-03-21T20:25:15.9850829Z   adding 'executorch/backends/qualcomm/builders/op_sin.py'
2025-03-21T20:25:15.9851043Z   adding 'executorch/backends/qualcomm/builders/op_skip_ops.py'
2025-03-21T20:25:15.9851280Z   adding 'executorch/backends/qualcomm/builders/op_slice_copy.py'
2025-03-21T20:25:15.9851478Z   adding 'executorch/backends/qualcomm/builders/op_softmax.py'
2025-03-21T20:25:15.9851710Z   adding 'executorch/backends/qualcomm/builders/op_space_to_depth.py'
2025-03-21T20:25:15.9851935Z   adding 'executorch/backends/qualcomm/builders/op_split_with_sizes.py'
2025-03-21T20:25:15.9852120Z   adding 'executorch/backends/qualcomm/builders/op_sqrt.py'
2025-03-21T20:25:15.9852307Z   adding 'executorch/backends/qualcomm/builders/op_squeeze.py'
2025-03-21T20:25:15.9852488Z   adding 'executorch/backends/qualcomm/builders/op_sub.py'
2025-03-21T20:25:15.9852697Z   adding 'executorch/backends/qualcomm/builders/op_sum_int_list.py'
2025-03-21T20:25:15.9852873Z   adding 'executorch/backends/qualcomm/builders/op_tanh.py'
2025-03-21T20:25:15.9853054Z   adding 'executorch/backends/qualcomm/builders/op_to.py'
2025-03-21T20:25:15.9853229Z   adding 'executorch/backends/qualcomm/builders/op_topk.py'
2025-03-21T20:25:16.0157294Z   adding 'executorch/backends/qualcomm/builders/op_transpose.py'
2025-03-21T20:25:16.0158498Z   adding 'executorch/backends/qualcomm/builders/op_unsqueeze.py'
2025-03-21T20:25:16.0158801Z   adding 'executorch/backends/qualcomm/builders/op_upsample_bilinear2d.py'
2025-03-21T20:25:16.0159160Z   adding 'executorch/backends/qualcomm/builders/op_upsample_nearest2d.py'
2025-03-21T20:25:16.0159365Z   adding 'executorch/backends/qualcomm/builders/op_where.py'
2025-03-21T20:25:16.0159622Z   adding 'executorch/backends/qualcomm/builders/qnn_constants.py'
2025-03-21T20:25:16.0159876Z   adding 'executorch/backends/qualcomm/builders/utils.py'
2025-03-21T20:25:16.0160115Z   adding 'executorch/backends/qualcomm/debugger/utils.py'
2025-03-21T20:25:16.0160497Z   adding 'executorch/backends/qualcomm/partition/common_defs.py'
2025-03-21T20:25:16.0160902Z   adding 'executorch/backends/qualcomm/partition/qnn_partitioner.py'
2025-03-21T20:25:16.0161083Z   adding 'executorch/backends/qualcomm/partition/utils.py'
2025-03-21T20:25:16.0161291Z   adding 'executorch/backends/qualcomm/quantizer/annotators.py'
2025-03-21T20:25:16.0161530Z   adding 'executorch/backends/qualcomm/quantizer/custom_annotation.py'
2025-03-21T20:25:16.0161763Z   adding 'executorch/backends/qualcomm/quantizer/qconfig.py'
2025-03-21T20:25:16.0161959Z   adding 'executorch/backends/qualcomm/quantizer/quantizer.py'
2025-03-21T20:25:16.0162271Z   adding 'executorch/backends/qualcomm/quantizer/observers/per_channel_param_observer.py'
2025-03-21T20:25:16.0162594Z   adding 'executorch/backends/qualcomm/serialization/qc_compiler_spec.fbs'
2025-03-21T20:25:16.0162809Z   adding 'executorch/backends/qualcomm/serialization/qc_schema.py'
2025-03-21T20:25:16.0163075Z   adding 'executorch/backends/qualcomm/serialization/qc_schema_serialize.py'
2025-03-21T20:25:16.0163239Z   adding 'executorch/backends/qualcomm/tests/models.py'
2025-03-21T20:25:16.0163458Z   adding 'executorch/backends/qualcomm/tests/test_qnn_delegate.py'
2025-03-21T20:25:16.0163655Z   adding 'executorch/backends/qualcomm/tests/utils.py'
2025-03-21T20:25:16.0163835Z   adding 'executorch/backends/qualcomm/utils/constants.py'
2025-03-21T20:25:16.0164092Z   adding 'executorch/backends/qualcomm/utils/utils.py'
2025-03-21T20:25:16.0164307Z   adding 'executorch/backends/transforms/__init__.py'
2025-03-21T20:25:16.0164593Z   adding 'executorch/backends/transforms/addmm_mm_to_linear.py'
2025-03-21T20:25:16.0164840Z   adding 'executorch/backends/transforms/convert_dtype_pass.py'
2025-03-21T20:25:16.0165073Z   adding 'executorch/backends/transforms/decompose_sdpa.py'
2025-03-21T20:25:16.0165435Z   adding 'executorch/backends/transforms/duplicate_dynamic_quant_chain.py'
2025-03-21T20:25:16.0165737Z   adding 'executorch/backends/transforms/fuse_batch_norm_with_conv.py'
2025-03-21T20:25:16.0165996Z   adding 'executorch/backends/transforms/fuse_conv_with_clamp.py'
2025-03-21T20:25:16.0166197Z   adding 'executorch/backends/transforms/fuse_dequant_linear.py'
2025-03-21T20:25:16.0166401Z   adding 'executorch/backends/transforms/fuse_view_copy.py'
2025-03-21T20:25:16.0166668Z   adding 'executorch/backends/transforms/mean_to_sum_div.py'
2025-03-21T20:25:16.0166931Z   adding 'executorch/backends/transforms/rank_0_to_rank_1.py'
2025-03-21T20:25:16.0167119Z   adding 'executorch/backends/transforms/remove_clone_ops.py'
2025-03-21T20:25:16.0167433Z   adding 'executorch/backends/transforms/replace_scalar_with_tensor.py'
2025-03-21T20:25:16.0167609Z   adding 'executorch/backends/transforms/utils.py'
2025-03-21T20:25:16.0167861Z   adding 'executorch/backends/transforms/view_copy_to_squeeze_unsqueeze.py'
2025-03-21T20:25:16.0168261Z   adding 'executorch/backends/transforms/test/test_create_delete_constant_placeholder.py'
2025-03-21T20:25:16.0168635Z   adding 'executorch/backends/transforms/test/test_duplicate_dynamic_quant_chain.py'
2025-03-21T20:25:16.0168979Z   adding 'executorch/backends/transforms/test/test_rank_0_to_rank_1.py'
2025-03-21T20:25:16.0169157Z   adding 'executorch/backends/vulkan/__init__.py'
2025-03-21T20:25:16.0169423Z   adding 'executorch/backends/vulkan/custom_ops_lib.py'
2025-03-21T20:25:16.0169893Z   adding 'executorch/backends/vulkan/op_registry.py'
2025-03-21T20:25:16.0170057Z   adding 'executorch/backends/vulkan/utils.py'
2025-03-21T20:25:16.0170256Z   adding 'executorch/backends/vulkan/vulkan_preprocess.py'
2025-03-21T20:25:16.0170507Z   adding 'executorch/backends/vulkan/_passes/__init__.py'
2025-03-21T20:25:16.0170796Z   adding 'executorch/backends/vulkan/_passes/insert_prepack_nodes.py'
2025-03-21T20:25:16.0171077Z   adding 'executorch/backends/vulkan/_passes/int4_weight_only_quantizer.py'
2025-03-21T20:25:16.0171305Z   adding 'executorch/backends/vulkan/_passes/remove_asserts.py'
2025-03-21T20:25:16.0171637Z   adding 'executorch/backends/vulkan/_passes/remove_local_scalar_dense_ops.py'
2025-03-21T20:25:16.0171908Z   adding 'executorch/backends/vulkan/_passes/remove_redundant_ops.py'
2025-03-21T20:25:16.0172448Z   adding 'executorch/backends/vulkan/_passes/squeeze_unsqueeze_inputs.py'
2025-03-21T20:25:16.0172890Z   adding 'executorch/backends/vulkan/_passes/tag_memory_meta_pass.py'
2025-03-21T20:25:16.0173184Z   adding 'executorch/backends/vulkan/partitioner/vulkan_partitioner.py'
2025-03-21T20:25:16.0173472Z   adding 'executorch/backends/vulkan/quantizer/vulkan_quantizer.py'
2025-03-21T20:25:16.0173739Z   adding 'executorch/backends/vulkan/runtime/gen_vulkan_spv.py'
2025-03-21T20:25:16.0174142Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/addmm_naive_buffer.yaml'
2025-03-21T20:25:16.0174492Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/addmm_naive_texture3d.yaml'
2025-03-21T20:25:16.0174801Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/addmm_optimized.yaml'
2025-03-21T20:25:16.0194509Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/arange.yaml'
2025-03-21T20:25:16.0194996Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/avg_pool2d.yaml'
2025-03-21T20:25:16.0195369Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/batchnorm.yaml'
2025-03-21T20:25:16.0195723Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/binary_op.yaml'
2025-03-21T20:25:16.0196294Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/bitw8_image_to_nchw_nobitw8buffer.yaml'
2025-03-21T20:25:16.0196688Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/buffer_to_buffer.yaml'
2025-03-21T20:25:16.0197079Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/buffer_to_nchw.yaml'
2025-03-21T20:25:16.0197373Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/clone.yaml'
2025-03-21T20:25:16.0197679Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/conv1d.yaml'
2025-03-21T20:25:16.0197924Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/conv2d.yaml'
2025-03-21T20:25:16.0198173Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/conv2d_dw.yaml'
2025-03-21T20:25:16.0198487Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/conv2d_dw_output_tile.yaml'
2025-03-21T20:25:16.0198813Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/conv2d_dw_prepack_weights.yaml'
2025-03-21T20:25:16.0199281Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/conv2d_dw_sned_output_tile.yaml'
2025-03-21T20:25:16.0199724Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/conv2d_prepack_weights.yaml'
2025-03-21T20:25:16.0199981Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/conv2d_pw.yaml'
2025-03-21T20:25:16.0200278Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/conv_transpose2d.yaml'
2025-03-21T20:25:16.0200639Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/conv_transpose2d_prepack_weights.yaml'
2025-03-21T20:25:16.0200945Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/copy_channel_offset.yaml'
2025-03-21T20:25:16.0201209Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/copy_offset.yaml'
2025-03-21T20:25:16.0201524Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/copy_packed_dim_offset.yaml'
2025-03-21T20:25:16.0201774Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/embedding.yaml'
2025-03-21T20:25:16.0202167Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/flip.yaml'
2025-03-21T20:25:16.0202408Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/full.yaml'
2025-03-21T20:25:16.0202666Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/grid_priors.yaml'
2025-03-21T20:25:16.0202943Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/image_to_nchw.yaml'
2025-03-21T20:25:16.0203203Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/index_select.yaml'
2025-03-21T20:25:16.0203513Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/index_select_channel.yaml'
2025-03-21T20:25:16.0203787Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/kv_cache_update.yaml'
2025-03-21T20:25:16.0204054Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/max_pool2d.yaml'
2025-03-21T20:25:16.0204343Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/native_layer_norm.yaml'
2025-03-21T20:25:16.0204709Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/nchw_to_bitw8_image_nobitw8buffer.yaml'
2025-03-21T20:25:16.0204999Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/nchw_to_buffer.yaml'
2025-03-21T20:25:16.0205261Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/nchw_to_image.yaml'
2025-03-21T20:25:16.0205500Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/no_op.yaml'
2025-03-21T20:25:16.0205757Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/pad_channel.yaml'
2025-03-21T20:25:16.0206053Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/pad_height_width.yaml'
2025-03-21T20:25:16.0206295Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/permute.yaml'
2025-03-21T20:25:16.0206550Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/q_4w_linear.yaml'
2025-03-21T20:25:16.0206818Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/q_8w_linear.yaml'
2025-03-21T20:25:16.0207127Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/q_8w_linear_optimized.yaml'
2025-03-21T20:25:16.0207509Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/reduce.yaml'
2025-03-21T20:25:16.0207781Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/repeat_channel.yaml'
2025-03-21T20:25:16.0208086Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/repeat_interleave.yaml'
2025-03-21T20:25:16.0208368Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/rotary_embedding.yaml'
2025-03-21T20:25:16.0208714Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/sdpa_attn_weight_scale_and_mask.yaml'
2025-03-21T20:25:16.0209002Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/select_batch_4d.yaml'
2025-03-21T20:25:16.0209373Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/select_channel_3d.yaml'
2025-03-21T20:25:16.0209673Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/select_channel_4d.yaml'
2025-03-21T20:25:16.0209951Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/select_height_3d.yaml'
2025-03-21T20:25:16.0547457Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/select_height_4d.yaml'
2025-03-21T20:25:16.0547941Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/select_width_3d.yaml'
2025-03-21T20:25:16.0548487Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/select_width_4d.yaml'
2025-03-21T20:25:16.0548774Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/slice_packed_dim.yaml'
2025-03-21T20:25:16.0549080Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/slice_unpacked_dim.yaml'
2025-03-21T20:25:16.0549325Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/softmax.yaml'
2025-03-21T20:25:16.0549569Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/unary_op.yaml'
2025-03-21T20:25:16.0549875Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/upsample_nearest2d.yaml'
2025-03-21T20:25:16.0550099Z   adding 'executorch/backends/vulkan/runtime/graph/ops/glsl/view.yaml'
2025-03-21T20:25:16.0550450Z   adding 'executorch/backends/vulkan/serialization/schema.fbs'
2025-03-21T20:25:16.0550778Z   adding 'executorch/backends/vulkan/serialization/vulkan_graph_builder.py'
2025-03-21T20:25:16.0551038Z   adding 'executorch/backends/vulkan/serialization/vulkan_graph_schema.py'
2025-03-21T20:25:16.0551410Z   adding 'executorch/backends/vulkan/serialization/vulkan_graph_serialize.py'
2025-03-21T20:25:16.0551622Z   adding 'executorch/backends/vulkan/test/test_serialization.py'
2025-03-21T20:25:16.0551842Z   adding 'executorch/backends/vulkan/test/test_vulkan_delegate.py'
2025-03-21T20:25:16.0552121Z   adding 'executorch/backends/vulkan/test/test_vulkan_delegate_header.py'
2025-03-21T20:25:16.0552354Z   adding 'executorch/backends/vulkan/test/glsl/all_shaders.yaml'
2025-03-21T20:25:16.0552536Z   adding 'executorch/backends/vulkan/test/op_tests/cases.py'
2025-03-21T20:25:16.0552806Z   adding 'executorch/backends/vulkan/test/op_tests/generate_op_benchmarks.py'
2025-03-21T20:25:16.0553088Z   adding 'executorch/backends/vulkan/test/op_tests/generate_op_correctness_tests.py'
2025-03-21T20:25:16.0553325Z   adding 'executorch/backends/vulkan/test/op_tests/utils/aten_types.py'
2025-03-21T20:25:16.0553591Z   adding 'executorch/backends/vulkan/test/op_tests/utils/gen_benchmark_vk.py'
2025-03-21T20:25:16.0553845Z   adding 'executorch/backends/vulkan/test/op_tests/utils/gen_computegraph.py'
2025-03-21T20:25:16.0554227Z   adding 'executorch/backends/vulkan/test/op_tests/utils/gen_correctness_base.py'
2025-03-21T20:25:16.0554584Z   adding 'executorch/backends/vulkan/test/op_tests/utils/gen_correctness_vk.py'
2025-03-21T20:25:16.0554825Z   adding 'executorch/backends/vulkan/test/op_tests/utils/test_suite.py'
2025-03-21T20:25:16.0555193Z   adding 'executorch/backends/vulkan/third-party/Vulkan-Headers/registry/apiconventions.py'
2025-03-21T20:25:16.0555508Z   adding 'executorch/backends/vulkan/third-party/Vulkan-Headers/registry/cgenerator.py'
2025-03-21T20:25:16.0555824Z   adding 'executorch/backends/vulkan/third-party/Vulkan-Headers/registry/conventions.py'
2025-03-21T20:25:16.0556124Z   adding 'executorch/backends/vulkan/third-party/Vulkan-Headers/registry/generator.py'
2025-03-21T20:25:16.0556415Z   adding 'executorch/backends/vulkan/third-party/Vulkan-Headers/registry/genvk.py'
2025-03-21T20:25:16.0556680Z   adding 'executorch/backends/vulkan/third-party/Vulkan-Headers/registry/reg.py'
2025-03-21T20:25:16.0557037Z   adding 'executorch/backends/vulkan/third-party/Vulkan-Headers/registry/vkconventions.py'
2025-03-21T20:25:16.0557355Z   adding 'executorch/backends/vulkan/third-party/Vulkan-Headers/registry/spec_tools/util.py'
2025-03-21T20:25:16.0557781Z   adding 'executorch/backends/vulkan/third-party/VulkanMemoryAllocator/tools/GpuMemDumpVis/GpuMemDumpVis.py'
2025-03-21T20:25:16.0557987Z   adding 'executorch/backends/vulkan/third-party/volk/generate.py'
2025-03-21T20:25:16.0558249Z   adding 'executorch/backends/vulkan/tools/gpuinfo/glsl/buf_bandwidth.yaml'
2025-03-21T20:25:16.0558517Z   adding 'executorch/backends/vulkan/tools/gpuinfo/glsl/buf_cacheline_size.yaml'
2025-03-21T20:25:16.0558767Z   adding 'executorch/backends/vulkan/tools/gpuinfo/glsl/reg_count.yaml'
2025-03-21T20:25:16.0559061Z   adding 'executorch/backends/vulkan/tools/gpuinfo/glsl/tex_bandwidth.yaml'
2025-03-21T20:25:16.0559404Z   adding 'executorch/backends/vulkan/tools/gpuinfo/glsl/tex_cacheline_concurr.yaml'
2025-03-21T20:25:16.0559648Z   adding 'executorch/backends/vulkan/tools/gpuinfo/glsl/warp_size.yaml'
2025-03-21T20:25:16.0559794Z   adding 'executorch/backends/xnnpack/__init__.py'
2025-03-21T20:25:16.0560051Z   adding 'executorch/backends/xnnpack/xnnpack_preprocess.py'
2025-03-21T20:25:16.0560230Z   adding 'executorch/backends/xnnpack/_passes/__init__.py'
2025-03-21T20:25:16.0560517Z   adding 'executorch/backends/xnnpack/_passes/channels_last_tagged_reshape_pass.py'
2025-03-21T20:25:16.0560742Z   adding 'executorch/backends/xnnpack/_passes/conv1d_unsqueeze_pass.py'
2025-03-21T20:25:16.0560954Z   adding 'executorch/backends/xnnpack/_passes/convert_to_linear.py'
2025-03-21T20:25:16.0561298Z   adding 'executorch/backends/xnnpack/_passes/convert_to_sdpa.py'
2025-03-21T20:25:16.0561566Z   adding 'executorch/backends/xnnpack/_passes/convert_to_upsample_bilinear2d.py'
2025-03-21T20:25:16.0561775Z   adding 'executorch/backends/xnnpack/_passes/decompose_cat.py'
2025-03-21T20:25:16.0561998Z   adding 'executorch/backends/xnnpack/_passes/fuse_activation_pass.py'
2025-03-21T20:25:16.0562252Z   adding 'executorch/backends/xnnpack/_passes/fuse_batch_norm_with_conv.py'
2025-03-21T20:25:16.0562465Z   adding 'executorch/backends/xnnpack/_passes/prelu_reshape_pass.py'
2025-03-21T20:25:16.0562675Z   adding 'executorch/backends/xnnpack/_passes/remove_getitem_op.py'
2025-03-21T20:25:16.0562914Z   adding 'executorch/backends/xnnpack/_passes/tag_implicit_q_dq_pass.py'
2025-03-21T20:25:16.0563103Z   adding 'executorch/backends/xnnpack/_passes/xnnpack_pass.py'
2025-03-21T20:25:16.0563298Z   adding 'executorch/backends/xnnpack/operators/__init__.py'
2025-03-21T20:25:16.0563500Z   adding 'executorch/backends/xnnpack/operators/node_visitor.py'
2025-03-21T20:25:16.0563694Z   adding 'executorch/backends/xnnpack/operators/op_abs.py'
2025-03-21T20:25:16.0563868Z   adding 'executorch/backends/xnnpack/operators/op_add.py'
2025-03-21T20:25:16.0564049Z   adding 'executorch/backends/xnnpack/operators/op_addmm.py'
2025-03-21T20:25:16.0564282Z   adding 'executorch/backends/xnnpack/operators/op_avg_pooling2d.py'
2025-03-21T20:25:16.0564453Z   adding 'executorch/backends/xnnpack/operators/op_bmm.py'
2025-03-21T20:25:16.0564644Z   adding 'executorch/backends/xnnpack/operators/op_cat.py'
2025-03-21T20:25:16.0564943Z   adding 'executorch/backends/xnnpack/operators/op_ceiling.py'
2025-03-21T20:25:16.0565211Z   adding 'executorch/backends/xnnpack/operators/op_clamp.py'
2025-03-21T20:25:16.0565400Z   adding 'executorch/backends/xnnpack/operators/op_conv2d.py'
2025-03-21T20:25:16.0565576Z   adding 'executorch/backends/xnnpack/operators/op_div.py'
2025-03-21T20:25:16.0565900Z   adding 'executorch/backends/xnnpack/operators/op_dynamic_dequantize_ops.py'
2025-03-21T20:25:16.0566165Z   adding 'executorch/backends/xnnpack/operators/op_dynamic_quantize_ops.py'
2025-03-21T20:25:16.0566351Z   adding 'executorch/backends/xnnpack/operators/op_elu.py'
2025-03-21T20:25:16.0566532Z   adding 'executorch/backends/xnnpack/operators/op_floor.py'
2025-03-21T20:25:16.0566744Z   adding 'executorch/backends/xnnpack/operators/op_hardswish.py'
2025-03-21T20:25:16.0566936Z   adding 'executorch/backends/xnnpack/operators/op_hardtanh.py'
2025-03-21T20:25:16.0567140Z   adding 'executorch/backends/xnnpack/operators/op_leaky_relu.py'
2025-03-21T20:25:16.0567339Z   adding 'executorch/backends/xnnpack/operators/op_linear.py'
2025-03-21T20:25:16.0567689Z   adding 'executorch/backends/xnnpack/operators/op_matrix_multiplication.py'
2025-03-21T20:25:16.0567897Z   adding 'executorch/backends/xnnpack/operators/op_max_dim.py'
2025-03-21T20:25:16.0568101Z   adding 'executorch/backends/xnnpack/operators/op_max_pool2d.py'
2025-03-21T20:25:16.0568309Z   adding 'executorch/backends/xnnpack/operators/op_maximum.py'
2025-03-21T20:25:16.0568559Z   adding 'executorch/backends/xnnpack/operators/op_mean_dim.py'
2025-03-21T20:25:16.0568752Z   adding 'executorch/backends/xnnpack/operators/op_minimum.py'
2025-03-21T20:25:16.0568956Z   adding 'executorch/backends/xnnpack/operators/op_multiply.py'
2025-03-21T20:25:16.0569137Z   adding 'executorch/backends/xnnpack/operators/op_negate.py'
2025-03-21T20:25:16.0569411Z   adding 'executorch/backends/xnnpack/operators/op_permute.py'
2025-03-21T20:25:16.0569586Z   adding 'executorch/backends/xnnpack/operators/op_prelu.py'
2025-03-21T20:25:16.0569807Z   adding 'executorch/backends/xnnpack/operators/op_quant_dequant.py'
2025-03-21T20:25:16.0569992Z   adding 'executorch/backends/xnnpack/operators/op_relu.py'
2025-03-21T20:25:16.0570280Z   adding 'executorch/backends/xnnpack/operators/op_rsqrt.py'
2025-03-21T20:25:16.0570537Z   adding 'executorch/backends/xnnpack/operators/op_sdpa.py'
2025-03-21T20:25:16.0570729Z   adding 'executorch/backends/xnnpack/operators/op_sigmoid.py'
2025-03-21T20:25:16.0571093Z   adding 'executorch/backends/xnnpack/operators/op_skip_ops.py'
2025-03-21T20:25:16.0571351Z   adding 'executorch/backends/xnnpack/operators/op_slice_copy.py'
2025-03-21T20:25:16.0571555Z   adding 'executorch/backends/xnnpack/operators/op_softmax.py'
2025-03-21T20:25:16.0571736Z   adding 'executorch/backends/xnnpack/operators/op_square.py'
2025-03-21T20:25:16.0571943Z   adding 'executorch/backends/xnnpack/operators/op_square_root.py'
2025-03-21T20:25:16.0572146Z   adding 'executorch/backends/xnnpack/operators/op_squeeze.py'
2025-03-21T20:25:16.0572388Z   adding 'executorch/backends/xnnpack/operators/op_static_constant_pad.py'
2025-03-21T20:25:16.0572666Z   adding 'executorch/backends/xnnpack/operators/op_static_resize_bilinear_2d.py'
2025-03-21T20:25:16.0572922Z   adding 'executorch/backends/xnnpack/operators/op_sub.py'
2025-03-21T20:25:16.0573183Z   adding 'executorch/backends/xnnpack/operators/op_to_copy.py'
2025-03-21T20:25:16.0573386Z   adding 'executorch/backends/xnnpack/operators/quant_params.py'
2025-03-21T20:25:16.0573574Z   adding 'executorch/backends/xnnpack/partition/configs.py'
2025-03-21T20:25:16.0573884Z   adding 'executorch/backends/xnnpack/partition/xnnpack_partitioner.py'
2025-03-21T20:25:16.0574105Z   adding 'executorch/backends/xnnpack/partition/config/__init__.py'
2025-03-21T20:25:16.0574347Z   adding 'executorch/backends/xnnpack/partition/config/gemm_configs.py'
2025-03-21T20:25:16.0574749Z   adding 'executorch/backends/xnnpack/partition/config/generic_node_configs.py'
2025-03-21T20:25:16.0575031Z   adding 'executorch/backends/xnnpack/partition/config/node_configs.py'
2025-03-21T20:25:16.0575299Z   adding 'executorch/backends/xnnpack/partition/config/quant_affine_configs.py'
2025-03-21T20:25:16.0575594Z   adding 'executorch/backends/xnnpack/partition/config/xnnpack_config.py'
2025-03-21T20:25:16.0575841Z   adding 'executorch/backends/xnnpack/partition/graphs/bilinear_2d.py'
2025-03-21T20:25:16.0576039Z   adding 'executorch/backends/xnnpack/partition/graphs/sdpa.py'
2025-03-21T20:25:16.0576284Z   adding 'executorch/backends/xnnpack/quantizer/xnnpack_quantizer.py'
2025-03-21T20:25:16.0576533Z   adding 'executorch/backends/xnnpack/quantizer/xnnpack_quantizer_utils.py'
2025-03-21T20:25:16.0854200Z   adding 'executorch/backends/xnnpack/serialization/runtime_schema.fbs'
2025-03-21T20:25:16.0854581Z   adding 'executorch/backends/xnnpack/serialization/schema.fbs'
2025-03-21T20:25:16.0855021Z   adding 'executorch/backends/xnnpack/serialization/xnnpack_graph_schema.py'
2025-03-21T20:25:16.0855514Z   adding 'executorch/backends/xnnpack/serialization/xnnpack_graph_serialize.py'
2025-03-21T20:25:16.0855887Z   adding 'executorch/backends/xnnpack/test/test_xnnpack_utils.py'
2025-03-21T20:25:16.0856288Z   adding 'executorch/backends/xnnpack/test/test_xnnpack_utils_classes.py'
2025-03-21T20:25:16.0856646Z   adding 'executorch/backends/xnnpack/test/models/deeplab_v3.py'
2025-03-21T20:25:16.0856952Z   adding 'executorch/backends/xnnpack/test/models/edsr.py'
2025-03-21T20:25:16.0857364Z   adding 'executorch/backends/xnnpack/test/models/emformer_rnnt.py'
2025-03-21T20:25:16.0857770Z   adding 'executorch/backends/xnnpack/test/models/inception_v3.py'
2025-03-21T20:25:16.0858149Z   adding 'executorch/backends/xnnpack/test/models/inception_v4.py'
2025-03-21T20:25:16.0858539Z   adding 'executorch/backends/xnnpack/test/models/llama2_et_example.py'
2025-03-21T20:25:16.0858805Z   adding 'executorch/backends/xnnpack/test/models/mobilebert.py'
2025-03-21T20:25:16.0859033Z   adding 'executorch/backends/xnnpack/test/models/mobilenet_v2.py'
2025-03-21T20:25:16.0859264Z   adding 'executorch/backends/xnnpack/test/models/mobilenet_v3.py'
2025-03-21T20:25:16.0859568Z   adding 'executorch/backends/xnnpack/test/models/resnet.py'
2025-03-21T20:25:16.0859977Z   adding 'executorch/backends/xnnpack/test/models/torchvision_vit.py'
2025-03-21T20:25:16.0860369Z   adding 'executorch/backends/xnnpack/test/models/very_big_model.py'
2025-03-21T20:25:16.0860692Z   adding 'executorch/backends/xnnpack/test/models/w2l.py'
2025-03-21T20:25:16.0861339Z   adding 'executorch/backends/xnnpack/test/ops/test_abs.py'
2025-03-21T20:25:16.0861634Z   adding 'executorch/backends/xnnpack/test/ops/test_add.py'
2025-03-21T20:25:16.0861849Z   adding 'executorch/backends/xnnpack/test/ops/test_avgpool2d.py'
2025-03-21T20:25:16.0862069Z   adding 'executorch/backends/xnnpack/test/ops/test_bilinear2d.py'
2025-03-21T20:25:16.0862374Z   adding 'executorch/backends/xnnpack/test/ops/test_bmm.py'
2025-03-21T20:25:16.0862674Z   adding 'executorch/backends/xnnpack/test/ops/test_cat.py'
2025-03-21T20:25:16.0862997Z   adding 'executorch/backends/xnnpack/test/ops/test_ceil.py'
2025-03-21T20:25:16.0863452Z   adding 'executorch/backends/xnnpack/test/ops/test_check_quant_params.py'
2025-03-21T20:25:16.0863783Z   adding 'executorch/backends/xnnpack/test/ops/test_clamp.py'
2025-03-21T20:25:16.0864114Z   adding 'executorch/backends/xnnpack/test/ops/test_conv1d.py'
2025-03-21T20:25:16.0864423Z   adding 'executorch/backends/xnnpack/test/ops/test_conv2d.py'
2025-03-21T20:25:16.0864757Z   adding 'executorch/backends/xnnpack/test/ops/test_div.py'
2025-03-21T20:25:16.0865066Z   adding 'executorch/backends/xnnpack/test/ops/test_elu.py'
2025-03-21T20:25:16.0865415Z   adding 'executorch/backends/xnnpack/test/ops/test_floor.py'
2025-03-21T20:25:16.0865783Z   adding 'executorch/backends/xnnpack/test/ops/test_hardswish.py'
2025-03-21T20:25:16.0866143Z   adding 'executorch/backends/xnnpack/test/ops/test_hardtanh.py'
2025-03-21T20:25:16.0866501Z   adding 'executorch/backends/xnnpack/test/ops/test_leaky_relu.py'
2025-03-21T20:25:16.0866834Z   adding 'executorch/backends/xnnpack/test/ops/test_linear.py'
2025-03-21T20:25:16.0867163Z   adding 'executorch/backends/xnnpack/test/ops/test_lstm.py'
2025-03-21T20:25:16.0867515Z   adding 'executorch/backends/xnnpack/test/ops/test_max_dim.py'
2025-03-21T20:25:16.0867869Z   adding 'executorch/backends/xnnpack/test/ops/test_maximum.py'
2025-03-21T20:25:16.0868226Z   adding 'executorch/backends/xnnpack/test/ops/test_maxpool2d.py'
2025-03-21T20:25:16.0868481Z   adding 'executorch/backends/xnnpack/test/ops/test_mean_dim.py'
2025-03-21T20:25:16.0868710Z   adding 'executorch/backends/xnnpack/test/ops/test_minimum.py'
2025-03-21T20:25:16.0869049Z   adding 'executorch/backends/xnnpack/test/ops/test_multiply.py'
2025-03-21T20:25:16.0869398Z   adding 'executorch/backends/xnnpack/test/ops/test_negate.py'
2025-03-21T20:25:16.0869751Z   adding 'executorch/backends/xnnpack/test/ops/test_permute.py'
2025-03-21T20:25:16.0870082Z   adding 'executorch/backends/xnnpack/test/ops/test_pow.py'
2025-03-21T20:25:16.0870402Z   adding 'executorch/backends/xnnpack/test/ops/test_prelu.py'
2025-03-21T20:25:16.0870800Z   adding 'executorch/backends/xnnpack/test/ops/test_quantize_per_tensor.py'
2025-03-21T20:25:16.0870986Z   adding 'executorch/backends/xnnpack/test/ops/test_relu.py'
2025-03-21T20:25:16.0871168Z   adding 'executorch/backends/xnnpack/test/ops/test_rsqrt.py'
2025-03-21T20:25:16.0871361Z   adding 'executorch/backends/xnnpack/test/ops/test_sdpa.py'
2025-03-21T20:25:16.0871566Z   adding 'executorch/backends/xnnpack/test/ops/test_sigmoid.py'
2025-03-21T20:25:16.0871790Z   adding 'executorch/backends/xnnpack/test/ops/test_slice_copy.py'
2025-03-21T20:25:16.0871983Z   adding 'executorch/backends/xnnpack/test/ops/test_softmax.py'
2025-03-21T20:25:16.0872175Z   adding 'executorch/backends/xnnpack/test/ops/test_sqrt.py'
2025-03-21T20:25:16.0872409Z   adding 'executorch/backends/xnnpack/test/ops/test_square.py'
2025-03-21T20:25:16.0872842Z   adding 'executorch/backends/xnnpack/test/ops/test_static_constant_pad.py'
2025-03-21T20:25:16.0873163Z   adding 'executorch/backends/xnnpack/test/ops/test_sub.py'
2025-03-21T20:25:16.0873637Z   adding 'executorch/backends/xnnpack/test/passes/test_activation_fusion.py'
2025-03-21T20:25:16.0874111Z   adding 'executorch/backends/xnnpack/test/passes/test_batch_norm_fusion.py'
2025-03-21T20:25:16.0874550Z   adding 'executorch/backends/xnnpack/test/passes/test_channels_last_tagged_reshape.py'
2025-03-21T20:25:16.0874952Z   adding 'executorch/backends/xnnpack/test/passes/test_convert_to_linear.py'
2025-03-21T20:25:16.0875543Z   adding 'executorch/backends/xnnpack/test/passes/test_decompose_cat_pass.py'
2025-03-21T20:25:16.0876033Z   adding 'executorch/backends/xnnpack/test/passes/test_remove_get_item_pass.py'
2025-03-21T20:25:16.0876546Z   adding 'executorch/backends/xnnpack/test/passes/test_tag_implicit_q_dq_pass.py'
2025-03-21T20:25:16.0877017Z   adding 'executorch/backends/xnnpack/test/quantizer/test_pt2e_quantization.py'
2025-03-21T20:25:16.0877496Z   adding 'executorch/backends/xnnpack/test/quantizer/test_representation.py'
2025-03-21T20:25:16.0877988Z   adding 'executorch/backends/xnnpack/test/quantizer/test_xnnpack_quantizer.py'
2025-03-21T20:25:16.0878506Z   adding 'executorch/backends/xnnpack/test/serialization/test_serialization.py'
2025-03-21T20:25:16.0878957Z   adding 'executorch/backends/xnnpack/test/serialization/test_xnnheader.py'
2025-03-21T20:25:16.0879296Z   adding 'executorch/backends/xnnpack/test/tester/__init__.py'
2025-03-21T20:25:16.0879653Z   adding 'executorch/backends/xnnpack/test/tester/tester.py'
2025-03-21T20:25:16.0880175Z   adding 'executorch/backends/xnnpack/third-party/generate-cpuinfo-wrappers.py'
2025-03-21T20:25:16.0880588Z   adding 'executorch/backends/xnnpack/third-party/FP16/configure.py'
2025-03-21T20:25:16.0880950Z   adding 'executorch/backends/xnnpack/third-party/FP16/confu.yaml'
2025-03-21T20:25:16.0881448Z   adding 'executorch/backends/xnnpack/third-party/FP16/include/fp16/__init__.py'
2025-03-21T20:25:16.0881907Z   adding 'executorch/backends/xnnpack/third-party/FP16/include/fp16/avx.py'
2025-03-21T20:25:16.0882362Z   adding 'executorch/backends/xnnpack/third-party/FP16/include/fp16/avx2.py'
2025-03-21T20:25:16.0882828Z   adding 'executorch/backends/xnnpack/third-party/FP16/test/peachpy/stubs.py'
2025-03-21T20:25:16.0883222Z   adding 'executorch/backends/xnnpack/third-party/FXdiv/configure.py'
2025-03-21T20:25:16.0883619Z   adding 'executorch/backends/xnnpack/third-party/FXdiv/confu.yaml'
2025-03-21T20:25:16.0884171Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/scripts/check_config.py'
2025-03-21T20:25:16.0884743Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/scripts/check_files_changed.py'
2025-03-21T20:25:16.0885370Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/scripts/generate-build-identifier.py'
2025-03-21T20:25:16.0885934Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/scripts/sort-filenames.py'
2025-03-21T20:25:16.0886469Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/bf16-gemm-minmax.yaml'
2025-03-21T20:25:16.0886907Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f16-conv-hwc2chw.yaml'
2025-03-21T20:25:16.0887447Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f16-dwconv2d-chw.yaml'
2025-03-21T20:25:16.0888075Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f16-f32acc-gemm-minmax.yaml'
2025-03-21T20:25:16.0888676Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f16-f32acc-igemm-minmax.yaml'
2025-03-21T20:25:16.0889191Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f16-f32acc-rdsum.yaml'
2025-03-21T20:25:16.0889793Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f16-f32acc-rsum.yaml'
2025-03-21T20:25:16.0890328Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f16-gemm-minmax.yaml'
2025-03-21T20:25:16.0890863Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f16-ibilinear-chw.yaml'
2025-03-21T20:25:16.0891350Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f16-ibilinear.yaml'
2025-03-21T20:25:16.0891888Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f16-igemm-minmax.yaml'
2025-03-21T20:25:16.0892528Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f16-raddstoreexpminusmax.yaml'
2025-03-21T20:25:16.0892939Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f16-rmax.yaml'
2025-03-21T20:25:16.0893339Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f16-rmin.yaml'
2025-03-21T20:25:16.0894053Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f16-rminmax.yaml'
2025-03-21T20:25:16.0894546Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f16-rsum.yaml'
2025-03-21T20:25:16.0895061Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f16-spmm-minmax.yaml'
2025-03-21T20:25:16.0895396Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f16-vmulcaddc-minmax.yaml'
2025-03-21T20:25:16.0895681Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f32-argmaxpool.yaml'
2025-03-21T20:25:16.0895972Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f32-conv-hwc.yaml'
2025-03-21T20:25:16.0896494Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f32-conv-hwc2chw.yaml'
2025-03-21T20:25:16.0897025Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f32-dwconv2d-chw.yaml'
2025-03-21T20:25:16.0897597Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f32-gemm-goi-minmax.yaml'
2025-03-21T20:25:16.0898092Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f32-gemm-minmax.yaml'
2025-03-21T20:25:16.0898602Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f32-gemm-relu.yaml'
2025-03-21T20:25:16.0899063Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f32-gemm.yaml'
2025-03-21T20:25:16.1152357Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f32-gemminc-minmax.yaml'
2025-03-21T20:25:16.1152910Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f32-ibilinear-chw.yaml'
2025-03-21T20:25:16.1153381Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f32-ibilinear.yaml'
2025-03-21T20:25:16.1153902Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f32-igemm-minmax.yaml'
2025-03-21T20:25:16.1154522Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f32-igemm-relu.yaml'
2025-03-21T20:25:16.1154869Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f32-igemm.yaml'
2025-03-21T20:25:16.1155260Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f32-ppmm-minmax.yaml'
2025-03-21T20:25:16.1155670Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f32-qc4w-gemm-minmax.yaml'
2025-03-21T20:25:16.1156198Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f32-qc8w-gemm-minmax.yaml'
2025-03-21T20:25:16.1156760Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f32-qc8w-gemm-relu.yaml'
2025-03-21T20:25:16.1157260Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f32-qc8w-gemm.yaml'
2025-03-21T20:25:16.1157741Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f32-raddexpminusmax.yaml'
2025-03-21T20:25:16.1158086Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f32-raddextexp.yaml'
2025-03-21T20:25:16.1158418Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f32-raddstoreexpminusmax.yaml'
2025-03-21T20:25:16.1158707Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f32-rdsum.yaml'
2025-03-21T20:25:16.1158974Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f32-rmax.yaml'
2025-03-21T20:25:16.1159229Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f32-rmin.yaml'
2025-03-21T20:25:16.1159514Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f32-rminmax.yaml'
2025-03-21T20:25:16.1159764Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f32-rsum.yaml'
2025-03-21T20:25:16.1160064Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f32-spmm-minmax.yaml'
2025-03-21T20:25:16.1160372Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f32-vmulcaddc-minmax.yaml'
2025-03-21T20:25:16.1160700Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f32-vscaleexpminusmax.yaml'
2025-03-21T20:25:16.1160991Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/f32-vscaleextexp.yaml'
2025-03-21T20:25:16.1161331Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/qd8-f16-qb4w-gemm-minmax.yaml'
2025-03-21T20:25:16.1161887Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/qd8-f16-qc4w-gemm-minmax.yaml'
2025-03-21T20:25:16.1162211Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/qd8-f16-qc8w-gemm-minmax.yaml'
2025-03-21T20:25:16.1162554Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/qd8-f16-qc8w-igemm-minmax.yaml'
2025-03-21T20:25:16.1162876Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/qd8-f32-qb4w-gemm-minmax.yaml'
2025-03-21T20:25:16.1163210Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/qd8-f32-qc4w-gemm-minmax.yaml'
2025-03-21T20:25:16.1163532Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/qd8-f32-qc8w-gemm-minmax.yaml'
2025-03-21T20:25:16.1163874Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/qd8-f32-qc8w-igemm-minmax.yaml'
2025-03-21T20:25:16.1164196Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/qp8-f32-qb4w-gemm-minmax.yaml'
2025-03-21T20:25:16.1164537Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/qp8-f32-qc4w-gemm-minmax.yaml'
2025-03-21T20:25:16.1164869Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/qs8-qc8w-gemm-minmax-fp32.yaml'
2025-03-21T20:25:16.1165210Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/qs8-qc8w-igemm-minmax-fp32.yaml'
2025-03-21T20:25:16.1165535Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/qs8-rdsum-minmax-fp32.yaml'
2025-03-21T20:25:16.1165791Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/qs8-rsum.yaml'
2025-03-21T20:25:16.1166112Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/qu8-gemm-minmax-fp32.yaml'
2025-03-21T20:25:16.1166423Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/qu8-gemm-minmax-rndnu.yaml'
2025-03-21T20:25:16.1166748Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/qu8-igemm-minmax-fp32.yaml'
2025-03-21T20:25:16.1167068Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/qu8-igemm-minmax-rndnu.yaml'
2025-03-21T20:25:16.1167343Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/qu8-rdsum.yaml'
2025-03-21T20:25:16.1167596Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/qu8-rsum.yaml'
2025-03-21T20:25:16.1167864Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/s8-ibilinear.yaml'
2025-03-21T20:25:16.1168146Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/u8-ibilinear.yaml'
2025-03-21T20:25:16.1168416Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/u8-lut32norm.yaml'
2025-03-21T20:25:16.1168678Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/u8-rmax.yaml'
2025-03-21T20:25:16.1168923Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/test/x8-lut.yaml'
2025-03-21T20:25:16.1169352Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-argmaxpool-test.py'
2025-03-21T20:25:16.1169669Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-conv-hwc-test.py'
2025-03-21T20:25:16.1170012Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-conv-hwc2chw-test.py'
2025-03-21T20:25:16.1170386Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-dwconv-multipass-test.py'
2025-03-21T20:25:16.1170730Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-dwconv-unipass-test.py'
2025-03-21T20:25:16.1171078Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-dwconv2d-chw-test.py'
2025-03-21T20:25:16.1171373Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-gemm-test.py'
2025-03-21T20:25:16.1171724Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-ibilinear-chw-test.py'
2025-03-21T20:25:16.1172042Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-ibilinear-test.py'
2025-03-21T20:25:16.1172368Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-lut-norm-test.py'
2025-03-21T20:25:16.1172773Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-lut-test.py'
2025-03-21T20:25:16.1173126Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-raddexpminusmax-test.py'
2025-03-21T20:25:16.1173461Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-raddextexp-test.py'
2025-03-21T20:25:16.1173846Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-raddstoreexpminusmax-test.py'
2025-03-21T20:25:16.1174182Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-rdsum-benchmark.py'
2025-03-21T20:25:16.1174478Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-rdsum-test.py'
2025-03-21T20:25:16.1174792Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-reduce-test.py'
2025-03-21T20:25:16.1175085Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-spmm-test.py'
2025-03-21T20:25:16.1175407Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-vbinary-test.py'
2025-03-21T20:25:16.1175730Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-vmulcaddc-test.py'
2025-03-21T20:25:16.1176099Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-vscaleexpminusmax-test.py'
2025-03-21T20:25:16.1176446Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-vscaleextexp-test.py'
2025-03-21T20:25:16.1176747Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/tools/generate-vunary-test.py'
2025-03-21T20:25:16.1177007Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/tools/primes.py'
2025-03-21T20:25:16.1177304Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/tools/update-microkernels.py'
2025-03-21T20:25:16.1177553Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/tools/xngen.py'
2025-03-21T20:25:16.1177807Z   adding 'executorch/backends/xnnpack/third-party/XNNPACK/tools/xnncommon.py'
2025-03-21T20:25:16.1178040Z   adding 'executorch/backends/xnnpack/third-party/cpuinfo/configure.py'
2025-03-21T20:25:16.1178272Z   adding 'executorch/backends/xnnpack/third-party/cpuinfo/confu.yaml'
2025-03-21T20:25:16.1178541Z   adding 'executorch/backends/xnnpack/third-party/cpuinfo/deps/clog/configure.py'
2025-03-21T20:25:16.1178812Z   adding 'executorch/backends/xnnpack/third-party/cpuinfo/deps/clog/confu.yaml'
2025-03-21T20:25:16.1179121Z   adding 'executorch/backends/xnnpack/third-party/cpuinfo/scripts/android-device-dump.py'
2025-03-21T20:25:16.1179472Z   adding 'executorch/backends/xnnpack/third-party/cpuinfo/scripts/arm-linux-filesystem-dump.py'
2025-03-21T20:25:16.1179784Z   adding 'executorch/backends/xnnpack/third-party/cpuinfo/scripts/parse-x86-cpuid-dump.py'
2025-03-21T20:25:16.1180047Z   adding 'executorch/backends/xnnpack/third-party/pthreadpool/configure.py'
2025-03-21T20:25:16.1180289Z   adding 'executorch/backends/xnnpack/third-party/pthreadpool/confu.yaml'
2025-03-21T20:25:16.1180454Z   adding 'executorch/backends/xnnpack/utils/configs.py'
2025-03-21T20:25:16.1180652Z   adding 'executorch/backends/xnnpack/utils/quant_utils.py'
2025-03-21T20:25:16.1180805Z   adding 'executorch/backends/xnnpack/utils/utils.py'
2025-03-21T20:25:16.1181021Z   adding 'executorch/backends/xnnpack/utils/xnnpack_constants.py'
2025-03-21T20:25:16.1181142Z   adding 'executorch/codegen/__init__.py'
2025-03-21T20:25:16.1181278Z   adding 'executorch/codegen/tools/__init__.py'
2025-03-21T20:25:16.1181442Z   adding 'executorch/codegen/tools/gen_all_oplist.py'
2025-03-21T20:25:16.1181582Z   adding 'executorch/codegen/tools/gen_oplist.py'
2025-03-21T20:25:16.1181734Z   adding 'executorch/codegen/tools/gen_ops_def.py'
2025-03-21T20:25:16.1181926Z   adding 'executorch/codegen/tools/gen_selected_op_variants.py'
2025-03-21T20:25:16.1182074Z   adding 'executorch/codegen/tools/merge_yaml.py'
2025-03-21T20:25:16.1182211Z   adding 'executorch/codegen/tools/yaml_util.py'
2025-03-21T20:25:16.1182400Z   adding 'executorch/codegen/tools/test/test_gen_all_oplist.py'
2025-03-21T20:25:16.1182685Z   adding 'executorch/codegen/tools/test/test_gen_oplist.py'
2025-03-21T20:25:16.4446205Z   adding 'executorch/codegen/tools/test/test_gen_oplist_real_model.py'
2025-03-21T20:25:16.4447332Z   adding 'executorch/codegen/tools/test/test_gen_selected_op_variants.py'
2025-03-21T20:25:16.4448195Z   adding 'executorch/data/bin/__init__.py'
2025-03-21T20:25:16.4448764Z   adding 'executorch/data/bin/flatc'
2025-03-21T20:25:16.4449451Z   adding 'executorch/devtools/__init__.py'
2025-03-21T20:25:16.4450155Z   adding 'executorch/devtools/backend_debug/__init__.py'
2025-03-21T20:25:16.4450972Z   adding 'executorch/devtools/backend_debug/delegation_info.py'
2025-03-21T20:25:16.4451967Z   adding 'executorch/devtools/backend_debug/tests/test_delegation_info.py'
2025-03-21T20:25:16.4452906Z   adding 'executorch/devtools/bundled_program/config.py'
2025-03-21T20:25:16.4453655Z   adding 'executorch/devtools/bundled_program/core.py'
2025-03-21T20:25:16.4454394Z   adding 'executorch/devtools/bundled_program/version.py'
2025-03-21T20:25:16.4455308Z   adding 'executorch/devtools/bundled_program/schema/__init__.py'
2025-03-21T20:25:16.4456328Z   adding 'executorch/devtools/bundled_program/schema/bundled_program_schema.fbs'
2025-03-21T20:25:16.4457480Z   adding 'executorch/devtools/bundled_program/schema/bundled_program_schema.py'
2025-03-21T20:25:16.4458558Z   adding 'executorch/devtools/bundled_program/schema/scalar_type.fbs'
2025-03-21T20:25:16.4459550Z   adding 'executorch/devtools/bundled_program/schema/test/test_schema.py'
2025-03-21T20:25:16.4460550Z   adding 'executorch/devtools/bundled_program/serialize/__init__.py'
2025-03-21T20:25:16.4461621Z   adding 'executorch/devtools/bundled_program/serialize/bundled_program_schema.fbs'
2025-03-21T20:25:16.4462757Z   adding 'executorch/devtools/bundled_program/serialize/scalar_type.fbs'
2025-03-21T20:25:16.4463871Z   adding 'executorch/devtools/bundled_program/serialize/test/test_serialize.py'
2025-03-21T20:25:16.4464963Z   adding 'executorch/devtools/bundled_program/test/test_bundle_data.py'
2025-03-21T20:25:16.4465945Z   adding 'executorch/devtools/bundled_program/test/test_config.py'
2025-03-21T20:25:16.4466913Z   adding 'executorch/devtools/bundled_program/test/test_end2end.py'
2025-03-21T20:25:16.4467858Z   adding 'executorch/devtools/bundled_program/util/test_util.py'
2025-03-21T20:25:16.4468730Z   adding 'executorch/devtools/debug_format/base_schema.py'
2025-03-21T20:25:16.4469499Z   adding 'executorch/devtools/debug_format/et_schema.py'
2025-03-21T20:25:16.4470297Z   adding 'executorch/devtools/etdump/etdump_schema_flatcc.fbs'
2025-03-21T20:25:16.4471078Z   adding 'executorch/devtools/etdump/scalar_type.fbs'
2025-03-21T20:25:16.4471808Z   adding 'executorch/devtools/etdump/schema_flatcc.py'
2025-03-21T20:25:16.4472548Z   adding 'executorch/devtools/etdump/serialize.py'
2025-03-21T20:25:16.4473299Z   adding 'executorch/devtools/etdump/tests/serialize_test.py'
2025-03-21T20:25:16.4474082Z   adding 'executorch/devtools/etrecord/__init__.py'
2025-03-21T20:25:16.4474773Z   adding 'executorch/devtools/etrecord/_etrecord.py'
2025-03-21T20:25:16.4475605Z   adding 'executorch/devtools/etrecord/tests/etrecord_test.py'
2025-03-21T20:25:16.4476387Z   adding 'executorch/devtools/inspector/__init__.py'
2025-03-21T20:25:16.4477133Z   adding 'executorch/devtools/inspector/_inspector.py'
2025-03-21T20:25:16.4477921Z   adding 'executorch/devtools/inspector/_inspector_utils.py'
2025-03-21T20:25:16.4478748Z   adding 'executorch/devtools/inspector/inspector_cli.py'
2025-03-21T20:25:16.4479615Z   adding 'executorch/devtools/inspector/tests/event_blocks_test.py'
2025-03-21T20:25:16.4480558Z   adding 'executorch/devtools/inspector/tests/inspector_test.py'
2025-03-21T20:25:16.4481529Z   adding 'executorch/devtools/inspector/tests/inspector_utils_test.py'
2025-03-21T20:25:16.4482556Z   adding 'executorch/devtools/size_analysis_tool/size_analysis_tool.py'
2025-03-21T20:25:16.4483581Z   adding 'executorch/devtools/size_analysis_tool/size_analysis_tool_test.py'
2025-03-21T20:25:16.4484510Z   adding 'executorch/devtools/visualization/__init__.py'
2025-03-21T20:25:16.4485813Z   adding 'executorch/devtools/visualization/visualization_utils.py'
2025-03-21T20:25:16.4486845Z   adding 'executorch/devtools/visualization/visualization_utils_test.py'
2025-03-21T20:25:16.4487774Z   adding 'executorch/examples/apple/coreml/llama/export.py'
2025-03-21T20:25:16.4488689Z   adding 'executorch/examples/apple/coreml/llama/llama_transformer.py'
2025-03-21T20:25:16.4489654Z   adding 'executorch/examples/apple/coreml/llama/run.py'
2025-03-21T20:25:16.4490427Z   adding 'executorch/examples/apple/coreml/llama/test.py'
2025-03-21T20:25:16.4491245Z   adding 'executorch/examples/apple/coreml/llama/utils.py'
2025-03-21T20:25:16.4492072Z   adding 'executorch/examples/llm_pte_finetuning/__init__.py'
2025-03-21T20:25:16.4492994Z   adding 'executorch/examples/llm_pte_finetuning/model_exporter.py'
2025-03-21T20:25:16.4493945Z   adding 'executorch/examples/llm_pte_finetuning/model_loading_lib.py'
2025-03-21T20:25:16.4495009Z   adding 'executorch/examples/llm_pte_finetuning/phi3_alpaca_code_config.yaml'
2025-03-21T20:25:16.4496049Z   adding 'executorch/examples/llm_pte_finetuning/phi3_config.yaml'
2025-03-21T20:25:16.4497013Z   adding 'executorch/examples/llm_pte_finetuning/qwen_05b_config.yaml'
2025-03-21T20:25:16.4497925Z   adding 'executorch/examples/llm_pte_finetuning/runner.py'
2025-03-21T20:25:16.4498807Z   adding 'executorch/examples/llm_pte_finetuning/training_lib.py'
2025-03-21T20:25:16.4499577Z   adding 'executorch/examples/models/__init__.py'
2025-03-21T20:25:16.4500294Z   adding 'executorch/examples/models/checkpoint.py'
2025-03-21T20:25:16.4500999Z   adding 'executorch/examples/models/model_base.py'
2025-03-21T20:25:16.4501711Z   adding 'executorch/examples/models/model_factory.py'
2025-03-21T20:25:16.4502511Z   adding 'executorch/examples/models/deeplab_v3/__init__.py'
2025-03-21T20:25:16.4503332Z   adding 'executorch/examples/models/deeplab_v3/model.py'
2025-03-21T20:25:16.4504078Z   adding 'executorch/examples/models/edsr/__init__.py'
2025-03-21T20:25:16.4504826Z   adding 'executorch/examples/models/edsr/model.py'
2025-03-21T20:25:16.4505606Z   adding 'executorch/examples/models/efficient_sam/__init__.py'
2025-03-21T20:25:16.4506475Z   adding 'executorch/examples/models/efficient_sam/model.py'
2025-03-21T20:25:16.4507555Z   adding 'executorch/examples/models/efficient_sam/efficient_sam_core/build_efficient_sam.py'
2025-03-21T20:25:16.4508876Z   adding 'executorch/examples/models/efficient_sam/efficient_sam_core/efficient_sam.py'
2025-03-21T20:25:16.4510261Z   adding 'executorch/examples/models/efficient_sam/efficient_sam_core/efficient_sam_decoder.py'
2025-03-21T20:25:16.4511673Z   adding 'executorch/examples/models/efficient_sam/efficient_sam_core/efficient_sam_encoder.py'
2025-03-21T20:25:16.4512943Z   adding 'executorch/examples/models/efficient_sam/efficient_sam_core/mlp.py'
2025-03-21T20:25:16.4514181Z   adding 'executorch/examples/models/efficient_sam/efficient_sam_core/two_way_transformer.py'
2025-03-21T20:25:16.4515336Z   adding 'executorch/examples/models/emformer_rnnt/__init__.py'
2025-03-21T20:25:16.4516204Z   adding 'executorch/examples/models/emformer_rnnt/model.py'
2025-03-21T20:25:16.4517059Z   adding 'executorch/examples/models/inception_v3/__init__.py'
2025-03-21T20:25:16.4517918Z   adding 'executorch/examples/models/inception_v3/model.py'
2025-03-21T20:25:16.4518780Z   adding 'executorch/examples/models/inception_v4/__init__.py'
2025-03-21T20:25:16.4519640Z   adding 'executorch/examples/models/inception_v4/model.py'
2025-03-21T20:25:16.4520444Z   adding 'executorch/examples/models/llama/__init__.py'
2025-03-21T20:25:16.4521194Z   adding 'executorch/examples/models/llama/attention.py'
2025-03-21T20:25:16.4521960Z   adding 'executorch/examples/models/llama/eval_llama.py'
2025-03-21T20:25:16.4522752Z   adding 'executorch/examples/models/llama/eval_llama_lib.py'
2025-03-21T20:25:16.4523585Z   adding 'executorch/examples/models/llama/export_llama.py'
2025-03-21T20:25:16.4524437Z   adding 'executorch/examples/models/llama/export_llama_lib.py'
2025-03-21T20:25:16.4525555Z   adding 'executorch/examples/models/llama/fairseq2.py'
2025-03-21T20:25:16.4526455Z   adding 'executorch/examples/models/llama/install_requirement_helper.py'
2025-03-21T20:25:16.4527389Z   adding 'executorch/examples/models/llama/llama_test.py'
2025-03-21T20:25:16.4528232Z   adding 'executorch/examples/models/llama/llama_transformer.py'
2025-03-21T20:25:16.4529066Z   adding 'executorch/examples/models/llama/model.py'
2025-03-21T20:25:16.4529878Z   adding 'executorch/examples/models/llama/model_args.py'
2025-03-21T20:25:16.4530612Z   adding 'executorch/examples/models/llama/norm.py'
2025-03-21T20:25:16.4531314Z   adding 'executorch/examples/models/llama/rope.py'
2025-03-21T20:25:16.4532111Z   adding 'executorch/examples/models/llama/static_attention.py'
2025-03-21T20:25:16.4533188Z   adding 'executorch/examples/models/llama/evaluate/__init__.py'
2025-03-21T20:25:16.4534092Z   adding 'executorch/examples/models/llama/evaluate/eager_eval.py'
2025-03-21T20:25:16.4535060Z   adding 'executorch/examples/models/llama/experimental/generate.py'
2025-03-21T20:25:16.4536099Z   adding 'executorch/examples/models/llama/experimental/load_gguf_q4_0.py'
2025-03-21T20:25:16.4537138Z   adding 'executorch/examples/models/llama/experimental/subclass.py'
2025-03-21T20:25:16.4538165Z   adding 'executorch/examples/models/llama/experimental/test_subclass.py'
2025-03-21T20:25:16.4539108Z   adding 'executorch/examples/models/llama/runner/eager.py'
2025-03-21T20:25:16.4539984Z   adding 'executorch/examples/models/llama/runner/generation.py'
2025-03-21T20:25:16.4540840Z   adding 'executorch/examples/models/llama/runner/native.py'
2025-03-21T20:25:16.4541820Z   adding 'executorch/examples/models/llama/source_transformation/__init__.py'
2025-03-21T20:25:16.4543066Z   adding 'executorch/examples/models/llama/source_transformation/apply_spin_quant_r1_r2.py'
2025-03-21T20:25:16.4544321Z   adding 'executorch/examples/models/llama/source_transformation/attention.py'
2025-03-21T20:25:16.4545527Z   adding 'executorch/examples/models/llama/source_transformation/attention_sink.py'
2025-03-21T20:25:16.4546699Z   adding 'executorch/examples/models/llama/source_transformation/lora.py'
2025-03-21T20:25:16.4547852Z   adding 'executorch/examples/models/llama/source_transformation/pre_quantization.py'
2025-03-21T20:25:16.4549105Z   adding 'executorch/examples/models/llama/source_transformation/prune_vocab.py'
2025-03-21T20:25:16.4550262Z   adding 'executorch/examples/models/llama/source_transformation/quantize.py'
2025-03-21T20:25:16.4551489Z   adding 'executorch/examples/models/llama/source_transformation/quantized_kv_cache.py'
2025-03-21T20:25:16.4552736Z   adding 'executorch/examples/models/llama/source_transformation/rms_norm.py'
2025-03-21T20:25:16.4553817Z   adding 'executorch/examples/models/llama/source_transformation/rope.py'
2025-03-21T20:25:16.4554886Z   adding 'executorch/examples/models/llama/source_transformation/sdpa.py'
2025-03-21T20:25:16.4555988Z   adding 'executorch/examples/models/llama/source_transformation/spin_quant.py'
2025-03-21T20:25:16.4557255Z   adding 'executorch/examples/models/llama/source_transformation/test_attention_sink.py'
2025-03-21T20:25:16.4558602Z   adding 'executorch/examples/models/llama/source_transformation/test_quantized_kv_cache.py'
2025-03-21T20:25:16.4560059Z   adding 'executorch/examples/models/llama/source_transformation/test_sdpa_with_quantized_kv_cache.py'
2025-03-21T20:25:16.4561421Z   adding 'executorch/examples/models/llama/source_transformation/vulkan_rope.py'
2025-03-21T20:25:16.4960312Z   adding 'executorch/examples/models/llama/tests/test_pre_quantization_transforms.py'
2025-03-21T20:25:16.4961090Z   adding 'executorch/examples/models/llama/tests/test_simple_sdpa.py'
2025-03-21T20:25:16.4961673Z   adding 'executorch/examples/models/llama/tests/test_static_attention.py'
2025-03-21T20:25:16.4962249Z   adding 'executorch/examples/models/llama/tokenizer/tiktoken.py'
2025-03-21T20:25:16.4962779Z   adding 'executorch/examples/models/llama3_2_vision/__init__.py'
2025-03-21T20:25:16.4963635Z   adding 'executorch/examples/models/llama3_2_vision/preprocess/__init__.py'
2025-03-21T20:25:16.4964300Z   adding 'executorch/examples/models/llama3_2_vision/preprocess/export_preprocess.py'
2025-03-21T20:25:16.4964939Z   adding 'executorch/examples/models/llama3_2_vision/preprocess/model.py'
2025-03-21T20:25:16.4965580Z   adding 'executorch/examples/models/llama3_2_vision/preprocess/test_preprocess.py'
2025-03-21T20:25:16.4966201Z   adding 'executorch/examples/models/llama3_2_vision/runner/eager.py'
2025-03-21T20:25:16.4966766Z   adding 'executorch/examples/models/llama3_2_vision/runner/exported.py'
2025-03-21T20:25:16.4967359Z   adding 'executorch/examples/models/llama3_2_vision/runner/generation.py'
2025-03-21T20:25:16.4967942Z   adding 'executorch/examples/models/llama3_2_vision/runner/native.py'
2025-03-21T20:25:16.4968508Z   adding 'executorch/examples/models/llama3_2_vision/text_decoder/model.py'
2025-03-21T20:25:16.4969144Z   adding 'executorch/examples/models/llama3_2_vision/text_decoder/test/__init__.py'
2025-03-21T20:25:16.4969945Z   adding 'executorch/examples/models/llama3_2_vision/text_decoder/test/test_text_decoder.py'
2025-03-21T20:25:16.4970640Z   adding 'executorch/examples/models/llama3_2_vision/vision_encoder/__init__.py'
2025-03-21T20:25:16.4971270Z   adding 'executorch/examples/models/llama3_2_vision/vision_encoder/model.py'
2025-03-21T20:25:16.4971919Z   adding 'executorch/examples/models/llama3_2_vision/vision_encoder/test/__init__.py'
2025-03-21T20:25:16.4972636Z   adding 'executorch/examples/models/llama3_2_vision/vision_encoder/test/test_vision_encoder.py'
2025-03-21T20:25:16.4973247Z   adding 'executorch/examples/models/llava/__init__.py'
2025-03-21T20:25:16.4973705Z   adding 'executorch/examples/models/llava/export_llava.py'
2025-03-21T20:25:16.4974173Z   adding 'executorch/examples/models/llava/image_util.py'
2025-03-21T20:25:16.4974611Z   adding 'executorch/examples/models/llava/model.py'
2025-03-21T20:25:16.4975096Z   adding 'executorch/examples/models/llava/test/test_llava.py'
2025-03-21T20:25:16.4975589Z   adding 'executorch/examples/models/llava/test/test_pte.py'
2025-03-21T20:25:16.4976031Z   adding 'executorch/examples/models/lstm/__init__.py'
2025-03-21T20:25:16.4976450Z   adding 'executorch/examples/models/lstm/model.py'
2025-03-21T20:25:16.4976894Z   adding 'executorch/examples/models/mobilebert/__init__.py'
2025-03-21T20:25:16.4977359Z   adding 'executorch/examples/models/mobilebert/model.py'
2025-03-21T20:25:16.4977833Z   adding 'executorch/examples/models/mobilenet_v2/__init__.py'
2025-03-21T20:25:16.4978317Z   adding 'executorch/examples/models/mobilenet_v2/model.py'
2025-03-21T20:25:16.4978781Z   adding 'executorch/examples/models/mobilenet_v3/__init__.py'
2025-03-21T20:25:16.4979321Z   adding 'executorch/examples/models/mobilenet_v3/model.py'
2025-03-21T20:25:16.4979800Z   adding 'executorch/examples/models/moshi/mimi/test_mimi.py'
2025-03-21T20:25:16.4980285Z   adding 'executorch/examples/models/phi-3-mini/__init__.py'
2025-03-21T20:25:16.4980757Z   adding 'executorch/examples/models/phi-3-mini/eager.py'
2025-03-21T20:25:16.4981256Z   adding 'executorch/examples/models/phi-3-mini/export_phi-3-mini.py'
2025-03-21T20:25:16.4981788Z   adding 'executorch/examples/models/phi-3-mini/phi_3_mini.py'
2025-03-21T20:25:16.4982289Z   adding 'executorch/examples/models/phi-3-mini/static_cache.py'
2025-03-21T20:25:16.4982823Z   adding 'executorch/examples/models/phi-3-mini-lora/export_model.py'
2025-03-21T20:25:16.4983340Z   adding 'executorch/examples/models/phi-4-mini/__init__.py'
2025-03-21T20:25:16.4983844Z   adding 'executorch/examples/models/phi-4-mini/convert_weights.py'
2025-03-21T20:25:16.4984334Z   adding 'executorch/examples/models/qwen2_5/__init__.py'
2025-03-21T20:25:16.4984822Z   adding 'executorch/examples/models/qwen2_5/convert_weights.py'
2025-03-21T20:25:16.4985339Z   adding 'executorch/examples/models/resnet/__init__.py'
2025-03-21T20:25:16.4985872Z   adding 'executorch/examples/models/resnet/model.py'
2025-03-21T20:25:16.4986294Z   adding 'executorch/examples/models/test/__init__.py'
2025-03-21T20:25:16.4986876Z   adding 'executorch/examples/models/test/test_export.py'
2025-03-21T20:25:16.4987368Z   adding 'executorch/examples/models/torchvision_vit/__init__.py'
2025-03-21T20:25:16.4987923Z   adding 'executorch/examples/models/torchvision_vit/model.py'
2025-03-21T20:25:16.4988477Z   adding 'executorch/examples/models/toy_model/__init__.py'
2025-03-21T20:25:16.4988934Z   adding 'executorch/examples/models/toy_model/model.py'
2025-03-21T20:25:16.4989379Z   adding 'executorch/examples/models/wav2letter/__init__.py'
2025-03-21T20:25:16.4989841Z   adding 'executorch/examples/models/wav2letter/model.py'
2025-03-21T20:25:16.4990280Z   adding 'executorch/exir/__init__.py'
2025-03-21T20:25:16.4990649Z   adding 'executorch/exir/_warnings.py'
2025-03-21T20:25:16.4991024Z   adding 'executorch/exir/common.py'
2025-03-21T20:25:16.4991361Z   adding 'executorch/exir/control_flow.py'
2025-03-21T20:25:16.4991697Z   adding 'executorch/exir/delegate.py'
2025-03-21T20:25:16.4992046Z   adding 'executorch/exir/delegate.pyi'
2025-03-21T20:25:16.4992440Z   adding 'executorch/exir/dim_order_utils.py'
2025-03-21T20:25:16.4992816Z   adding 'executorch/exir/dynamic_shape.py'
2025-03-21T20:25:16.4993228Z   adding 'executorch/exir/error.py'
2025-03-21T20:25:16.4993543Z   adding 'executorch/exir/graph.py'
2025-03-21T20:25:16.4993879Z   adding 'executorch/exir/graph_module.py'
2025-03-21T20:25:16.4994267Z   adding 'executorch/exir/lowered_backend_module.py'
2025-03-21T20:25:16.4994672Z   adding 'executorch/exir/memory.py'
2025-03-21T20:25:16.4995039Z   adding 'executorch/exir/memory_planning.py'
2025-03-21T20:25:16.4995459Z   adding 'executorch/exir/pass_base.py'
2025-03-21T20:25:16.4995812Z   adding 'executorch/exir/pass_manager.py'
2025-03-21T20:25:16.4996174Z   adding 'executorch/exir/print_program.py'
2025-03-21T20:25:16.4996531Z   adding 'executorch/exir/scalar_type.py'
2025-03-21T20:25:16.4996910Z   adding 'executorch/exir/schema.py'
2025-03-21T20:25:16.4997239Z   adding 'executorch/exir/sym_util.py'
2025-03-21T20:25:16.4997692Z   adding 'executorch/exir/tensor.py'
2025-03-21T20:25:16.4998017Z   adding 'executorch/exir/tracer.py'
2025-03-21T20:25:16.4998343Z   adding 'executorch/exir/types.py'
2025-03-21T20:25:16.4998676Z   adding 'executorch/exir/version.py'
2025-03-21T20:25:16.4998997Z   adding 'executorch/exir/wrap.py'
2025-03-21T20:25:16.4999356Z   adding 'executorch/exir/_serialize/__init__.py'
2025-03-21T20:25:16.4999756Z   adding 'executorch/exir/_serialize/_cord.py'
2025-03-21T20:25:16.5000155Z   adding 'executorch/exir/_serialize/_dataclass.py'
2025-03-21T20:25:16.5000576Z   adding 'executorch/exir/_serialize/_flatbuffer.py'
2025-03-21T20:25:16.5001007Z   adding 'executorch/exir/_serialize/_named_data_store.py'
2025-03-21T20:25:16.5001446Z   adding 'executorch/exir/_serialize/_program.py'
2025-03-21T20:25:16.5001857Z   adding 'executorch/exir/_serialize/_serialize.py'
2025-03-21T20:25:16.5002293Z   adding 'executorch/exir/_serialize/data_serializer.py'
2025-03-21T20:25:16.5002766Z   adding 'executorch/exir/_serialize/padding.py'
2025-03-21T20:25:16.5003218Z   adding 'executorch/exir/_serialize/program.fbs'
2025-03-21T20:25:16.5003635Z   adding 'executorch/exir/_serialize/scalar_type.fbs'
2025-03-21T20:25:16.5004062Z   adding 'executorch/exir/_serialize/test/__init__.py'
2025-03-21T20:25:16.5004501Z   adding 'executorch/exir/_serialize/test/test_cord.py'
2025-03-21T20:25:16.5004962Z   adding 'executorch/exir/_serialize/test/test_flatbuffer.py'
2025-03-21T20:25:16.5005474Z   adding 'executorch/exir/_serialize/test/test_named_data_store.py'
2025-03-21T20:25:16.5006004Z   adding 'executorch/exir/_serialize/test/test_program.py'
2025-03-21T20:25:16.5006505Z   adding 'executorch/exir/backend/backend_api.py'
2025-03-21T20:25:16.5006918Z   adding 'executorch/exir/backend/backend_details.py'
2025-03-21T20:25:16.5007360Z   adding 'executorch/exir/backend/compile_spec_schema.py'
2025-03-21T20:25:16.5007805Z   adding 'executorch/exir/backend/operator_support.py'
2025-03-21T20:25:16.5008210Z   adding 'executorch/exir/backend/partitioner.py'
2025-03-21T20:25:16.5008743Z   adding 'executorch/exir/backend/utils.py'
2025-03-21T20:25:16.5009340Z   adding 'executorch/exir/backend/canonical_partitioners/config_partitioner.py'
2025-03-21T20:25:16.5010036Z   adding 'executorch/exir/backend/canonical_partitioners/duplicate_constant_node_pass.py'
2025-03-21T20:25:16.5010759Z   adding 'executorch/exir/backend/canonical_partitioners/duplicate_dequant_node_pass.py'
2025-03-21T20:25:16.5011467Z   adding 'executorch/exir/backend/canonical_partitioners/pattern_op_partitioner.py'
2025-03-21T20:25:16.5012077Z   adding 'executorch/exir/backend/test/backend_with_compiler_demo.py'
2025-03-21T20:25:16.5012783Z   adding 'executorch/exir/backend/test/backend_with_delegate_mapping_demo.py'
2025-03-21T20:25:16.5013379Z   adding 'executorch/exir/backend/test/backend_with_named_data_map.py'
2025-03-21T20:25:16.5013909Z   adding 'executorch/exir/backend/test/hta_partitioner_demo.py'
2025-03-21T20:25:16.5014411Z   adding 'executorch/exir/backend/test/op_partitioner_demo.py'
2025-03-21T20:25:16.5014894Z   adding 'executorch/exir/backend/test/qnn_backend_demo.py'
2025-03-21T20:25:16.5015431Z   adding 'executorch/exir/backend/test/test_backend_with_named_data_map.py'
2025-03-21T20:25:16.5015960Z   adding 'executorch/exir/backend/test/test_backends.py'
2025-03-21T20:25:16.5016433Z   adding 'executorch/exir/backend/test/test_backends_lifted.py'
2025-03-21T20:25:16.5016934Z   adding 'executorch/exir/backend/test/test_backends_nested.py'
2025-03-21T20:25:16.5017461Z   adding 'executorch/exir/backend/test/test_compatibility.py'
2025-03-21T20:25:16.5018011Z   adding 'executorch/exir/backend/test/test_debug_handle_map.py'
2025-03-21T20:25:16.5018535Z   adding 'executorch/exir/backend/test/test_delegate_map_builder.py'
2025-03-21T20:25:16.5019062Z   adding 'executorch/exir/backend/test/test_graph_partition.py'
2025-03-21T20:25:16.5019593Z   adding 'executorch/exir/backend/test/test_lowered_backend_module.py'
2025-03-21T20:25:16.5020114Z   adding 'executorch/exir/backend/test/test_partitioner.py'
2025-03-21T20:25:16.5020555Z   adding 'executorch/exir/backend/test/test_passes.py'
2025-03-21T20:25:16.5020979Z   adding 'executorch/exir/backend/test/test_utils.py'
2025-03-21T20:25:16.5021479Z   adding 'executorch/exir/backend/test/demos/test_delegate_aten_mode.py'
2025-03-21T20:25:16.5022158Z   adding 'executorch/exir/backend/test/demos/test_xnnpack_qnnpack.py'
2025-03-21T20:25:16.5022776Z   adding 'executorch/exir/backend/test/demos/rpc/executor_backend_partitioner.py'
2025-03-21T20:25:16.5023443Z   adding 'executorch/exir/backend/test/demos/rpc/executor_backend_preprocess.py'
2025-03-21T20:25:16.5024007Z   adding 'executorch/exir/backend/test/demos/rpc/test_rpc.py'
2025-03-21T20:25:16.5024443Z   adding 'executorch/exir/capture/__init__.py'
2025-03-21T20:25:16.5024826Z   adding 'executorch/exir/capture/_capture.py'
2025-03-21T20:25:16.5025203Z   adding 'executorch/exir/capture/_config.py'
2025-03-21T20:25:16.5025614Z   adding 'executorch/exir/capture/_unlift.py'
2025-03-21T20:25:16.5026053Z   adding 'executorch/exir/dialects/__init__.py'
2025-03-21T20:25:16.5026425Z   adding 'executorch/exir/dialects/_ops.py'
2025-03-21T20:25:16.5026803Z   adding 'executorch/exir/dialects/backend/_ops.py'
2025-03-21T20:25:16.5027282Z   adding 'executorch/exir/dialects/backend/test/test_backend_ops.py'
2025-03-21T20:25:16.5977232Z   adding 'executorch/exir/dialects/edge/_ops.py'
2025-03-21T20:25:16.5977944Z   adding 'executorch/exir/dialects/edge/edge.yaml'
2025-03-21T20:25:16.5978687Z   adding 'executorch/exir/dialects/edge/arg/model.py'
2025-03-21T20:25:16.5979411Z   adding 'executorch/exir/dialects/edge/arg/type.py'
2025-03-21T20:25:16.5980177Z   adding 'executorch/exir/dialects/edge/dtype/runner.py'
2025-03-21T20:25:16.5980658Z   adding 'executorch/exir/dialects/edge/dtype/supported.py'
2025-03-21T20:25:16.5981119Z   adding 'executorch/exir/dialects/edge/dtype/utils.py'
2025-03-21T20:25:16.5981540Z   adding 'executorch/exir/dialects/edge/op/api.py'
2025-03-21T20:25:16.5982269Z   adding 'executorch/exir/dialects/edge/op/sample_input.py'
2025-03-21T20:25:16.5982731Z   adding 'executorch/exir/dialects/edge/op/test/test_api.py'
2025-03-21T20:25:16.5983176Z   adding 'executorch/exir/dialects/edge/spec/gen.py'
2025-03-21T20:25:16.5983597Z   adding 'executorch/exir/dialects/edge/spec/utils.py'
2025-03-21T20:25:16.5984058Z   adding 'executorch/exir/dialects/edge/test/test_edge_ops.py'
2025-03-21T20:25:16.5984558Z   adding 'executorch/exir/dialects/edge/test/test_edge_yaml.py'
2025-03-21T20:25:16.5985058Z   adding 'executorch/exir/dialects/test/test_exir_dialect_ops.py'
2025-03-21T20:25:16.5985510Z   adding 'executorch/exir/emit/__init__.py'
2025-03-21T20:25:16.5985889Z   adding 'executorch/exir/emit/_emit_program.py'
2025-03-21T20:25:16.5986266Z   adding 'executorch/exir/emit/_emitter.py'
2025-03-21T20:25:16.5986642Z   adding 'executorch/exir/emit/test/test_emit.py'
2025-03-21T20:25:16.5987018Z   adding 'executorch/exir/operator/convert.py'
2025-03-21T20:25:16.5987395Z   adding 'executorch/exir/operator/manip.py'
2025-03-21T20:25:16.5987767Z   adding 'executorch/exir/operator/util.py'
2025-03-21T20:25:16.5988174Z   adding 'executorch/exir/operator/test/test_operator.py'
2025-03-21T20:25:16.5988620Z   adding 'executorch/exir/passes/__init__.py'
2025-03-21T20:25:16.5989119Z   adding 'executorch/exir/passes/_quant_patterns_and_replacements.py'
2025-03-21T20:25:16.5989599Z   adding 'executorch/exir/passes/const_prop_pass.py'
2025-03-21T20:25:16.5990027Z   adding 'executorch/exir/passes/constant_prop_pass.py'
2025-03-21T20:25:16.5990548Z   adding 'executorch/exir/passes/debug_handle_generator_pass.py'
2025-03-21T20:25:16.5991036Z   adding 'executorch/exir/passes/dim_order_ops_registry.py'
2025-03-21T20:25:16.5991512Z   adding 'executorch/exir/passes/dynamic_shape_prop_pass.py'
2025-03-21T20:25:16.5992022Z   adding 'executorch/exir/passes/executorch_prim_ops_registry.py'
2025-03-21T20:25:16.5992525Z   adding 'executorch/exir/passes/external_constants_pass.py'
2025-03-21T20:25:16.5992995Z   adding 'executorch/exir/passes/init_mutable_pass.py'
2025-03-21T20:25:16.5993554Z   adding 'executorch/exir/passes/insert_write_back_for_buffers_pass.py'
2025-03-21T20:25:16.5994083Z   adding 'executorch/exir/passes/memory_format_ops_pass.py'
2025-03-21T20:25:16.5994553Z   adding 'executorch/exir/passes/memory_planning_pass.py'
2025-03-21T20:25:16.5995013Z   adding 'executorch/exir/passes/normalize_transpose_pass.py'
2025-03-21T20:25:16.5995571Z   adding 'executorch/exir/passes/normalize_view_copy_base_pass.py'
2025-03-21T20:25:16.5996047Z   adding 'executorch/exir/passes/pass_registry.py'
2025-03-21T20:25:16.5996501Z   adding 'executorch/exir/passes/prune_empty_tensors_pass.py'
2025-03-21T20:25:16.5997097Z   adding 'executorch/exir/passes/quant_fusion_pass.py'
2025-03-21T20:25:16.5997512Z   adding 'executorch/exir/passes/quantize_io_pass.py'
2025-03-21T20:25:16.5998019Z   adding 'executorch/exir/passes/remove_graph_asserts_pass.py'
2025-03-21T20:25:16.5998532Z   adding 'executorch/exir/passes/remove_mixed_type_operators.py'
2025-03-21T20:25:16.5999010Z   adding 'executorch/exir/passes/remove_noop_pass.py'
2025-03-21T20:25:16.5999478Z   adding 'executorch/exir/passes/replace_aten_with_edge_pass.py'
2025-03-21T20:25:16.6000083Z   adding 'executorch/exir/passes/replace_broken_ops_with_function_ops_pass.py'
2025-03-21T20:25:16.6000677Z   adding 'executorch/exir/passes/replace_edge_with_backend_pass.py'
2025-03-21T20:25:16.6001183Z   adding 'executorch/exir/passes/replace_sym_size_op_pass.py'
2025-03-21T20:25:16.6001702Z   adding 'executorch/exir/passes/replace_view_copy_with_view_pass.py'
2025-03-21T20:25:16.6002211Z   adding 'executorch/exir/passes/scalar_to_tensor_pass.py'
2025-03-21T20:25:16.6002693Z   adding 'executorch/exir/passes/spec_prop_pass.py'
2025-03-21T20:25:16.6003108Z   adding 'executorch/exir/passes/sym_shape_eval_pass.py'
2025-03-21T20:25:16.6003543Z   adding 'executorch/exir/passes/sym_to_tensor_pass.py'
2025-03-21T20:25:16.6003998Z   adding 'executorch/exir/passes/weights_to_outputs_pass.py'
2025-03-21T20:25:16.6004574Z   adding 'executorch/exir/program/__init__.py'
2025-03-21T20:25:16.6004967Z   adding 'executorch/exir/program/_fake_program.py'
2025-03-21T20:25:16.6005396Z   adding 'executorch/exir/program/_program.py'
2025-03-21T20:25:16.6005786Z   adding 'executorch/exir/program/test/__init__.py'
2025-03-21T20:25:16.6006223Z   adding 'executorch/exir/program/test/test_fake_program.py'
2025-03-21T20:25:16.6006684Z   adding 'executorch/exir/program/test/test_program.py'
2025-03-21T20:25:16.6007091Z   adding 'executorch/exir/serde/__init__.py'
2025-03-21T20:25:16.6007480Z   adding 'executorch/exir/serde/export_serialize.py'
2025-03-21T20:25:16.6007896Z   adding 'executorch/exir/serde/schema.py'
2025-03-21T20:25:16.6008269Z   adding 'executorch/exir/serde/schema_check.py'
2025-03-21T20:25:16.6008654Z   adding 'executorch/exir/serde/serialize.py'
2025-03-21T20:25:16.6009022Z   adding 'executorch/exir/serde/union.py'
2025-03-21T20:25:16.6009467Z   adding 'executorch/exir/serde/upgrade.py'
2025-03-21T20:25:16.6009835Z   adding 'executorch/exir/tests/asr_joiner.py'
2025-03-21T20:25:16.6010206Z   adding 'executorch/exir/tests/common.py'
2025-03-21T20:25:16.6010595Z   adding 'executorch/exir/tests/control_flow_models.py'
2025-03-21T20:25:16.6011032Z   adding 'executorch/exir/tests/dynamic_shape_models.py'
2025-03-21T20:25:16.6011478Z   adding 'executorch/exir/tests/models.py'
2025-03-21T20:25:16.6011857Z   adding 'executorch/exir/tests/test_arg_validator.py'
2025-03-21T20:25:16.6012290Z   adding 'executorch/exir/tests/test_capture.py'
2025-03-21T20:25:16.6012679Z   adding 'executorch/exir/tests/test_common.py'
2025-03-21T20:25:16.6013071Z   adding 'executorch/exir/tests/test_delegate.py'
2025-03-21T20:25:16.6013493Z   adding 'executorch/exir/tests/test_dim_order_utils.py'
2025-03-21T20:25:16.6014024Z   adding 'executorch/exir/tests/test_dynamic_shape_propagation.py'
2025-03-21T20:25:16.6014482Z   adding 'executorch/exir/tests/test_error.py'
2025-03-21T20:25:16.6014866Z   adding 'executorch/exir/tests/test_joint_graph.py'
2025-03-21T20:25:16.6015330Z   adding 'executorch/exir/tests/test_memory_format_ops_pass.py'
2025-03-21T20:25:16.6015850Z   adding 'executorch/exir/tests/test_memory_format_ops_pass_aten.py'
2025-03-21T20:25:16.6016397Z   adding 'executorch/exir/tests/test_memory_format_ops_pass_utils.py'
2025-03-21T20:25:16.6016946Z   adding 'executorch/exir/tests/test_memory_planning.py'
2025-03-21T20:25:16.6017356Z   adding 'executorch/exir/tests/test_op_convert.py'
2025-03-21T20:25:16.6017761Z   adding 'executorch/exir/tests/test_pass_infra.py'
2025-03-21T20:25:16.6018155Z   adding 'executorch/exir/tests/test_passes.py'
2025-03-21T20:25:16.6018564Z   adding 'executorch/exir/tests/test_print_program.py'
2025-03-21T20:25:16.6019081Z   adding 'executorch/exir/tests/test_prune_empty_tensors_pass.py'
2025-03-21T20:25:16.6019556Z   adding 'executorch/exir/tests/test_quant_fusion_pass.py'
2025-03-21T20:25:16.6019994Z   adding 'executorch/exir/tests/test_quantization.py'
2025-03-21T20:25:16.6020432Z   adding 'executorch/exir/tests/test_quantize_io_pass.py'
2025-03-21T20:25:16.6020888Z   adding 'executorch/exir/tests/test_remove_view_copy.py'
2025-03-21T20:25:16.6021302Z   adding 'executorch/exir/tests/test_serde.py'
2025-03-21T20:25:16.6021683Z   adding 'executorch/exir/tests/test_tensor.py'
2025-03-21T20:25:16.6022092Z   adding 'executorch/exir/tests/test_tracer.py'
2025-03-21T20:25:16.6022491Z   adding 'executorch/exir/tests/test_verification.py'
2025-03-21T20:25:16.6022896Z   adding 'executorch/exir/tests/test_warnings.py'
2025-03-21T20:25:16.6023284Z   adding 'executorch/exir/tests/transformer.py'
2025-03-21T20:25:16.6023700Z   adding 'executorch/exir/verification/arg_validator.py'
2025-03-21T20:25:16.6024117Z   adding 'executorch/exir/verification/dev_html.py'
2025-03-21T20:25:16.6024540Z   adding 'executorch/exir/verification/interpreter.py'
2025-03-21T20:25:16.6024962Z   adding 'executorch/exir/verification/verifier.py'
2025-03-21T20:25:16.6025408Z   adding 'executorch/exir/verification/test/test_verifier.py'
2025-03-21T20:25:16.6026088Z   adding 'executorch/extension/android_test/add_model.py'
2025-03-21T20:25:16.6026522Z   adding 'executorch/extension/export_util/__init__.py'
2025-03-21T20:25:16.6026946Z   adding 'executorch/extension/export_util/utils.py'
2025-03-21T20:25:16.6027370Z   adding 'executorch/extension/flat_tensor/__init__.py'
2025-03-21T20:25:16.6027845Z   adding 'executorch/extension/flat_tensor/serialize/__init__.py'
2025-03-21T20:25:16.6028380Z   adding 'executorch/extension/flat_tensor/serialize/flat_tensor.fbs'
2025-03-21T20:25:16.6028962Z   adding 'executorch/extension/flat_tensor/serialize/flat_tensor_schema.py'
2025-03-21T20:25:16.6029569Z   adding 'executorch/extension/flat_tensor/serialize/scalar_type.fbs'
2025-03-21T20:25:16.6030110Z   adding 'executorch/extension/flat_tensor/serialize/serialize.py'
2025-03-21T20:25:16.6030639Z   adding 'executorch/extension/flat_tensor/test/test_serialize.py'
2025-03-21T20:25:16.6031130Z   adding 'executorch/extension/gguf_util/convert_main.py'
2025-03-21T20:25:16.6031576Z   adding 'executorch/extension/gguf_util/converter.py'
2025-03-21T20:25:16.6031998Z   adding 'executorch/extension/gguf_util/load_gguf.py'
2025-03-21T20:25:16.6032699Z   adding 'executorch/extension/gguf_util/converters/llama_converter.py'
2025-03-21T20:25:16.6033220Z   adding 'executorch/extension/llm/custom_ops/__init__.py'
2025-03-21T20:25:16.6033696Z   adding 'executorch/extension/llm/custom_ops/custom_ops.py'
2025-03-21T20:25:16.6034219Z   adding 'executorch/extension/llm/custom_ops/libcustom_ops_aot_lib.so'
2025-03-21T20:25:16.6034768Z   adding 'executorch/extension/llm/custom_ops/model_sharding.py'
2025-03-21T20:25:16.6035282Z   adding 'executorch/extension/llm/custom_ops/op_tile_crop_aot.py'
2025-03-21T20:25:16.6035839Z   adding 'executorch/extension/llm/custom_ops/preprocess_custom_ops.py'
2025-03-21T20:25:16.6036442Z   adding 'executorch/extension/llm/custom_ops/test_preprocess_custom_ops.py'
2025-03-21T20:25:16.6037095Z   adding 'executorch/extension/llm/custom_ops/test_sdpa_with_kv_cache.py'
2025-03-21T20:25:16.6037672Z   adding 'executorch/extension/llm/custom_ops/test_update_cache.py'
2025-03-21T20:25:16.6038286Z   adding 'executorch/extension/llm/custom_ops/spinquant/special_hadamard_code_gen.py'
2025-03-21T20:25:16.6038972Z   adding 'executorch/extension/llm/custom_ops/spinquant/third-party/FFHT/example.py'
2025-03-21T20:25:16.6039649Z   adding 'executorch/extension/llm/custom_ops/spinquant/third-party/FFHT/gen.py'
2025-03-21T20:25:16.6040250Z   adding 'executorch/extension/llm/export/__init__.py'
2025-03-21T20:25:16.6040683Z   adding 'executorch/extension/llm/export/builder.py'
2025-03-21T20:25:16.6041134Z   adding 'executorch/extension/llm/export/export_passes.py'
2025-03-21T20:25:16.6041608Z   adding 'executorch/extension/llm/export/partitioner_lib.py'
2025-03-21T20:25:16.6042091Z   adding 'executorch/extension/llm/export/quantizer_lib.py'
2025-03-21T20:25:16.6042581Z   adding 'executorch/extension/llm/export/test_export_passes.py'
2025-03-21T20:25:16.6043056Z   adding 'executorch/extension/llm/modules/__init__.py'
2025-03-21T20:25:16.6043555Z   adding 'executorch/extension/llm/modules/_position_embeddings.py'
2025-03-21T20:25:16.6044055Z   adding 'executorch/extension/llm/modules/attention.py'
2025-03-21T20:25:16.6044486Z   adding 'executorch/extension/llm/modules/kv_cache.py'
2025-03-21T20:25:17.1515425Z   adding 'executorch/extension/llm/modules/test/__init__.py'
2025-03-21T20:25:17.1516339Z   adding 'executorch/extension/llm/modules/test/test_attention.py'
2025-03-21T20:25:17.1517299Z   adding 'executorch/extension/llm/modules/test/test_kv_cache.py'
2025-03-21T20:25:17.1518232Z   adding 'executorch/extension/llm/modules/test/test_position_embeddings.py'
2025-03-21T20:25:17.1518790Z   adding 'executorch/extension/llm/tokenizer/__init__.py'
2025-03-21T20:25:17.1519262Z   adding 'executorch/extension/llm/tokenizer/hf_tokenizer.py'
2025-03-21T20:25:17.1519737Z   adding 'executorch/extension/llm/tokenizer/tokenizer.py'
2025-03-21T20:25:17.1520186Z   adding 'executorch/extension/llm/tokenizer/utils.py'
2025-03-21T20:25:17.1521042Z   adding 'executorch/extension/llm/tokenizer/test/test_tokenizer.py'
2025-03-21T20:25:17.1521598Z   adding 'executorch/extension/llm/tokenizers/setup.py'
2025-03-21T20:25:17.1522136Z   adding 'executorch/extension/llm/tokenizers/pytorch_tokenizers/__init__.py'
2025-03-21T20:25:17.1522837Z   adding 'executorch/extension/llm/tokenizers/pytorch_tokenizers/hf_tokenizer.py'
2025-03-21T20:25:17.1523573Z   adding 'executorch/extension/llm/tokenizers/pytorch_tokenizers/llama2c.py'
2025-03-21T20:25:17.1524203Z   adding 'executorch/extension/llm/tokenizers/pytorch_tokenizers/tiktoken.py'
2025-03-21T20:25:17.1524885Z   adding 'executorch/extension/llm/tokenizers/pytorch_tokenizers/tools/llama2c/__init__.py'
2025-03-21T20:25:17.1525681Z   adding 'executorch/extension/llm/tokenizers/pytorch_tokenizers/tools/llama2c/convert.py'
2025-03-21T20:25:17.1526389Z   adding 'executorch/extension/llm/tokenizers/third-party/abseil-cpp/conanfile.py'
2025-03-21T20:25:17.1527179Z   adding 'executorch/extension/llm/tokenizers/third-party/abseil-cpp/create_lts.py'
2025-03-21T20:25:17.1527939Z   adding 'executorch/extension/llm/tokenizers/third-party/abseil-cpp/absl/abseil.podspec.gen.py'
2025-03-21T20:25:17.1528716Z   adding 'executorch/extension/llm/tokenizers/third-party/abseil-cpp/absl/copts/copts.py'
2025-03-21T20:25:17.1529564Z   adding 'executorch/extension/llm/tokenizers/third-party/abseil-cpp/absl/copts/generate_copts.py'
2025-03-21T20:25:17.1530409Z   adding 'executorch/extension/llm/tokenizers/third-party/json/docs/mkdocs/scripts/check_structure.py'
2025-03-21T20:25:17.1531243Z   adding 'executorch/extension/llm/tokenizers/third-party/json/tests/thirdparty/imapdl/filterbr.py'
2025-03-21T20:25:17.1532052Z   adding 'executorch/extension/llm/tokenizers/third-party/json/tools/amalgamate/amalgamate.py'
2025-03-21T20:25:17.1533154Z   adding 'executorch/extension/llm/tokenizers/third-party/json/tools/gdb_pretty_printer/nlohmann-json.py'
2025-03-21T20:25:17.1534049Z   adding 'executorch/extension/llm/tokenizers/third-party/json/tools/generate_natvis/generate_natvis.py'
2025-03-21T20:25:17.1534906Z   adding 'executorch/extension/llm/tokenizers/third-party/json/tools/serve_header/serve_header.py'
2025-03-21T20:25:17.1535660Z   adding 'executorch/extension/llm/tokenizers/third-party/re2/benchlog/benchplot.py'
2025-03-21T20:25:17.1536323Z   adding 'executorch/extension/llm/tokenizers/third-party/re2/python/re2.py'
2025-03-21T20:25:17.1537047Z   adding 'executorch/extension/llm/tokenizers/third-party/re2/python/re2_test.py'
2025-03-21T20:25:17.1537697Z   adding 'executorch/extension/llm/tokenizers/third-party/re2/python/setup.py'
2025-03-21T20:25:17.1538401Z   adding 'executorch/extension/llm/tokenizers/third-party/re2/python/toolchains/generate.py'
2025-03-21T20:25:17.1539161Z   adding 'executorch/extension/llm/tokenizers/third-party/re2/re2/make_unicode_casefold.py'
2025-03-21T20:25:17.1540020Z   adding 'executorch/extension/llm/tokenizers/third-party/re2/re2/make_unicode_groups.py'
2025-03-21T20:25:17.1540711Z   adding 'executorch/extension/llm/tokenizers/third-party/re2/re2/unicode.py'
2025-03-21T20:25:17.1541378Z   adding 'executorch/extension/llm/tokenizers/third-party/sentencepiece/python/setup.py'
2025-03-21T20:25:17.1542242Z   adding 'executorch/extension/llm/tokenizers/third-party/sentencepiece/python/src/sentencepiece/__init__.py'
2025-03-21T20:25:17.1543248Z   adding 'executorch/extension/llm/tokenizers/third-party/sentencepiece/python/src/sentencepiece/_version.py'
2025-03-21T20:25:17.1544276Z   adding 'executorch/extension/llm/tokenizers/third-party/sentencepiece/python/src/sentencepiece/sentencepiece_model_pb2.py'
2025-03-21T20:25:17.1545458Z   adding 'executorch/extension/llm/tokenizers/third-party/sentencepiece/python/src/sentencepiece/sentencepiece_pb2.py'
2025-03-21T20:25:17.1546379Z   adding 'executorch/extension/llm/tokenizers/third-party/sentencepiece/python/test/__init__.py'
2025-03-21T20:25:17.1547236Z   adding 'executorch/extension/llm/tokenizers/third-party/sentencepiece/python/test/sentencepiece_test.py'
2025-03-21T20:25:17.1548211Z   adding 'executorch/extension/llm/tokenizers/tools/llama2c/convert.py'
2025-03-21T20:25:17.1548869Z   adding 'executorch/extension/pybindings/_portable_lib.cpython-310-x86_64-linux-gnu.so'
2025-03-21T20:25:17.1549467Z   adding 'executorch/extension/pybindings/portable_lib.py'
2025-03-21T20:25:17.1549944Z   adding 'executorch/extension/pybindings/pybindings.pyi'
2025-03-21T20:25:17.1550421Z   adding 'executorch/extension/pybindings/test/make_test.py'
2025-03-21T20:25:17.1550998Z   adding 'executorch/extension/pybindings/test/test_backend_pybinding.py'
2025-03-21T20:25:17.1551634Z   adding 'executorch/extension/pybindings/test/test_pybindings.py'
2025-03-21T20:25:17.1552391Z   adding 'executorch/extension/pytree/__init__.py'
2025-03-21T20:25:17.1552874Z   adding 'executorch/extension/pytree/test/test.py'
2025-03-21T20:25:17.1553384Z   adding 'executorch/extension/training/__init__.py'
2025-03-21T20:25:17.1554129Z   adding 'executorch/extension/training/examples/XOR/export_model.py'
2025-03-21T20:25:17.1554784Z   adding 'executorch/extension/training/examples/XOR/model.py'
2025-03-21T20:25:17.1555407Z   adding 'executorch/extension/training/examples/XOR/test/test_export.py'
2025-03-21T20:25:17.1556396Z   adding 'executorch/extension/training/pybindings/_training_lib.pyi'
2025-03-21T20:25:17.1557434Z   adding 'executorch/extension/training/pybindings/_training_module.py'
2025-03-21T20:25:17.1558481Z   adding 'executorch/extension/training/pybindings/test/test.py'
2025-03-21T20:25:17.1559930Z   adding 'executorch/include/executorch/extension/kernel_util/make_boxed_from_unboxed_functor.h'
2025-03-21T20:25:17.1561425Z   adding 'executorch/include/executorch/extension/kernel_util/meta_programming.h'
2025-03-21T20:25:17.1562815Z   adding 'executorch/include/executorch/extension/kernel_util/type_list.h'
2025-03-21T20:25:17.1563801Z   adding 'executorch/include/executorch/extension/tensor/tensor.h'
2025-03-21T20:25:17.1564920Z   adding 'executorch/include/executorch/extension/tensor/tensor_accessor.h'
2025-03-21T20:25:17.1565938Z   adding 'executorch/include/executorch/extension/tensor/tensor_ptr.h'
2025-03-21T20:25:17.1566723Z   adding 'executorch/include/executorch/extension/tensor/tensor_ptr_maker.h'
2025-03-21T20:25:17.1567681Z   adding 'executorch/include/executorch/extension/threadpool/cpuinfo_utils.h'
2025-03-21T20:25:17.1569028Z   adding 'executorch/include/executorch/extension/threadpool/threadpool.h'
2025-03-21T20:25:17.1570355Z   adding 'executorch/include/executorch/extension/threadpool/threadpool_guard.h'
2025-03-21T20:25:17.1571524Z   adding 'executorch/include/executorch/runtime/core/array_ref.h'
2025-03-21T20:25:17.1572703Z   adding 'executorch/include/executorch/runtime/core/data_loader.h'
2025-03-21T20:25:17.1573798Z   adding 'executorch/include/executorch/runtime/core/defines.h'
2025-03-21T20:25:17.1574685Z   adding 'executorch/include/executorch/runtime/core/error.h'
2025-03-21T20:25:17.1575827Z   adding 'executorch/include/executorch/runtime/core/evalue.h'
2025-03-21T20:25:17.1576847Z   adding 'executorch/include/executorch/runtime/core/event_tracer.h'
2025-03-21T20:25:17.1577975Z   adding 'executorch/include/executorch/runtime/core/event_tracer_hooks.h'
2025-03-21T20:25:17.1579365Z   adding 'executorch/include/executorch/runtime/core/event_tracer_hooks_delegate.h'
2025-03-21T20:25:17.1580602Z   adding 'executorch/include/executorch/runtime/core/freeable_buffer.h'
2025-03-21T20:25:17.1581942Z   adding 'executorch/include/executorch/runtime/core/hierarchical_allocator.h'
2025-03-21T20:25:17.1582888Z   adding 'executorch/include/executorch/runtime/core/memory_allocator.h'
2025-03-21T20:25:17.1583599Z   adding 'executorch/include/executorch/runtime/core/named_data_map.h'
2025-03-21T20:25:17.1584756Z   adding 'executorch/include/executorch/runtime/core/result.h'
2025-03-21T20:25:17.1585674Z   adding 'executorch/include/executorch/runtime/core/span.h'
2025-03-21T20:25:17.1586446Z   adding 'executorch/include/executorch/runtime/core/tag.h'
2025-03-21T20:25:17.1587784Z   adding 'executorch/include/executorch/runtime/core/tensor_layout.h'
2025-03-21T20:25:17.1588916Z   adding 'executorch/include/executorch/runtime/core/tensor_shape_dynamism.h'
2025-03-21T20:25:17.1589692Z   adding 'executorch/include/executorch/runtime/core/exec_aten/exec_aten.h'
2025-03-21T20:25:17.1590579Z   adding 'executorch/include/executorch/runtime/core/exec_aten/testing_util/tensor_factory.h'
2025-03-21T20:25:17.1591396Z   adding 'executorch/include/executorch/runtime/core/exec_aten/testing_util/tensor_util.h'
2025-03-21T20:25:17.1592276Z   adding 'executorch/include/executorch/runtime/core/exec_aten/util/dim_order_util.h'
2025-03-21T20:25:17.1593143Z   adding 'executorch/include/executorch/runtime/core/exec_aten/util/scalar_type_util.h'
2025-03-21T20:25:17.1593985Z   adding 'executorch/include/executorch/runtime/core/exec_aten/util/tensor_dimension_limit.h'
2025-03-21T20:25:17.1595064Z   adding 'executorch/include/executorch/runtime/core/exec_aten/util/tensor_shape_to_c_string.h'
2025-03-21T20:25:17.1596519Z   adding 'executorch/include/executorch/runtime/core/exec_aten/util/tensor_util.h'
2025-03-21T20:25:17.1597761Z   adding 'executorch/include/executorch/runtime/core/portable_type/bfloat16.h'
2025-03-21T20:25:17.1599191Z   adding 'executorch/include/executorch/runtime/core/portable_type/bfloat16_math.h'
2025-03-21T20:25:17.1600630Z   adding 'executorch/include/executorch/runtime/core/portable_type/bits_types.h'
2025-03-21T20:25:17.1601964Z   adding 'executorch/include/executorch/runtime/core/portable_type/complex.h'
2025-03-21T20:25:17.1603344Z   adding 'executorch/include/executorch/runtime/core/portable_type/device.h'
2025-03-21T20:25:17.1604625Z   adding 'executorch/include/executorch/runtime/core/portable_type/half.h'
2025-03-21T20:25:17.1605410Z   adding 'executorch/include/executorch/runtime/core/portable_type/optional.h'
2025-03-21T20:25:17.1606243Z   adding 'executorch/include/executorch/runtime/core/portable_type/qint_types.h'
2025-03-21T20:25:17.1606991Z   adding 'executorch/include/executorch/runtime/core/portable_type/scalar.h'
2025-03-21T20:25:17.1607737Z   adding 'executorch/include/executorch/runtime/core/portable_type/scalar_type.h'
2025-03-21T20:25:20.1156608Z   adding 'executorch/include/executorch/runtime/core/portable_type/string_view.h'
2025-03-21T20:25:20.1157782Z   adding 'executorch/include/executorch/runtime/core/portable_type/tensor.h'
2025-03-21T20:25:20.1158863Z   adding 'executorch/include/executorch/runtime/core/portable_type/tensor_impl.h'
2025-03-21T20:25:20.1159766Z   adding 'executorch/include/executorch/runtime/core/portable_type/tensor_options.h'
2025-03-21T20:25:20.1160746Z   adding 'executorch/include/executorch/runtime/core/portable_type/c10/c10/macros/Export.h'
2025-03-21T20:25:20.1161631Z   adding 'executorch/include/executorch/runtime/core/portable_type/c10/c10/macros/Macros.h'
2025-03-21T20:25:20.1162629Z   adding 'executorch/include/executorch/runtime/core/portable_type/c10/c10/util/BFloat16-inl.h'
2025-03-21T20:25:20.1163734Z   adding 'executorch/include/executorch/runtime/core/portable_type/c10/c10/util/BFloat16-math.h'
2025-03-21T20:25:20.1164759Z   adding 'executorch/include/executorch/runtime/core/portable_type/c10/c10/util/BFloat16.h'
2025-03-21T20:25:20.1165592Z   adding 'executorch/include/executorch/runtime/core/portable_type/c10/c10/util/Half-inl.h'
2025-03-21T20:25:20.1166655Z   adding 'executorch/include/executorch/runtime/core/portable_type/c10/c10/util/Half.h'
2025-03-21T20:25:20.1167658Z   adding 'executorch/include/executorch/runtime/core/portable_type/c10/c10/util/TypeSafeSignMath.h'
2025-03-21T20:25:20.1168486Z   adding 'executorch/include/executorch/runtime/core/portable_type/c10/c10/util/bit_cast.h'
2025-03-21T20:25:20.1169723Z   adding 'executorch/include/executorch/runtime/core/portable_type/c10/c10/util/floating_point_utils.h'
2025-03-21T20:25:20.1170743Z   adding 'executorch/include/executorch/runtime/core/portable_type/c10/c10/util/irange.h'
2025-03-21T20:25:20.1171548Z   adding 'executorch/include/executorch/runtime/kernel/kernel_includes.h'
2025-03-21T20:25:20.1172711Z   adding 'executorch/include/executorch/runtime/kernel/kernel_runtime_context.h'
2025-03-21T20:25:20.1173546Z   adding 'executorch/include/executorch/runtime/kernel/operator_registry.h'
2025-03-21T20:25:20.1174298Z   adding 'executorch/include/executorch/runtime/kernel/thread_parallel_interface.h'
2025-03-21T20:25:20.1175156Z   adding 'executorch/include/executorch/runtime/kernel/test/test_util.h'
2025-03-21T20:25:20.1175823Z   adding 'executorch/include/executorch/runtime/platform/abort.h'
2025-03-21T20:25:20.1176593Z   adding 'executorch/include/executorch/runtime/platform/assert.h'
2025-03-21T20:25:20.1177232Z   adding 'executorch/include/executorch/runtime/platform/clock.h'
2025-03-21T20:25:20.1177873Z   adding 'executorch/include/executorch/runtime/platform/compat_unistd.h'
2025-03-21T20:25:20.1178648Z   adding 'executorch/include/executorch/runtime/platform/compiler.h'
2025-03-21T20:25:20.1179290Z   adding 'executorch/include/executorch/runtime/platform/log.h'
2025-03-21T20:25:20.1180039Z   adding 'executorch/include/executorch/runtime/platform/platform.h'
2025-03-21T20:25:20.1180745Z   adding 'executorch/include/executorch/runtime/platform/profiler.h'
2025-03-21T20:25:20.1181485Z   adding 'executorch/include/executorch/runtime/platform/runtime.h'
2025-03-21T20:25:20.1182157Z   adding 'executorch/include/executorch/runtime/platform/system.h'
2025-03-21T20:25:20.1182876Z   adding 'executorch/include/executorch/runtime/platform/types.h'
2025-03-21T20:25:20.1183572Z   adding 'executorch/include/executorch/runtime/platform/test/stub_platform.h'
2025-03-21T20:25:20.1184298Z   adding 'executorch/kernels/quantized/__init__.py'
2025-03-21T20:25:20.1184894Z   adding 'executorch/kernels/quantized/libquantized_ops_aot_lib.so'
2025-03-21T20:25:20.1185584Z   adding 'executorch/kernels/quantized/quantized.yaml'
2025-03-21T20:25:20.1186220Z   adding 'executorch/kernels/quantized/test/supported_features_def.yaml'
2025-03-21T20:25:20.1186870Z   adding 'executorch/kernels/quantized/test/test_out_variants.py'
2025-03-21T20:25:20.1187595Z   adding 'executorch/kernels/quantized/test/test_quant_dequant_per_token.py'
2025-03-21T20:25:20.1188273Z   adding 'executorch/runtime/__init__.py'
2025-03-21T20:25:20.1188807Z   adding 'executorch/runtime/kernel/test/functions.yaml'
2025-03-21T20:25:20.1189304Z   adding 'executorch/runtime/test/test_runtime.py'
2025-03-21T20:25:20.1189954Z   adding 'executorch/schema/program.fbs'
2025-03-21T20:25:20.1190371Z   adding 'executorch/schema/scalar_type.fbs'
2025-03-21T20:25:20.1190862Z   adding 'executorch/share/cmake/executorch-config.cmake'
2025-03-21T20:25:20.1201314Z   adding 'executorch/util/activation_memory_profiler.py'
2025-03-21T20:25:20.1201806Z   adding 'executorch/util/collect_env.py'
2025-03-21T20:25:20.1202180Z   adding 'executorch/util/python_profiler.py'
2025-03-21T20:25:20.1202601Z   adding 'executorch-0.6.0a0+be92d7d.dist-info/LICENSE'
2025-03-21T20:25:20.1203138Z   adding 'executorch-0.6.0a0+be92d7d.dist-info/METADATA'
2025-03-21T20:25:20.1203601Z   adding 'executorch-0.6.0a0+be92d7d.dist-info/WHEEL'
2025-03-21T20:25:20.1204074Z   adding 'executorch-0.6.0a0+be92d7d.dist-info/entry_points.txt'
2025-03-21T20:25:20.1204691Z   adding 'executorch-0.6.0a0+be92d7d.dist-info/top_level.txt'
2025-03-21T20:25:20.1205154Z   adding 'executorch-0.6.0a0+be92d7d.dist-info/RECORD'
2025-03-21T20:25:20.1205559Z   removing pip-out/bdist.linux-x86_64/wheel
2025-03-21T20:25:20.1206321Z   Building wheel for executorch (pyproject.toml) ... [?25l[?25hdone
2025-03-21T20:25:20.1207424Z   Created wheel for executorch: filename=executorch-0.6.0a0+be92d7d-cp310-cp310-linux_x86_64.whl size=8540631 sha256=9ee33db6f9ecb1c085f737610e388d1de9e410de375467105f5eb27d99842fab
2025-03-21T20:25:20.1208710Z   Stored in directory: /tmp/pip-ephem-wheel-cache-238w_hk5/wheels/9e/f0/2b/6a778c77421b91e006bef425e288a1e5c7c35b04c51317756b
2025-03-21T20:25:20.1209526Z Successfully built executorch
2025-03-21T20:25:20.1210262Z Installing collected packages: flatbuffers, tabulate, pytest, execnet, pytest-xdist, pytest-rerunfailures, executorch
2025-03-21T20:25:20.1211213Z   changing mode of /opt/conda/envs/py_3.10/bin/tabulate to 755
2025-03-21T20:25:20.1211636Z   Attempting uninstall: pytest
2025-03-21T20:25:20.1212031Z     Found existing installation: pytest 7.2.0
2025-03-21T20:25:20.1212394Z     Uninstalling pytest-7.2.0:
2025-03-21T20:25:20.1212785Z       Removing file or directory /opt/conda/envs/py_3.10/bin/py.test
2025-03-21T20:25:20.1213284Z       Removing file or directory /opt/conda/envs/py_3.10/bin/pytest
2025-03-21T20:25:20.1213974Z       Removing file or directory /opt/conda/envs/py_3.10/lib/python3.10/site-packages/__pycache__/py.cpython-310.pyc
2025-03-21T20:25:20.1214762Z       Removing file or directory /opt/conda/envs/py_3.10/lib/python3.10/site-packages/_pytest/
2025-03-21T20:25:20.1215433Z       Removing file or directory /opt/conda/envs/py_3.10/lib/python3.10/site-packages/py.py
2025-03-21T20:25:20.1216180Z       Removing file or directory /opt/conda/envs/py_3.10/lib/python3.10/site-packages/pytest-7.2.0.dist-info/
2025-03-21T20:25:20.1216939Z       Removing file or directory /opt/conda/envs/py_3.10/lib/python3.10/site-packages/pytest/
2025-03-21T20:25:20.1217468Z       Successfully uninstalled pytest-7.2.0
2025-03-21T20:25:20.1217884Z   changing mode of /opt/conda/envs/py_3.10/bin/py.test to 755
2025-03-21T20:25:20.1218352Z   changing mode of /opt/conda/envs/py_3.10/bin/pytest to 755
2025-03-21T20:25:20.1218795Z   changing mode of /opt/conda/envs/py_3.10/bin/flatc to 755
2025-03-21T20:25:20.1219652Z Successfully installed execnet-2.1.1 executorch-0.6.0a0+be92d7d flatbuffers-25.2.10 pytest-8.3.5 pytest-rerunfailures-15.0 pytest-xdist-3.6.1 tabulate-0.9.0
2025-03-21T20:25:20.1220425Z + pip list
2025-03-21T20:25:20.1220741Z Package                       Version            Editable project location
2025-03-21T20:25:20.1221226Z ----------------------------- ------------------ -----------------------------------
2025-03-21T20:25:20.1221637Z alabaster                     0.7.16
2025-03-21T20:25:20.1221937Z attrs                         25.3.0
2025-03-21T20:25:20.1222237Z babel                         2.17.0
2025-03-21T20:25:20.1222539Z beautifulsoup4                4.13.3
2025-03-21T20:25:20.1222848Z breathe                       4.34.0
2025-03-21T20:25:20.1223129Z bs4                           0.0.2
2025-03-21T20:25:20.1223428Z certifi                       2025.1.31
2025-03-21T20:25:20.1223755Z charset-normalizer            3.4.1
2025-03-21T20:25:20.1224063Z cmake                         3.31.6
2025-03-21T20:25:20.1224369Z contourpy                     1.3.1
2025-03-21T20:25:20.1224658Z coverage                      7.7.0
2025-03-21T20:25:20.1224958Z cycler                        0.12.1
2025-03-21T20:25:20.1225261Z docutils                      0.16
2025-03-21T20:25:20.1225572Z exceptiongroup                1.2.2
2025-03-21T20:25:20.1225878Z execnet                       2.1.1
2025-03-21T20:25:20.1226188Z executorch                    0.6.0a0+be92d7d
2025-03-21T20:25:20.1226525Z exhale                        0.2.3
2025-03-21T20:25:20.1226836Z expecttest                    0.1.6
2025-03-21T20:25:20.1227141Z filelock                      3.18.0
2025-03-21T20:25:20.1227447Z flatbuffers                   25.2.10
2025-03-21T20:25:20.1227741Z fonttools                     4.56.0
2025-03-21T20:25:20.1228047Z fsspec                        2025.3.0
2025-03-21T20:25:20.1228360Z huggingface-hub               0.29.3
2025-03-21T20:25:20.1228671Z hypothesis                    6.84.2
2025-03-21T20:25:20.1228974Z idna                          3.10
2025-03-21T20:25:20.1229256Z imagesize                     1.4.1
2025-03-21T20:25:20.1229557Z iniconfig                     2.1.0
2025-03-21T20:25:20.1229853Z Jinja2                        3.1.6
2025-03-21T20:25:20.1230152Z kiwisolver                    1.4.8
2025-03-21T20:25:20.1230448Z lxml                          5.3.1
2025-03-21T20:25:20.1230742Z markdown-it-py                2.2.0
2025-03-21T20:25:20.1231050Z MarkupSafe                    3.0.2
2025-03-21T20:25:20.1231446Z matplotlib                    3.10.1
2025-03-21T20:25:20.1231845Z mdit-py-plugins               0.3.5
2025-03-21T20:25:20.1232154Z mdurl                         0.1.2
2025-03-21T20:25:20.1232657Z mpmath                        1.3.0
2025-03-21T20:25:20.1232964Z myst-parser                   0.18.1
2025-03-21T20:25:20.1233268Z networkx                      3.4.2
2025-03-21T20:25:20.1233567Z numpy                         2.2.4
2025-03-21T20:25:20.1233881Z nvidia-cublas-cu12            12.1.3.1
2025-03-21T20:25:20.1234205Z nvidia-cuda-cupti-cu12        12.1.105
2025-03-21T20:25:20.1234543Z nvidia-cuda-nvrtc-cu12        12.1.105
2025-03-21T20:25:20.1234874Z nvidia-cuda-runtime-cu12      12.1.105
2025-03-21T20:25:20.1235201Z nvidia-cudnn-cu12             9.1.0.70
2025-03-21T20:25:20.1235528Z nvidia-cufft-cu12             11.0.2.54
2025-03-21T20:25:20.1235845Z nvidia-curand-cu12            10.3.2.106
2025-03-21T20:25:20.1236182Z nvidia-cusolver-cu12          11.4.5.107
2025-03-21T20:25:20.1236520Z nvidia-cusparse-cu12          12.1.0.106
2025-03-21T20:25:20.1236859Z nvidia-nccl-cu12              2.20.5
2025-03-21T20:25:20.1237185Z nvidia-nvjitlink-cu12         12.8.93
2025-03-21T20:25:20.1237496Z nvidia-nvtx-cu12              12.1.105
2025-03-21T20:25:20.1237812Z packaging                     24.2
2025-03-21T20:25:20.1238116Z pandas                        2.2.3
2025-03-21T20:25:20.1238420Z parameterized                 0.9.0
2025-03-21T20:25:20.1238726Z pillow                        11.1.0
2025-03-21T20:25:20.1239018Z pip                           25.0
2025-03-21T20:25:20.1239319Z pluggy                        1.5.0
2025-03-21T20:25:20.1239619Z Pygments                      2.19.1
2025-03-21T20:25:20.1239922Z pyparsing                     3.2.1
2025-03-21T20:25:20.1240224Z pytest                        8.3.5
2025-03-21T20:25:20.1240514Z pytest-cov                    4.1.0
2025-03-21T20:25:20.1240832Z pytest-rerunfailures          15.0
2025-03-21T20:25:20.1241144Z pytest-xdist                  3.6.1
2025-03-21T20:25:20.1241474Z python-dateutil               2.9.0.post0
2025-03-21T20:25:20.1241936Z pytorch_sphinx_theme          0.0.24             /opt/conda/src/pytorch-sphinx-theme
2025-03-21T20:25:25.3793128Z pytz                          2025.1
2025-03-21T20:25:25.3793673Z PyYAML                        6.0.1
2025-03-21T20:25:25.3794246Z regex                         2024.11.6
2025-03-21T20:25:25.3794657Z requests                      2.32.3
2025-03-21T20:25:25.3794969Z ruamel.yaml                   0.17.32
2025-03-21T20:25:25.3795286Z ruamel.yaml.clib              0.2.12
2025-03-21T20:25:25.3795585Z safetensors                   0.5.3
2025-03-21T20:25:25.3795894Z setuptools                    75.8.0
2025-03-21T20:25:25.3796205Z six                           1.17.0
2025-03-21T20:25:25.3796510Z snowballstemmer               2.2.0
2025-03-21T20:25:25.3796827Z sortedcontainers              2.4.0
2025-03-21T20:25:25.3797127Z soupsieve                     2.6
2025-03-21T20:25:25.3797425Z Sphinx                        5.3.0
2025-03-21T20:25:25.3797772Z sphinx-copybutton             0.5.0
2025-03-21T20:25:25.3798124Z sphinx_design                 0.4.1
2025-03-21T20:25:25.3798431Z sphinx-gallery                0.14.0
2025-03-21T20:25:25.3798800Z sphinxcontrib-applehelp       2.0.0
2025-03-21T20:25:25.3799241Z sphinxcontrib-devhelp         2.0.0
2025-03-21T20:25:25.3799670Z sphinxcontrib-htmlhelp        2.1.0
2025-03-21T20:25:25.3799987Z sphinxcontrib-jsmath          1.0.1
2025-03-21T20:25:25.3800315Z sphinxcontrib-qthelp          2.0.0
2025-03-21T20:25:25.3800656Z sphinxcontrib-serializinghtml 2.0.0
2025-03-21T20:25:25.3800984Z sympy                         1.13.3
2025-03-21T20:25:25.3801283Z tabulate                      0.9.0
2025-03-21T20:25:25.3801566Z timm                          1.0.7
2025-03-21T20:25:25.3801871Z tokenizers                    0.21.1
2025-03-21T20:25:25.3802173Z tomli                         2.0.1
2025-03-21T20:25:25.3802498Z torch                         2.7.0a0+git295f2ed
2025-03-21T20:25:25.3802866Z torchao                       0.10.0+git64bcf4c
2025-03-21T20:25:25.3803531Z torchaudio                    2.6.0a0+c670ad8
2025-03-21T20:25:25.3803869Z torchsr                       1.0.4
2025-03-21T20:25:25.3804197Z torchvision                   0.19.0a0+d23a6e1
2025-03-21T20:25:25.3804535Z tqdm                          4.67.1
2025-03-21T20:25:25.3804849Z transformers                  4.47.1
2025-03-21T20:25:25.3805138Z triton                        3.0.0
2025-03-21T20:25:25.3805486Z typing_extensions             4.12.2
2025-03-21T20:25:25.3805821Z tzdata                        2025.1
2025-03-21T20:25:25.3806116Z urllib3                       2.3.0
2025-03-21T20:25:25.3806409Z wheel                         0.45.1
2025-03-21T20:25:25.3806693Z zstd                          1.5.5.1
2025-03-21T20:25:25.3807011Z + build_executorch_runner cmake Release
2025-03-21T20:25:25.3807338Z + [[ cmake == \b\u\c\k\2 ]]
2025-03-21T20:25:25.3807625Z + [[ cmake == \c\m\a\k\e ]]
2025-03-21T20:25:25.3807904Z + build_executorch_runner_cmake Release
2025-03-21T20:25:25.3808246Z + CMAKE_OUTPUT_DIR=cmake-out
2025-03-21T20:25:25.3808553Z + clean_executorch_install_folders
2025-03-21T20:25:25.3808882Z + ./install_executorch.sh --clean
2025-03-21T20:25:25.3809199Z Cleaning build artifacts...
2025-03-21T20:25:25.3809537Z Cleaning pip-out/...
2025-03-21T20:25:25.3809808Z Cleaning cmake-out/...
2025-03-21T20:25:25.3810088Z Done cleaning build artifacts.
2025-03-21T20:25:25.3810377Z + mkdir cmake-out
2025-03-21T20:25:25.3810628Z + pushd cmake-out
2025-03-21T20:25:25.3810916Z /pytorch/executorch/cmake-out /pytorch/executorch
2025-03-21T20:25:25.3811289Z + [[ Release == \D\e\b\u\g ]]
2025-03-21T20:25:25.3811568Z + CXXFLAGS=
2025-03-21T20:25:25.3811794Z + CXXFLAGS=
2025-03-21T20:25:25.3812150Z + retry cmake -DPYTHON_EXECUTABLE=python -DCMAKE_BUILD_TYPE=Release ..
2025-03-21T20:25:25.3812675Z + cmake -DPYTHON_EXECUTABLE=python -DCMAKE_BUILD_TYPE=Release ..
2025-03-21T20:25:25.3813130Z -- The C compiler identification is Clang 12.0.1
2025-03-21T20:25:25.3813539Z -- The CXX compiler identification is Clang 12.0.1
2025-03-21T20:25:25.3813915Z -- Detecting C compiler ABI info
2025-03-21T20:25:25.3814246Z -- Detecting C compiler ABI info - done
2025-03-21T20:25:25.3814635Z -- Check for working C compiler: /opt/cache/bin/cc - skipped
2025-03-21T20:25:25.3815039Z -- Detecting C compile features
2025-03-21T20:25:25.3815357Z -- Detecting C compile features - done
2025-03-21T20:25:25.3815690Z -- Detecting CXX compiler ABI info
2025-03-21T20:25:25.3816027Z -- Detecting CXX compiler ABI info - done
2025-03-21T20:25:25.3816431Z -- Check for working CXX compiler: /opt/cache/bin/c++ - skipped
2025-03-21T20:25:25.3816859Z -- Detecting CXX compile features
2025-03-21T20:25:25.3817187Z -- Detecting CXX compile features - done
2025-03-21T20:25:25.3818047Z CMake Deprecation Warning at backends/xnnpack/third-party/FXdiv/CMakeLists.txt:1 (CMAKE_MINIMUM_REQUIRED):
2025-03-21T20:25:25.3818784Z   Compatibility with CMake < 3.10 will be removed from a future version of
2025-03-21T20:25:25.3819227Z   CMake.
2025-03-21T20:25:25.3819355Z 
2025-03-21T20:25:25.3819614Z   Update the VERSION argument <min> value.  Or, use the <min>...<max> syntax
2025-03-21T20:25:25.3820171Z   to tell CMake that the project requires at least <min> but has been updated
2025-03-21T20:25:25.3820682Z   to work with policies introduced by <max> or earlier.
2025-03-21T20:25:25.3820954Z 
2025-03-21T20:25:25.3821069Z 
2025-03-21T20:25:25.3821695Z CMake Deprecation Warning at backends/xnnpack/third-party/cpuinfo/CMakeLists.txt:1 (CMAKE_MINIMUM_REQUIRED):
2025-03-21T20:25:25.3822446Z   Compatibility with CMake < 3.10 will be removed from a future version of
2025-03-21T20:25:25.3822882Z   CMake.
2025-03-21T20:25:25.3823002Z 
2025-03-21T20:25:25.3823234Z   Update the VERSION argument <min> value.  Or, use the <min>...<max> syntax
2025-03-21T20:25:25.3823813Z   to tell CMake that the project requires at least <min> but has been updated
2025-03-21T20:25:25.3824316Z   to work with policies introduced by <max> or earlier.
2025-03-21T20:25:25.3824684Z 
2025-03-21T20:25:25.3825355Z 
2025-03-21T20:25:25.3825615Z -- Performing Test CMAKE_HAVE_LIBC_PTHREAD
2025-03-21T20:25:25.3826007Z -- Performing Test CMAKE_HAVE_LIBC_PTHREAD - Success
2025-03-21T20:25:25.3826380Z -- Found Threads: TRUE
2025-03-21T20:25:25.3827083Z CMake Deprecation Warning at backends/xnnpack/third-party/pthreadpool/CMakeLists.txt:1 (CMAKE_MINIMUM_REQUIRED):
2025-03-21T20:25:25.3827843Z   Compatibility with CMake < 3.10 will be removed from a future version of
2025-03-21T20:25:25.3828276Z   CMake.
2025-03-21T20:25:25.3828395Z 
2025-03-21T20:25:25.3828633Z   Update the VERSION argument <min> value.  Or, use the <min>...<max> syntax
2025-03-21T20:25:25.3829184Z   to tell CMake that the project requires at least <min> but has been updated
2025-03-21T20:25:25.3829679Z   to work with policies introduced by <max> or earlier.
2025-03-21T20:25:25.3829949Z 
2025-03-21T20:25:25.3830056Z 
2025-03-21T20:25:25.3830299Z -- Using python executable 'python'
2025-03-21T20:25:25.3830630Z -- Resolved buck2 as buck2.
2025-03-21T20:25:25.3830900Z -- Killing buck2 daemon
2025-03-21T20:25:25.3831161Z 'buck2 killall'
2025-03-21T20:25:25.3831421Z -- executorch: Generating source lists
2025-03-21T20:25:25.3832025Z -- executorch: Generating source file list /pytorch/executorch/cmake-out/executorch_srcs.cmake
2025-03-21T20:25:25.3833183Z -- executorch: Using sources file /pytorch/executorch/cmake-out/executorch_srcs.cmake
2025-03-21T20:25:25.3833691Z -- executorch: Using PAL default 'posix'
2025-03-21T20:25:25.3834033Z -- Generating operator lib:
2025-03-21T20:25:25.3834329Z --   LIB_NAME: portable_ops_lib
2025-03-21T20:25:25.3834748Z --   OPS_SCHEMA_YAML: /pytorch/executorch/kernels/portable/functions.yaml
2025-03-21T20:25:25.3835183Z --   ROOT_OPS: 
2025-03-21T20:25:25.3835421Z --   INCLUDE_ALL_OPS: 
2025-03-21T20:25:25.3836708Z Command - python;-m;codegen.tools.gen_oplist;--output_path=/pytorch/executorch/cmake-out/kernels/portable/portable_ops_lib/selected_operators.yaml;--ops_schema_yaml_path="/pytorch/executorch/kernels/portable/functions.yaml"
2025-03-21T20:25:25.3837841Z -- Generating kernel bindings:
2025-03-21T20:25:25.3838151Z --   LIB_NAME: portable_ops_lib
2025-03-21T20:25:25.3838571Z --   FUNCTIONS_YAML: /pytorch/executorch/kernels/portable/functions.yaml
2025-03-21T20:25:25.3839007Z --   CUSTOM_OPS_YAML: 
2025-03-21T20:25:25.3839283Z --   ADD_EXCEPTION_BOUNDARY: FALSE
2025-03-21T20:25:25.3840959Z Generated files /pytorch/executorch/cmake-out/kernels/portable/portable_ops_lib/RegisterCodegenUnboxedKernelsEverything.cpp;/pytorch/executorch/cmake-out/kernels/portable/portable_ops_lib/Functions.h;/pytorch/executorch/cmake-out/kernels/portable/portable_ops_lib/NativeFunctions.h
2025-03-21T20:25:25.3842428Z -- Generating operator lib:
2025-03-21T20:25:25.3842724Z --   LIB_NAME: portable_ops_lib
2025-03-21T20:25:25.3843029Z --   KERNEL_LIBS: portable_kernels
2025-03-21T20:25:25.3843335Z --   DEPS: executorch
2025-03-21T20:25:25.3843909Z CMake Deprecation Warning at third-party/gflags/CMakeLists.txt:73 (cmake_minimum_required):
2025-03-21T20:25:25.3844563Z   Compatibility with CMake < 3.10 will be removed from a future version of
2025-03-21T20:25:25.3844995Z   CMake.
2025-03-21T20:25:25.3845129Z 
2025-03-21T20:25:25.3845356Z   Update the VERSION argument <min> value.  Or, use the <min>...<max> syntax
2025-03-21T20:25:25.3845922Z   to tell CMake that the project requires at least <min> but has been updated
2025-03-21T20:25:25.3846424Z   to work with policies introduced by <max> or earlier.
2025-03-21T20:25:25.3846679Z 
2025-03-21T20:25:25.3846783Z 
2025-03-21T20:25:25.3847017Z -- Looking for C++ include unistd.h
2025-03-21T20:25:25.3847351Z -- Looking for C++ include unistd.h - found
2025-03-21T20:25:25.3847695Z -- Looking for C++ include stdint.h
2025-03-21T20:25:25.3848022Z -- Looking for C++ include stdint.h - found
2025-03-21T20:25:25.3848352Z -- Looking for C++ include inttypes.h
2025-03-21T20:25:25.3848696Z -- Looking for C++ include inttypes.h - found
2025-03-21T20:25:25.3849388Z -- Looking for C++ include sys/types.h
2025-03-21T20:25:25.3849745Z -- Looking for C++ include sys/types.h - found
2025-03-21T20:25:25.3850098Z -- Looking for C++ include sys/stat.h
2025-03-21T20:25:25.3850425Z -- Looking for C++ include sys/stat.h - found
2025-03-21T20:25:25.3850772Z -- Looking for C++ include fnmatch.h
2025-03-21T20:25:25.3851108Z -- Looking for C++ include fnmatch.h - found
2025-03-21T20:25:25.3851452Z -- Looking for C++ include stddef.h
2025-03-21T20:25:25.3851778Z -- Looking for C++ include stddef.h - found
2025-03-21T20:25:25.3852096Z -- Check size of uint32_t
2025-03-21T20:25:25.3852386Z -- Check size of uint32_t - done
2025-03-21T20:25:25.3852680Z -- Looking for strtoll
2025-03-21T20:25:25.3852950Z -- Looking for strtoll - found
2025-03-21T20:25:25.3853226Z -- 
2025-03-21T20:25:25.3853433Z -- ******** Summary ********
2025-03-21T20:25:25.3853727Z --   CMAKE_BUILD_TYPE              : Release
2025-03-21T20:25:25.3854059Z --   CMAKE_CXX_STANDARD            : 17
2025-03-21T20:25:25.3854398Z --   CMAKE_CXX_COMPILER_ID         : Clang
2025-03-21T20:25:25.3854732Z --   CMAKE_TOOLCHAIN_FILE          : 
2025-03-21T20:25:25.3855034Z --   BUCK2                         : buck2
2025-03-21T20:25:25.3855367Z --   PYTHON_EXECUTABLE             : python
2025-03-21T20:25:25.3855870Z --   FLATC_EXECUTABLE              : /pytorch/executorch/cmake-out/third-party/flatbuffers/flatc
2025-03-21T20:25:25.3856395Z --   EXECUTORCH_ENABLE_LOGGING              : OFF
2025-03-21T20:25:25.3856784Z --   EXECUTORCH_ENABLE_PROGRAM_VERIFICATION : OFF
2025-03-21T20:25:25.3857169Z --   EXECUTORCH_LOG_LEVEL                   : Info
2025-03-21T20:25:25.3857527Z --   EXECUTORCH_BUILD_ANDROID_JNI           : OFF
2025-03-21T20:25:25.3857901Z --   EXECUTORCH_BUILD_ARM_BAREMETAL         : OFF
2025-03-21T20:25:25.3858273Z --   EXECUTORCH_BUILD_CADENCE               : OFF
2025-03-21T20:25:25.3858635Z --   EXECUTORCH_BUILD_COREML                : OFF
2025-03-21T20:25:25.3858996Z --   EXECUTORCH_BUILD_CPUINFO               : ON
2025-03-21T20:25:25.3859355Z --   EXECUTORCH_BUILD_DEVTOOLS              : OFF
2025-03-21T20:25:25.3859726Z --   EXECUTORCH_BUILD_EXECUTOR_RUNNER       : ON
2025-03-21T20:25:25.3860101Z --   EXECUTORCH_BUILD_EXTENSION_DATA_LOADER : OFF
2025-03-21T20:25:25.3860482Z --   EXECUTORCH_BUILD_EXTENSION_FLAT_TENSOR : OFF
2025-03-21T20:25:25.3860847Z --   EXECUTORCH_BUILD_EXTENSION_LLM : OFF
2025-03-21T20:25:25.3861196Z --   EXECUTORCH_BUILD_EXTENSION_MODULE      : OFF
2025-03-21T20:25:25.3861577Z --   EXECUTORCH_BUILD_EXTENSION_RUNNER_UTIL : OFF
2025-03-21T20:25:25.3861958Z --   EXECUTORCH_BUILD_EXTENSION_TENSOR      : OFF
2025-03-21T20:25:25.3862342Z --   EXECUTORCH_BUILD_EXTENSION_TRAINING    : OFF
2025-03-21T20:25:25.3862719Z --   EXECUTORCH_BUILD_FLATC                 : ON
2025-03-21T20:25:25.3863070Z --   EXECUTORCH_BUILD_GFLAGS                : ON
2025-03-21T20:25:25.3863440Z --   EXECUTORCH_BUILD_HOST_TARGETS          : ON
2025-03-21T20:25:25.3863816Z --   EXECUTORCH_BUILD_KERNELS_CUSTOM        : OFF
2025-03-21T20:25:25.3864206Z --   EXECUTORCH_BUILD_KERNELS_CUSTOM_AOT    : OFF
2025-03-21T20:25:25.3864597Z --   EXECUTORCH_BUILD_KERNELS_OPTIMIZED     : OFF
2025-03-21T20:25:25.3864965Z --   EXECUTORCH_BUILD_KERNELS_QUANTIZED     : OFF
2025-03-21T20:25:25.3865343Z --   EXECUTORCH_BUILD_MPS                   : OFF
2025-03-21T20:25:25.3865712Z --   EXECUTORCH_BUILD_NEURON                : OFF
2025-03-21T20:25:25.3866085Z --   EXECUTORCH_BUILD_PTHREADPOOL           : ON
2025-03-21T20:25:26.6057446Z --   EXECUTORCH_BUILD_PYBIND                : OFF
2025-03-21T20:25:26.6058195Z --   EXECUTORCH_BUILD_QNN                   : OFF
2025-03-21T20:25:26.6058856Z --   EXECUTORCH_BUILD_SIZE_TEST             : OFF
2025-03-21T20:25:26.6059520Z --   EXECUTORCH_BUILD_TESTS                 : OFF
2025-03-21T20:25:26.6060170Z --   EXECUTORCH_BUILD_VULKAN                : OFF
2025-03-21T20:25:26.6060838Z --   EXECUTORCH_BUILD_XNNPACK               : OFF
2025-03-21T20:25:26.6061465Z -- Configuring done (4.9s)
2025-03-21T20:25:26.6062385Z -- Generating done (0.1s)
2025-03-21T20:25:26.6063030Z -- Build files have been written to: /pytorch/executorch/cmake-out
2025-03-21T20:25:26.6063698Z + popd
2025-03-21T20:25:26.6064076Z /pytorch/executorch
2025-03-21T20:25:26.6064492Z ++ uname
2025-03-21T20:25:26.6064867Z + '[' Linux == Darwin ']'
2025-03-21T20:25:26.6065304Z ++ nproc
2025-03-21T20:25:26.6065653Z + CMAKE_JOBS=7
2025-03-21T20:25:26.6066086Z + cmake --build cmake-out -j 7
2025-03-21T20:25:26.6066992Z [  0%] Creating directories for 'flatbuffers'
2025-03-21T20:25:26.6068275Z [  0%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/api.c.o
2025-03-21T20:25:26.6069915Z [  0%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/init.c.o
2025-03-21T20:25:26.6071618Z [  0%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/cache.c.o
2025-03-21T20:25:26.6073366Z [  0%] Building C object backends/xnnpack/third-party/pthreadpool/CMakeFiles/pthreadpool.dir/src/legacy-api.c.o
2025-03-21T20:25:26.6075226Z [  0%] Building CXX object third-party/gflags/CMakeFiles/gflags_nothreads_static.dir/src/gflags.cc.o
2025-03-21T20:25:26.6076954Z [  0%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/api.c.o
2025-03-21T20:25:26.6078154Z [  1%] No download step for 'flatbuffers'
2025-03-21T20:25:26.6078848Z [  2%] No update step for 'flatbuffers'
2025-03-21T20:25:26.6079455Z [  2%] No patch step for 'flatbuffers'
2025-03-21T20:25:26.6080363Z [  2%] Performing configure step for 'flatbuffers'
2025-03-21T20:25:26.6081053Z CMake Warning:
2025-03-21T20:25:26.6081601Z   Ignoring empty string ("") provided on the command line.
2025-03-21T20:25:26.6082083Z 
2025-03-21T20:25:26.6082275Z 
2025-03-21T20:25:26.6082708Z fatal: No names found, cannot describe anything.
2025-03-21T20:25:26.6083594Z CMake Warning at CMake/Version.cmake:32 (message):
2025-03-21T20:25:26.6084277Z   git describe failed with exit code: 128
2025-03-21T20:25:26.6084673Z 
2025-03-21T20:25:26.6085021Z   Make sure you cloned with tags or run 'git fetch --tags'.
2025-03-21T20:25:26.6085719Z Call Stack (most recent call first):
2025-03-21T20:25:26.6086256Z   CMakeLists.txt:5 (include)
2025-03-21T20:25:26.6086559Z 
2025-03-21T20:25:26.6086802Z 
2025-03-21T20:25:26.6087188Z -- Proceeding with version: 24.3.25.0
2025-03-21T20:25:26.6088452Z [  3%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/cache.c.o
2025-03-21T20:25:26.6090475Z [  4%] Building C object backends/xnnpack/third-party/pthreadpool/CMakeFiles/pthreadpool.dir/src/portable-api.c.o
2025-03-21T20:25:26.6092413Z [  4%] Building CXX object third-party/gflags/CMakeFiles/gflags_nothreads_static.dir/src/gflags_reporting.cc.o
2025-03-21T20:25:26.6094124Z [  5%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/log.c.o
2025-03-21T20:25:26.6095741Z [  5%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/init.c.o
2025-03-21T20:25:26.6097524Z [  5%] Building CXX object third-party/gflags/CMakeFiles/gflags_nothreads_static.dir/src/gflags_completions.cc.o
2025-03-21T20:25:26.6099400Z [  5%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/init.c.o
2025-03-21T20:25:26.6101264Z [  5%] Building C object backends/xnnpack/third-party/pthreadpool/CMakeFiles/pthreadpool.dir/src/memory.c.o
2025-03-21T20:25:26.6102994Z [  5%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/info.c.o
2025-03-21T20:25:26.6104725Z [  5%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/log.c.o
2025-03-21T20:25:26.6105930Z -- The CXX compiler identification is Clang 12.0.1
2025-03-21T20:25:26.6106922Z -- Detecting CXX compiler ABI info
2025-03-21T20:25:26.6108323Z [  5%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/x86/init.c.o
2025-03-21T20:25:26.6110304Z [  5%] Building C object backends/xnnpack/third-party/pthreadpool/CMakeFiles/pthreadpool.dir/src/pthreads.c.o
2025-03-21T20:25:26.6111772Z [  5%] Linking CXX static library libgflags_nothreads.a
2025-03-21T20:25:26.6113243Z [  5%] Building C object backends/xnnpack/third-party/pthreadpool/CMakeFiles/pthreadpool.dir/src/fastpath.c.o
2025-03-21T20:25:26.6114367Z [  5%] Built target gflags_nothreads_static
2025-03-21T20:25:26.6115685Z [  5%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/vendor.c.o
2025-03-21T20:25:26.6117566Z [  6%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/x86/info.c.o
2025-03-21T20:25:26.6119636Z [  6%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/x86/vendor.c.o
2025-03-21T20:25:26.6121727Z [  6%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/x86/uarch.c.o
2025-03-21T20:25:26.6123752Z [  6%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/x86/name.c.o
2025-03-21T20:25:26.6125833Z [  6%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/x86/topology.c.o
2025-03-21T20:25:26.6127198Z [  8%] Linking C static library libpthreadpool.a
2025-03-21T20:25:26.6128508Z [  8%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/x86/isa.c.o
2025-03-21T20:25:26.6129723Z [  8%] Built target pthreadpool
2025-03-21T20:25:26.6131002Z [  8%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/x86/cache/init.c.o
2025-03-21T20:25:26.6132406Z -- Detecting CXX compiler ABI info - done
2025-03-21T20:25:26.6133897Z [  8%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/x86/cache/descriptor.c.o
2025-03-21T20:25:26.6135906Z [  8%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/uarch.c.o
2025-03-21T20:25:26.6137137Z -- Check for working CXX compiler: /opt/cache/bin/c++ - skipped
2025-03-21T20:25:26.6137911Z -- Detecting CXX compile features
2025-03-21T20:25:26.6138470Z -- Detecting CXX compile features - done
2025-03-21T20:25:26.6139755Z [  9%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/name.c.o
2025-03-21T20:25:26.6140754Z -- Looking for strtof_l
2025-03-21T20:25:26.6141947Z [  9%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/topology.c.o
2025-03-21T20:25:26.6143631Z [  9%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/isa.c.o
2025-03-21T20:25:26.6145343Z [  9%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/cache/init.c.o
2025-03-21T20:25:26.6147302Z [  9%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/x86/cache/deterministic.c.o
2025-03-21T20:25:26.6149346Z [ 10%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/cache/descriptor.c.o
2025-03-21T20:25:26.6151324Z [ 10%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/cache/deterministic.c.o
2025-03-21T20:25:26.6153266Z [ 10%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/x86/linux/init.c.o
2025-03-21T20:25:26.6155097Z [ 10%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/linux/init.c.o
2025-03-21T20:25:26.6157040Z [ 11%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/x86/linux/cpuinfo.c.o
2025-03-21T20:25:26.6158871Z [ 11%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/linux/cpuinfo.c.o
2025-03-21T20:25:26.6160524Z [ 11%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/linux/smallfile.c.o
2025-03-21T20:25:26.6162106Z [ 11%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/linux/smallfile.c.o
2025-03-21T20:25:26.6163317Z [ 11%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/linux/multiline.c.o
2025-03-21T20:25:26.6164434Z [ 11%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/linux/cpulist.c.o
2025-03-21T20:25:26.6165549Z [ 12%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/linux/processors.c.o
2025-03-21T20:25:26.6166244Z -- Looking for strtof_l - found
2025-03-21T20:25:26.6166558Z -- Looking for strtoull_l
2025-03-21T20:25:26.6167234Z [ 13%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/linux/multiline.c.o
2025-03-21T20:25:26.6168232Z [ 13%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/linux/cpulist.c.o
2025-03-21T20:25:26.6169327Z [ 13%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/linux/processors.c.o
2025-03-21T20:25:26.6170107Z [ 13%] Linking C static library libcpuinfo_internals.a
2025-03-21T20:25:26.6170519Z [ 13%] Built target cpuinfo_internals
2025-03-21T20:25:26.6170929Z [ 13%] Linking C static library libcpuinfo.a
2025-03-21T20:25:26.6171297Z [ 13%] Built target cpuinfo
2025-03-21T20:25:26.6171589Z -- Looking for strtoull_l - found
2025-03-21T20:25:26.6171893Z -- Looking for realpath
2025-03-21T20:25:26.6172173Z -- Looking for realpath - found
2025-03-21T20:25:26.6172522Z -- CMAKE_CXX_FLAGS: "-DFLATBUFFERS_MAX_ALIGNMENT=1024"
2025-03-21T20:25:26.6172902Z -- Configuring done (1.0s)
2025-03-21T20:25:26.6173190Z -- Generating done (0.0s)
2025-03-21T20:25:26.6173661Z -- Build files have been written to: /pytorch/executorch/cmake-out/third-party/flatbuffers
2025-03-21T20:25:26.6174287Z [ 13%] Performing build step for 'flatbuffers'
2025-03-21T20:25:26.6174861Z [  2%] Building CXX object CMakeFiles/flatc.dir/src/idl_parser.cpp.o
2025-03-21T20:25:29.6211921Z [  5%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_text.cpp.o
2025-03-21T20:25:29.6212635Z [  7%] Building CXX object CMakeFiles/flatc.dir/src/reflection.cpp.o
2025-03-21T20:25:29.6213264Z [ 13%] Building CXX object CMakeFiles/flatc.dir/src/util.cpp.o
2025-03-21T20:25:29.6213905Z [ 13%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_binary.cpp.o
2025-03-21T20:25:29.6214561Z [ 15%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_cpp.cpp.o
2025-03-21T20:25:29.6215252Z [ 18%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_csharp.cpp.o
2025-03-21T20:25:29.6215909Z [ 21%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_dart.cpp.o
2025-03-21T20:25:29.6216552Z [ 23%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_kotlin.cpp.o
2025-03-21T20:25:29.6217261Z [ 26%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_kotlin_kmp.cpp.o
2025-03-21T20:25:29.6217925Z [ 28%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_go.cpp.o
2025-03-21T20:25:29.6218562Z [ 31%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_java.cpp.o
2025-03-21T20:25:29.6219197Z [ 34%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_ts.cpp.o
2025-03-21T20:25:29.6219830Z [ 36%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_php.cpp.o
2025-03-21T20:25:29.6220485Z [ 39%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_python.cpp.o
2025-03-21T20:25:29.6221453Z [ 42%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_lobster.cpp.o
2025-03-21T20:25:29.6222117Z [ 44%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_rust.cpp.o
2025-03-21T20:25:29.6222754Z [ 47%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_fbs.cpp.o
2025-03-21T20:25:29.6223395Z [ 50%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_grpc.cpp.o
2025-03-21T20:25:29.6224079Z [ 52%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_json_schema.cpp.o
2025-03-21T20:25:29.6224760Z [ 55%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_swift.cpp.o
2025-03-21T20:25:29.6225486Z [ 57%] Building CXX object CMakeFiles/flatc.dir/src/file_name_saving_file_manager.cpp.o
2025-03-21T20:25:29.6226232Z [ 60%] Building CXX object CMakeFiles/flatc.dir/src/file_binary_writer.cpp.o
2025-03-21T20:25:29.6226902Z [ 63%] Building CXX object CMakeFiles/flatc.dir/src/file_writer.cpp.o
2025-03-21T20:25:29.6227530Z [ 65%] Building CXX object CMakeFiles/flatc.dir/src/flatc.cpp.o
2025-03-21T20:25:29.6228141Z [ 68%] Building CXX object CMakeFiles/flatc.dir/src/flatc_main.cpp.o
2025-03-21T20:25:29.6228795Z [ 71%] Building CXX object CMakeFiles/flatc.dir/src/binary_annotator.cpp.o
2025-03-21T20:25:29.6229510Z [ 73%] Building CXX object CMakeFiles/flatc.dir/src/annotated_binary_text_gen.cpp.o
2025-03-21T20:25:29.6230208Z [ 76%] Building CXX object CMakeFiles/flatc.dir/src/bfbs_gen_lua.cpp.o
2025-03-21T20:25:29.6230848Z [ 78%] Building CXX object CMakeFiles/flatc.dir/src/bfbs_gen_nim.cpp.o
2025-03-21T20:25:29.6231507Z [ 81%] Building CXX object CMakeFiles/flatc.dir/src/code_generators.cpp.o
2025-03-21T20:25:29.6233314Z [ 84%] Building CXX object CMakeFiles/flatc.dir/grpc/src/compiler/cpp_generator.cc.o
2025-03-21T20:25:29.6234492Z [ 86%] Building CXX object CMakeFiles/flatc.dir/grpc/src/compiler/go_generator.cc.o
2025-03-21T20:25:29.6235338Z [ 89%] Building CXX object CMakeFiles/flatc.dir/grpc/src/compiler/java_generator.cc.o
2025-03-21T20:25:29.6236147Z [ 92%] Building CXX object CMakeFiles/flatc.dir/grpc/src/compiler/python_generator.cc.o
2025-03-21T20:25:29.6236946Z [ 94%] Building CXX object CMakeFiles/flatc.dir/grpc/src/compiler/swift_generator.cc.o
2025-03-21T20:25:29.6237720Z [ 97%] Building CXX object CMakeFiles/flatc.dir/grpc/src/compiler/ts_generator.cc.o
2025-03-21T20:25:29.6238823Z [100%] Linking CXX executable flatc
2025-03-21T20:25:29.6239335Z [100%] Built target flatc
2025-03-21T20:25:29.6239705Z [ 13%] No install step for 'flatbuffers'
2025-03-21T20:25:29.6240130Z [ 13%] Completed 'flatbuffers'
2025-03-21T20:25:29.6240470Z [ 13%] Built target flatbuffers
2025-03-21T20:25:29.6240848Z [ 13%] Generating common_schema headers
2025-03-21T20:25:29.6241203Z [ 13%] Built target common_schema
2025-03-21T20:25:29.6241583Z [ 13%] Generating program_schema headers
2025-03-21T20:25:29.6241962Z [ 13%] Built target program_schema
2025-03-21T20:25:29.6242567Z [ 13%] Building CXX object CMakeFiles/executorch_core.dir/runtime/backend/interface.cpp.o
2025-03-21T20:25:29.6243525Z [ 14%] Building CXX object CMakeFiles/executorch_core.dir/runtime/core/exec_aten/util/tensor_shape_to_c_string.cpp.o
2025-03-21T20:25:29.6244427Z [ 14%] Building CXX object CMakeFiles/executorch_core.dir/runtime/core/evalue.cpp.o
2025-03-21T20:25:29.6245336Z [ 14%] Building CXX object CMakeFiles/executorch_core.dir/runtime/core/exec_aten/util/tensor_util_portable.cpp.o
2025-03-21T20:25:29.6246308Z [ 14%] Building CXX object CMakeFiles/executorch_core.dir/runtime/core/portable_type/tensor_impl.cpp.o
2025-03-21T20:25:29.6247143Z [ 14%] Building CXX object CMakeFiles/executorch_core.dir/runtime/core/tag.cpp.o
2025-03-21T20:25:29.6247934Z [ 15%] Building CXX object CMakeFiles/executorch_core.dir/runtime/core/tensor_layout.cpp.o
2025-03-21T20:25:29.6249018Z [ 15%] Building CXX object CMakeFiles/executorch_core.dir/runtime/executor/method.cpp.o
2025-03-21T20:25:29.6249931Z [ 15%] Building CXX object CMakeFiles/executorch_core.dir/runtime/executor/method_meta.cpp.o
2025-03-21T20:25:29.6250762Z [ 15%] Building CXX object CMakeFiles/executorch_core.dir/runtime/executor/program.cpp.o
2025-03-21T20:25:29.6251600Z [ 16%] Building CXX object CMakeFiles/executorch_core.dir/runtime/executor/pte_data_map.cpp.o
2025-03-21T20:25:29.6252494Z [ 16%] Building CXX object CMakeFiles/executorch_core.dir/runtime/executor/tensor_parser_exec_aten.cpp.o
2025-03-21T20:25:29.6253443Z [ 16%] Building CXX object CMakeFiles/executorch_core.dir/runtime/executor/tensor_parser_portable.cpp.o
2025-03-21T20:25:29.6254422Z [ 16%] Building CXX object CMakeFiles/executorch_core.dir/runtime/kernel/operator_registry.cpp.o
2025-03-21T20:25:29.6255260Z [ 16%] Building CXX object CMakeFiles/executorch_core.dir/runtime/platform/abort.cpp.o
2025-03-21T20:25:29.6256057Z [ 17%] Building CXX object CMakeFiles/executorch_core.dir/runtime/platform/log.cpp.o
2025-03-21T20:25:29.6256862Z [ 17%] Building CXX object CMakeFiles/executorch_core.dir/runtime/platform/profiler.cpp.o
2025-03-21T20:25:29.6257671Z [ 17%] Building CXX object CMakeFiles/executorch_core.dir/runtime/platform/runtime.cpp.o
2025-03-21T20:25:29.6258578Z [ 17%] Building CXX object CMakeFiles/executorch_core.dir/schema/extended_header.cpp.o
2025-03-21T20:25:29.6259420Z [ 17%] Building CXX object CMakeFiles/executorch_core.dir/runtime/platform/default/posix.cpp.o
2025-03-21T20:25:29.6260124Z [ 18%] Linking CXX static library libexecutorch_core.a
2025-03-21T20:25:29.6260542Z [ 18%] Built target executorch_core
2025-03-21T20:25:29.6261232Z [ 19%] Building CXX object CMakeFiles/executorch.dir/kernels/prim_ops/et_copy_index.cpp.o
2025-03-21T20:25:29.6262079Z [ 19%] Building CXX object CMakeFiles/executorch.dir/kernels/prim_ops/register_prim_ops.cpp.o
2025-03-21T20:25:29.6262899Z [ 19%] Building CXX object CMakeFiles/executorch.dir/kernels/prim_ops/et_view.cpp.o
2025-03-21T20:25:29.6263898Z [ 19%] Building CXX object extension/threadpool/CMakeFiles/extension_threadpool.dir/threadpool.cpp.o
2025-03-21T20:25:29.6264889Z [ 19%] Building CXX object extension/threadpool/CMakeFiles/extension_threadpool.dir/threadpool_guard.cpp.o
2025-03-21T20:25:29.6265897Z [ 19%] Building CXX object extension/threadpool/CMakeFiles/extension_threadpool.dir/thread_parallel.cpp.o
2025-03-21T20:25:29.6266885Z [ 20%] Building CXX object extension/threadpool/CMakeFiles/extension_threadpool.dir/cpuinfo_utils.cpp.o
2025-03-21T20:25:29.6267652Z [ 20%] Linking CXX static library libextension_threadpool.a
2025-03-21T20:25:29.6268179Z [ 20%] Linking CXX static library libexecutorch.a
2025-03-21T20:25:29.6268578Z [ 20%] Built target extension_threadpool
2025-03-21T20:25:29.6268919Z [ 20%] Built target executorch
2025-03-21T20:25:29.6269668Z [ 20%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op__empty_dim_order.cpp.o
2025-03-21T20:25:29.6270759Z [ 21%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op__to_dim_order_copy.cpp.o
2025-03-21T20:25:29.6272055Z [ 21%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_abs.cpp.o
2025-03-21T20:25:29.6273235Z [ 21%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_acos.cpp.o
2025-03-21T20:25:29.6274462Z [ 21%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_acosh.cpp.o
2025-03-21T20:25:29.6275473Z [ 22%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op__empty_dim_order.cpp.o
2025-03-21T20:25:29.6276562Z [ 22%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op__to_dim_order_copy.cpp.o
2025-03-21T20:25:29.6277821Z [ 22%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_abs.cpp.o
2025-03-21T20:25:29.6278797Z [ 22%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_acos.cpp.o
2025-03-21T20:25:29.6279699Z [ 23%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_add.cpp.o
2025-03-21T20:25:29.6280723Z [ 23%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_acosh.cpp.o
2025-03-21T20:25:29.6281659Z [ 23%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_addmm.cpp.o
2025-03-21T20:25:29.6282572Z [ 23%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_alias_copy.cpp.o
2025-03-21T20:25:29.6283518Z [ 24%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_add.cpp.o
2025-03-21T20:25:29.6284493Z [ 24%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_addmm.cpp.o
2025-03-21T20:25:31.6232166Z [ 24%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_allclose.cpp.o
2025-03-21T20:25:31.6235497Z [ 24%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_alias_copy.cpp.o
2025-03-21T20:25:31.6237490Z [ 24%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_allclose.cpp.o
2025-03-21T20:25:31.6239418Z [ 25%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_amax.cpp.o
2025-03-21T20:25:31.6241300Z [ 25%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_amin.cpp.o
2025-03-21T20:25:31.6243155Z [ 25%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_any.cpp.o
2025-03-21T20:25:31.6244977Z [ 25%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_amax.cpp.o
2025-03-21T20:25:31.6246815Z [ 25%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_arange.cpp.o
2025-03-21T20:25:31.6248728Z [ 25%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_argmax.cpp.o
2025-03-21T20:25:31.6250611Z [ 26%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_amin.cpp.o
2025-03-21T20:25:31.6252298Z [ 26%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_any.cpp.o
2025-03-21T20:25:31.6253997Z [ 26%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_arange.cpp.o
2025-03-21T20:25:31.6255853Z [ 27%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_argmin.cpp.o
2025-03-21T20:25:31.6257869Z [ 27%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_as_strided_copy.cpp.o
2025-03-21T20:25:31.6259709Z [ 27%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_argmax.cpp.o
2025-03-21T20:25:31.6261413Z [ 27%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_argmin.cpp.o
2025-03-21T20:25:31.6263238Z [ 28%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_as_strided_copy.cpp.o
2025-03-21T20:25:31.6264969Z [ 28%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_asin.cpp.o
2025-03-21T20:25:31.6266703Z [ 28%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_asinh.cpp.o
2025-03-21T20:25:31.6268525Z [ 28%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_asin.cpp.o
2025-03-21T20:25:31.6270421Z [ 28%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_asinh.cpp.o
2025-03-21T20:25:31.6272597Z [ 28%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_atan.cpp.o
2025-03-21T20:25:31.6274318Z [ 29%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_atan2.cpp.o
2025-03-21T20:25:31.6275923Z [ 29%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_atanh.cpp.o
2025-03-21T20:25:31.6277669Z [ 29%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_avg_pool2d.cpp.o
2025-03-21T20:25:31.6279520Z [ 29%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_atan.cpp.o
2025-03-21T20:25:31.6281375Z [ 29%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_bitwise_and.cpp.o
2025-03-21T20:25:31.6283245Z [ 30%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_atan2.cpp.o
2025-03-21T20:25:31.6285121Z [ 30%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_atanh.cpp.o
2025-03-21T20:25:31.6286973Z [ 30%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_bitwise_not.cpp.o
2025-03-21T20:25:31.6288722Z [ 31%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_bitwise_or.cpp.o
2025-03-21T20:25:31.6290776Z [ 31%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_avg_pool2d.cpp.o
2025-03-21T20:25:31.6292620Z [ 31%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_bitwise_xor.cpp.o
2025-03-21T20:25:31.6294380Z [ 31%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_bmm.cpp.o
2025-03-21T20:25:31.6296252Z [ 31%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_bitwise_and.cpp.o
2025-03-21T20:25:31.6298274Z [ 32%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_bitwise_not.cpp.o
2025-03-21T20:25:31.6300097Z [ 32%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_cat.cpp.o
2025-03-21T20:25:31.6301861Z [ 32%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_bitwise_or.cpp.o
2025-03-21T20:25:31.6303829Z [ 32%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_bitwise_xor.cpp.o
2025-03-21T20:25:31.6305773Z [ 33%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_cdist_forward.cpp.o
2025-03-21T20:25:31.6307556Z [ 33%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_ceil.cpp.o
2025-03-21T20:25:31.6309326Z [ 33%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_bmm.cpp.o
2025-03-21T20:25:31.6311113Z [ 33%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_clamp.cpp.o
2025-03-21T20:25:31.6312847Z [ 33%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_clone.cpp.o
2025-03-21T20:25:31.6314643Z [ 33%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_cat.cpp.o
2025-03-21T20:25:31.6316612Z [ 34%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_cdist_forward.cpp.o
2025-03-21T20:25:31.6318596Z [ 34%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_constant_pad_nd.cpp.o
2025-03-21T20:25:31.6320470Z [ 34%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_ceil.cpp.o
2025-03-21T20:25:31.6322326Z [ 35%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_convolution.cpp.o
2025-03-21T20:25:31.6324252Z [ 35%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_convolution_backward.cpp.o
2025-03-21T20:25:31.6326197Z [ 35%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_copy.cpp.o
2025-03-21T20:25:31.6328120Z [ 35%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_clamp.cpp.o
2025-03-21T20:25:31.6330080Z [ 35%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_clone.cpp.o
2025-03-21T20:25:31.6331858Z [ 35%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_cos.cpp.o
2025-03-21T20:25:31.6334010Z [ 35%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_constant_pad_nd.cpp.o
2025-03-21T20:25:31.6335882Z [ 36%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_convolution.cpp.o
2025-03-21T20:25:31.6337357Z [ 36%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_cosh.cpp.o
2025-03-21T20:25:31.6338615Z [ 37%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_cumsum.cpp.o
2025-03-21T20:25:31.6340017Z [ 37%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_convolution_backward.cpp.o
2025-03-21T20:25:31.6341480Z [ 37%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_copy.cpp.o
2025-03-21T20:25:31.6342778Z [ 37%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_detach_copy.cpp.o
2025-03-21T20:25:31.6344050Z [ 37%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_cos.cpp.o
2025-03-21T20:25:31.6345364Z [ 38%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_cosh.cpp.o
2025-03-21T20:25:31.6346717Z [ 38%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_diagonal_copy.cpp.o
2025-03-21T20:25:31.6347968Z [ 38%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_div.cpp.o
2025-03-21T20:25:31.6349283Z [ 38%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_cumsum.cpp.o
2025-03-21T20:25:31.6350714Z [ 38%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_detach_copy.cpp.o
2025-03-21T20:25:31.6352049Z [ 39%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_embedding.cpp.o
2025-03-21T20:25:31.6353403Z [ 39%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_diagonal_copy.cpp.o
2025-03-21T20:25:31.6354759Z [ 39%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_div.cpp.o
2025-03-21T20:25:31.6356091Z [ 40%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_embedding.cpp.o
2025-03-21T20:25:31.6357363Z [ 40%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_empty.cpp.o
2025-03-21T20:25:31.6358771Z [ 40%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_empty.cpp.o
2025-03-21T20:25:33.7102992Z [ 40%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_eq.cpp.o
2025-03-21T20:25:33.7104744Z [ 40%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_eq.cpp.o
2025-03-21T20:25:33.7106097Z [ 40%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_erf.cpp.o
2025-03-21T20:25:33.7107946Z [ 41%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_exp.cpp.o
2025-03-21T20:25:33.7109552Z [ 41%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_erf.cpp.o
2025-03-21T20:25:33.7111310Z [ 41%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_expand_copy.cpp.o
2025-03-21T20:25:33.7113455Z [ 41%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_expm1.cpp.o
2025-03-21T20:25:33.7115300Z [ 41%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_exp.cpp.o
2025-03-21T20:25:33.7116980Z [ 42%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_expand_copy.cpp.o
2025-03-21T20:25:33.7118677Z [ 42%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_expm1.cpp.o
2025-03-21T20:25:33.7120235Z [ 42%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_fill.cpp.o
2025-03-21T20:25:33.7121226Z [ 42%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_flip.cpp.o
2025-03-21T20:25:33.7122199Z [ 43%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_floor.cpp.o
2025-03-21T20:25:33.7123130Z [ 43%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_fill.cpp.o
2025-03-21T20:25:33.7124031Z [ 43%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_flip.cpp.o
2025-03-21T20:25:33.7124912Z [ 43%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_floor.cpp.o
2025-03-21T20:25:33.7125840Z [ 44%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_floor_divide.cpp.o
2025-03-21T20:25:33.7126737Z [ 44%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_fmod.cpp.o
2025-03-21T20:25:33.7127710Z [ 44%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_floor_divide.cpp.o
2025-03-21T20:25:33.7128712Z [ 44%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_fmod.cpp.o
2025-03-21T20:25:33.7129798Z [ 44%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_full.cpp.o
2025-03-21T20:25:33.7130729Z [ 44%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_full.cpp.o
2025-03-21T20:25:33.7131636Z [ 44%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_full_like.cpp.o
2025-03-21T20:25:33.7132822Z [ 45%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_gather.cpp.o
2025-03-21T20:25:33.7133702Z [ 45%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_ge.cpp.o
2025-03-21T20:25:33.7134688Z [ 45%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_full_like.cpp.o
2025-03-21T20:25:33.7135701Z [ 46%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_gather.cpp.o
2025-03-21T20:25:33.7136670Z [ 46%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_ge.cpp.o
2025-03-21T20:25:33.7137593Z [ 46%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_gelu.cpp.o
2025-03-21T20:25:33.7138474Z [ 46%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_glu.cpp.o
2025-03-21T20:25:33.7139336Z [ 46%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_gt.cpp.o
2025-03-21T20:25:33.7140219Z [ 47%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_hardtanh.cpp.o
2025-03-21T20:25:33.7141170Z [ 47%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_gelu.cpp.o
2025-03-21T20:25:33.7142140Z [ 47%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_glu.cpp.o
2025-03-21T20:25:33.7143196Z [ 48%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_gt.cpp.o
2025-03-21T20:25:33.7144192Z [ 48%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_hardtanh.cpp.o
2025-03-21T20:25:33.7146129Z [ 48%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_index.cpp.o
2025-03-21T20:25:33.7147741Z [ 48%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_index.cpp.o
2025-03-21T20:25:33.7149379Z [ 48%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_index_put.cpp.o
2025-03-21T20:25:33.7151152Z [ 48%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_index_select.cpp.o
2025-03-21T20:25:33.7153006Z [ 48%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_index_put.cpp.o
2025-03-21T20:25:33.7154886Z [ 48%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_index_select.cpp.o
2025-03-21T20:25:33.7156604Z [ 49%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_isinf.cpp.o
2025-03-21T20:25:33.7158247Z [ 49%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_isnan.cpp.o
2025-03-21T20:25:33.7159826Z [ 49%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_le.cpp.o
2025-03-21T20:25:33.7161333Z [ 49%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_leaky_relu.cpp.o
2025-03-21T20:25:33.7162969Z [ 49%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_lift_fresh_copy.cpp.o
2025-03-21T20:25:33.7164739Z [ 50%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_linear_scratch_example.cpp.o
2025-03-21T20:25:33.7166512Z [ 51%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_isinf.cpp.o
2025-03-21T20:25:33.7168133Z [ 51%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_log.cpp.o
2025-03-21T20:25:33.7169624Z [ 51%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_log10.cpp.o
2025-03-21T20:25:33.7171110Z [ 51%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_log1p.cpp.o
2025-03-21T20:25:33.7172643Z [ 51%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_isnan.cpp.o
2025-03-21T20:25:33.7174352Z [ 51%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_le.cpp.o
2025-03-21T20:25:33.7176402Z [ 51%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_leaky_relu.cpp.o
2025-03-21T20:25:33.7178347Z [ 51%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_log2.cpp.o
2025-03-21T20:25:33.7180110Z [ 52%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_log_softmax.cpp.o
2025-03-21T20:25:33.7181530Z [ 52%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_logical_and.cpp.o
2025-03-21T20:25:33.7182839Z [ 52%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_logical_not.cpp.o
2025-03-21T20:25:33.7184212Z [ 52%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_lift_fresh_copy.cpp.o
2025-03-21T20:25:33.7185766Z [ 53%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_linear_scratch_example.cpp.o
2025-03-21T20:25:33.7187151Z [ 53%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_logical_or.cpp.o
2025-03-21T20:25:33.7188415Z [ 54%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_logical_xor.cpp.o
2025-03-21T20:25:33.7189633Z [ 54%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_logit.cpp.o
2025-03-21T20:25:33.7190853Z [ 54%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_lt.cpp.o
2025-03-21T20:25:33.7192288Z [ 54%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_log.cpp.o
2025-03-21T20:25:33.7193699Z [ 54%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_masked_fill.cpp.o
2025-03-21T20:25:33.7195067Z [ 54%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_masked_scatter.cpp.o
2025-03-21T20:25:33.7196378Z [ 54%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_log10.cpp.o
2025-03-21T20:25:33.7197723Z [ 54%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_log1p.cpp.o
2025-03-21T20:25:33.7199003Z [ 55%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_masked_select.cpp.o
2025-03-21T20:25:33.7200234Z [ 55%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_max.cpp.o
2025-03-21T20:25:33.7201454Z [ 56%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_log2.cpp.o
2025-03-21T20:25:33.7202828Z [ 56%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_log_softmax.cpp.o
2025-03-21T20:25:35.7600863Z [ 56%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_max_pool2d_with_indices.cpp.o
2025-03-21T20:25:35.7603340Z [ 56%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_max_pool2d_with_indices_backward.cpp.o
2025-03-21T20:25:35.7605625Z [ 56%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_logical_and.cpp.o
2025-03-21T20:25:35.7607523Z [ 56%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_maximum.cpp.o
2025-03-21T20:25:35.7609569Z [ 57%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_mean.cpp.o
2025-03-21T20:25:35.7611457Z [ 57%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_min.cpp.o
2025-03-21T20:25:35.7613493Z [ 57%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_logical_not.cpp.o
2025-03-21T20:25:35.7615677Z [ 57%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_logical_or.cpp.o
2025-03-21T20:25:35.7617696Z [ 57%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_minimum.cpp.o
2025-03-21T20:25:35.7619512Z [ 57%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_mm.cpp.o
2025-03-21T20:25:35.7621584Z [ 58%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_logical_xor.cpp.o
2025-03-21T20:25:35.7623676Z [ 58%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_logit.cpp.o
2025-03-21T20:25:35.7625586Z [ 58%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_lt.cpp.o
2025-03-21T20:25:35.7627750Z [ 58%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_masked_fill.cpp.o
2025-03-21T20:25:35.7629712Z [ 59%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_mul.cpp.o
2025-03-21T20:25:35.7631800Z [ 60%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_masked_scatter.cpp.o
2025-03-21T20:25:35.7634126Z [ 60%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_narrow_copy.cpp.o
2025-03-21T20:25:35.7636116Z [ 60%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_native_batch_norm.cpp.o
2025-03-21T20:25:35.7638370Z [ 60%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_masked_select.cpp.o
2025-03-21T20:25:35.7640400Z [ 60%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_max.cpp.o
2025-03-21T20:25:35.7643022Z [ 60%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_max_pool2d_with_indices.cpp.o
2025-03-21T20:25:35.7645601Z [ 60%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_max_pool2d_with_indices_backward.cpp.o
2025-03-21T20:25:35.7647896Z [ 61%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_maximum.cpp.o
2025-03-21T20:25:35.7650066Z [ 61%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_mean.cpp.o
2025-03-21T20:25:35.7652139Z [ 61%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_native_group_norm.cpp.o
2025-03-21T20:25:35.7654187Z [ 61%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_min.cpp.o
2025-03-21T20:25:35.7656276Z [ 61%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_native_layer_norm.cpp.o
2025-03-21T20:25:35.7658144Z [ 62%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_ne.cpp.o
2025-03-21T20:25:35.7660100Z [ 62%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_minimum.cpp.o
2025-03-21T20:25:35.7662604Z [ 62%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_mm.cpp.o
2025-03-21T20:25:35.7664799Z [ 63%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_mul.cpp.o
2025-03-21T20:25:35.7666901Z [ 63%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_neg.cpp.o
2025-03-21T20:25:35.7668787Z [ 63%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_nonzero.cpp.o
2025-03-21T20:25:35.7670681Z [ 63%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_ones.cpp.o
2025-03-21T20:25:35.7672642Z [ 63%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_narrow_copy.cpp.o
2025-03-21T20:25:35.7674655Z [ 63%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_pdist_forward.cpp.o
2025-03-21T20:25:35.7676825Z [ 63%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_native_batch_norm.cpp.o
2025-03-21T20:25:35.7679053Z [ 63%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_native_group_norm.cpp.o
2025-03-21T20:25:35.7681394Z [ 64%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_native_layer_norm.cpp.o
2025-03-21T20:25:35.7683424Z [ 65%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_permute_copy.cpp.o
2025-03-21T20:25:35.7685251Z [ 65%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_pixel_shuffle.cpp.o
2025-03-21T20:25:35.7687378Z [ 65%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_ne.cpp.o
2025-03-21T20:25:35.7689450Z [ 65%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_pixel_unshuffle.cpp.o
2025-03-21T20:25:35.7691373Z [ 65%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_pow.cpp.o
2025-03-21T20:25:35.7693290Z [ 66%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_prod.cpp.o
2025-03-21T20:25:35.7695182Z [ 66%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_neg.cpp.o
2025-03-21T20:25:35.7697274Z [ 66%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_nonzero.cpp.o
2025-03-21T20:25:35.7699364Z [ 66%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_reciprocal.cpp.o
2025-03-21T20:25:35.7701372Z [ 66%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_ones.cpp.o
2025-03-21T20:25:35.7703746Z [ 66%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_reflection_pad1d.cpp.o
2025-03-21T20:25:35.7705673Z [ 67%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_pdist_forward.cpp.o
2025-03-21T20:25:35.7707792Z [ 67%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_permute_copy.cpp.o
2025-03-21T20:25:35.7709853Z [ 67%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_pixel_shuffle.cpp.o
2025-03-21T20:25:35.7711857Z [ 67%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_pixel_unshuffle.cpp.o
2025-03-21T20:25:35.7713696Z [ 67%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_pow.cpp.o
2025-03-21T20:25:35.7715657Z [ 67%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_reflection_pad2d.cpp.o
2025-03-21T20:25:35.7717521Z [ 68%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_prod.cpp.o
2025-03-21T20:25:35.7719497Z [ 68%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_reciprocal.cpp.o
2025-03-21T20:25:35.7721238Z [ 68%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_reflection_pad3d.cpp.o
2025-03-21T20:25:35.7722897Z [ 69%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_relu.cpp.o
2025-03-21T20:25:35.7724795Z [ 69%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_reflection_pad1d.cpp.o
2025-03-21T20:25:35.7726836Z [ 69%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_reflection_pad2d.cpp.o
2025-03-21T20:25:35.7728481Z [ 69%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_remainder.cpp.o
2025-03-21T20:25:35.7730409Z [ 70%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_reflection_pad3d.cpp.o
2025-03-21T20:25:35.7732412Z [ 70%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_relu.cpp.o
2025-03-21T20:25:35.7734030Z [ 70%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_remainder.cpp.o
2025-03-21T20:25:35.7735813Z [ 70%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_repeat.cpp.o
2025-03-21T20:25:35.7737803Z [ 70%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_repeat_interleave.cpp.o
2025-03-21T20:25:35.7739763Z [ 70%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_repeat.cpp.o
2025-03-21T20:25:35.7741686Z [ 70%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_repeat_interleave.cpp.o
2025-03-21T20:25:35.7743683Z [ 71%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_replication_pad1d.cpp.o
2025-03-21T20:25:37.8769930Z [ 72%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_replication_pad1d.cpp.o
2025-03-21T20:25:37.8772142Z [ 72%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_replication_pad2d.cpp.o
2025-03-21T20:25:37.8774384Z [ 72%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_replication_pad3d.cpp.o
2025-03-21T20:25:37.8776562Z [ 72%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_roll.cpp.o
2025-03-21T20:25:37.8778597Z [ 73%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_round.cpp.o
2025-03-21T20:25:37.8780623Z [ 73%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_replication_pad2d.cpp.o
2025-03-21T20:25:37.8783327Z [ 73%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_rsqrt.cpp.o
2025-03-21T20:25:37.8785392Z [ 73%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_replication_pad3d.cpp.o
2025-03-21T20:25:37.8787481Z [ 73%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_rsub.cpp.o
2025-03-21T20:25:37.8789436Z [ 73%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_roll.cpp.o
2025-03-21T20:25:37.8791454Z [ 73%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_scalar_tensor.cpp.o
2025-03-21T20:25:37.8793420Z [ 73%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_round.cpp.o
2025-03-21T20:25:37.8795396Z [ 73%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_scatter.cpp.o
2025-03-21T20:25:37.8797351Z [ 74%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_rsqrt.cpp.o
2025-03-21T20:25:37.8799407Z [ 75%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_scatter_add.cpp.o
2025-03-21T20:25:37.8801532Z [ 75%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_select_copy.cpp.o
2025-03-21T20:25:37.8803483Z [ 75%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_rsub.cpp.o
2025-03-21T20:25:37.8805683Z [ 75%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_select_scatter.cpp.o
2025-03-21T20:25:37.8807708Z [ 75%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_scalar_tensor.cpp.o
2025-03-21T20:25:37.8809696Z [ 75%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_scatter.cpp.o
2025-03-21T20:25:37.8811761Z [ 75%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_sigmoid.cpp.o
2025-03-21T20:25:37.8813791Z [ 75%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_sign.cpp.o
2025-03-21T20:25:37.8815834Z [ 76%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_sin.cpp.o
2025-03-21T20:25:37.8817805Z [ 76%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_scatter_add.cpp.o
2025-03-21T20:25:37.8819682Z [ 77%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_select_copy.cpp.o
2025-03-21T20:25:37.8821750Z [ 77%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_sinh.cpp.o
2025-03-21T20:25:37.8823702Z [ 77%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_select_scatter.cpp.o
2025-03-21T20:25:37.8825772Z [ 77%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_slice_copy.cpp.o
2025-03-21T20:25:37.8828023Z [ 77%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_slice_scatter.cpp.o
2025-03-21T20:25:37.8830113Z [ 78%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_softmax.cpp.o
2025-03-21T20:25:37.8832167Z [ 78%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_split_copy.cpp.o
2025-03-21T20:25:37.8834444Z [ 78%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_sigmoid.cpp.o
2025-03-21T20:25:37.8836581Z [ 78%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_split_with_sizes_copy.cpp.o
2025-03-21T20:25:37.8838663Z [ 78%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_sqrt.cpp.o
2025-03-21T20:25:37.8841027Z [ 78%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_squeeze_copy.cpp.o
2025-03-21T20:25:37.8843260Z [ 79%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_stack.cpp.o
2025-03-21T20:25:37.8845223Z [ 79%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_sign.cpp.o
2025-03-21T20:25:37.8847065Z [ 80%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_sin.cpp.o
2025-03-21T20:25:37.8849001Z [ 80%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_sub.cpp.o
2025-03-21T20:25:37.8851026Z [ 80%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_sinh.cpp.o
2025-03-21T20:25:37.8852903Z [ 80%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_slice_copy.cpp.o
2025-03-21T20:25:37.8854791Z [ 80%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_sum.cpp.o
2025-03-21T20:25:37.8856840Z [ 80%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_slice_scatter.cpp.o
2025-03-21T20:25:37.8858869Z [ 80%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_t_copy.cpp.o
2025-03-21T20:25:37.8860849Z [ 80%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_tan.cpp.o
2025-03-21T20:25:37.8862801Z [ 80%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_softmax.cpp.o
2025-03-21T20:25:37.8864678Z [ 81%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_split_copy.cpp.o
2025-03-21T20:25:37.8866755Z [ 81%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_split_with_sizes_copy.cpp.o
2025-03-21T20:25:37.8868707Z [ 81%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_sqrt.cpp.o
2025-03-21T20:25:37.8870726Z [ 82%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_tanh.cpp.o
2025-03-21T20:25:37.8872744Z [ 82%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_squeeze_copy.cpp.o
2025-03-21T20:25:37.8874690Z [ 82%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_stack.cpp.o
2025-03-21T20:25:37.8876615Z [ 82%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_to_copy.cpp.o
2025-03-21T20:25:37.8878754Z [ 82%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_topk.cpp.o
2025-03-21T20:25:37.8880618Z [ 83%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_sub.cpp.o
2025-03-21T20:25:37.8882323Z [ 83%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_sum.cpp.o
2025-03-21T20:25:37.8884263Z [ 83%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_t_copy.cpp.o
2025-03-21T20:25:37.8886068Z [ 83%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_tan.cpp.o
2025-03-21T20:25:37.8887857Z [ 84%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_tanh.cpp.o
2025-03-21T20:25:37.8890086Z [ 84%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_transpose_copy.cpp.o
2025-03-21T20:25:37.8892241Z [ 85%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_tril.cpp.o
2025-03-21T20:25:37.8894220Z [ 85%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_to_copy.cpp.o
2025-03-21T20:25:37.8896060Z [ 85%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_topk.cpp.o
2025-03-21T20:25:37.8897925Z [ 85%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_trunc.cpp.o
2025-03-21T20:25:37.8900230Z [ 85%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_transpose_copy.cpp.o
2025-03-21T20:25:37.8902171Z [ 85%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_tril.cpp.o
2025-03-21T20:25:37.8903980Z [ 86%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_trunc.cpp.o
2025-03-21T20:25:37.8915902Z [ 86%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_unbind_copy.cpp.o
2025-03-21T20:25:37.8918053Z [ 86%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_unbind_copy.cpp.o
2025-03-21T20:25:37.8919810Z [ 86%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_unfold_copy.cpp.o
2025-03-21T20:25:37.8921629Z [ 86%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_unsqueeze_copy.cpp.o
2025-03-21T20:25:37.8923508Z [ 87%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_upsample_bilinear2d.cpp.o
2025-03-21T20:25:37.8925479Z [ 87%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_upsample_nearest2d.cpp.o
2025-03-21T20:25:42.4340418Z [ 87%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_var.cpp.o
2025-03-21T20:25:42.4341459Z [ 87%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_unfold_copy.cpp.o
2025-03-21T20:25:42.4342461Z [ 87%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_view_copy.cpp.o
2025-03-21T20:25:42.4343470Z [ 87%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_unsqueeze_copy.cpp.o
2025-03-21T20:25:42.4344573Z [ 88%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_upsample_bilinear2d.cpp.o
2025-03-21T20:25:42.4345725Z [ 88%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_upsample_nearest2d.cpp.o
2025-03-21T20:25:42.4346772Z [ 88%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_var.cpp.o
2025-03-21T20:25:42.4347688Z [ 88%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_where.cpp.o
2025-03-21T20:25:42.4348656Z [ 88%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_view_copy.cpp.o
2025-03-21T20:25:42.4349659Z [ 88%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_where.cpp.o
2025-03-21T20:25:42.4350644Z [ 89%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_zeros.cpp.o
2025-03-21T20:25:42.4351577Z [ 90%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_zeros.cpp.o
2025-03-21T20:25:42.4352558Z [ 90%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/pattern/unary_ufunc_realh.cpp.o
2025-03-21T20:25:42.4353649Z [ 90%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/pattern/unary_ufunc_realh.cpp.o
2025-03-21T20:25:42.4354846Z [ 90%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/pattern/unary_ufunc_realhb_to_bool.cpp.o
2025-03-21T20:25:42.4356038Z [ 90%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/pattern/unary_ufunc_realhb_to_bool.cpp.o
2025-03-21T20:25:42.4357230Z [ 90%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/pattern/unary_ufunc_realhbbf16_to_floathbf16.cpp.o
2025-03-21T20:25:42.4358528Z [ 90%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/pattern/unary_ufunc_realhbbf16_to_floathbf16.cpp.o
2025-03-21T20:25:42.4359750Z [ 91%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/activation_ops_util.cpp.o
2025-03-21T20:25:42.4361198Z [ 91%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/advanced_index_util.cpp.o
2025-03-21T20:25:42.4362279Z [ 91%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/activation_ops_util.cpp.o
2025-03-21T20:25:42.4363326Z [ 91%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/broadcast_util.cpp.o
2025-03-21T20:25:42.4364386Z [ 92%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/advanced_index_util.cpp.o
2025-03-21T20:25:42.4365439Z [ 92%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/copy_ops_util.cpp.o
2025-03-21T20:25:42.4366497Z [ 92%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/broadcast_util.cpp.o
2025-03-21T20:25:42.4367558Z [ 92%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/delinearize_index.cpp.o
2025-03-21T20:25:42.4368654Z [ 93%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/distance_util.cpp.o
2025-03-21T20:25:42.4369806Z [ 93%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/dtype_util.cpp.o
2025-03-21T20:25:42.4370818Z [ 93%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/copy_ops_util.cpp.o
2025-03-21T20:25:42.4371837Z [ 93%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/index_util.cpp.o
2025-03-21T20:25:42.4372892Z [ 93%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/kernel_ops_util.cpp.o
2025-03-21T20:25:42.4373978Z [ 94%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/matmul_ops_util.cpp.o
2025-03-21T20:25:42.4375116Z [ 94%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/normalization_ops_util.cpp.o
2025-03-21T20:25:42.4376207Z [ 94%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/delinearize_index.cpp.o
2025-03-21T20:25:42.4377254Z [ 94%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/padding_util.cpp.o
2025-03-21T20:25:42.4378318Z [ 94%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/reduce_util.cpp.o
2025-03-21T20:25:42.4379366Z [ 94%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/repeat_util.cpp.o
2025-03-21T20:25:42.4380366Z [ 95%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/distance_util.cpp.o
2025-03-21T20:25:42.4381332Z [ 95%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/dtype_util.cpp.o
2025-03-21T20:25:42.4382292Z [ 95%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/index_util.cpp.o
2025-03-21T20:25:42.4383331Z [ 96%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/select_copy_util.cpp.o
2025-03-21T20:25:42.4384370Z [ 96%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/kernel_ops_util.cpp.o
2025-03-21T20:25:42.4385364Z [ 96%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/matmul_ops_util.cpp.o
2025-03-21T20:25:42.4386388Z [ 96%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/slice_util.cpp.o
2025-03-21T20:25:42.4387435Z [ 96%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/upsample_util.cpp.o
2025-03-21T20:25:42.4388512Z [ 97%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/normalization_ops_util.cpp.o
2025-03-21T20:25:42.4389664Z [ 97%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/padding_util.cpp.o
2025-03-21T20:25:42.4390638Z [ 97%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/reduce_util.cpp.o
2025-03-21T20:25:42.4391599Z [ 97%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/repeat_util.cpp.o
2025-03-21T20:25:42.4392590Z [ 97%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/select_copy_util.cpp.o
2025-03-21T20:25:42.4393568Z [ 98%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/slice_util.cpp.o
2025-03-21T20:25:42.4394344Z [ 98%] Linking CXX static library liboptimized_portable_kernels.a
2025-03-21T20:25:42.4395165Z [ 98%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/upsample_util.cpp.o
2025-03-21T20:25:42.4395925Z [ 98%] Linking CXX static library libportable_kernels.a
2025-03-21T20:25:42.4396373Z [ 98%] Built target optimized_portable_kernels
2025-03-21T20:25:42.4396732Z [ 98%] Built target portable_kernels
2025-03-21T20:25:42.4397239Z [ 99%] Generating selected_operators.yaml for portable_ops_lib
2025-03-21T20:25:42.4397780Z [ 99%] Generating code for kernel registration
2025-03-21T20:25:42.4398737Z [ 99%] Building CXX object kernels/portable/CMakeFiles/portable_ops_lib.dir/portable_ops_lib/RegisterCodegenUnboxedKernelsEverything.cpp.o
2025-03-21T20:25:42.4399663Z [ 99%] Linking CXX static library libportable_ops_lib.a
2025-03-21T20:25:42.4400084Z [ 99%] Built target portable_ops_lib
2025-03-21T20:25:42.4400766Z [ 99%] Building CXX object CMakeFiles/executor_runner.dir/extension/data_loader/file_data_loader.cpp.o
2025-03-21T20:25:42.4401774Z [ 99%] Building CXX object CMakeFiles/executor_runner.dir/examples/portable/executor_runner/executor_runner.cpp.o
2025-03-21T20:25:42.4402756Z [ 99%] Building CXX object CMakeFiles/executor_runner.dir/extension/evalue_util/print_evalue.cpp.o
2025-03-21T20:25:42.4403648Z [100%] Building CXX object CMakeFiles/executor_runner.dir/extension/runner_util/inputs.cpp.o
2025-03-21T20:25:42.4404610Z [100%] Building CXX object CMakeFiles/executor_runner.dir/runtime/executor/test/test_backend_compiler_lib.cpp.o
2025-03-21T20:25:42.4405594Z [100%] Building CXX object CMakeFiles/executor_runner.dir/extension/runner_util/inputs_portable.cpp.o
2025-03-21T20:25:42.4406289Z [100%] Linking CXX executable executor_runner
2025-03-21T20:25:42.4406671Z [100%] Built target executor_runner
2025-03-21T20:25:42.4406962Z + [[ '' == *main* ]]
2025-03-21T20:25:42.4407209Z + [[ '' == *gh* ]]
2025-03-21T20:25:42.4407480Z + PYTHON_EXECUTABLE=python
2025-03-21T20:25:42.4407822Z + bash examples/models/llama/install_requirements.sh
2025-03-21T20:25:42.4408191Z Collecting tiktoken
2025-03-21T20:25:42.4408695Z   Downloading tiktoken-0.9.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (6.7 kB)
2025-03-21T20:25:42.4409358Z Collecting sentencepiece
2025-03-21T20:25:42.4409920Z   Downloading sentencepiece-0.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (7.7 kB)
2025-03-21T20:25:42.4410790Z Requirement already satisfied: tokenizers in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (0.21.1)
2025-03-21T20:25:42.4411373Z Collecting snakeviz
2025-03-21T20:25:44.9621186Z   Downloading snakeviz-2.2.2-py3-none-any.whl.metadata (3.6 kB)
2025-03-21T20:25:44.9621925Z Collecting lm_eval==0.4.5
2025-03-21T20:25:44.9622344Z   Downloading lm_eval-0.4.5-py3-none-any.whl.metadata (44 kB)
2025-03-21T20:25:44.9622765Z Collecting blobfile
2025-03-21T20:25:44.9623120Z   Downloading blobfile-3.0.0-py3-none-any.whl.metadata (15 kB)
2025-03-21T20:25:44.9623593Z Collecting accelerate>=0.26.0 (from lm_eval==0.4.5)
2025-03-21T20:25:44.9624071Z   Downloading accelerate-1.5.2-py3-none-any.whl.metadata (19 kB)
2025-03-21T20:25:44.9624981Z Collecting evaluate (from lm_eval==0.4.5)
2025-03-21T20:25:44.9625428Z   Downloading evaluate-0.4.3-py3-none-any.whl.metadata (9.2 kB)
2025-03-21T20:25:44.9625880Z Collecting datasets>=2.16.0 (from lm_eval==0.4.5)
2025-03-21T20:25:44.9626344Z   Downloading datasets-3.4.1-py3-none-any.whl.metadata (19 kB)
2025-03-21T20:25:44.9626792Z Collecting jsonlines (from lm_eval==0.4.5)
2025-03-21T20:25:44.9627246Z   Downloading jsonlines-4.0.0-py3-none-any.whl.metadata (1.6 kB)
2025-03-21T20:25:44.9627698Z Collecting numexpr (from lm_eval==0.4.5)
2025-03-21T20:25:44.9628268Z   Downloading numexpr-2.10.2-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl.metadata (8.1 kB)
2025-03-21T20:25:44.9628872Z Collecting peft>=0.2.0 (from lm_eval==0.4.5)
2025-03-21T20:25:44.9629302Z   Downloading peft-0.15.0-py3-none-any.whl.metadata (13 kB)
2025-03-21T20:25:44.9629744Z Collecting pybind11>=2.6.2 (from lm_eval==0.4.5)
2025-03-21T20:25:44.9630202Z   Downloading pybind11-2.13.6-py3-none-any.whl.metadata (9.5 kB)
2025-03-21T20:25:44.9630676Z Collecting pytablewriter (from lm_eval==0.4.5)
2025-03-21T20:25:44.9631146Z   Downloading pytablewriter-1.2.1-py3-none-any.whl.metadata (38 kB)
2025-03-21T20:25:44.9631639Z Collecting rouge-score>=0.0.4 (from lm_eval==0.4.5)
2025-03-21T20:25:44.9632036Z   Downloading rouge_score-0.1.2.tar.gz (17 kB)
2025-03-21T20:25:44.9632850Z   Preparing metadata (setup.py) ... [?25l- done
2025-03-21T20:25:44.9633332Z [?25hCollecting sacrebleu>=1.5.0 (from lm_eval==0.4.5)
2025-03-21T20:25:44.9633799Z   Downloading sacrebleu-2.5.1-py3-none-any.whl.metadata (51 kB)
2025-03-21T20:25:44.9634282Z Collecting scikit-learn>=0.24.1 (from lm_eval==0.4.5)
2025-03-21T20:25:44.9634916Z   Downloading scikit_learn-1.6.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (18 kB)
2025-03-21T20:25:44.9635524Z Collecting sqlitedict (from lm_eval==0.4.5)
2025-03-21T20:25:44.9635896Z   Downloading sqlitedict-2.1.0.tar.gz (21 kB)
2025-03-21T20:25:44.9636323Z   Preparing metadata (setup.py) ... [?25l- done
2025-03-21T20:25:44.9637222Z [?25hRequirement already satisfied: torch>=1.8 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from lm_eval==0.4.5) (2.7.0a0+git295f2ed)
2025-03-21T20:25:44.9637984Z Collecting tqdm-multiprocess (from lm_eval==0.4.5)
2025-03-21T20:25:44.9638499Z   Downloading tqdm_multiprocess-0.0.11-py3-none-any.whl.metadata (5.7 kB)
2025-03-21T20:25:44.9639332Z Requirement already satisfied: transformers>=4.1 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from lm_eval==0.4.5) (4.47.1)
2025-03-21T20:25:44.9640044Z Collecting zstandard (from lm_eval==0.4.5)
2025-03-21T20:25:44.9640637Z   Downloading zstandard-0.23.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (3.0 kB)
2025-03-21T20:25:44.9641217Z Collecting dill (from lm_eval==0.4.5)
2025-03-21T20:25:44.9641625Z   Downloading dill-0.3.9-py3-none-any.whl.metadata (10 kB)
2025-03-21T20:25:44.9642052Z Collecting word2number (from lm_eval==0.4.5)
2025-03-21T20:25:44.9642423Z   Downloading word2number-1.1.zip (9.7 kB)
2025-03-21T20:25:44.9642861Z   Preparing metadata (setup.py) ... [?25l- done
2025-03-21T20:25:44.9643317Z [?25hCollecting more-itertools (from lm_eval==0.4.5)
2025-03-21T20:25:44.9643809Z   Downloading more_itertools-10.6.0-py3-none-any.whl.metadata (37 kB)
2025-03-21T20:25:44.9644596Z Requirement already satisfied: regex>=2022.1.18 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from tiktoken) (2024.11.6)
2025-03-21T20:25:44.9645582Z Requirement already satisfied: requests>=2.26.0 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from tiktoken) (2.32.3)
2025-03-21T20:25:44.9646597Z Requirement already satisfied: huggingface-hub<1.0,>=0.16.4 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from tokenizers) (0.29.3)
2025-03-21T20:25:44.9647308Z Collecting tornado>=2.0 (from snakeviz)
2025-03-21T20:25:44.9647992Z   Downloading tornado-6.4.2-cp38-abi3-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (2.5 kB)
2025-03-21T20:25:44.9648947Z Collecting pycryptodomex>=3.8 (from blobfile)
2025-03-21T20:25:44.9649660Z   Downloading pycryptodomex-3.22.0-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (3.4 kB)
2025-03-21T20:25:44.9650584Z Requirement already satisfied: urllib3<3,>=1.25.3 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from blobfile) (2.3.0)
2025-03-21T20:25:44.9651525Z Requirement already satisfied: lxml>=4.9 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from blobfile) (5.3.1)
2025-03-21T20:25:44.9652469Z Requirement already satisfied: filelock>=3.0 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from blobfile) (3.18.0)
2025-03-21T20:25:44.9653522Z Requirement already satisfied: numpy<3.0.0,>=1.17 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from accelerate>=0.26.0->lm_eval==0.4.5) (2.2.4)
2025-03-21T20:25:44.9654654Z Requirement already satisfied: packaging>=20.0 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from accelerate>=0.26.0->lm_eval==0.4.5) (24.2)
2025-03-21T20:25:44.9655476Z Collecting psutil (from accelerate>=0.26.0->lm_eval==0.4.5)
2025-03-21T20:25:44.9656248Z   Downloading psutil-7.0.0-cp36-abi3-manylinux_2_12_x86_64.manylinux2010_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (22 kB)
2025-03-21T20:25:44.9657409Z Requirement already satisfied: pyyaml in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from accelerate>=0.26.0->lm_eval==0.4.5) (6.0.1)
2025-03-21T20:25:44.9658553Z Requirement already satisfied: safetensors>=0.4.3 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from accelerate>=0.26.0->lm_eval==0.4.5) (0.5.3)
2025-03-21T20:25:44.9659400Z Collecting pyarrow>=15.0.0 (from datasets>=2.16.0->lm_eval==0.4.5)
2025-03-21T20:25:44.9659988Z   Downloading pyarrow-19.0.1-cp310-cp310-manylinux_2_28_x86_64.whl.metadata (3.3 kB)
2025-03-21T20:25:44.9660483Z Collecting dill (from lm_eval==0.4.5)
2025-03-21T20:25:44.9660886Z   Downloading dill-0.3.8-py3-none-any.whl.metadata (10 kB)
2025-03-21T20:25:44.9661682Z Requirement already satisfied: pandas in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from datasets>=2.16.0->lm_eval==0.4.5) (2.2.3)
2025-03-21T20:25:44.9662786Z Requirement already satisfied: tqdm>=4.66.3 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from datasets>=2.16.0->lm_eval==0.4.5) (4.67.1)
2025-03-21T20:25:44.9663568Z Collecting xxhash (from datasets>=2.16.0->lm_eval==0.4.5)
2025-03-21T20:25:44.9664191Z   Downloading xxhash-3.5.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (12 kB)
2025-03-21T20:25:44.9664859Z Collecting multiprocess<0.70.17 (from datasets>=2.16.0->lm_eval==0.4.5)
2025-03-21T20:25:44.9665446Z   Downloading multiprocess-0.70.16-py310-none-any.whl.metadata (7.2 kB)
2025-03-21T20:25:44.9666139Z Collecting fsspec<=2024.12.0,>=2023.1.0 (from fsspec[http]<=2024.12.0,>=2023.1.0->datasets>=2.16.0->lm_eval==0.4.5)
2025-03-21T20:25:44.9666786Z   Downloading fsspec-2024.12.0-py3-none-any.whl.metadata (11 kB)
2025-03-21T20:25:44.9667295Z Collecting aiohttp (from datasets>=2.16.0->lm_eval==0.4.5)
2025-03-21T20:25:44.9667938Z   Downloading aiohttp-3.11.14-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (7.7 kB)
2025-03-21T20:25:44.9668992Z Requirement already satisfied: typing-extensions>=3.7.4.3 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from huggingface-hub<1.0,>=0.16.4->tokenizers) (4.12.2)
2025-03-21T20:25:44.9670241Z Requirement already satisfied: charset-normalizer<4,>=2 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from requests>=2.26.0->tiktoken) (3.4.1)
2025-03-21T20:25:44.9671347Z Requirement already satisfied: idna<4,>=2.5 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from requests>=2.26.0->tiktoken) (3.10)
2025-03-21T20:25:44.9672442Z Requirement already satisfied: certifi>=2017.4.17 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from requests>=2.26.0->tiktoken) (2025.1.31)
2025-03-21T20:25:44.9673257Z Collecting absl-py (from rouge-score>=0.0.4->lm_eval==0.4.5)
2025-03-21T20:25:44.9673884Z   Downloading absl_py-2.2.0-py3-none-any.whl.metadata (2.4 kB)
2025-03-21T20:25:44.9674367Z Collecting nltk (from rouge-score>=0.0.4->lm_eval==0.4.5)
2025-03-21T20:25:44.9674861Z   Downloading nltk-3.9.1-py3-none-any.whl.metadata (2.9 kB)
2025-03-21T20:25:44.9675662Z Requirement already satisfied: six>=1.14.0 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from rouge-score>=0.0.4->lm_eval==0.4.5) (1.17.0)
2025-03-21T20:25:44.9676457Z Collecting portalocker (from sacrebleu>=1.5.0->lm_eval==0.4.5)
2025-03-21T20:25:44.9676996Z   Downloading portalocker-3.1.1-py3-none-any.whl.metadata (8.6 kB)
2025-03-21T20:25:44.9677965Z Requirement already satisfied: tabulate>=0.8.9 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from sacrebleu>=1.5.0->lm_eval==0.4.5) (0.9.0)
2025-03-21T20:25:44.9678780Z Collecting colorama (from sacrebleu>=1.5.0->lm_eval==0.4.5)
2025-03-21T20:25:44.9679297Z   Downloading colorama-0.4.6-py2.py3-none-any.whl.metadata (17 kB)
2025-03-21T20:25:44.9679847Z Collecting scipy>=1.6.0 (from scikit-learn>=0.24.1->lm_eval==0.4.5)
2025-03-21T20:25:44.9680484Z   Downloading scipy-1.15.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (61 kB)
2025-03-21T20:25:44.9681141Z Collecting joblib>=1.2.0 (from scikit-learn>=0.24.1->lm_eval==0.4.5)
2025-03-21T20:25:44.9681663Z   Downloading joblib-1.4.2-py3-none-any.whl.metadata (5.4 kB)
2025-03-21T20:25:44.9682216Z Collecting threadpoolctl>=3.1.0 (from scikit-learn>=0.24.1->lm_eval==0.4.5)
2025-03-21T20:25:44.9682805Z   Downloading threadpoolctl-3.6.0-py3-none-any.whl.metadata (13 kB)
2025-03-21T20:25:44.9683631Z Requirement already satisfied: sympy>=1.13.3 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from torch>=1.8->lm_eval==0.4.5) (1.13.3)
2025-03-21T20:25:44.9684697Z Requirement already satisfied: networkx in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from torch>=1.8->lm_eval==0.4.5) (3.4.2)
2025-03-21T20:25:44.9685734Z Requirement already satisfied: jinja2 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from torch>=1.8->lm_eval==0.4.5) (3.1.6)
2025-03-21T20:25:46.3403358Z Requirement already satisfied: attrs>=19.2.0 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from jsonlines->lm_eval==0.4.5) (25.3.0)
2025-03-21T20:25:46.3404720Z Requirement already satisfied: setuptools>=38.3.0 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from pytablewriter->lm_eval==0.4.5) (75.8.0)
2025-03-21T20:25:46.3405620Z Collecting DataProperty<2,>=1.1.0 (from pytablewriter->lm_eval==0.4.5)
2025-03-21T20:25:46.3406194Z   Downloading DataProperty-1.1.0-py3-none-any.whl.metadata (11 kB)
2025-03-21T20:25:46.3406761Z Collecting mbstrdecoder<2,>=1.0.0 (from pytablewriter->lm_eval==0.4.5)
2025-03-21T20:25:46.3407332Z   Downloading mbstrdecoder-1.1.4-py3-none-any.whl.metadata (4.3 kB)
2025-03-21T20:25:46.3407901Z Collecting pathvalidate<4,>=2.3.0 (from pytablewriter->lm_eval==0.4.5)
2025-03-21T20:25:46.3408454Z   Downloading pathvalidate-3.2.3-py3-none-any.whl.metadata (12 kB)
2025-03-21T20:25:46.3409134Z Collecting tabledata<2,>=1.3.1 (from pytablewriter->lm_eval==0.4.5)
2025-03-21T20:25:46.3409733Z   Downloading tabledata-1.3.4-py3-none-any.whl.metadata (3.7 kB)
2025-03-21T20:25:46.3410314Z Collecting tcolorpy<1,>=0.0.5 (from pytablewriter->lm_eval==0.4.5)
2025-03-21T20:25:46.3410956Z   Downloading tcolorpy-0.1.7-py3-none-any.whl.metadata (6.3 kB)
2025-03-21T20:25:46.3411658Z Collecting typepy<2,>=1.3.2 (from typepy[datetime]<2,>=1.3.2->pytablewriter->lm_eval==0.4.5)
2025-03-21T20:25:46.3412617Z   Downloading typepy-1.3.4-py3-none-any.whl.metadata (9.2 kB)
2025-03-21T20:25:46.3413370Z Collecting aiohappyeyeballs>=2.3.0 (from aiohttp->datasets>=2.16.0->lm_eval==0.4.5)
2025-03-21T20:25:46.3414057Z   Downloading aiohappyeyeballs-2.6.1-py3-none-any.whl.metadata (5.9 kB)
2025-03-21T20:25:46.3414673Z Collecting aiosignal>=1.1.2 (from aiohttp->datasets>=2.16.0->lm_eval==0.4.5)
2025-03-21T20:25:46.3415245Z   Downloading aiosignal-1.3.2-py2.py3-none-any.whl.metadata (3.8 kB)
2025-03-21T20:25:46.3416174Z Collecting async-timeout<6.0,>=4.0 (from aiohttp->datasets>=2.16.0->lm_eval==0.4.5)
2025-03-21T20:25:46.3416770Z   Downloading async_timeout-5.0.1-py3-none-any.whl.metadata (5.1 kB)
2025-03-21T20:25:46.3417329Z Collecting frozenlist>=1.1.1 (from aiohttp->datasets>=2.16.0->lm_eval==0.4.5)
2025-03-21T20:25:46.3418209Z   Downloading frozenlist-1.5.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (13 kB)
2025-03-21T20:25:46.3419217Z Collecting multidict<7.0,>=4.5 (from aiohttp->datasets>=2.16.0->lm_eval==0.4.5)
2025-03-21T20:25:46.3420052Z   Downloading multidict-6.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (4.9 kB)
2025-03-21T20:25:46.3420978Z Collecting propcache>=0.2.0 (from aiohttp->datasets>=2.16.0->lm_eval==0.4.5)
2025-03-21T20:25:46.3421682Z   Downloading propcache-0.3.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (10 kB)
2025-03-21T20:25:46.3422696Z Collecting yarl<2.0,>=1.17.0 (from aiohttp->datasets>=2.16.0->lm_eval==0.4.5)
2025-03-21T20:25:46.3423419Z   Downloading yarl-1.18.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (69 kB)
2025-03-21T20:25:46.3424272Z Collecting chardet<6,>=3.0.4 (from mbstrdecoder<2,>=1.0.0->pytablewriter->lm_eval==0.4.5)
2025-03-21T20:25:46.3424910Z   Downloading chardet-5.2.0-py3-none-any.whl.metadata (3.4 kB)
2025-03-21T20:25:46.3425765Z Requirement already satisfied: mpmath<1.4,>=1.1.0 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from sympy>=1.13.3->torch>=1.8->lm_eval==0.4.5) (1.3.0)
2025-03-21T20:25:46.3427168Z Requirement already satisfied: python-dateutil<3.0.0,>=2.8.0 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from typepy[datetime]<2,>=1.3.2->pytablewriter->lm_eval==0.4.5) (2.9.0.post0)
2025-03-21T20:25:46.3428840Z Requirement already satisfied: pytz>=2018.9 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from typepy[datetime]<2,>=1.3.2->pytablewriter->lm_eval==0.4.5) (2025.1)
2025-03-21T20:25:46.3430314Z Requirement already satisfied: MarkupSafe>=2.0 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from jinja2->torch>=1.8->lm_eval==0.4.5) (3.0.2)
2025-03-21T20:25:46.3431228Z Collecting click (from nltk->rouge-score>=0.0.4->lm_eval==0.4.5)
2025-03-21T20:25:46.3431732Z   Downloading click-8.1.8-py3-none-any.whl.metadata (2.3 kB)
2025-03-21T20:25:46.3432995Z Requirement already satisfied: tzdata>=2022.7 in /opt/conda/envs/py_3.10/lib/python3.10/site-packages (from pandas->datasets>=2.16.0->lm_eval==0.4.5) (2025.1)
2025-03-21T20:25:46.3433868Z Downloading lm_eval-0.4.5-py3-none-any.whl (2.4 MB)
2025-03-21T20:25:46.3434711Z [?25l   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 0.0/2.4 MB ? eta -:--:--
2025-03-21T20:25:46.3435476Z    ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 2.4/2.4 MB 140.7 MB/s eta 0:00:00
2025-03-21T20:25:46.3436273Z [?25hDownloading tiktoken-0.9.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.2 MB)
2025-03-21T20:25:46.3437238Z [?25l   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 0.0/1.2 MB ? eta -:--:--
2025-03-21T20:25:46.3437914Z    ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.2/1.2 MB 70.2 MB/s eta 0:00:00
2025-03-21T20:25:46.3438725Z [?25hDownloading sentencepiece-0.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)
2025-03-21T20:25:46.3439656Z [?25l   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 0.0/1.3 MB ? eta -:--:--
2025-03-21T20:25:46.3440465Z    ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.3/1.3 MB 88.8 MB/s eta 0:00:00
2025-03-21T20:25:46.3441053Z [?25hDownloading snakeviz-2.2.2-py3-none-any.whl (183 kB)
2025-03-21T20:25:46.3441560Z Downloading blobfile-3.0.0-py3-none-any.whl (75 kB)
2025-03-21T20:25:46.3441999Z Downloading accelerate-1.5.2-py3-none-any.whl (345 kB)
2025-03-21T20:25:46.3442439Z Downloading datasets-3.4.1-py3-none-any.whl (487 kB)
2025-03-21T20:25:46.3443120Z Downloading dill-0.3.8-py3-none-any.whl (116 kB)
2025-03-21T20:25:46.3443537Z Downloading evaluate-0.4.3-py3-none-any.whl (84 kB)
2025-03-21T20:25:46.3443937Z Downloading peft-0.15.0-py3-none-any.whl (410 kB)
2025-03-21T20:25:46.3444381Z Downloading pybind11-2.13.6-py3-none-any.whl (243 kB)
2025-03-21T20:25:46.3445083Z Downloading pycryptodomex-3.22.0-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.3 MB)
2025-03-21T20:25:46.3445973Z [?25l   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 0.0/2.3 MB ? eta -:--:--
2025-03-21T20:25:46.3447122Z    ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 2.3/2.3 MB 154.5 MB/s eta 0:00:00
2025-03-21T20:25:46.3447852Z [?25hDownloading sacrebleu-2.5.1-py3-none-any.whl (104 kB)
2025-03-21T20:25:46.3448532Z Downloading scikit_learn-1.6.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (13.5 MB)
2025-03-21T20:25:46.3449956Z [?25l   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 0.0/13.5 MB ? eta -:--:--
2025-03-21T20:25:46.3450680Z    ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 13.5/13.5 MB 180.9 MB/s eta 0:00:00
2025-03-21T20:25:46.3451968Z [?25hDownloading tornado-6.4.2-cp38-abi3-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (437 kB)
2025-03-21T20:25:46.3452941Z Downloading jsonlines-4.0.0-py3-none-any.whl (8.7 kB)
2025-03-21T20:25:46.3453409Z Downloading more_itertools-10.6.0-py3-none-any.whl (63 kB)
2025-03-21T20:25:46.3454247Z Downloading numexpr-2.10.2-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (397 kB)
2025-03-21T20:25:46.3454971Z Downloading pytablewriter-1.2.1-py3-none-any.whl (91 kB)
2025-03-21T20:25:46.3455676Z Downloading tqdm_multiprocess-0.0.11-py3-none-any.whl (9.8 kB)
2025-03-21T20:25:46.3456390Z Downloading zstandard-0.23.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (5.4 MB)
2025-03-21T20:25:46.3457253Z [?25l   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 0.0/5.4 MB ? eta -:--:--
2025-03-21T20:25:46.3457937Z    ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 5.4/5.4 MB 85.4 MB/s eta 0:00:00
2025-03-21T20:25:46.3458532Z [?25hDownloading DataProperty-1.1.0-py3-none-any.whl (27 kB)
2025-03-21T20:25:46.3458994Z Downloading fsspec-2024.12.0-py3-none-any.whl (183 kB)
2025-03-21T20:25:46.3459591Z Downloading aiohttp-3.11.14-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.6 MB)
2025-03-21T20:25:46.3460482Z [?25l   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 0.0/1.6 MB ? eta -:--:--
2025-03-21T20:25:46.3461327Z    ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.6/1.6 MB 94.2 MB/s eta 0:00:00
2025-03-21T20:25:46.3462095Z [?25hDownloading joblib-1.4.2-py3-none-any.whl (301 kB)
2025-03-21T20:25:46.3462706Z Downloading mbstrdecoder-1.1.4-py3-none-any.whl (7.9 kB)
2025-03-21T20:25:46.3463389Z Downloading multiprocess-0.70.16-py310-none-any.whl (134 kB)
2025-03-21T20:25:46.3464028Z Downloading pathvalidate-3.2.3-py3-none-any.whl (24 kB)
2025-03-21T20:26:00.5146624Z Downloading pyarrow-19.0.1-cp310-cp310-manylinux_2_28_x86_64.whl (42.1 MB)
2025-03-21T20:26:00.5147670Z [?25l   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 0.0/42.1 MB ? eta -:--:--
2025-03-21T20:26:00.5149707Z    ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 42.1/42.1 MB 222.4 MB/s eta 0:00:00
2025-03-21T20:26:00.5150491Z [?25hDownloading scipy-1.15.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (37.6 MB)
2025-03-21T20:26:00.5151272Z [?25l   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 0.0/37.6 MB ? eta -:--:--
2025-03-21T20:26:00.5152239Z    ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 37.6/37.6 MB 196.5 MB/s eta 0:00:00
2025-03-21T20:26:00.5153310Z [?25hDownloading tabledata-1.3.4-py3-none-any.whl (11 kB)
2025-03-21T20:26:00.5154125Z Downloading tcolorpy-0.1.7-py3-none-any.whl (8.1 kB)
2025-03-21T20:26:00.5154912Z Downloading threadpoolctl-3.6.0-py3-none-any.whl (18 kB)
2025-03-21T20:26:00.5155670Z Downloading typepy-1.3.4-py3-none-any.whl (31 kB)
2025-03-21T20:26:00.5156414Z Downloading absl_py-2.2.0-py3-none-any.whl (276 kB)
2025-03-21T20:26:00.5157199Z Downloading colorama-0.4.6-py2.py3-none-any.whl (25 kB)
2025-03-21T20:26:00.5157948Z Downloading nltk-3.9.1-py3-none-any.whl (1.5 MB)
2025-03-21T20:26:00.5159040Z [?25l   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 0.0/1.5 MB ? eta -:--:--
2025-03-21T20:26:00.5160180Z    ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.5/1.5 MB 160.6 MB/s eta 0:00:00
2025-03-21T20:26:00.5160897Z [?25hDownloading portalocker-3.1.1-py3-none-any.whl (19 kB)
2025-03-21T20:26:00.5161674Z Downloading psutil-7.0.0-cp36-abi3-manylinux_2_12_x86_64.manylinux2010_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (277 kB)
2025-03-21T20:26:00.5162561Z Downloading xxhash-3.5.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (194 kB)
2025-03-21T20:26:00.5163179Z Downloading aiohappyeyeballs-2.6.1-py3-none-any.whl (15 kB)
2025-03-21T20:26:00.5163678Z Downloading aiosignal-1.3.2-py2.py3-none-any.whl (7.6 kB)
2025-03-21T20:26:00.5164151Z Downloading async_timeout-5.0.1-py3-none-any.whl (6.2 kB)
2025-03-21T20:26:00.5164600Z Downloading chardet-5.2.0-py3-none-any.whl (199 kB)
2025-03-21T20:26:00.5165330Z Downloading frozenlist-1.5.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (241 kB)
2025-03-21T20:26:00.5166229Z Downloading multidict-6.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (129 kB)
2025-03-21T20:26:00.5166972Z Downloading propcache-0.3.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (205 kB)
2025-03-21T20:26:00.5167703Z Downloading yarl-1.18.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (319 kB)
2025-03-21T20:26:00.5168267Z Downloading click-8.1.8-py3-none-any.whl (98 kB)
2025-03-21T20:26:00.5168777Z Building wheels for collected packages: rouge-score, sqlitedict, word2number
2025-03-21T20:26:00.5169456Z   Building wheel for rouge-score (setup.py) ... [?25l- done
2025-03-21T20:26:00.5170477Z [?25h  Created wheel for rouge-score: filename=rouge_score-0.1.2-py3-none-any.whl size=24986 sha256=e479021234b2f98482c630e7ed7c13df33be16689d0dad9667cf623e34d7009e
2025-03-21T20:26:00.5171560Z   Stored in directory: /var/lib/ci-user/.cache/pip/wheels/5f/dd/89/461065a73be61a532ff8599a28e9beef17985c9e9c31e541b4
2025-03-21T20:26:00.5172343Z   Building wheel for sqlitedict (setup.py) ... [?25l- done
2025-03-21T20:26:00.5173351Z [?25h  Created wheel for sqlitedict: filename=sqlitedict-2.1.0-py3-none-any.whl size=16928 sha256=b6826726653b5b4e4b3acc74015f8c31ffa13b4800eb2303b216f6755abc9b91
2025-03-21T20:26:00.5174628Z   Stored in directory: /var/lib/ci-user/.cache/pip/wheels/79/d6/e7/304e0e6cb2221022c26d8161f7c23cd4f259a9e41e8bbcfabd
2025-03-21T20:26:00.5175512Z   Building wheel for word2number (setup.py) ... [?25l- done
2025-03-21T20:26:00.5176524Z [?25h  Created wheel for word2number: filename=word2number-1.1-py3-none-any.whl size=5625 sha256=4484577d2414686e3ccc2f09cc3f0d14c1070a7b375008a46d8312925c541b1e
2025-03-21T20:26:00.5177620Z   Stored in directory: /var/lib/ci-user/.cache/pip/wheels/84/ff/26/d3cfbd971e96c5aa3737ecfced81628830d7359b55fbb8ca3b
2025-03-21T20:26:00.5178318Z Successfully built rouge-score sqlitedict word2number
2025-03-21T20:26:00.5180951Z Installing collected packages: word2number, sqlitedict, sentencepiece, zstandard, xxhash, tornado, threadpoolctl, tcolorpy, scipy, pycryptodomex, pybind11, pyarrow, psutil, propcache, portalocker, pathvalidate, numexpr, multidict, more-itertools, jsonlines, joblib, fsspec, frozenlist, dill, colorama, click, chardet, async-timeout, aiohappyeyeballs, absl-py, yarl, tqdm-multiprocess, tiktoken, snakeviz, scikit-learn, sacrebleu, nltk, multiprocess, mbstrdecoder, blobfile, aiosignal, typepy, rouge-score, aiohttp, accelerate, peft, datasets, DataProperty, tabledata, evaluate, pytablewriter, lm_eval
2025-03-21T20:26:00.5183490Z   Attempting uninstall: fsspec
2025-03-21T20:26:00.5183831Z     Found existing installation: fsspec 2025.3.0
2025-03-21T20:26:00.5184193Z     Uninstalling fsspec-2025.3.0:
2025-03-21T20:26:00.5184519Z       Successfully uninstalled fsspec-2025.3.0
2025-03-21T20:26:00.5187749Z Successfully installed DataProperty-1.1.0 absl-py-2.2.0 accelerate-1.5.2 aiohappyeyeballs-2.6.1 aiohttp-3.11.14 aiosignal-1.3.2 async-timeout-5.0.1 blobfile-3.0.0 chardet-5.2.0 click-8.1.8 colorama-0.4.6 datasets-3.4.1 dill-0.3.8 evaluate-0.4.3 frozenlist-1.5.0 fsspec-2024.12.0 joblib-1.4.2 jsonlines-4.0.0 lm_eval-0.4.5 mbstrdecoder-1.1.4 more-itertools-10.6.0 multidict-6.2.0 multiprocess-0.70.16 nltk-3.9.1 numexpr-2.10.2 pathvalidate-3.2.3 peft-0.15.0 portalocker-3.1.1 propcache-0.3.0 psutil-7.0.0 pyarrow-19.0.1 pybind11-2.13.6 pycryptodomex-3.22.0 pytablewriter-1.2.1 rouge-score-0.1.2 sacrebleu-2.5.1 scikit-learn-1.6.1 scipy-1.15.2 sentencepiece-0.2.0 snakeviz-2.2.2 sqlitedict-2.1.0 tabledata-1.3.4 tcolorpy-0.1.7 threadpoolctl-3.6.0 tiktoken-0.9.0 tornado-6.4.2 tqdm-multiprocess-0.0.11 typepy-1.3.4 word2number-1.1 xxhash-3.5.0 yarl-1.18.3 zstandard-0.23.0
2025-03-21T20:26:00.5191124Z Failed to import examples.models due to lm_eval conflict. Removing lm_eval examples module
2025-03-21T20:26:00.5191628Z + PYTHON_EXECUTABLE=python
2025-03-21T20:26:00.5192204Z + bash .ci/scripts/test_llama.sh -model stories110M -build_tool cmake -mode qnn -dtype fp32 -pt2e_quantize qnn_16a16w
2025-03-21T20:26:00.5192821Z ++ dirname .ci/scripts/test_llama.sh
2025-03-21T20:26:00.5193144Z + source .ci/scripts/utils.sh
2025-03-21T20:26:00.5193424Z + [[ 10 -gt 0 ]]
2025-03-21T20:26:00.5193649Z + case "$1" in
2025-03-21T20:26:00.5193893Z + MODEL_NAME=stories110M
2025-03-21T20:26:00.5194157Z + shift 2
2025-03-21T20:26:00.5194376Z + [[ 8 -gt 0 ]]
2025-03-21T20:26:00.5194612Z + case "$1" in
2025-03-21T20:26:00.5194837Z + BUILD_TOOL=cmake
2025-03-21T20:26:00.5195072Z + shift 2
2025-03-21T20:26:00.5195286Z + [[ 6 -gt 0 ]]
2025-03-21T20:26:00.5195517Z + case "$1" in
2025-03-21T20:26:00.5195730Z + MODE=qnn
2025-03-21T20:26:00.5195950Z + shift 2
2025-03-21T20:26:00.5196165Z + [[ 4 -gt 0 ]]
2025-03-21T20:26:00.5196394Z + case "$1" in
2025-03-21T20:26:00.5196624Z + DTYPE=fp32
2025-03-21T20:26:00.5196834Z + shift 2
2025-03-21T20:26:00.5197048Z + [[ 2 -gt 0 ]]
2025-03-21T20:26:00.5197278Z + case "$1" in
2025-03-21T20:26:00.5197520Z + PT2E_QUANTIZE=qnn_16a16w
2025-03-21T20:26:00.5197789Z + shift 2
2025-03-21T20:26:00.5197992Z + [[ 0 -gt 0 ]]
2025-03-21T20:26:00.5198226Z + MODE=qnn
2025-03-21T20:26:00.5198450Z + UPLOAD_DIR=
2025-03-21T20:26:00.5198712Z + PT2E_QUANTIZE=qnn_16a16w
2025-03-21T20:26:00.5198983Z + CMAKE_BUILD_TYPE=Release
2025-03-21T20:26:00.5199253Z + [[ 0 -lt 4 ]]
2025-03-21T20:26:00.5199537Z + echo 'Expecting atleast 4 positional arguments'
2025-03-21T20:26:00.5200055Z Expecting atleast 4 positional arguments
2025-03-21T20:26:00.5200391Z + echo 'Usage: [...]'
2025-03-21T20:26:00.5200635Z Usage: [...]
2025-03-21T20:26:00.5200874Z + [[ -z stories110M ]]
2025-03-21T20:26:00.5201139Z + [[ -z cmake ]]
2025-03-21T20:26:00.5201376Z + [[ -z fp32 ]]
2025-03-21T20:26:00.5201600Z + [[ -z qnn ]]
2025-03-21T20:26:00.5201846Z + [[ qnn =~ .*xnnpack.* ]]
2025-03-21T20:26:00.5202117Z + XNNPACK=OFF
2025-03-21T20:26:00.5202357Z + [[ qnn =~ .*custom.* ]]
2025-03-21T20:26:00.5202621Z + CUSTOM=OFF
2025-03-21T20:26:00.5202841Z + [[ qnn =~ .*qe.* ]]
2025-03-21T20:26:00.5203087Z + QE=OFF
2025-03-21T20:26:00.5203312Z + [[ qnn =~ .*mps.* ]]
2025-03-21T20:26:00.5203558Z + MPS=OFF
2025-03-21T20:26:00.5203788Z + echo 'MPS option OFF'
2025-03-21T20:26:00.5204035Z MPS option OFF
2025-03-21T20:26:00.5204273Z + [[ qnn =~ .*coreml.* ]]
2025-03-21T20:26:00.5204532Z + COREML=OFF
2025-03-21T20:26:00.5204768Z + [[ qnn =~ .*quantize_kv.* ]]
2025-03-21T20:26:00.5205038Z + QUANTIZE_KV_CACHE=OFF
2025-03-21T20:26:00.5205314Z + echo 'COREML option OFF'
2025-03-21T20:26:00.5205584Z COREML option OFF
2025-03-21T20:26:00.5205823Z + [[ qnn =~ .*qnn.* ]]
2025-03-21T20:26:00.5206069Z + QNN=ON
2025-03-21T20:26:00.5206297Z +++ dirname -- .ci/scripts/test_llama.sh
2025-03-21T20:26:00.5206621Z ++ cd -- .ci/scripts/..
2025-03-21T20:26:00.5206874Z ++ pwd
2025-03-21T20:26:00.5207139Z + export EXECUTORCH_ROOT=/pytorch/executorch/.ci
2025-03-21T20:26:00.5207519Z + EXECUTORCH_ROOT=/pytorch/executorch/.ci
2025-03-21T20:26:00.5207862Z + export QNN_SDK_ROOT=/tmp/qnn/2.28.0.241029
2025-03-21T20:26:00.5208205Z + QNN_SDK_ROOT=/tmp/qnn/2.28.0.241029
2025-03-21T20:26:00.5208618Z + export LD_LIBRARY_PATH=/tmp/qnn/2.28.0.241029/lib/x86_64-linux-clang
2025-03-21T20:26:00.5209114Z + LD_LIBRARY_PATH=/tmp/qnn/2.28.0.241029/lib/x86_64-linux-clang
2025-03-21T20:26:00.5209594Z + export PYTHONPATH=..
2025-03-21T20:26:00.5209849Z + PYTHONPATH=..
2025-03-21T20:26:00.5210143Z + cp schema/program.fbs exir/_serialize/program.fbs
2025-03-21T20:26:00.5210584Z + cp schema/scalar_type.fbs exir/_serialize/scalar_type.fbs
2025-03-21T20:26:00.5211303Z + cp -f build-x86/backends/qualcomm/PyQnnManagerAdaptor.cpython-310-x86_64-linux-gnu.so backends/qualcomm/python
2025-03-21T20:26:00.5212261Z + cp -f build-x86/backends/qualcomm/PyQnnWrapperAdaptor.cpython-310-x86_64-linux-gnu.so backends/qualcomm/python
2025-03-21T20:26:00.5212895Z + echo 'QNN option ON'
2025-03-21T20:26:00.5213144Z QNN option ON
2025-03-21T20:26:00.5213408Z + echo 'QNN_SDK_ROOT: /tmp/qnn/2.28.0.241029'
2025-03-21T20:26:00.5213751Z QNN_SDK_ROOT: /tmp/qnn/2.28.0.241029
2025-03-21T20:26:00.5214052Z + [[ -z '' ]]
2025-03-21T20:26:00.5214266Z + BUCK=buck2
2025-03-21T20:26:00.5214497Z + [[ -z python ]]
2025-03-21T20:26:00.5214739Z + which python
2025-03-21T20:26:00.5214993Z /opt/conda/envs/py_3.10/bin/python
2025-03-21T20:26:00.5215300Z + PARAMS=params.json
2025-03-21T20:26:00.5215551Z + CHECKPOINT_FILE_NAME=
2025-03-21T20:26:00.5215817Z + touch params.json
2025-03-21T20:26:00.5216082Z + [[ stories110M == \l\l\a\m\a ]]
2025-03-21T20:26:00.5216389Z + [[ stories110M == \s\t\o\r\i\e\s* ]]
2025-03-21T20:26:00.5216720Z + CHECKPOINT_FILE_NAME=stories110M.pt
2025-03-21T20:26:00.5217040Z + download_stories_model_artifacts
2025-03-21T20:26:00.5217641Z + curl -Ls https://huggingface.co/karpathy/tinyllamas/resolve/main/stories110M.pt --output stories110M.pt
2025-03-21T20:26:00.5218530Z + curl -Ls https://raw.githubusercontent.com/karpathy/llama2.c/master/tokenizer.model --output tokenizer.model
2025-03-21T20:26:14.0047107Z + touch params.json
2025-03-21T20:26:14.0047926Z + echo '{"dim": 768, "multiple_of": 32, "n_heads": 12, "n_layers": 12, "norm_eps": 1e-05, "vocab_size": 32000}'
2025-03-21T20:26:14.0048863Z + EXPORTED_MODEL_NAME=tinyllama_qnn_fp32
2025-03-21T20:26:14.0049352Z + [[ fp32 == \f\p\1\6 ]]
2025-03-21T20:26:14.0049624Z + [[ fp32 == \b\f\1\6 ]]
2025-03-21T20:26:14.0049885Z + [[ fp32 == \f\p\3\2 ]]
2025-03-21T20:26:14.0050143Z + :
2025-03-21T20:26:14.0050381Z + EXPORTED_MODEL_NAME=tinyllama_qnn_fp32.pte
2025-03-21T20:26:14.0051171Z + echo 'Exporting tinyllama_qnn_fp32.pte'
2025-03-21T20:26:14.0051532Z Exporting tinyllama_qnn_fp32.pte
2025-03-21T20:26:14.0052018Z + EXPORT_ARGS='-c stories110M.pt -p params.json -d fp32 -n tinyllama_qnn_fp32.pte -kv'
2025-03-21T20:26:14.0052501Z + [[ OFF == \O\N ]]
2025-03-21T20:26:14.0052733Z + [[ OFF == \O\N ]]
2025-03-21T20:26:14.0052969Z + [[ OFF == \O\N ]]
2025-03-21T20:26:14.0053204Z + [[ OFF == \O\N ]]
2025-03-21T20:26:14.0053444Z + [[ OFF == \O\N ]]
2025-03-21T20:26:14.0053679Z + [[ ON == \O\N ]]
2025-03-21T20:26:14.0054209Z + EXPORT_ARGS='-c stories110M.pt -p params.json -d fp32 -n tinyllama_qnn_fp32.pte -kv -kv -v --qnn --disable_dynamic_shape'
2025-03-21T20:26:14.0054837Z + echo 'PT2E_QUANTIZE is qnn_16a16w'
2025-03-21T20:26:14.0055157Z PT2E_QUANTIZE is qnn_16a16w
2025-03-21T20:26:14.0055452Z + [[ qnn_16a16w == \q\n\n\_\1\6\a\1\6\w ]]
2025-03-21T20:26:14.0056312Z + EXPORT_ARGS+=' --tokenizer_path tokenizer.model --pt2e_quantize qnn_16a16w --calibration_tasks wikitext --calibration_limit 1 --calibration_seq_length 128 --calibration_data Once '
2025-03-21T20:26:14.0057162Z + [[ OFF == \O\N ]]
2025-03-21T20:26:14.0058420Z + python -m examples.models.llama.export_llama -c stories110M.pt -p params.json -d fp32 -n tinyllama_qnn_fp32.pte -kv -kv -v --qnn --disable_dynamic_shape --tokenizer_path tokenizer.model --pt2e_quantize qnn_16a16w --calibration_tasks wikitext --calibration_limit 1 --calibration_seq_length 128 --calibration_data Once
2025-03-21T20:26:14.0059944Z [INFO 2025-03-21 20:26:05,055 utils.py:162] NumExpr defaulting to 8 threads.
2025-03-21T20:26:14.0060723Z [WARNING 2025-03-21 20:26:05,686 quantizer_lib.py:180] Disable per channel quantization for linear and conv due to the error with QNN HTP 16a16w.
2025-03-21T20:26:14.0061877Z [INFO 2025-03-21 20:26:05,686 export_llama_lib.py:627] Applying quantizers: [<executorch.backends.qualcomm.quantizer.quantizer.QnnQuantizer object at 0x7fa87ad2f8b0>]
2025-03-21T20:26:14.0063131Z [INFO 2025-03-21 20:26:05,686 export_llama_lib.py:992] Loading model with checkpoint=stories110M.pt, params=params.json, use_kv_cache=True, weight_type=WeightType.LLAMA
2025-03-21T20:26:14.0065041Z [INFO 2025-03-21 20:26:06,222 builder.py:161] Applied source transforms: [<function replace_kv_cache_with_simple_kv_cache at 0x7fa87a60d360>, <function replace_sdpa_with_flex_sdpa at 0x7fa87a647010>, <function replace_causal_mask at 0x7fa87a60d510>, <function replace_rms_norm_with_native_rms_norm at 0x7fa87a6456c0>, <function convert_linear_to_conv2d at 0x7fa87a448700>]
2025-03-21T20:26:14.0066646Z [INFO 2025-03-21 20:26:06,223 builder.py:162] Model after source transforms: Transformer(
2025-03-21T20:26:14.0067133Z   (tok_embeddings): Embedding(32000, 768)
2025-03-21T20:26:14.0067457Z   (rope): Rope(
2025-03-21T20:26:14.0067713Z     (apply_rotary_emb): RotaryEmbedding()
2025-03-21T20:26:14.0068028Z   )
2025-03-21T20:26:14.0068250Z   (layers): ModuleList(
2025-03-21T20:26:14.0068524Z     (0-11): 12 x TransformerBlock(
2025-03-21T20:26:14.0068830Z       (attention): AttentionMHA(
2025-03-21T20:26:14.0069129Z         (wq): Conv2D(
2025-03-21T20:26:14.0069480Z           (conv): Conv2d(768, 768, kernel_size=(1, 1), stride=(1, 1), bias=False)
2025-03-21T20:26:14.0069887Z         )
2025-03-21T20:26:14.0070107Z         (wk): Conv2D(
2025-03-21T20:26:14.0070440Z           (conv): Conv2d(768, 768, kernel_size=(1, 1), stride=(1, 1), bias=False)
2025-03-21T20:26:14.0070837Z         )
2025-03-21T20:26:14.0071053Z         (wv): Conv2D(
2025-03-21T20:26:14.0071400Z           (conv): Conv2d(768, 768, kernel_size=(1, 1), stride=(1, 1), bias=False)
2025-03-21T20:26:14.0071799Z         )
2025-03-21T20:26:14.0072004Z         (wo): Conv2D(
2025-03-21T20:26:14.0072346Z           (conv): Conv2d(768, 768, kernel_size=(1, 1), stride=(1, 1), bias=False)
2025-03-21T20:26:14.0072744Z         )
2025-03-21T20:26:14.0072966Z         (rope): Rope(
2025-03-21T20:26:14.0073251Z           (apply_rotary_emb): RotaryEmbedding()
2025-03-21T20:26:14.0073568Z         )
2025-03-21T20:26:14.0073914Z         (kv_cache): KVCacheSimple()
2025-03-21T20:26:14.0074295Z         (SDPA): SDPAFlex()
2025-03-21T20:26:14.0074565Z       )
2025-03-21T20:26:14.0074797Z       (feed_forward): FeedForward(
2025-03-21T20:26:14.0075079Z         (w1): Conv2D(
2025-03-21T20:26:14.0075435Z           (conv): Conv2d(2048, 768, kernel_size=(1, 1), stride=(1, 1), bias=False)
2025-03-21T20:26:14.0075839Z         )
2025-03-21T20:26:14.0076056Z         (w2): Conv2D(
2025-03-21T20:26:14.0076403Z           (conv): Conv2d(768, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
2025-03-21T20:26:14.0076795Z         )
2025-03-21T20:26:14.0077011Z         (w3): Conv2D(
2025-03-21T20:26:14.0077361Z           (conv): Conv2d(2048, 768, kernel_size=(1, 1), stride=(1, 1), bias=False)
2025-03-21T20:26:14.0077762Z         )
2025-03-21T20:26:14.0077973Z       )
2025-03-21T20:26:14.0078298Z       (attention_norm): RMSNorm((768,), eps=1e-05, elementwise_affine=True)
2025-03-21T20:26:14.0078803Z       (ffn_norm): RMSNorm((768,), eps=1e-05, elementwise_affine=True)
2025-03-21T20:26:14.0079192Z     )
2025-03-21T20:26:14.0079402Z   )
2025-03-21T20:26:14.0079689Z   (norm): RMSNorm((768,), eps=1e-05, elementwise_affine=True)
2025-03-21T20:26:14.0080051Z   (output): Conv2D(
2025-03-21T20:26:14.0080401Z     (conv): Conv2d(32000, 768, kernel_size=(1, 1), stride=(1, 1), bias=False)
2025-03-21T20:26:14.0080806Z   )
2025-03-21T20:26:14.0081017Z )
2025-03-21T20:26:14.0082208Z /opt/conda/envs/py_3.10/lib/python3.10/site-packages/torch/backends/mkldnn/__init__.py:78: UserWarning: TF32 acceleration on top of oneDNN is available for Intel GPUs. The current Torch version does not have Intel GPU Support. (Triggered internally at /pytorch/aten/src/ATen/Context.cpp:148.)
2025-03-21T20:26:14.0083517Z   torch._C._set_onednn_allow_tf32(_allow_tf32)
2025-03-21T20:26:14.0084810Z /opt/conda/envs/py_3.10/lib/python3.10/site-packages/torch/backends/mkldnn/__init__.py:78: UserWarning: TF32 acceleration on top of oneDNN is available for Intel GPUs. The current Torch version does not have Intel GPU Support. (Triggered internally at /pytorch/aten/src/ATen/Context.cpp:148.)
2025-03-21T20:26:14.0086113Z   torch._C._set_onednn_allow_tf32(_allow_tf32)
2025-03-21T20:26:14.0086633Z [INFO 2025-03-21 20:26:13,063 builder.py:251] Running canonical pass: RemoveRedundantTransposes
2025-03-21T20:26:14.0087642Z [INFO 2025-03-21 20:26:13,129 builder.py:337] Using pt2e [<executorch.backends.qualcomm.quantizer.quantizer.QnnQuantizer object at 0x7fa87ad2f8b0>] to quantizing the model...
2025-03-21T20:26:14.0088916Z [INFO 2025-03-21 20:26:13,129 builder.py:344] Applied quantizers: [<executorch.backends.qualcomm.quantizer.quantizer.QnnQuantizer object at 0x7fa87ad2f8b0>]
2025-03-21T20:26:14.0089855Z No quant config is implemented for op, aten._to_copy.default
2025-03-21T20:26:14.0090323Z No quant config is implemented for op, aten._to_copy.default
2025-03-21T20:26:14.0090772Z No quant config is implemented for op, aten.type_as.default
2025-03-21T20:26:14.0091229Z No quant config is implemented for op, aten.type_as.default
2025-03-21T20:26:14.0091697Z No quant config is implemented for op, aten._to_copy.default
2025-03-21T20:26:14.0092158Z No quant config is implemented for op, aten._to_copy.default
2025-03-21T20:26:14.0092618Z No quant config is implemented for op, aten.type_as.default
2025-03-21T20:26:14.0093074Z No quant config is implemented for op, aten.type_as.default
2025-03-21T20:26:14.0093518Z No quant config is implemented for op, aten._to_copy.default
2025-03-21T20:26:14.0093975Z No quant config is implemented for op, aten._to_copy.default
2025-03-21T20:26:14.0094430Z No quant config is implemented for op, aten.type_as.default
2025-03-21T20:26:14.0094886Z No quant config is implemented for op, aten.type_as.default
2025-03-21T20:26:14.0095342Z No quant config is implemented for op, aten._to_copy.default
2025-03-21T20:26:14.0095788Z No quant config is implemented for op, aten._to_copy.default
2025-03-21T20:26:14.0096241Z No quant config is implemented for op, aten.type_as.default
2025-03-21T20:26:14.0096854Z No quant config is implemented for op, aten.type_as.default
2025-03-21T20:26:14.0097314Z No quant config is implemented for op, aten._to_copy.default
2025-03-21T20:26:14.0097779Z No quant config is implemented for op, aten._to_copy.default
2025-03-21T20:26:14.0098224Z No quant config is implemented for op, aten.type_as.default
2025-03-21T20:26:14.0098679Z No quant config is implemented for op, aten.type_as.default
2025-03-21T20:26:14.0099139Z No quant config is implemented for op, aten._to_copy.default
2025-03-21T20:26:14.0099598Z No quant config is implemented for op, aten._to_copy.default
2025-03-21T20:26:14.0100054Z No quant config is implemented for op, aten.type_as.default
2025-03-21T20:26:14.0100513Z No quant config is implemented for op, aten.type_as.default
2025-03-21T20:26:14.0100957Z No quant config is implemented for op, aten._to_copy.default
2025-03-21T20:26:14.0101415Z No quant config is implemented for op, aten._to_copy.default
2025-03-21T20:26:14.0101874Z No quant config is implemented for op, aten.type_as.default
2025-03-21T20:26:14.0102336Z No quant config is implemented for op, aten.type_as.default
2025-03-21T20:26:14.0102794Z No quant config is implemented for op, aten._to_copy.default
2025-03-21T20:26:14.0103241Z No quant config is implemented for op, aten._to_copy.default
2025-03-21T20:26:14.0103714Z No quant config is implemented for op, aten.type_as.default
2025-03-21T20:26:14.0104171Z No quant config is implemented for op, aten.type_as.default
2025-03-21T20:26:14.0104636Z No quant config is implemented for op, aten._to_copy.default
2025-03-21T20:26:14.0105100Z No quant config is implemented for op, aten._to_copy.default
2025-03-21T20:26:14.0105562Z No quant config is implemented for op, aten.type_as.default
2025-03-21T20:26:14.0106006Z No quant config is implemented for op, aten.type_as.default
2025-03-21T20:26:14.0106466Z No quant config is implemented for op, aten._to_copy.default
2025-03-21T20:26:14.0106932Z No quant config is implemented for op, aten._to_copy.default
2025-03-21T20:26:14.0107401Z No quant config is implemented for op, aten.type_as.default
2025-03-21T20:26:14.0107862Z No quant config is implemented for op, aten.type_as.default
2025-03-21T20:26:14.0108314Z No quant config is implemented for op, aten._to_copy.default
2025-03-21T20:26:14.0108779Z No quant config is implemented for op, aten._to_copy.default
2025-03-21T20:26:14.0109244Z No quant config is implemented for op, aten.type_as.default
2025-03-21T20:26:14.0109705Z No quant config is implemented for op, aten.type_as.default
2025-03-21T20:26:14.0110164Z No quant config is implemented for op, aten._to_copy.default
2025-03-21T20:26:14.0110625Z No quant config is implemented for op, aten._to_copy.default
2025-03-21T20:26:14.0111068Z No quant config is implemented for op, aten.type_as.default
2025-03-21T20:26:14.0111524Z No quant config is implemented for op, aten.type_as.default
2025-03-21T20:26:14.0111980Z No quant config is implemented for op, aten.copy_.default
2025-03-21T20:26:14.0112431Z No quant config is implemented for op, aten.copy_.default
2025-03-21T20:26:14.0112884Z No quant config is implemented for op, aten.copy_.default
2025-03-21T20:26:14.0113317Z No quant config is implemented for op, aten.copy_.default
2025-03-21T20:26:14.0113756Z No quant config is implemented for op, aten.copy_.default
2025-03-21T20:30:47.9499886Z No quant config is implemented for op, aten.copy_.default
2025-03-21T20:30:47.9500672Z No quant config is implemented for op, aten.copy_.default
2025-03-21T20:30:47.9501372Z No quant config is implemented for op, aten.copy_.default
2025-03-21T20:30:47.9502252Z No quant config is implemented for op, aten.copy_.default
2025-03-21T20:30:47.9502944Z No quant config is implemented for op, aten.copy_.default
2025-03-21T20:30:47.9503652Z No quant config is implemented for op, aten.copy_.default
2025-03-21T20:30:47.9504347Z No quant config is implemented for op, aten.copy_.default
2025-03-21T20:30:47.9505070Z No quant config is implemented for op, aten.copy_.default
2025-03-21T20:30:47.9506514Z No quant config is implemented for op, aten.copy_.default
2025-03-21T20:30:47.9507195Z No quant config is implemented for op, aten.copy_.default
2025-03-21T20:30:47.9507982Z No quant config is implemented for op, aten.copy_.default
2025-03-21T20:30:47.9508648Z No quant config is implemented for op, aten.copy_.default
2025-03-21T20:30:47.9509331Z No quant config is implemented for op, aten.copy_.default
2025-03-21T20:30:47.9510014Z No quant config is implemented for op, aten.copy_.default
2025-03-21T20:30:47.9510692Z No quant config is implemented for op, aten.copy_.default
2025-03-21T20:30:47.9511397Z No quant config is implemented for op, aten.copy_.default
2025-03-21T20:30:47.9512109Z No quant config is implemented for op, aten.copy_.default
2025-03-21T20:30:47.9512823Z No quant config is implemented for op, aten.copy_.default
2025-03-21T20:30:47.9513522Z No quant config is implemented for op, aten.copy_.default
2025-03-21T20:30:47.9514837Z [INFO 2025-03-21 20:26:25,049 builder.py:353] Calibrating with tasks: ['wikitext'], limit: 1, calibration_data: Once, tokenizer_path: tokenizer.model, seq_length: 128
2025-03-21T20:30:47.9516658Z [INFO 2025-03-21 20:26:25,049 builder.py:364] Calibrating with tasks: ['wikitext'], limit: 1, calibration_data: Once, tokenizer_path: tokenizer.model, seq_length: 128
2025-03-21T20:30:47.9517960Z [INFO 2025-03-21 20:26:25,049 builder.py:265] Run calibration...
2025-03-21T20:30:47.9518797Z [INFO 2025-03-21 20:26:25,327 config.py:54] PyTorch version 2.7.0a0+git295f2ed available.
2025-03-21T20:30:47.9519723Z [INFO 2025-03-21 20:26:26,991 tokenizer.py:33] #words: 32000 - BOS ID: 1 - EOS ID: 2
2025-03-21T20:30:47.9520571Z [INFO 2025-03-21 20:26:42,906 huggingface.py:129] Using device 'cpu'
2025-03-21T20:30:47.9521046Z 
2025-03-21T20:30:47.9521221Z config.json:   0% 0.00/665 [00:00<?, ?B/s]
2025-03-21T20:30:47.9521785Z config.json: 100% 665/665 [00:00<00:00, 5.33MB/s]
2025-03-21T20:30:47.9522482Z [INFO 2025-03-21 20:26:43,163 huggingface.py:481] Using model type 'default'
2025-03-21T20:30:47.9522999Z 
2025-03-21T20:30:47.9523239Z tokenizer_config.json:   0% 0.00/26.0 [00:00<?, ?B/s]
2025-03-21T20:30:47.9523930Z tokenizer_config.json: 100% 26.0/26.0 [00:00<00:00, 258kB/s]
2025-03-21T20:30:47.9524387Z 
2025-03-21T20:30:47.9524584Z vocab.json:   0% 0.00/1.04M [00:00<?, ?B/s]
2025-03-21T20:30:47.9525112Z vocab.json: 100% 1.04M/1.04M [00:00<00:00, 47.2MB/s]
2025-03-21T20:30:47.9525520Z 
2025-03-21T20:30:47.9525707Z merges.txt:   0% 0.00/456k [00:00<?, ?B/s]
2025-03-21T20:30:47.9526261Z merges.txt: 100% 456k/456k [00:00<00:00, 48.6MB/s]
2025-03-21T20:30:47.9526649Z 
2025-03-21T20:30:47.9526852Z tokenizer.json:   0% 0.00/1.36M [00:00<?, ?B/s]
2025-03-21T20:30:47.9527475Z tokenizer.json: 100% 1.36M/1.36M [00:00<00:00, 28.6MB/s]
2025-03-21T20:30:47.9528594Z [INFO 2025-03-21 20:26:45,023 huggingface.py:365] Model parallel was set to False, max memory was not set, and device map was set to {'': 'cpu'}
2025-03-21T20:30:47.9529544Z 
2025-03-21T20:30:47.9529750Z model.safetensors:   0% 0.00/548M [00:00<?, ?B/s]
2025-03-21T20:30:47.9530410Z model.safetensors:   6% 31.5M/548M [00:00<00:02, 228MB/s]
2025-03-21T20:30:47.9531097Z model.safetensors:  11% 62.9M/548M [00:00<00:02, 218MB/s]
2025-03-21T20:30:47.9531766Z model.safetensors:  17% 94.4M/548M [00:00<00:02, 223MB/s]
2025-03-21T20:30:47.9532623Z model.safetensors:  23% 126M/548M [00:00<00:01, 226MB/s] 
2025-03-21T20:30:47.9533292Z model.safetensors:  29% 157M/548M [00:00<00:01, 221MB/s]
2025-03-21T20:30:47.9533939Z model.safetensors:  34% 189M/548M [00:00<00:01, 225MB/s]
2025-03-21T20:30:47.9534625Z model.safetensors:  40% 220M/548M [00:00<00:01, 225MB/s]
2025-03-21T20:30:47.9535302Z model.safetensors:  46% 252M/548M [00:01<00:01, 231MB/s]
2025-03-21T20:30:47.9535966Z model.safetensors:  52% 283M/548M [00:01<00:01, 232MB/s]
2025-03-21T20:30:47.9536630Z model.safetensors:  57% 315M/548M [00:01<00:01, 228MB/s]
2025-03-21T20:30:47.9537304Z model.safetensors:  63% 346M/548M [00:01<00:00, 226MB/s]
2025-03-21T20:30:47.9537970Z model.safetensors:  69% 377M/548M [00:01<00:00, 229MB/s]
2025-03-21T20:30:47.9538956Z model.safetensors:  75% 409M/548M [00:01<00:00, 231MB/s]
2025-03-21T20:30:47.9539623Z model.safetensors:  80% 440M/548M [00:01<00:00, 230MB/s]
2025-03-21T20:30:47.9540276Z model.safetensors:  86% 472M/548M [00:02<00:00, 231MB/s]
2025-03-21T20:30:47.9540933Z model.safetensors:  92% 503M/548M [00:02<00:00, 233MB/s]
2025-03-21T20:30:47.9541575Z model.safetensors:  98% 535M/548M [00:02<00:00, 237MB/s]
2025-03-21T20:30:47.9542248Z model.safetensors: 100% 548M/548M [00:02<00:00, 229MB/s]
2025-03-21T20:30:47.9542659Z 
2025-03-21T20:30:47.9542902Z generation_config.json:   0% 0.00/124 [00:00<?, ?B/s]
2025-03-21T20:30:47.9543581Z generation_config.json: 100% 124/124 [00:00<00:00, 1.25MB/s]
2025-03-21T20:30:47.9544923Z [INFO 2025-03-21 20:26:47,985 evaluator.py:164] Setting random seed to 0 | Setting numpy seed to 1234 | Setting torch manual seed to 1234 | Setting fewshot manual seed to 1234
2025-03-21T20:30:47.9546291Z [INFO 2025-03-21 20:26:47,985 evaluator.py:217] Using pre-initialized model
2025-03-21T20:30:47.9547668Z [WARNING 2025-03-21 20:26:55,480 task.py:799] [Task: wikitext] metric word_perplexity is defined, but aggregation is not. using default aggregation=weighted_perplexity
2025-03-21T20:30:47.9549530Z [WARNING 2025-03-21 20:26:55,480 task.py:811] [Task: wikitext] metric word_perplexity is defined, but higher_is_better is not. using default higher_is_better=False
2025-03-21T20:30:47.9551367Z [WARNING 2025-03-21 20:26:55,480 task.py:799] [Task: wikitext] metric byte_perplexity is defined, but aggregation is not. using default aggregation=weighted_perplexity
2025-03-21T20:30:47.9553203Z [WARNING 2025-03-21 20:26:55,480 task.py:811] [Task: wikitext] metric byte_perplexity is defined, but higher_is_better is not. using default higher_is_better=False
2025-03-21T20:30:47.9554976Z [WARNING 2025-03-21 20:26:55,480 task.py:799] [Task: wikitext] metric bits_per_byte is defined, but aggregation is not. using default aggregation=bits_per_byte
2025-03-21T20:30:47.9556731Z [WARNING 2025-03-21 20:26:55,480 task.py:811] [Task: wikitext] metric bits_per_byte is defined, but higher_is_better is not. using default higher_is_better=False
2025-03-21T20:30:47.9557700Z 
2025-03-21T20:30:47.9557890Z README.md:   0% 0.00/8.76k [00:00<?, ?B/s]
2025-03-21T20:30:47.9558445Z README.md: 100% 8.76k/8.76k [00:00<00:00, 55.4MB/s]
2025-03-21T20:30:47.9558815Z 
2025-03-21T20:30:47.9559149Z wikitext-2-raw-v1-train.parquet:   0% 0.00/6.18M [00:00<?, ?B/s]
2025-03-21T20:30:47.9560005Z wikitext-2-raw-v1-train.parquet: 100% 6.18M/6.18M [00:00<00:00, 173MB/s]
2025-03-21T20:30:47.9560541Z 
2025-03-21T20:30:47.9560891Z wikitext-2-raw-v1-validation.parquet:   0% 0.00/641k [00:00<?, ?B/s]
2025-03-21T20:30:47.9561796Z wikitext-2-raw-v1-validation.parquet: 100% 641k/641k [00:00<00:00, 337MB/s]
2025-03-21T20:30:47.9562366Z 
2025-03-21T20:30:47.9562669Z wikitext-2-raw-v1-test.parquet:   0% 0.00/715k [00:00<?, ?B/s]
2025-03-21T20:30:47.9563452Z wikitext-2-raw-v1-test.parquet: 100% 715k/715k [00:00<00:00, 468MB/s]
2025-03-21T20:30:47.9563965Z 
2025-03-21T20:30:47.9564257Z Generating train split:   0% 0/629 [00:00<?, ? examples/s]
2025-03-21T20:30:47.9565005Z Generating train split: 100% 629/629 [00:00<00:00, 9882.41 examples/s]
2025-03-21T20:30:47.9565522Z 
2025-03-21T20:30:47.9565826Z Generating validation split:   0% 0/60 [00:00<?, ? examples/s]
2025-03-21T20:30:47.9566651Z Generating validation split: 100% 60/60 [00:00<00:00, 10557.91 examples/s]
2025-03-21T20:30:47.9567181Z 
2025-03-21T20:30:47.9567450Z Generating test split:   0% 0/62 [00:00<?, ? examples/s]
2025-03-21T20:30:47.9568210Z Generating test split: 100% 62/62 [00:00<00:00, 12668.53 examples/s]
2025-03-21T20:30:47.9569069Z [INFO 2025-03-21 20:26:58,519 task.py:415] Building contexts for wikitext on rank 0...
2025-03-21T20:30:47.9569672Z 
2025-03-21T20:30:47.9569820Z   0% 0/1 [00:00<?, ?it/s]
2025-03-21T20:30:47.9570236Z 100% 1/1 [00:00<00:00, 1414.61it/s]
2025-03-21T20:30:47.9570920Z [INFO 2025-03-21 20:26:58,520 evaluator.py:489] Running loglikelihood_rolling requests
2025-03-21T20:30:47.9571680Z 
2025-03-21T20:30:47.9571837Z   0% 0/1 [00:00<?, ?it/s]
2025-03-21T20:30:47.9572232Z 100% 1/1 [03:12<00:00, 192.25s/it]
2025-03-21T20:30:47.9572668Z 100% 1/1 [03:12<00:00, 192.25s/it]
2025-03-21T20:30:47.9574366Z wikitext: {'alias': 'wikitext', 'word_perplexity,none': 23972.96746951233, 'word_perplexity_stderr,none': 'N/A', 'byte_perplexity,none': 6.993931199436942, 'byte_perplexity_stderr,none': 'N/A', 'bits_per_byte,none': 2.806103604054025, 'bits_per_byte_stderr,none': 'N/A'}
2025-03-21T20:30:47.9576284Z [INFO 2025-03-21 20:30:14,397 builder.py:326] Calibration finish...
2025-03-21T20:30:47.9578514Z /opt/conda/envs/py_3.10/lib/python3.10/site-packages/torch/backends/mkldnn/__init__.py:78: UserWarning: TF32 acceleration on top of oneDNN is available for Intel GPUs. The current Torch version does not have Intel GPU Support. (Triggered internally at /pytorch/aten/src/ATen/Context.cpp:148.)
2025-03-21T20:30:47.9580605Z   torch._C._set_onednn_allow_tf32(_allow_tf32)
2025-03-21T20:30:47.9582719Z /opt/conda/envs/py_3.10/lib/python3.10/site-packages/torch/backends/mkldnn/__init__.py:78: UserWarning: TF32 acceleration on top of oneDNN is available for Intel GPUs. The current Torch version does not have Intel GPU Support. (Triggered internally at /pytorch/aten/src/ATen/Context.cpp:148.)
2025-03-21T20:30:47.9584880Z   torch._C._set_onednn_allow_tf32(_allow_tf32)
2025-03-21T20:30:47.9585526Z [INFO 2025-03-21 20:30:47,948 utils.py:50] Core ATen graph:
2025-03-21T20:30:47.9586084Z graph():
2025-03-21T20:30:47.9586601Z     %b__frozen_param0 : [num_users=1] = placeholder[target=b__frozen_param0]
2025-03-21T20:30:47.9587471Z     %b__frozen_param1 : [num_users=1] = placeholder[target=b__frozen_param1]
2025-03-21T20:30:47.9588318Z     %b__frozen_param2 : [num_users=1] = placeholder[target=b__frozen_param2]
2025-03-21T20:30:47.9589163Z     %b__frozen_param3 : [num_users=1] = placeholder[target=b__frozen_param3]
2025-03-21T20:30:47.9590027Z     %b__frozen_param4 : [num_users=1] = placeholder[target=b__frozen_param4]
2025-03-21T20:30:47.9590883Z     %b__frozen_param5 : [num_users=1] = placeholder[target=b__frozen_param5]
2025-03-21T20:30:47.9591737Z     %b__frozen_param6 : [num_users=1] = placeholder[target=b__frozen_param6]
2025-03-21T20:30:47.9592568Z     %b__frozen_param7 : [num_users=1] = placeholder[target=b__frozen_param7]
2025-03-21T20:30:47.9593411Z     %b__frozen_param8 : [num_users=1] = placeholder[target=b__frozen_param8]
2025-03-21T20:30:47.9594253Z     %b__frozen_param9 : [num_users=1] = placeholder[target=b__frozen_param9]
2025-03-21T20:30:47.9595090Z     %b__frozen_param10 : [num_users=1] = placeholder[target=b__frozen_param10]
2025-03-21T20:30:47.9595972Z     %b__frozen_param11 : [num_users=1] = placeholder[target=b__frozen_param11]
2025-03-21T20:30:47.9596817Z     %b__frozen_param12 : [num_users=1] = placeholder[target=b__frozen_param12]
2025-03-21T20:30:47.9597675Z     %b__frozen_param13 : [num_users=1] = placeholder[target=b__frozen_param13]
2025-03-21T20:30:47.9598538Z     %b__frozen_param14 : [num_users=1] = placeholder[target=b__frozen_param14]
2025-03-21T20:30:47.9599418Z     %b__frozen_param15 : [num_users=1] = placeholder[target=b__frozen_param15]
2025-03-21T20:30:47.9600280Z     %b__frozen_param16 : [num_users=1] = placeholder[target=b__frozen_param16]
2025-03-21T20:30:47.9601146Z     %b__frozen_param17 : [num_users=1] = placeholder[target=b__frozen_param17]
2025-03-21T20:30:47.9602009Z     %b__frozen_param18 : [num_users=1] = placeholder[target=b__frozen_param18]
2025-03-21T20:30:47.9620629Z     %b__frozen_param19 : [num_users=1] = placeholder[target=b__frozen_param19]
2025-03-21T20:30:47.9621709Z     %b__frozen_param20 : [num_users=1] = placeholder[target=b__frozen_param20]
2025-03-21T20:30:47.9622591Z     %b__frozen_param21 : [num_users=1] = placeholder[target=b__frozen_param21]
2025-03-21T20:30:47.9623458Z     %b__frozen_param22 : [num_users=1] = placeholder[target=b__frozen_param22]
2025-03-21T20:30:47.9624284Z     %b__frozen_param23 : [num_users=1] = placeholder[target=b__frozen_param23]
2025-03-21T20:30:47.9625389Z     %b__frozen_param24 : [num_users=1] = placeholder[target=b__frozen_param24]
2025-03-21T20:30:47.9626269Z     %b__frozen_param25 : [num_users=1] = placeholder[target=b__frozen_param25]
2025-03-21T20:30:47.9627141Z     %b__frozen_param26 : [num_users=1] = placeholder[target=b__frozen_param26]
2025-03-21T20:30:47.9628003Z     %b__frozen_param27 : [num_users=1] = placeholder[target=b__frozen_param27]
2025-03-21T20:30:47.9628870Z     %b__frozen_param28 : [num_users=1] = placeholder[target=b__frozen_param28]
2025-03-21T20:30:47.9629716Z     %b__frozen_param29 : [num_users=1] = placeholder[target=b__frozen_param29]
2025-03-21T20:30:47.9630566Z     %b__frozen_param30 : [num_users=1] = placeholder[target=b__frozen_param30]
2025-03-21T20:30:47.9631446Z     %b__frozen_param31 : [num_users=1] = placeholder[target=b__frozen_param31]
2025-03-21T20:30:47.9632456Z     %b__frozen_param32 : [num_users=1] = placeholder[target=b__frozen_param32]
2025-03-21T20:30:47.9633339Z     %b__frozen_param33 : [num_users=1] = placeholder[target=b__frozen_param33]
2025-03-21T20:30:47.9634216Z     %b__frozen_param34 : [num_users=1] = placeholder[target=b__frozen_param34]
2025-03-21T20:30:47.9635073Z     %b__frozen_param35 : [num_users=1] = placeholder[target=b__frozen_param35]
2025-03-21T20:30:47.9635914Z     %b__frozen_param36 : [num_users=1] = placeholder[target=b__frozen_param36]
2025-03-21T20:30:47.9636782Z     %b__frozen_param37 : [num_users=1] = placeholder[target=b__frozen_param37]
2025-03-21T20:30:47.9637645Z     %b__frozen_param38 : [num_users=1] = placeholder[target=b__frozen_param38]
2025-03-21T20:30:47.9638510Z     %b__frozen_param39 : [num_users=1] = placeholder[target=b__frozen_param39]
2025-03-21T20:30:47.9639384Z     %b__frozen_param40 : [num_users=1] = placeholder[target=b__frozen_param40]
2025-03-21T20:30:47.9640254Z     %b__frozen_param41 : [num_users=1] = placeholder[target=b__frozen_param41]
2025-03-21T20:30:47.9641115Z     %b__frozen_param42 : [num_users=1] = placeholder[target=b__frozen_param42]
2025-03-21T20:30:47.9642010Z     %b__frozen_param43 : [num_users=1] = placeholder[target=b__frozen_param43]
2025-03-21T20:30:47.9642878Z     %b__frozen_param44 : [num_users=1] = placeholder[target=b__frozen_param44]
2025-03-21T20:30:47.9643754Z     %b__frozen_param45 : [num_users=1] = placeholder[target=b__frozen_param45]
2025-03-21T20:30:47.9644628Z     %b__frozen_param46 : [num_users=1] = placeholder[target=b__frozen_param46]
2025-03-21T20:30:47.9645486Z     %b__frozen_param47 : [num_users=1] = placeholder[target=b__frozen_param47]
2025-03-21T20:30:47.9646336Z     %b__frozen_param48 : [num_users=1] = placeholder[target=b__frozen_param48]
2025-03-21T20:30:47.9647197Z     %b__frozen_param49 : [num_users=1] = placeholder[target=b__frozen_param49]
2025-03-21T20:30:47.9648058Z     %b__frozen_param50 : [num_users=1] = placeholder[target=b__frozen_param50]
2025-03-21T20:30:47.9648923Z     %b__frozen_param51 : [num_users=1] = placeholder[target=b__frozen_param51]
2025-03-21T20:30:47.9649872Z     %b__frozen_param52 : [num_users=1] = placeholder[target=b__frozen_param52]
2025-03-21T20:30:47.9650718Z     %b__frozen_param53 : [num_users=1] = placeholder[target=b__frozen_param53]
2025-03-21T20:30:47.9651581Z     %b__frozen_param54 : [num_users=1] = placeholder[target=b__frozen_param54]
2025-03-21T20:30:47.9652465Z     %b__frozen_param55 : [num_users=1] = placeholder[target=b__frozen_param55]
2025-03-21T20:30:47.9653330Z     %b__frozen_param56 : [num_users=1] = placeholder[target=b__frozen_param56]
2025-03-21T20:30:47.9654186Z     %b__frozen_param57 : [num_users=1] = placeholder[target=b__frozen_param57]
2025-03-21T20:30:47.9655055Z     %b__frozen_param58 : [num_users=1] = placeholder[target=b__frozen_param58]
2025-03-21T20:30:47.9655902Z     %b__frozen_param59 : [num_users=1] = placeholder[target=b__frozen_param59]
2025-03-21T20:30:47.9656773Z     %b__frozen_param60 : [num_users=1] = placeholder[target=b__frozen_param60]
2025-03-21T20:30:47.9657530Z     %b__frozen_param61 : [num_users=1] = placeholder[target=b__frozen_param61]
2025-03-21T20:30:47.9658602Z     %b__frozen_param62 : [num_users=1] = placeholder[target=b__frozen_param62]
2025-03-21T20:30:47.9659411Z     %b__frozen_param63 : [num_users=1] = placeholder[target=b__frozen_param63]
2025-03-21T20:30:47.9660196Z     %b__frozen_param64 : [num_users=1] = placeholder[target=b__frozen_param64]
2025-03-21T20:30:47.9660983Z     %b__frozen_param65 : [num_users=1] = placeholder[target=b__frozen_param65]
2025-03-21T20:30:47.9661779Z     %b__frozen_param66 : [num_users=1] = placeholder[target=b__frozen_param66]
2025-03-21T20:30:47.9662576Z     %b__frozen_param67 : [num_users=1] = placeholder[target=b__frozen_param67]
2025-03-21T20:30:47.9663382Z     %b__frozen_param68 : [num_users=1] = placeholder[target=b__frozen_param68]
2025-03-21T20:30:47.9664188Z     %b__frozen_param69 : [num_users=1] = placeholder[target=b__frozen_param69]
2025-03-21T20:30:47.9664973Z     %b__frozen_param70 : [num_users=1] = placeholder[target=b__frozen_param70]
2025-03-21T20:30:47.9665753Z     %b__frozen_param71 : [num_users=1] = placeholder[target=b__frozen_param71]
2025-03-21T20:30:47.9666552Z     %b__frozen_param72 : [num_users=1] = placeholder[target=b__frozen_param72]
2025-03-21T20:30:47.9667359Z     %b__frozen_param73 : [num_users=1] = placeholder[target=b__frozen_param73]
2025-03-21T20:30:47.9668147Z     %b__frozen_param74 : [num_users=1] = placeholder[target=b__frozen_param74]
2025-03-21T20:30:47.9668956Z     %b__frozen_param75 : [num_users=1] = placeholder[target=b__frozen_param75]
2025-03-21T20:30:47.9669753Z     %b__frozen_param76 : [num_users=1] = placeholder[target=b__frozen_param76]
2025-03-21T20:30:47.9670543Z     %b__frozen_param77 : [num_users=1] = placeholder[target=b__frozen_param77]
2025-03-21T20:30:47.9671341Z     %b__frozen_param78 : [num_users=1] = placeholder[target=b__frozen_param78]
2025-03-21T20:30:47.9672154Z     %b__frozen_param79 : [num_users=1] = placeholder[target=b__frozen_param79]
2025-03-21T20:30:47.9672946Z     %b__frozen_param80 : [num_users=1] = placeholder[target=b__frozen_param80]
2025-03-21T20:30:47.9673750Z     %b__frozen_param81 : [num_users=1] = placeholder[target=b__frozen_param81]
2025-03-21T20:30:47.9674539Z     %b__frozen_param82 : [num_users=1] = placeholder[target=b__frozen_param82]
2025-03-21T20:30:47.9675321Z     %b__frozen_param83 : [num_users=1] = placeholder[target=b__frozen_param83]
2025-03-21T20:30:47.9676116Z     %b__frozen_param84 : [num_users=1] = placeholder[target=b__frozen_param84]
2025-03-21T20:30:47.9676908Z     %b__frozen_param85 : [num_users=1] = placeholder[target=b__frozen_param85]
2025-03-21T20:30:47.9677723Z     %b__frozen_param86 : [num_users=1] = placeholder[target=b__frozen_param86]
2025-03-21T20:30:47.9678558Z     %b__frozen_param87 : [num_users=1] = placeholder[target=b__frozen_param87]
2025-03-21T20:30:47.9679373Z     %b__frozen_param88 : [num_users=1] = placeholder[target=b__frozen_param88]
2025-03-21T20:30:47.9680193Z     %b__frozen_param89 : [num_users=1] = placeholder[target=b__frozen_param89]
2025-03-21T20:30:47.9681037Z     %b__frozen_param90 : [num_users=1] = placeholder[target=b__frozen_param90]
2025-03-21T20:30:47.9681880Z     %b__frozen_param91 : [num_users=1] = placeholder[target=b__frozen_param91]
2025-03-21T20:30:47.9682698Z     %b__frozen_param92 : [num_users=1] = placeholder[target=b__frozen_param92]
2025-03-21T20:30:47.9683539Z     %b__frozen_param93 : [num_users=1] = placeholder[target=b__frozen_param93]
2025-03-21T20:30:47.9684340Z     %b__frozen_param94 : [num_users=1] = placeholder[target=b__frozen_param94]
2025-03-21T20:30:47.9685075Z     %b__frozen_param95 : [num_users=1] = placeholder[target=b__frozen_param95]
2025-03-21T20:30:47.9685941Z     %b__frozen_param96 : [num_users=1] = placeholder[target=b__frozen_param96]
2025-03-21T20:30:47.9686820Z     %b__frozen_param97 : [num_users=1] = placeholder[target=b__frozen_param97]
2025-03-21T20:30:47.9687682Z     %b__frozen_param98 : [num_users=1] = placeholder[target=b__frozen_param98]
2025-03-21T20:30:47.9688550Z     %b__frozen_param99 : [num_users=1] = placeholder[target=b__frozen_param99]
2025-03-21T20:30:47.9689756Z     %b__frozen_param100 : [num_users=1] = placeholder[target=b__frozen_param100]
2025-03-21T20:30:47.9690648Z     %b__frozen_param101 : [num_users=1] = placeholder[target=b__frozen_param101]
2025-03-21T20:30:47.9691522Z     %b__frozen_param102 : [num_users=1] = placeholder[target=b__frozen_param102]
2025-03-21T20:30:47.9692389Z     %b__frozen_param103 : [num_users=1] = placeholder[target=b__frozen_param103]
2025-03-21T20:30:47.9693271Z     %b__frozen_param104 : [num_users=1] = placeholder[target=b__frozen_param104]
2025-03-21T20:30:47.9694162Z     %b__frozen_param105 : [num_users=1] = placeholder[target=b__frozen_param105]
2025-03-21T20:30:47.9695066Z     %b__frozen_param106 : [num_users=1] = placeholder[target=b__frozen_param106]
2025-03-21T20:30:47.9695949Z     %b__frozen_param107 : [num_users=1] = placeholder[target=b__frozen_param107]
2025-03-21T20:30:47.9696863Z     %b__frozen_param108 : [num_users=1] = placeholder[target=b__frozen_param108]
2025-03-21T20:30:47.9697786Z     %b__frozen_param109 : [num_users=1] = placeholder[target=b__frozen_param109]
2025-03-21T20:30:47.9698700Z     %b__frozen_param110 : [num_users=1] = placeholder[target=b__frozen_param110]
2025-03-21T20:30:47.9699593Z     %b__frozen_param111 : [num_users=1] = placeholder[target=b__frozen_param111]
2025-03-21T20:30:47.9700501Z     %b__frozen_param112 : [num_users=1] = placeholder[target=b__frozen_param112]
2025-03-21T20:30:47.9701946Z     %b_getattr_l__self___layers___0___attention_kv_cache_past_k_caches : [num_users=1] = placeholder[target=b_getattr_l__self___layers___0___attention_kv_cache_past_k_caches]
2025-03-21T20:30:47.9704422Z     %b__frozen_param113 : [num_users=1] = placeholder[target=b__frozen_param113]
2025-03-21T20:30:47.9705631Z     %b_getattr_l__self___layers___0___attention_kv_cache_past_v_caches : [num_users=1] = placeholder[target=b_getattr_l__self___layers___0___attention_kv_cache_past_v_caches]
2025-03-21T20:30:47.9706844Z     %b__frozen_param114 : [num_users=1] = placeholder[target=b__frozen_param114]
2025-03-21T20:30:47.9707609Z     %b__frozen_param115 : [num_users=1] = placeholder[target=b__frozen_param115]
2025-03-21T20:30:47.9708822Z     %b_getattr_l__self___layers___1___attention_kv_cache_past_k_caches : [num_users=1] = placeholder[target=b_getattr_l__self___layers___1___attention_kv_cache_past_k_caches]
2025-03-21T20:30:47.9710037Z     %b__frozen_param116 : [num_users=1] = placeholder[target=b__frozen_param116]
2025-03-21T20:30:47.9711263Z     %b_getattr_l__self___layers___1___attention_kv_cache_past_v_caches : [num_users=1] = placeholder[target=b_getattr_l__self___layers___1___attention_kv_cache_past_v_caches]
2025-03-21T20:30:47.9712517Z     %b__frozen_param117 : [num_users=1] = placeholder[target=b__frozen_param117]
2025-03-21T20:30:47.9713347Z     %b__frozen_param118 : [num_users=1] = placeholder[target=b__frozen_param118]
2025-03-21T20:30:47.9714765Z     %b_getattr_l__self___layers___2___attention_kv_cache_past_k_caches : [num_users=1] = placeholder[target=b_getattr_l__self___layers___2___attention_kv_cache_past_k_caches]
2025-03-21T20:30:47.9716188Z     %b__frozen_param119 : [num_users=1] = placeholder[target=b__frozen_param119]
2025-03-21T20:30:47.9717640Z     %b_getattr_l__self___layers___2___attention_kv_cache_past_v_caches : [num_users=1] = placeholder[target=b_getattr_l__self___layers___2___attention_kv_cache_past_v_caches]
2025-03-21T20:30:47.9719097Z     %b__frozen_param120 : [num_users=1] = placeholder[target=b__frozen_param120]
2025-03-21T20:30:47.9719890Z     %b__frozen_param121 : [num_users=1] = placeholder[target=b__frozen_param121]
2025-03-21T20:30:47.9721226Z     %b_getattr_l__self___layers___3___attention_kv_cache_past_k_caches : [num_users=1] = placeholder[target=b_getattr_l__self___layers___3___attention_kv_cache_past_k_caches]
2025-03-21T20:30:47.9722714Z     %b__frozen_param122 : [num_users=1] = placeholder[target=b__frozen_param122]
2025-03-21T20:30:47.9724358Z     %b_getattr_l__self___layers___3___attention_kv_cache_past_v_caches : [num_users=1] = placeholder[target=b_getattr_l__self___layers___3___attention_kv_cache_past_v_caches]
2025-03-21T20:30:47.9725901Z     %b__frozen_param123 : [num_users=1] = placeholder[target=b__frozen_param123]
2025-03-21T20:30:47.9726816Z     %b__frozen_param124 : [num_users=1] = placeholder[target=b__frozen_param124]
2025-03-21T20:30:47.9728290Z     %b_getattr_l__self___layers___4___attention_kv_cache_past_k_caches : [num_users=1] = placeholder[target=b_getattr_l__self___layers___4___attention_kv_cache_past_k_caches]
2025-03-21T20:30:47.9729903Z     %b__frozen_param125 : [num_users=1] = placeholder[target=b__frozen_param125]
2025-03-21T20:30:47.9731389Z     %b_getattr_l__self___layers___4___attention_kv_cache_past_v_caches : [num_users=1] = placeholder[target=b_getattr_l__self___layers___4___attention_kv_cache_past_v_caches]
2025-03-21T20:30:47.9733049Z     %b__frozen_param126 : [num_users=1] = placeholder[target=b__frozen_param126]
2025-03-21T20:30:47.9733992Z     %b__frozen_param127 : [num_users=1] = placeholder[target=b__frozen_param127]
2025-03-21T20:30:47.9735514Z     %b_getattr_l__self___layers___5___attention_kv_cache_past_k_caches : [num_users=1] = placeholder[target=b_getattr_l__self___layers___5___attention_kv_cache_past_k_caches]
2025-03-21T20:30:47.9737006Z     %b__frozen_param128 : [num_users=1] = placeholder[target=b__frozen_param128]
2025-03-21T20:30:47.9738483Z     %b_getattr_l__self___layers___5___attention_kv_cache_past_v_caches : [num_users=1] = placeholder[target=b_getattr_l__self___layers___5___attention_kv_cache_past_v_caches]
2025-03-21T20:30:47.9739991Z     %b__frozen_param129 : [num_users=1] = placeholder[target=b__frozen_param129]
2025-03-21T20:30:47.9740965Z     %b__frozen_param130 : [num_users=1] = placeholder[target=b__frozen_param130]
2025-03-21T20:30:47.9742474Z     %b_getattr_l__self___layers___6___attention_kv_cache_past_k_caches : [num_users=1] = placeholder[target=b_getattr_l__self___layers___6___attention_kv_cache_past_k_caches]
2025-03-21T20:30:47.9743987Z     %b__frozen_param131 : [num_users=1] = placeholder[target=b__frozen_param131]
2025-03-21T20:30:47.9745534Z     %b_getattr_l__self___layers___6___attention_kv_cache_past_v_caches : [num_users=1] = placeholder[target=b_getattr_l__self___layers___6___attention_kv_cache_past_v_caches]
2025-03-21T20:30:47.9747061Z     %b__frozen_param132 : [num_users=1] = placeholder[target=b__frozen_param132]
2025-03-21T20:30:47.9748034Z     %b__frozen_param133 : [num_users=1] = placeholder[target=b__frozen_param133]
2025-03-21T20:30:47.9749408Z     %b_getattr_l__self___layers___7___attention_kv_cache_past_k_caches : [num_users=1] = placeholder[target=b_getattr_l__self___layers___7___attention_kv_cache_past_k_caches]
2025-03-21T20:30:47.9750814Z     %b__frozen_param134 : [num_users=1] = placeholder[target=b__frozen_param134]
2025-03-21T20:30:47.9752027Z     %b_getattr_l__self___layers___7___attention_kv_cache_past_v_caches : [num_users=1] = placeholder[target=b_getattr_l__self___layers___7___attention_kv_cache_past_v_caches]
2025-03-21T20:30:47.9753269Z     %b__frozen_param135 : [num_users=1] = placeholder[target=b__frozen_param135]
2025-03-21T20:30:47.9754073Z     %b__frozen_param136 : [num_users=1] = placeholder[target=b__frozen_param136]
2025-03-21T20:30:47.9755295Z     %b_getattr_l__self___layers___8___attention_kv_cache_past_k_caches : [num_users=1] = placeholder[target=b_getattr_l__self___layers___8___attention_kv_cache_past_k_caches]
2025-03-21T20:30:47.9756629Z     %b__frozen_param137 : [num_users=1] = placeholder[target=b__frozen_param137]
2025-03-21T20:30:47.9758087Z     %b_getattr_l__self___layers___8___attention_kv_cache_past_v_caches : [num_users=1] = placeholder[target=b_getattr_l__self___layers___8___attention_kv_cache_past_v_caches]
2025-03-21T20:30:47.9759652Z     %b__frozen_param138 : [num_users=1] = placeholder[target=b__frozen_param138]
2025-03-21T20:30:47.9760643Z     %b__frozen_param139 : [num_users=1] = placeholder[target=b__frozen_param139]
2025-03-21T20:30:47.9762414Z     %b_getattr_l__self___layers___9___attention_kv_cache_past_k_caches : [num_users=1] = placeholder[target=b_getattr_l__self___layers___9___attention_kv_cache_past_k_caches]
2025-03-21T20:30:47.9764712Z     %b__frozen_param140 : [num_users=1] = placeholder[target=b__frozen_param140]
2025-03-21T20:30:47.9766279Z     %b_getattr_l__self___layers___9___attention_kv_cache_past_v_caches : [num_users=1] = placeholder[target=b_getattr_l__self___layers___9___attention_kv_cache_past_v_caches]
2025-03-21T20:30:47.9767862Z     %b__frozen_param141 : [num_users=1] = placeholder[target=b__frozen_param141]
2025-03-21T20:30:47.9768869Z     %b__frozen_param142 : [num_users=1] = placeholder[target=b__frozen_param142]
2025-03-21T20:30:47.9770592Z     %b_getattr_l__self___layers___10___attention_kv_cache_past_k_caches : [num_users=1] = placeholder[target=b_getattr_l__self___layers___10___attention_kv_cache_past_k_caches]
2025-03-21T20:30:47.9772199Z     %b__frozen_param143 : [num_users=1] = placeholder[target=b__frozen_param143]
2025-03-21T20:30:47.9773816Z     %b_getattr_l__self___layers___10___attention_kv_cache_past_v_caches : [num_users=1] = placeholder[target=b_getattr_l__self___layers___10___attention_kv_cache_past_v_caches]
2025-03-21T20:30:47.9775420Z     %b__frozen_param144 : [num_users=1] = placeholder[target=b__frozen_param144]
2025-03-21T20:30:47.9776431Z     %b__frozen_param145 : [num_users=1] = placeholder[target=b__frozen_param145]
2025-03-21T20:30:47.9778021Z     %b_getattr_l__self___layers___11___attention_kv_cache_past_k_caches : [num_users=1] = placeholder[target=b_getattr_l__self___layers___11___attention_kv_cache_past_k_caches]
2025-03-21T20:30:47.9779530Z     %b__frozen_param146 : [num_users=1] = placeholder[target=b__frozen_param146]
2025-03-21T20:30:47.9780957Z     %b_getattr_l__self___layers___11___attention_kv_cache_past_v_caches : [num_users=1] = placeholder[target=b_getattr_l__self___layers___11___attention_kv_cache_past_v_caches]
2025-03-21T20:30:47.9782382Z     %b__frozen_param147 : [num_users=1] = placeholder[target=b__frozen_param147]
2025-03-21T20:30:47.9783308Z     %b__frozen_param148 : [num_users=1] = placeholder[target=b__frozen_param148]
2025-03-21T20:30:47.9784208Z     %b__frozen_param149 : [num_users=1] = placeholder[target=b__frozen_param149]
2025-03-21T20:30:47.9785102Z     %b__frozen_param150 : [num_users=1] = placeholder[target=b__frozen_param150]
2025-03-21T20:30:47.9786047Z     %b__frozen_param151 : [num_users=1] = placeholder[target=b__frozen_param151]
2025-03-21T20:30:47.9787037Z     %b__frozen_param152 : [num_users=1] = placeholder[target=b__frozen_param152]
2025-03-21T20:30:47.9788009Z     %b__frozen_param153 : [num_users=1] = placeholder[target=b__frozen_param153]
2025-03-21T20:30:47.9788998Z     %b__frozen_param154 : [num_users=1] = placeholder[target=b__frozen_param154]
2025-03-21T20:30:47.9790005Z     %b__frozen_param155 : [num_users=1] = placeholder[target=b__frozen_param155]
2025-03-21T20:30:47.9790993Z     %b__frozen_param156 : [num_users=1] = placeholder[target=b__frozen_param156]
2025-03-21T20:30:47.9792011Z     %b__frozen_param157 : [num_users=1] = placeholder[target=b__frozen_param157]
2025-03-21T20:30:47.9793030Z     %b__frozen_param158 : [num_users=1] = placeholder[target=b__frozen_param158]
2025-03-21T20:30:47.9794041Z     %b__frozen_param159 : [num_users=1] = placeholder[target=b__frozen_param159]
2025-03-21T20:30:47.9795055Z     %b__frozen_param160 : [num_users=1] = placeholder[target=b__frozen_param160]
2025-03-21T20:30:47.9795929Z     %tokens : [num_users=1] = placeholder[target=tokens]
2025-03-21T20:30:47.9796847Z     %attn_options_input_pos : [num_users=38] = placeholder[target=attn_options_input_pos]
2025-03-21T20:30:47.9798955Z     %dequantize_per_tensor : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param0, 1.9342933228472248e-05, 48293, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:47.9802111Z     %dequantize_per_tensor_1 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param1, 1.2487619642342906e-05, 11698, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:47.9805266Z     %dequantize_per_tensor_2 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param2, 3.4356886317254975e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9808156Z     %dequantize_per_tensor_3 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param3, 3.6641056794906035e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9811112Z     %dequantize_per_tensor_4 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param4, 2.7063433662988245e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9814017Z     %dequantize_per_tensor_5 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param5, 2.292680619575549e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9816879Z     %dequantize_per_tensor_6 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param6, 7.301607183762826e-06, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:47.9819750Z     %dequantize_per_tensor_7 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param7, 1.1212039680685848e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9822603Z     %dequantize_per_tensor_8 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param8, 8.377747690246906e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9825400Z     %dequantize_per_tensor_9 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param9, 1.5975101632648148e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9828203Z     %dequantize_per_tensor_10 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param10, 1.629848702577874e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:47.9831014Z     %dequantize_per_tensor_11 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param11, 2.386650157859549e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9834124Z     %dequantize_per_tensor_12 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param12, 2.1627405658364296e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9837187Z     %dequantize_per_tensor_13 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param13, 3.6092917525820667e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9840253Z     %dequantize_per_tensor_14 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param14, 2.6657653506845236e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9843294Z     %dequantize_per_tensor_15 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param15, 1.0056614883069415e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:47.9846333Z     %dequantize_per_tensor_16 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param16, 1.3041529200563673e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9849662Z     %dequantize_per_tensor_17 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param17, 1.2415116543706972e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9852733Z     %dequantize_per_tensor_18 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param18, 4.851280027651228e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9855430Z     %dequantize_per_tensor_19 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param19, 1.34903066282277e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:47.9858315Z     %dequantize_per_tensor_20 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param20, 1.2616974345291965e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9861377Z     %dequantize_per_tensor_21 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param21, 1.8000935597228818e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9864436Z     %dequantize_per_tensor_22 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param22, 3.838254997390322e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9867505Z     %dequantize_per_tensor_23 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param23, 1.5086939129105303e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9870547Z     %dequantize_per_tensor_24 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param24, 1.2551431609608699e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:47.9873584Z     %dequantize_per_tensor_25 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param25, 7.637921953573823e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9876655Z     %dequantize_per_tensor_26 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param26, 8.152154805429745e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9879422Z     %dequantize_per_tensor_27 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param27, 5.8997531596105546e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9882292Z     %dequantize_per_tensor_28 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param28, 1.4751847629668191e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:47.9885295Z     %dequantize_per_tensor_29 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param29, 1.285897542402381e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9888371Z     %dequantize_per_tensor_30 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param30, 1.776821409293916e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9891502Z     %dequantize_per_tensor_31 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param31, 3.8338889680744614e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9894567Z     %dequantize_per_tensor_32 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param32, 1.043909833242651e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9897603Z     %dequantize_per_tensor_33 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param33, 1.2991034964215942e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:47.9900869Z     %dequantize_per_tensor_34 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param34, 9.01338535186369e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9903745Z     %dequantize_per_tensor_35 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param35, 8.421571692451835e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9906599Z     %dequantize_per_tensor_36 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param36, 5.0727699999697506e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9909426Z     %dequantize_per_tensor_37 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param37, 1.6460680853924714e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:47.9912266Z     %dequantize_per_tensor_38 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param38, 1.0061074135592207e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9915143Z     %dequantize_per_tensor_39 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param39, 1.3427632438833825e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9918002Z     %dequantize_per_tensor_40 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param40, 3.969049885199638e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9920817Z     %dequantize_per_tensor_41 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param41, 4.623624136002036e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9923647Z     %dequantize_per_tensor_42 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param42, 1.4132921023701783e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:47.9926476Z     %dequantize_per_tensor_43 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param43, 9.02163446880877e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9929407Z     %dequantize_per_tensor_44 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param44, 6.684962045255816e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9932113Z     %dequantize_per_tensor_45 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param45, 4.520918082562275e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9935255Z     %dequantize_per_tensor_46 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param46, 1.633507781662047e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:47.9938237Z     %dequantize_per_tensor_47 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param47, 1.2622019312402699e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9941296Z     %dequantize_per_tensor_48 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param48, 1.2933628568134736e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9944365Z     %dequantize_per_tensor_49 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param49, 3.8965881685726345e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9947697Z     %dequantize_per_tensor_50 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param50, 7.438241027557524e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9950731Z     %dequantize_per_tensor_51 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param51, 1.4315685803012457e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:47.9953763Z     %dequantize_per_tensor_52 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param52, 6.619334271817934e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9956474Z     %dequantize_per_tensor_53 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param53, 1.2854585293098353e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9959368Z     %dequantize_per_tensor_54 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param54, 4.18269082729239e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9962340Z     %dequantize_per_tensor_55 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param55, 1.734791112539824e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:47.9965366Z     %dequantize_per_tensor_56 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param56, 1.3876242519472726e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9968446Z     %dequantize_per_tensor_57 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param57, 1.4166372238832992e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9971598Z     %dequantize_per_tensor_58 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param58, 4.262657057552133e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9974657Z     %dequantize_per_tensor_59 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param59, 4.859185082750628e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9977699Z     %dequantize_per_tensor_60 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param60, 1.4755311894987244e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:47.9980568Z     %dequantize_per_tensor_61 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param61, 7.526988156314474e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9983382Z     %dequantize_per_tensor_62 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param62, 5.435513230622746e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9986347Z     %dequantize_per_tensor_63 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param63, 2.4650629711686634e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9989377Z     %dequantize_per_tensor_64 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param64, 1.9291985154268332e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:47.9992411Z     %dequantize_per_tensor_65 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param65, 1.2612830687430687e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9995690Z     %dequantize_per_tensor_66 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param66, 1.120004162658006e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:47.9998751Z     %dequantize_per_tensor_67 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param67, 4.108746452402556e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0001799Z     %dequantize_per_tensor_68 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param68, 4.289444405003451e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0004750Z     %dequantize_per_tensor_69 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param69, 1.58265156642301e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0007459Z     %dequantize_per_tensor_70 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param70, 8.079993676801678e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0010309Z     %dequantize_per_tensor_71 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param71, 5.950272225163644e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0013272Z     %dequantize_per_tensor_72 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param72, 8.790708307060413e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0016303Z     %dequantize_per_tensor_73 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param73, 2.0017856513732113e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0019376Z     %dequantize_per_tensor_74 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param74, 1.0534595276112668e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0022447Z     %dequantize_per_tensor_75 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param75, 9.947799298970494e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0025502Z     %dequantize_per_tensor_76 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param76, 4.18247509514913e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0028552Z     %dequantize_per_tensor_77 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param77, 5.61682645638939e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0031617Z     %dequantize_per_tensor_78 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param78, 1.605357465450652e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0034550Z     %dequantize_per_tensor_79 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param79, 5.956742825219408e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0037444Z     %dequantize_per_tensor_80 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param80, 5.543797669815831e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0040494Z     %dequantize_per_tensor_81 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param81, 1.7314116121269763e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0043834Z     %dequantize_per_tensor_82 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param82, 2.1098459910717793e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0046894Z     %dequantize_per_tensor_83 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param83, 9.977230547519866e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0050059Z     %dequantize_per_tensor_84 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param84, 1.0152723916689865e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0053133Z     %dequantize_per_tensor_85 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param85, 4.536270353128202e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0056211Z     %dequantize_per_tensor_86 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param86, 5.920260718994541e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0058981Z     %dequantize_per_tensor_87 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param87, 1.749423063301947e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0061741Z     %dequantize_per_tensor_88 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param88, 6.546213626279496e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0064523Z     %dequantize_per_tensor_89 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param89, 8.761990102357231e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0067497Z     %dequantize_per_tensor_90 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param90, 1.633228748687543e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0070514Z     %dequantize_per_tensor_91 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param91, 2.414468144706916e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0073542Z     %dequantize_per_tensor_92 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param92, 1.072352006303845e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0076614Z     %dequantize_per_tensor_93 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param93, 1.0837483387149405e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0079713Z     %dequantize_per_tensor_94 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param94, 4.776206424139673e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0082784Z     %dequantize_per_tensor_95 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param95, 7.434290637320373e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0085839Z     %dequantize_per_tensor_96 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param96, 1.9142669771099463e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0088581Z     %dequantize_per_tensor_97 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param97, 9.545610737404786e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0091920Z     %dequantize_per_tensor_98 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param98, 1.0316829502698965e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0094976Z     %dequantize_per_tensor_99 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param99, 2.7532219974091277e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0098041Z     %dequantize_per_tensor_100 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param100, 2.333568590984214e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0101125Z     %dequantize_per_tensor_101 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param101, 1.1849775546579622e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0104258Z     %dequantize_per_tensor_102 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param102, 9.849293746810872e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0107366Z     %dequantize_per_tensor_103 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param103, 5.271489044389455e-06, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0110466Z     %dequantize_per_tensor_104 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param104, 1.626361336093396e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0113371Z     %dequantize_per_tensor_105 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param105, 2.1847066818736494e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0116201Z     %dequantize_per_tensor_106 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param106, 1.223628714797087e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0119111Z     %dequantize_per_tensor_107 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param107, 1.3578906873590313e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0122159Z     %dequantize_per_tensor_108 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param108, 3.873001696774736e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0125216Z     %dequantize_per_tensor_109 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param109, 0.0001457274629501626, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0128330Z     %dequantize_per_tensor_110 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param110, 2.8508189643616788e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0131534Z     %dequantize_per_tensor_111 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param111, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0133753Z     %dequantize_per_tensor_112 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param112, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0135361Z     %dequantize_per_tensor_113 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param113, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0137224Z     %dequantize_per_tensor_114 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param114, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0138831Z     %dequantize_per_tensor_115 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param115, 0.0038910505827516317, 65535, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0140434Z     %dequantize_per_tensor_116 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param116, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0142034Z     %dequantize_per_tensor_117 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param117, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0143634Z     %dequantize_per_tensor_118 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param118, 0.0038910505827516317, 65535, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0145240Z     %dequantize_per_tensor_119 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param119, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0146839Z     %dequantize_per_tensor_120 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param120, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0148442Z     %dequantize_per_tensor_121 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param121, 0.0038910505827516317, 65535, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0150049Z     %dequantize_per_tensor_122 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param122, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0151652Z     %dequantize_per_tensor_123 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param123, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0153253Z     %dequantize_per_tensor_124 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param124, 0.0038910505827516317, 65535, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0154845Z     %dequantize_per_tensor_125 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param125, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0156456Z     %dequantize_per_tensor_126 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param126, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0158058Z     %dequantize_per_tensor_127 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param127, 0.0038910505827516317, 65535, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0159664Z     %dequantize_per_tensor_128 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param128, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0161259Z     %dequantize_per_tensor_129 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param129, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0162951Z     %dequantize_per_tensor_130 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param130, 0.0038910505827516317, 65535, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0164546Z     %dequantize_per_tensor_131 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param131, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0166149Z     %dequantize_per_tensor_132 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param132, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0167751Z     %dequantize_per_tensor_133 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param133, 0.0038910505827516317, 65535, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0169418Z     %dequantize_per_tensor_134 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param134, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0171022Z     %dequantize_per_tensor_135 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param135, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0172620Z     %dequantize_per_tensor_136 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param136, 0.0038910505827516317, 65535, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0174215Z     %dequantize_per_tensor_137 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param137, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0175819Z     %dequantize_per_tensor_138 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param138, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0177418Z     %dequantize_per_tensor_139 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param139, 0.0038910505827516317, 65535, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0179019Z     %dequantize_per_tensor_140 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param140, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0180621Z     %dequantize_per_tensor_141 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param141, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0182212Z     %dequantize_per_tensor_142 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param142, 0.0038910505827516317, 65535, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0183807Z     %dequantize_per_tensor_143 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param143, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0185415Z     %dequantize_per_tensor_144 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param144, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0187066Z     %dequantize_per_tensor_145 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param145, 0.0038910505827516317, 65535, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0188725Z     %dequantize_per_tensor_146 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param146, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0190320Z     %dequantize_per_tensor_147 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param147, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0191925Z     %dequantize_per_tensor_148 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param148, 0.0038910505827516317, 65535, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0193249Z     %embedding : [num_users=1] = call_function[target=torch.ops.aten.embedding.default](args = (%dequantize_per_tensor, %tokens), kwargs = {})
2025-03-21T20:30:48.0194526Z     %quantize_per_tensor : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%embedding, 1.9342933228472248e-05, 48293, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0196093Z     %dequantize_per_tensor_149 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor, 1.9342933228472248e-05, 48293, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0197729Z     %dequantize_per_tensor_150 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor, 1.9342933228472248e-05, 48293, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0199088Z     %index : [num_users=1] = call_function[target=torch.ops.aten.index.Tensor](args = (%dequantize_per_tensor_111, [%attn_options_input_pos]), kwargs = {})
2025-03-21T20:30:48.0200371Z     %quantize_per_tensor_1 : [num_users=12] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0201926Z     %dequantize_per_tensor_151 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0203540Z     %dequantize_per_tensor_152 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0205159Z     %dequantize_per_tensor_153 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0206784Z     %dequantize_per_tensor_154 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0208406Z     %dequantize_per_tensor_155 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0210081Z     %dequantize_per_tensor_156 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0211704Z     %dequantize_per_tensor_157 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0213380Z     %dequantize_per_tensor_158 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0215051Z     %dequantize_per_tensor_159 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0216673Z     %dequantize_per_tensor_160 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0218298Z     %dequantize_per_tensor_161 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0219925Z     %dequantize_per_tensor_162 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0221290Z     %index_1 : [num_users=1] = call_function[target=torch.ops.aten.index.Tensor](args = (%dequantize_per_tensor_112, [%attn_options_input_pos]), kwargs = {})
2025-03-21T20:30:48.0222575Z     %quantize_per_tensor_2 : [num_users=12] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_1, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0224135Z     %dequantize_per_tensor_163 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_2, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0225763Z     %dequantize_per_tensor_164 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_2, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0227393Z     %dequantize_per_tensor_165 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_2, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0229006Z     %dequantize_per_tensor_166 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_2, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0230632Z     %dequantize_per_tensor_167 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_2, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0232440Z     %dequantize_per_tensor_168 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_2, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0234077Z     %dequantize_per_tensor_169 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_2, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0235704Z     %dequantize_per_tensor_170 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_2, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0237337Z     %dequantize_per_tensor_171 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_2, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0239047Z     %dequantize_per_tensor_172 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_2, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0240735Z     %dequantize_per_tensor_173 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_2, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0242358Z     %dequantize_per_tensor_174 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_2, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0243762Z     %rms_norm : [num_users=1] = call_function[target=torch.ops.aten.rms_norm.default](args = (%dequantize_per_tensor_150, [768], %dequantize_per_tensor_1, 1e-05), kwargs = {})
2025-03-21T20:30:48.0245108Z     %quantize_per_tensor_3 : [num_users=3] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%rms_norm, 0.00010396946890978143, 52957, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0246683Z     %dequantize_per_tensor_175 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_3, 0.00010396946890978143, 52957, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0248321Z     %dequantize_per_tensor_176 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_3, 0.00010396946890978143, 52957, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0250016Z     %dequantize_per_tensor_177 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_3, 0.00010396946890978143, 52957, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0251345Z     %unsqueeze : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_177, -1), kwargs = {})
2025-03-21T20:30:48.0252608Z     %quantize_per_tensor_4 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze, 0.00010396946890978143, 52957, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0254184Z     %dequantize_per_tensor_178 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_4, 0.00010396946890978143, 52957, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0255494Z     %transpose : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_178, 1, 2), kwargs = {})
2025-03-21T20:30:48.0256747Z     %quantize_per_tensor_5 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose, 0.00010396946890978143, 52957, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0258320Z     %dequantize_per_tensor_179 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_5, 0.00010396946890978143, 52957, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0259691Z     %conv2d : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_179, %dequantize_per_tensor_2), kwargs = {})
2025-03-21T20:30:48.0260982Z     %quantize_per_tensor_6 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d, 0.0004140927630942315, 29454, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0262540Z     %dequantize_per_tensor_180 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_6, 0.0004140927630942315, 29454, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0263854Z     %transpose_1 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_180, 1, 2), kwargs = {})
2025-03-21T20:30:48.0265212Z     %quantize_per_tensor_7 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_1, 0.0004140927630942315, 29454, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0266785Z     %dequantize_per_tensor_181 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_7, 0.0004140927630942315, 29454, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0268071Z     %squeeze : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_181, -1), kwargs = {})
2025-03-21T20:30:48.0269272Z     %quantize_per_tensor_8 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze, 0.0004140927630942315, 29454, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0270840Z     %dequantize_per_tensor_182 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_8, 0.0004140927630942315, 29454, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0272178Z     %unsqueeze_1 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_176, -1), kwargs = {})
2025-03-21T20:30:48.0273452Z     %quantize_per_tensor_9 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_1, 0.00010396946890978143, 52957, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0275032Z     %dequantize_per_tensor_183 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_9, 0.00010396946890978143, 52957, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0276342Z     %transpose_2 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_183, 1, 2), kwargs = {})
2025-03-21T20:30:48.0277599Z     %quantize_per_tensor_10 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_2, 0.00010396946890978143, 52957, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0279182Z     %dequantize_per_tensor_184 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_10, 0.00010396946890978143, 52957, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0280558Z     %conv2d_1 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_184, %dequantize_per_tensor_3), kwargs = {})
2025-03-21T20:30:48.0281856Z     %quantize_per_tensor_11 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_1, 0.0002585018228273839, 30370, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0283416Z     %dequantize_per_tensor_185 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_11, 0.0002585018228273839, 30370, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0284724Z     %transpose_3 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_185, 1, 2), kwargs = {})
2025-03-21T20:30:48.0285965Z     %quantize_per_tensor_12 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_3, 0.0002585018228273839, 30370, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0287538Z     %dequantize_per_tensor_186 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_12, 0.0002585018228273839, 30370, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0288825Z     %squeeze_1 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_186, -1), kwargs = {})
2025-03-21T20:30:48.0290151Z     %quantize_per_tensor_13 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_1, 0.0002585018228273839, 30370, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0291767Z     %dequantize_per_tensor_187 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_13, 0.0002585018228273839, 30370, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0293097Z     %unsqueeze_2 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_175, -1), kwargs = {})
2025-03-21T20:30:48.0294377Z     %quantize_per_tensor_14 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_2, 0.00010396946890978143, 52957, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0295959Z     %dequantize_per_tensor_188 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_14, 0.00010396946890978143, 52957, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0297273Z     %transpose_4 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_188, 1, 2), kwargs = {})
2025-03-21T20:30:48.0298526Z     %quantize_per_tensor_15 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_4, 0.00010396946890978143, 52957, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0300106Z     %dequantize_per_tensor_189 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_15, 0.00010396946890978143, 52957, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0301478Z     %conv2d_2 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_189, %dequantize_per_tensor_4), kwargs = {})
2025-03-21T20:30:48.0302770Z     %quantize_per_tensor_16 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_2, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0304333Z     %dequantize_per_tensor_190 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_16, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0305645Z     %transpose_5 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_190, 1, 2), kwargs = {})
2025-03-21T20:30:48.0306899Z     %quantize_per_tensor_17 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_5, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0308471Z     %dequantize_per_tensor_191 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_17, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0309760Z     %squeeze_2 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_191, -1), kwargs = {})
2025-03-21T20:30:48.0310973Z     %quantize_per_tensor_18 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_2, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0312533Z     %dequantize_per_tensor_192 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_18, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0313840Z     %view : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_182, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.0315102Z     %quantize_per_tensor_19 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view, 0.0004140927630942315, 29454, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0316693Z     %dequantize_per_tensor_193 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_19, 0.0004140927630942315, 29454, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0318005Z     %view_1 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_187, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.0319222Z     %quantize_per_tensor_20 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_1, 0.0002585018228273839, 30370, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0320775Z     %dequantize_per_tensor_194 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_20, 0.0002585018228273839, 30370, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0322082Z     %view_2 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_192, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.0323310Z     %quantize_per_tensor_21 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_2, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0324865Z     %dequantize_per_tensor_195 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_21, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0326218Z     %_to_copy : [num_users=1] = call_function[target=torch.ops.aten._to_copy.default](args = (%dequantize_per_tensor_193,), kwargs = {dtype: torch.float32})
2025-03-21T20:30:48.0327499Z     %quantize_per_tensor_22 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%_to_copy, 0.0004140927630942315, 29454, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0329062Z     %dequantize_per_tensor_196 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_22, 0.0004140927630942315, 29454, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0330444Z     %view_3 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_196, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:30:48.0331675Z     %quantize_per_tensor_23 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_3, 0.0004140927630942315, 29454, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0333385Z     %dequantize_per_tensor_197 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_23, 0.0004140927630942315, 29454, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0334664Z     %unbind : [num_users=2] = call_function[target=torch.ops.aten.unbind.int](args = (%dequantize_per_tensor_197, -1), kwargs = {})
2025-03-21T20:30:48.0335468Z     %getitem : [num_users=1] = call_function[target=operator.getitem](args = (%unbind, 0), kwargs = {})
2025-03-21T20:30:48.0336193Z     %getitem_1 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind, 1), kwargs = {})
2025-03-21T20:30:48.0337306Z     %quantize_per_tensor_24 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem, 0.00039459901745431125, 27671, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0338874Z     %dequantize_per_tensor_198 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_24, 0.00039459901745431125, 27671, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0340682Z     %dequantize_per_tensor_199 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_24, 0.00039459901745431125, 27671, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0342251Z     %quantize_per_tensor_25 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_1, 0.0003584773512557149, 34023, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0343826Z     %dequantize_per_tensor_200 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_25, 0.0003584773512557149, 34023, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0345463Z     %dequantize_per_tensor_201 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_25, 0.0003584773512557149, 34023, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0346828Z     %_to_copy_1 : [num_users=1] = call_function[target=torch.ops.aten._to_copy.default](args = (%dequantize_per_tensor_194,), kwargs = {dtype: torch.float32})
2025-03-21T20:30:48.0348115Z     %quantize_per_tensor_26 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%_to_copy_1, 0.0002585018228273839, 30370, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0349677Z     %dequantize_per_tensor_202 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_26, 0.0002585018228273839, 30370, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0350997Z     %view_4 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_202, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:30:48.0352243Z     %quantize_per_tensor_27 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_4, 0.0002585018228273839, 30370, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0353802Z     %dequantize_per_tensor_203 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_27, 0.0002585018228273839, 30370, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0355083Z     %unbind_1 : [num_users=2] = call_function[target=torch.ops.aten.unbind.int](args = (%dequantize_per_tensor_203, -1), kwargs = {})
2025-03-21T20:30:48.0355924Z     %getitem_2 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_1, 0), kwargs = {})
2025-03-21T20:30:48.0356675Z     %getitem_3 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_1, 1), kwargs = {})
2025-03-21T20:30:48.0357803Z     %quantize_per_tensor_28 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_2, 0.0002567824558354914, 30134, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0359377Z     %dequantize_per_tensor_204 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_28, 0.0002567824558354914, 30134, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0361015Z     %dequantize_per_tensor_205 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_28, 0.0002567824558354914, 30134, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0362581Z     %quantize_per_tensor_29 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_3, 0.0002435054339002818, 32240, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0364144Z     %dequantize_per_tensor_206 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_29, 0.0002435054339002818, 32240, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0365858Z     %dequantize_per_tensor_207 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_29, 0.0002435054339002818, 32240, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0367164Z     %view_5 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_162, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:30:48.0368380Z     %quantize_per_tensor_30 : [num_users=4] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_5, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0369987Z     %dequantize_per_tensor_208 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_30, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0371623Z     %dequantize_per_tensor_209 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_30, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0373253Z     %dequantize_per_tensor_210 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_30, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0374888Z     %dequantize_per_tensor_211 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_30, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0376186Z     %view_6 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_174, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:30:48.0377407Z     %quantize_per_tensor_31 : [num_users=4] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_6, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0378954Z     %dequantize_per_tensor_212 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_31, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0380578Z     %dequantize_per_tensor_213 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_31, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0382206Z     %dequantize_per_tensor_214 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_31, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0383834Z     %dequantize_per_tensor_215 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_31, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0385168Z     %mul : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_199, %dequantize_per_tensor_211), kwargs = {})
2025-03-21T20:30:48.0386405Z     %quantize_per_tensor_32 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul, 0.0003940780588891357, 27683, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0387951Z     %dequantize_per_tensor_216 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_32, 0.0003940780588891357, 27683, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0389296Z     %mul_1 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_200, %dequantize_per_tensor_214), kwargs = {})
2025-03-21T20:30:48.0390621Z     %quantize_per_tensor_33 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_1, 0.00031320139532908797, 30302, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0392213Z     %dequantize_per_tensor_217 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_33, 0.00031320139532908797, 30302, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0393554Z     %sub : [num_users=1] = call_function[target=torch.ops.aten.sub.Tensor](args = (%dequantize_per_tensor_216, %dequantize_per_tensor_217), kwargs = {})
2025-03-21T20:30:48.0394791Z     %quantize_per_tensor_34 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%sub, 0.000392118061427027, 27719, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0396325Z     %dequantize_per_tensor_218 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_34, 0.000392118061427027, 27719, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0397664Z     %mul_2 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_198, %dequantize_per_tensor_215), kwargs = {})
2025-03-21T20:30:48.0398920Z     %quantize_per_tensor_35 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_2, 0.00019886602240148932, 32650, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0400470Z     %dequantize_per_tensor_219 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_35, 0.00019886602240148932, 32650, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0401817Z     %mul_3 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_201, %dequantize_per_tensor_210), kwargs = {})
2025-03-21T20:30:48.0403048Z     %quantize_per_tensor_36 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_3, 0.000358294986654073, 34007, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0404587Z     %dequantize_per_tensor_220 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_36, 0.000358294986654073, 34007, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0405918Z     %add : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_219, %dequantize_per_tensor_220), kwargs = {})
2025-03-21T20:30:48.0407157Z     %quantize_per_tensor_37 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add, 0.0003606027748901397, 33984, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0408701Z     %dequantize_per_tensor_221 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_37, 0.0003606027748901397, 33984, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0410108Z     %mul_4 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_205, %dequantize_per_tensor_209), kwargs = {})
2025-03-21T20:30:48.0411357Z     %quantize_per_tensor_38 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_4, 0.0002772818843368441, 32772, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0412900Z     %dequantize_per_tensor_222 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_38, 0.0002772818843368441, 32772, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0414249Z     %mul_5 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_206, %dequantize_per_tensor_212), kwargs = {})
2025-03-21T20:30:48.0415557Z     %quantize_per_tensor_39 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_5, 0.00019303792214486748, 32722, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0417158Z     %dequantize_per_tensor_223 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_39, 0.00019303792214486748, 32722, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0418498Z     %sub_1 : [num_users=1] = call_function[target=torch.ops.aten.sub.Tensor](args = (%dequantize_per_tensor_222, %dequantize_per_tensor_223), kwargs = {})
2025-03-21T20:30:48.0419741Z     %quantize_per_tensor_40 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%sub_1, 0.00027735860203392804, 32706, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0421295Z     %dequantize_per_tensor_224 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_40, 0.00027735860203392804, 32706, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0422638Z     %mul_6 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_204, %dequantize_per_tensor_213), kwargs = {})
2025-03-21T20:30:48.0423889Z     %quantize_per_tensor_41 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_6, 0.0002768072590697557, 32698, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0425431Z     %dequantize_per_tensor_225 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_41, 0.0002768072590697557, 32698, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0426770Z     %mul_7 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_207, %dequantize_per_tensor_208), kwargs = {})
2025-03-21T20:30:48.0428014Z     %quantize_per_tensor_42 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_7, 0.0002400432713329792, 32705, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0429563Z     %dequantize_per_tensor_226 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_42, 0.0002400432713329792, 32705, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0430898Z     %add_1 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_225, %dequantize_per_tensor_226), kwargs = {})
2025-03-21T20:30:48.0432141Z     %quantize_per_tensor_43 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_1, 0.0002778804919216782, 32772, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0433878Z     %dequantize_per_tensor_227 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_43, 0.0002778804919216782, 32772, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0435274Z     %stack : [num_users=1] = call_function[target=torch.ops.aten.stack.default](args = ([%dequantize_per_tensor_218, %dequantize_per_tensor_221], -1), kwargs = {})
2025-03-21T20:30:48.0436557Z     %quantize_per_tensor_44 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%stack, 0.0004132623434998095, 29653, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0438100Z     %dequantize_per_tensor_228 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_44, 0.0004132623434998095, 29653, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0439402Z     %view_7 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_228, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.0440706Z     %quantize_per_tensor_45 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_7, 0.0004132623434998095, 29653, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0442314Z     %dequantize_per_tensor_229 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_45, 0.0004132623434998095, 29653, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0443705Z     %stack_1 : [num_users=1] = call_function[target=torch.ops.aten.stack.default](args = ([%dequantize_per_tensor_224, %dequantize_per_tensor_227], -1), kwargs = {})
2025-03-21T20:30:48.0445011Z     %quantize_per_tensor_46 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%stack_1, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0446573Z     %dequantize_per_tensor_230 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_46, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0447883Z     %view_8 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_230, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.0449109Z     %quantize_per_tensor_47 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_8, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0450719Z     %dequantize_per_tensor_231 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_47, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0452086Z     %type_as : [num_users=1] = call_function[target=torch.ops.aten.type_as.default](args = (%dequantize_per_tensor_229, %dequantize_per_tensor_193), kwargs = {})
2025-03-21T20:30:48.0453365Z     %quantize_per_tensor_48 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%type_as, 0.0004132623434998095, 29653, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0454919Z     %dequantize_per_tensor_232 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_48, 0.0004132623434998095, 29653, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0456288Z     %type_as_1 : [num_users=1] = call_function[target=torch.ops.aten.type_as.default](args = (%dequantize_per_tensor_231, %dequantize_per_tensor_194), kwargs = {})
2025-03-21T20:30:48.0457575Z     %quantize_per_tensor_49 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%type_as_1, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0459132Z     %dequantize_per_tensor_233 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_49, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0460448Z     %transpose_6 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_232, 1, 2), kwargs = {})
2025-03-21T20:30:48.0461703Z     %quantize_per_tensor_50 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_6, 0.0004132623434998095, 29653, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0463275Z     %dequantize_per_tensor_234 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_50, 0.0004132623434998095, 29653, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0464771Z     %index_put : [num_users=1] = call_function[target=torch.ops.aten.index_put.default](args = (%dequantize_per_tensor_113, [None, %attn_options_input_pos], %dequantize_per_tensor_233), kwargs = {})
2025-03-21T20:30:48.0466304Z     %quantize_per_tensor_51 : [num_users=13] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_put, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0467869Z     %dequantize_per_tensor_235 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_51, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0469502Z     %dequantize_per_tensor_236 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_51, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0471139Z     %dequantize_per_tensor_237 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_51, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0472775Z     %dequantize_per_tensor_238 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_51, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0474399Z     %dequantize_per_tensor_239 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_51, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0476036Z     %dequantize_per_tensor_240 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_51, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0477673Z     %dequantize_per_tensor_241 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_51, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0479313Z     %dequantize_per_tensor_242 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_51, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0480953Z     %dequantize_per_tensor_243 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_51, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0482592Z     %dequantize_per_tensor_244 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_51, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0484233Z     %dequantize_per_tensor_245 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_51, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0485880Z     %dequantize_per_tensor_246 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_51, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0487511Z     %dequantize_per_tensor_247 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_51, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0489013Z     %index_put_1 : [num_users=1] = call_function[target=torch.ops.aten.index_put.default](args = (%dequantize_per_tensor_114, [None, %attn_options_input_pos], %dequantize_per_tensor_195), kwargs = {})
2025-03-21T20:30:48.0490581Z     %quantize_per_tensor_52 : [num_users=13] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_put_1, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0492209Z     %dequantize_per_tensor_248 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_52, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0493843Z     %dequantize_per_tensor_249 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_52, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0495483Z     %dequantize_per_tensor_250 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_52, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0497124Z     %dequantize_per_tensor_251 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_52, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0498759Z     %dequantize_per_tensor_252 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_52, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0500388Z     %dequantize_per_tensor_253 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_52, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0502009Z     %dequantize_per_tensor_254 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_52, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0503643Z     %dequantize_per_tensor_255 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_52, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0505281Z     %dequantize_per_tensor_256 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_52, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0506915Z     %dequantize_per_tensor_257 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_52, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0508551Z     %dequantize_per_tensor_258 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_52, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0510192Z     %dequantize_per_tensor_259 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_52, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0511829Z     %dequantize_per_tensor_260 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_52, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0513144Z     %transpose_7 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_247, 1, 2), kwargs = {})
2025-03-21T20:30:48.0514397Z     %quantize_per_tensor_53 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_7, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0515970Z     %dequantize_per_tensor_261 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_53, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0517372Z     %select : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_261, 0, 0), kwargs = {})
2025-03-21T20:30:48.0518578Z     %quantize_per_tensor_54 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0520135Z     %dequantize_per_tensor_262 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_54, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0521418Z     %select_1 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_262, 0, 0), kwargs = {})
2025-03-21T20:30:48.0522618Z     %quantize_per_tensor_55 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_1, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0524184Z     %dequantize_per_tensor_263 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_55, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0525493Z     %transpose_8 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_246, 1, 2), kwargs = {})
2025-03-21T20:30:48.0526744Z     %quantize_per_tensor_56 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_8, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0528314Z     %dequantize_per_tensor_264 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_56, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0529660Z     %select_2 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_264, 0, 0), kwargs = {})
2025-03-21T20:30:48.0530875Z     %quantize_per_tensor_57 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_2, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0532645Z     %dequantize_per_tensor_265 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_57, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0533933Z     %select_3 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_265, 0, 1), kwargs = {})
2025-03-21T20:30:48.0535151Z     %quantize_per_tensor_58 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_3, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0536720Z     %dequantize_per_tensor_266 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_58, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0538024Z     %transpose_9 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_245, 1, 2), kwargs = {})
2025-03-21T20:30:48.0539275Z     %quantize_per_tensor_59 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_9, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0540852Z     %dequantize_per_tensor_267 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_59, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0542237Z     %select_4 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_267, 0, 0), kwargs = {})
2025-03-21T20:30:48.0543512Z     %quantize_per_tensor_60 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_4, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0545075Z     %dequantize_per_tensor_268 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_60, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0546351Z     %select_5 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_268, 0, 2), kwargs = {})
2025-03-21T20:30:48.0547559Z     %quantize_per_tensor_61 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_5, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0549126Z     %dequantize_per_tensor_269 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_61, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0550438Z     %transpose_10 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_244, 1, 2), kwargs = {})
2025-03-21T20:30:48.0551693Z     %quantize_per_tensor_62 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_10, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0553271Z     %dequantize_per_tensor_270 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_62, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0554540Z     %select_6 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_270, 0, 0), kwargs = {})
2025-03-21T20:30:48.0555750Z     %quantize_per_tensor_63 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_6, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0557307Z     %dequantize_per_tensor_271 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_63, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0558584Z     %select_7 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_271, 0, 3), kwargs = {})
2025-03-21T20:30:48.0559789Z     %quantize_per_tensor_64 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_7, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0561354Z     %dequantize_per_tensor_272 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_64, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0562664Z     %transpose_11 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_243, 1, 2), kwargs = {})
2025-03-21T20:30:48.0563917Z     %quantize_per_tensor_65 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_11, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0565492Z     %dequantize_per_tensor_273 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_65, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0566826Z     %select_8 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_273, 0, 0), kwargs = {})
2025-03-21T20:30:48.0568099Z     %quantize_per_tensor_66 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_8, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0569712Z     %dequantize_per_tensor_274 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_66, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0570979Z     %select_9 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_274, 0, 4), kwargs = {})
2025-03-21T20:30:48.0572184Z     %quantize_per_tensor_67 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_9, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0573744Z     %dequantize_per_tensor_275 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_67, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0575060Z     %transpose_12 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_242, 1, 2), kwargs = {})
2025-03-21T20:30:48.0576319Z     %quantize_per_tensor_68 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_12, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0577896Z     %dequantize_per_tensor_276 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_68, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0579178Z     %select_10 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_276, 0, 0), kwargs = {})
2025-03-21T20:30:48.0580394Z     %quantize_per_tensor_69 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_10, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0581955Z     %dequantize_per_tensor_277 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_69, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0583235Z     %select_11 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_277, 0, 5), kwargs = {})
2025-03-21T20:30:48.0584435Z     %quantize_per_tensor_70 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_11, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0585988Z     %dequantize_per_tensor_278 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_70, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0587308Z     %transpose_13 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_241, 1, 2), kwargs = {})
2025-03-21T20:30:48.0588561Z     %quantize_per_tensor_71 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_13, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0590134Z     %dequantize_per_tensor_279 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_71, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0591412Z     %select_12 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_279, 0, 0), kwargs = {})
2025-03-21T20:30:48.0592720Z     %quantize_per_tensor_72 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_12, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0594282Z     %dequantize_per_tensor_280 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_72, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0595557Z     %select_13 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_280, 0, 6), kwargs = {})
2025-03-21T20:30:48.0596767Z     %quantize_per_tensor_73 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_13, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0598327Z     %dequantize_per_tensor_281 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_73, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0599636Z     %transpose_14 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_240, 1, 2), kwargs = {})
2025-03-21T20:30:48.0600891Z     %quantize_per_tensor_74 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_14, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0602446Z     %dequantize_per_tensor_282 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_74, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0603723Z     %select_14 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_282, 0, 0), kwargs = {})
2025-03-21T20:30:48.0604935Z     %quantize_per_tensor_75 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_14, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0606494Z     %dequantize_per_tensor_283 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_75, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0607772Z     %select_15 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_283, 0, 7), kwargs = {})
2025-03-21T20:30:48.0608980Z     %quantize_per_tensor_76 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_15, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0610602Z     %dequantize_per_tensor_284 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_76, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0611911Z     %transpose_15 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_239, 1, 2), kwargs = {})
2025-03-21T20:30:48.0613160Z     %quantize_per_tensor_77 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_15, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0614731Z     %dequantize_per_tensor_285 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_77, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0616004Z     %select_16 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_285, 0, 0), kwargs = {})
2025-03-21T20:30:48.0617261Z     %quantize_per_tensor_78 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_16, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0618846Z     %dequantize_per_tensor_286 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_78, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0620118Z     %select_17 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_286, 0, 8), kwargs = {})
2025-03-21T20:30:48.0621320Z     %quantize_per_tensor_79 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_17, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0622876Z     %dequantize_per_tensor_287 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_79, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0624185Z     %transpose_16 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_238, 1, 2), kwargs = {})
2025-03-21T20:30:48.0625432Z     %quantize_per_tensor_80 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_16, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0627000Z     %dequantize_per_tensor_288 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_80, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0628271Z     %select_18 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_288, 0, 0), kwargs = {})
2025-03-21T20:30:48.0629475Z     %quantize_per_tensor_81 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_18, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0631034Z     %dequantize_per_tensor_289 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_81, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0632498Z     %select_19 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_289, 0, 9), kwargs = {})
2025-03-21T20:30:48.0633697Z     %quantize_per_tensor_82 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_19, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0635265Z     %dequantize_per_tensor_290 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_82, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0636580Z     %transpose_17 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_237, 1, 2), kwargs = {})
2025-03-21T20:30:48.0637832Z     %quantize_per_tensor_83 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_17, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0639405Z     %dequantize_per_tensor_291 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_83, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0640678Z     %select_20 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_291, 0, 0), kwargs = {})
2025-03-21T20:30:48.0641960Z     %quantize_per_tensor_84 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_20, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0643576Z     %dequantize_per_tensor_292 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_84, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0644856Z     %select_21 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_292, 0, 10), kwargs = {})
2025-03-21T20:30:48.0646068Z     %quantize_per_tensor_85 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_21, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0647624Z     %dequantize_per_tensor_293 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_85, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0648940Z     %transpose_18 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_236, 1, 2), kwargs = {})
2025-03-21T20:30:48.0650241Z     %quantize_per_tensor_86 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_18, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0651809Z     %dequantize_per_tensor_294 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_86, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0653090Z     %select_22 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_294, 0, 0), kwargs = {})
2025-03-21T20:30:48.0654299Z     %quantize_per_tensor_87 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_22, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0655857Z     %dequantize_per_tensor_295 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_87, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0657127Z     %select_23 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_295, 0, 11), kwargs = {})
2025-03-21T20:30:48.0658336Z     %quantize_per_tensor_88 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_23, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0659889Z     %dequantize_per_tensor_296 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_88, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0662202Z     %cat : [num_users=1] = call_function[target=torch.ops.aten.cat.default](args = ([%dequantize_per_tensor_263, %dequantize_per_tensor_266, %dequantize_per_tensor_269, %dequantize_per_tensor_272, %dequantize_per_tensor_275, %dequantize_per_tensor_278, %dequantize_per_tensor_281, %dequantize_per_tensor_284, %dequantize_per_tensor_287, %dequantize_per_tensor_290, %dequantize_per_tensor_293, %dequantize_per_tensor_296],), kwargs = {})
2025-03-21T20:30:48.0664410Z     %quantize_per_tensor_89 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%cat, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0665945Z     %dequantize_per_tensor_297 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_89, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0667303Z     %view_9 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_297, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:30:48.0668583Z     %quantize_per_tensor_90 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_9, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0670125Z     %dequantize_per_tensor_298 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_90, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0671423Z     %transpose_19 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_260, 1, 2), kwargs = {})
2025-03-21T20:30:48.0672680Z     %quantize_per_tensor_91 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_19, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0674271Z     %dequantize_per_tensor_299 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_91, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0675546Z     %select_24 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_299, 0, 0), kwargs = {})
2025-03-21T20:30:48.0676750Z     %quantize_per_tensor_92 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_24, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0678313Z     %dequantize_per_tensor_300 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_92, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0679591Z     %select_25 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_300, 0, 0), kwargs = {})
2025-03-21T20:30:48.0680799Z     %quantize_per_tensor_93 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_25, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0682359Z     %dequantize_per_tensor_301 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_93, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0683664Z     %transpose_20 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_259, 1, 2), kwargs = {})
2025-03-21T20:30:48.0684910Z     %quantize_per_tensor_94 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_20, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0686497Z     %dequantize_per_tensor_302 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_94, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0687765Z     %select_26 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_302, 0, 0), kwargs = {})
2025-03-21T20:30:48.0688983Z     %quantize_per_tensor_95 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_26, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0690624Z     %dequantize_per_tensor_303 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_95, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0691963Z     %select_27 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_303, 0, 1), kwargs = {})
2025-03-21T20:30:48.0693219Z     %quantize_per_tensor_96 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_27, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0694789Z     %dequantize_per_tensor_304 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_96, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0696105Z     %transpose_21 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_258, 1, 2), kwargs = {})
2025-03-21T20:30:48.0697362Z     %quantize_per_tensor_97 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_21, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0698956Z     %dequantize_per_tensor_305 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_97, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0700231Z     %select_28 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_305, 0, 0), kwargs = {})
2025-03-21T20:30:48.0701440Z     %quantize_per_tensor_98 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_28, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0703006Z     %dequantize_per_tensor_306 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_98, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0704270Z     %select_29 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_306, 0, 2), kwargs = {})
2025-03-21T20:30:48.0728906Z     %quantize_per_tensor_99 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_29, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0730685Z     %dequantize_per_tensor_307 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_99, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0731999Z     %transpose_22 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_257, 1, 2), kwargs = {})
2025-03-21T20:30:48.0733457Z     %quantize_per_tensor_100 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_22, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0735061Z     %dequantize_per_tensor_308 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_100, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0736340Z     %select_30 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_308, 0, 0), kwargs = {})
2025-03-21T20:30:48.0737541Z     %quantize_per_tensor_101 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_30, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0739108Z     %dequantize_per_tensor_309 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_101, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0740381Z     %select_31 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_309, 0, 3), kwargs = {})
2025-03-21T20:30:48.0741797Z     %quantize_per_tensor_102 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_31, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0743367Z     %dequantize_per_tensor_310 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_102, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0744689Z     %transpose_23 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_256, 1, 2), kwargs = {})
2025-03-21T20:30:48.0745953Z     %quantize_per_tensor_103 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_23, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0747535Z     %dequantize_per_tensor_311 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_103, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0748820Z     %select_32 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_311, 0, 0), kwargs = {})
2025-03-21T20:30:48.0750029Z     %quantize_per_tensor_104 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_32, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0751589Z     %dequantize_per_tensor_312 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_104, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0752872Z     %select_33 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_312, 0, 4), kwargs = {})
2025-03-21T20:30:48.0754098Z     %quantize_per_tensor_105 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_33, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0755670Z     %dequantize_per_tensor_313 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_105, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0756982Z     %transpose_24 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_255, 1, 2), kwargs = {})
2025-03-21T20:30:48.0758227Z     %quantize_per_tensor_106 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_24, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0759806Z     %dequantize_per_tensor_314 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_106, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0761082Z     %select_34 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_314, 0, 0), kwargs = {})
2025-03-21T20:30:48.0762304Z     %quantize_per_tensor_107 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_34, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0763871Z     %dequantize_per_tensor_315 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_107, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0765148Z     %select_35 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_315, 0, 5), kwargs = {})
2025-03-21T20:30:48.0766460Z     %quantize_per_tensor_108 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_35, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0768021Z     %dequantize_per_tensor_316 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_108, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0769401Z     %transpose_25 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_254, 1, 2), kwargs = {})
2025-03-21T20:30:48.0770662Z     %quantize_per_tensor_109 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_25, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0772244Z     %dequantize_per_tensor_317 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_109, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0773527Z     %select_36 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_317, 0, 0), kwargs = {})
2025-03-21T20:30:48.0774729Z     %quantize_per_tensor_110 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_36, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0776289Z     %dequantize_per_tensor_318 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_110, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0777565Z     %select_37 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_318, 0, 6), kwargs = {})
2025-03-21T20:30:48.0778776Z     %quantize_per_tensor_111 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_37, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0780346Z     %dequantize_per_tensor_319 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_111, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0781658Z     %transpose_26 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_253, 1, 2), kwargs = {})
2025-03-21T20:30:48.0782909Z     %quantize_per_tensor_112 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_26, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0784490Z     %dequantize_per_tensor_320 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_112, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0785775Z     %select_38 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_320, 0, 0), kwargs = {})
2025-03-21T20:30:48.0786979Z     %quantize_per_tensor_113 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_38, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0788552Z     %dequantize_per_tensor_321 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_113, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0789837Z     %select_39 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_321, 0, 7), kwargs = {})
2025-03-21T20:30:48.0791092Z     %quantize_per_tensor_114 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_39, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0792717Z     %dequantize_per_tensor_322 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_114, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0794036Z     %transpose_27 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_252, 1, 2), kwargs = {})
2025-03-21T20:30:48.0795289Z     %quantize_per_tensor_115 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_27, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0796879Z     %dequantize_per_tensor_323 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_115, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0798172Z     %select_40 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_323, 0, 0), kwargs = {})
2025-03-21T20:30:48.0799376Z     %quantize_per_tensor_116 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_40, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0800950Z     %dequantize_per_tensor_324 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_116, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0802235Z     %select_41 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_324, 0, 8), kwargs = {})
2025-03-21T20:30:48.0803436Z     %quantize_per_tensor_117 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_41, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0805012Z     %dequantize_per_tensor_325 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_117, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0806317Z     %transpose_28 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_251, 1, 2), kwargs = {})
2025-03-21T20:30:48.0807564Z     %quantize_per_tensor_118 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_28, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0809150Z     %dequantize_per_tensor_326 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_118, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0810501Z     %select_42 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_326, 0, 0), kwargs = {})
2025-03-21T20:30:48.0811703Z     %quantize_per_tensor_119 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_42, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0813278Z     %dequantize_per_tensor_327 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_119, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0814562Z     %select_43 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_327, 0, 9), kwargs = {})
2025-03-21T20:30:48.0815826Z     %quantize_per_tensor_120 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_43, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0817449Z     %dequantize_per_tensor_328 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_120, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0818757Z     %transpose_29 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_250, 1, 2), kwargs = {})
2025-03-21T20:30:48.0820013Z     %quantize_per_tensor_121 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_29, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0821599Z     %dequantize_per_tensor_329 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_121, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0822888Z     %select_44 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_329, 0, 0), kwargs = {})
2025-03-21T20:30:48.0824079Z     %quantize_per_tensor_122 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_44, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0825641Z     %dequantize_per_tensor_330 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_122, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0826916Z     %select_45 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_330, 0, 10), kwargs = {})
2025-03-21T20:30:48.0828130Z     %quantize_per_tensor_123 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_45, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0829684Z     %dequantize_per_tensor_331 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_123, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0831000Z     %transpose_30 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_249, 1, 2), kwargs = {})
2025-03-21T20:30:48.0832400Z     %quantize_per_tensor_124 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_30, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0834002Z     %dequantize_per_tensor_332 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_124, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0835277Z     %select_46 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_332, 0, 0), kwargs = {})
2025-03-21T20:30:48.0836497Z     %quantize_per_tensor_125 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_46, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0838066Z     %dequantize_per_tensor_333 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_125, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0839348Z     %select_47 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_333, 0, 11), kwargs = {})
2025-03-21T20:30:48.0840637Z     %quantize_per_tensor_126 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_47, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0842262Z     %dequantize_per_tensor_334 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_126, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0844588Z     %cat_1 : [num_users=1] = call_function[target=torch.ops.aten.cat.default](args = ([%dequantize_per_tensor_301, %dequantize_per_tensor_304, %dequantize_per_tensor_307, %dequantize_per_tensor_310, %dequantize_per_tensor_313, %dequantize_per_tensor_316, %dequantize_per_tensor_319, %dequantize_per_tensor_322, %dequantize_per_tensor_325, %dequantize_per_tensor_328, %dequantize_per_tensor_331, %dequantize_per_tensor_334],), kwargs = {})
2025-03-21T20:30:48.0846812Z     %quantize_per_tensor_127 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%cat_1, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0848369Z     %dequantize_per_tensor_335 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_127, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0849740Z     %view_10 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_335, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:30:48.0850972Z     %quantize_per_tensor_128 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_10, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0852532Z     %dequantize_per_tensor_336 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_128, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0854171Z     %quantize_per_tensor_129 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%dequantize_per_tensor_336, 2.6003737730206922e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0855812Z     %dequantize_per_tensor_337 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_129, 2.6003737730206922e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0857176Z     %index_2 : [num_users=1] = call_function[target=torch.ops.aten.index.Tensor](args = (%dequantize_per_tensor_115, [%attn_options_input_pos]), kwargs = {})
2025-03-21T20:30:48.0858459Z     %quantize_per_tensor_130 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_2, 0.0038910505827516317, 65535, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0860018Z     %dequantize_per_tensor_338 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_130, 0.0038910505827516317, 65535, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0861336Z     %transpose_31 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_298, -2, -1), kwargs = {})
2025-03-21T20:30:48.0862607Z     %quantize_per_tensor_131 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_31, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0864168Z     %dequantize_per_tensor_339 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_131, 0.0002779011847451329, 32770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0865855Z     %quantize_per_tensor_132 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%dequantize_per_tensor_339, 0.00027792342007160187, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0867546Z     %dequantize_per_tensor_340 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_132, 0.00027792342007160187, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.0868923Z     %matmul : [num_users=1] = call_function[target=torch.ops.aten.matmul.default](args = (%dequantize_per_tensor_234, %dequantize_per_tensor_340), kwargs = {})
2025-03-21T20:30:48.0870220Z     %quantize_per_tensor_133 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%matmul, 0.006018729880452156, 34998, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0871763Z     %dequantize_per_tensor_341 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_133, 0.006018729880452156, 34998, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0873379Z     %dequantize_per_tensor_342 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param149, 1.9073777366429567e-06, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0874693Z     %mul_8 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_341, %dequantize_per_tensor_342), kwargs = {})
2025-03-21T20:30:48.0875925Z     %quantize_per_tensor_134 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_8, 0.0007523412350565195, 34998, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0877480Z     %dequantize_per_tensor_343 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_134, 0.0007523412350565195, 34998, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0878818Z     %add_2 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_343, %dequantize_per_tensor_338), kwargs = {})
2025-03-21T20:30:48.0880064Z     %quantize_per_tensor_135 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_2, 0.00445493683218956, 61746, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0881582Z     %dequantize_per_tensor_344 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_135, 0.00445493683218956, 61746, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0882832Z     %softmax : [num_users=1] = call_function[target=torch.ops.aten.softmax.int](args = (%dequantize_per_tensor_344, -1), kwargs = {})
2025-03-21T20:30:48.0884017Z     %quantize_per_tensor_136 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%softmax, 1.5259021893143654e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0885554Z     %dequantize_per_tensor_345 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_136, 1.5259021893143654e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0886921Z     %matmul_1 : [num_users=1] = call_function[target=torch.ops.aten.matmul.default](args = (%dequantize_per_tensor_345, %dequantize_per_tensor_337), kwargs = {})
2025-03-21T20:30:48.0888227Z     %quantize_per_tensor_137 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%matmul_1, 2.0544466678984463e-05, 35449, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0889850Z     %dequantize_per_tensor_346 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_137, 2.0544466678984463e-05, 35449, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0891270Z     %transpose_32 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_346, 1, 2), kwargs = {})
2025-03-21T20:30:48.0892527Z     %quantize_per_tensor_138 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_32, 2.0544466678984463e-05, 35449, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0894107Z     %dequantize_per_tensor_347 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_138, 2.0544466678984463e-05, 35449, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0895417Z     %view_11 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_347, [1, 1, 768]), kwargs = {})
2025-03-21T20:30:48.0896643Z     %quantize_per_tensor_139 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_11, 2.0544466678984463e-05, 35449, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0898199Z     %dequantize_per_tensor_348 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_139, 2.0544466678984463e-05, 35449, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0899522Z     %unsqueeze_3 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_348, -1), kwargs = {})
2025-03-21T20:30:48.0900789Z     %quantize_per_tensor_140 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_3, 2.0544466678984463e-05, 35449, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0902361Z     %dequantize_per_tensor_349 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_140, 2.0544466678984463e-05, 35449, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0903673Z     %transpose_33 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_349, 1, 2), kwargs = {})
2025-03-21T20:30:48.0904931Z     %quantize_per_tensor_141 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_33, 2.0544466678984463e-05, 35449, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0906515Z     %dequantize_per_tensor_350 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_141, 2.0544466678984463e-05, 35449, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0907879Z     %conv2d_3 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_350, %dequantize_per_tensor_5), kwargs = {})
2025-03-21T20:30:48.0909186Z     %quantize_per_tensor_142 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_3, 2.3234304535435513e-05, 31262, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0910749Z     %dequantize_per_tensor_351 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_142, 2.3234304535435513e-05, 31262, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0912057Z     %transpose_34 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_351, 1, 2), kwargs = {})
2025-03-21T20:30:48.0913306Z     %quantize_per_tensor_143 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_34, 2.3234304535435513e-05, 31262, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0914891Z     %dequantize_per_tensor_352 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_143, 2.3234304535435513e-05, 31262, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0916275Z     %squeeze_3 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_352, -1), kwargs = {})
2025-03-21T20:30:48.0917483Z     %quantize_per_tensor_144 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_3, 2.3234304535435513e-05, 31262, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0919044Z     %dequantize_per_tensor_353 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_144, 2.3234304535435513e-05, 31262, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0920393Z     %add_3 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_149, %dequantize_per_tensor_353), kwargs = {})
2025-03-21T20:30:48.0921649Z     %quantize_per_tensor_145 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_3, 2.3993761715246364e-05, 31139, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0923220Z     %dequantize_per_tensor_354 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_145, 2.3993761715246364e-05, 31139, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0924862Z     %dequantize_per_tensor_355 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_145, 2.3993761715246364e-05, 31139, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0926277Z     %rms_norm_1 : [num_users=1] = call_function[target=torch.ops.aten.rms_norm.default](args = (%dequantize_per_tensor_355, [768], %dequantize_per_tensor_6, 1e-05), kwargs = {})
2025-03-21T20:30:48.0927608Z     %quantize_per_tensor_146 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%rms_norm_1, 6.304631824605167e-05, 32297, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0929183Z     %dequantize_per_tensor_356 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_146, 6.304631824605167e-05, 32297, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0930879Z     %dequantize_per_tensor_357 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_146, 6.304631824605167e-05, 32297, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0932208Z     %unsqueeze_4 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_357, -1), kwargs = {})
2025-03-21T20:30:48.0933634Z     %quantize_per_tensor_147 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_4, 6.304631824605167e-05, 32297, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0935197Z     %dequantize_per_tensor_358 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_147, 6.304631824605167e-05, 32297, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0936512Z     %transpose_35 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_358, 1, 2), kwargs = {})
2025-03-21T20:30:48.0937760Z     %quantize_per_tensor_148 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_35, 6.304631824605167e-05, 32297, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0939332Z     %dequantize_per_tensor_359 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_148, 6.304631824605167e-05, 32297, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0940695Z     %conv2d_4 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_359, %dequantize_per_tensor_7), kwargs = {})
2025-03-21T20:30:48.0942180Z     %quantize_per_tensor_149 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_4, 0.00015858362894505262, 37454, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0943757Z     %dequantize_per_tensor_360 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_149, 0.00015858362894505262, 37454, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0945073Z     %transpose_36 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_360, 1, 2), kwargs = {})
2025-03-21T20:30:48.0946320Z     %quantize_per_tensor_150 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_36, 0.00015858362894505262, 37454, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0947897Z     %dequantize_per_tensor_361 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_150, 0.00015858362894505262, 37454, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0949174Z     %squeeze_4 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_361, -1), kwargs = {})
2025-03-21T20:30:48.0950393Z     %quantize_per_tensor_151 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_4, 0.00015858362894505262, 37454, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0951960Z     %dequantize_per_tensor_362 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_151, 0.00015858362894505262, 37454, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0953597Z     %dequantize_per_tensor_363 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_151, 0.00015858362894505262, 37454, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0954889Z     %sigmoid : [num_users=1] = call_function[target=torch.ops.aten.sigmoid.default](args = (%dequantize_per_tensor_363,), kwargs = {})
2025-03-21T20:30:48.0956076Z     %quantize_per_tensor_152 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%sigmoid, 1.52587890625e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0957570Z     %dequantize_per_tensor_364 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_152, 1.52587890625e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0958883Z     %mul_9 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_362, %dequantize_per_tensor_364), kwargs = {})
2025-03-21T20:30:48.0960123Z     %quantize_per_tensor_153 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_9, 7.141960668377578e-05, 3899, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0961653Z     %dequantize_per_tensor_365 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_153, 7.141960668377578e-05, 3899, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0962975Z     %unsqueeze_5 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_356, -1), kwargs = {})
2025-03-21T20:30:48.0964232Z     %quantize_per_tensor_154 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_5, 6.304631824605167e-05, 32297, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0965861Z     %dequantize_per_tensor_366 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_154, 6.304631824605167e-05, 32297, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0967205Z     %transpose_37 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_366, 1, 2), kwargs = {})
2025-03-21T20:30:48.0968461Z     %quantize_per_tensor_155 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_37, 6.304631824605167e-05, 32297, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0970097Z     %dequantize_per_tensor_367 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_155, 6.304631824605167e-05, 32297, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0971457Z     %conv2d_5 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_367, %dequantize_per_tensor_8), kwargs = {})
2025-03-21T20:30:48.0972745Z     %quantize_per_tensor_156 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_5, 0.00017520938126835972, 26511, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0974324Z     %dequantize_per_tensor_368 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_156, 0.00017520938126835972, 26511, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0975642Z     %transpose_38 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_368, 1, 2), kwargs = {})
2025-03-21T20:30:48.0976901Z     %quantize_per_tensor_157 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_38, 0.00017520938126835972, 26511, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0978492Z     %dequantize_per_tensor_369 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_157, 0.00017520938126835972, 26511, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0979784Z     %squeeze_5 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_369, -1), kwargs = {})
2025-03-21T20:30:48.0981002Z     %quantize_per_tensor_158 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_5, 0.00017520938126835972, 26511, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0982574Z     %dequantize_per_tensor_370 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_158, 0.00017520938126835972, 26511, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0983928Z     %mul_10 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_365, %dequantize_per_tensor_370), kwargs = {})
2025-03-21T20:30:48.0985181Z     %quantize_per_tensor_159 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_10, 0.00046910217497497797, 34492, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0986737Z     %dequantize_per_tensor_371 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_159, 0.00046910217497497797, 34492, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0988070Z     %unsqueeze_6 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_371, -1), kwargs = {})
2025-03-21T20:30:48.0989343Z     %quantize_per_tensor_160 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_6, 0.00046910217497497797, 34492, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0990983Z     %dequantize_per_tensor_372 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_160, 0.00046910217497497797, 34492, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0992355Z     %transpose_39 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_372, 1, 2), kwargs = {})
2025-03-21T20:30:48.0993616Z     %quantize_per_tensor_161 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_39, 0.00046910217497497797, 34492, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0995201Z     %dequantize_per_tensor_373 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_161, 0.00046910217497497797, 34492, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0996569Z     %conv2d_6 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_373, %dequantize_per_tensor_9), kwargs = {})
2025-03-21T20:30:48.0997868Z     %quantize_per_tensor_162 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_6, 0.00015648982662241906, 29373, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.0999445Z     %dequantize_per_tensor_374 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_162, 0.00015648982662241906, 29373, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1000758Z     %transpose_40 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_374, 1, 2), kwargs = {})
2025-03-21T20:30:48.1002007Z     %quantize_per_tensor_163 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_40, 0.00015648982662241906, 29373, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1003590Z     %dequantize_per_tensor_375 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_163, 0.00015648982662241906, 29373, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1004878Z     %squeeze_6 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_375, -1), kwargs = {})
2025-03-21T20:30:48.1006091Z     %quantize_per_tensor_164 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_6, 0.00015648982662241906, 29373, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1007662Z     %dequantize_per_tensor_376 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_164, 0.00015648982662241906, 29373, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1009000Z     %add_4 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_354, %dequantize_per_tensor_376), kwargs = {})
2025-03-21T20:30:48.1010303Z     %quantize_per_tensor_165 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_4, 0.0001625629374757409, 28917, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1011851Z     %dequantize_per_tensor_377 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_165, 0.0001625629374757409, 28917, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1013484Z     %dequantize_per_tensor_378 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_165, 0.0001625629374757409, 28917, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1014899Z     %rms_norm_2 : [num_users=1] = call_function[target=torch.ops.aten.rms_norm.default](args = (%dequantize_per_tensor_378, [768], %dequantize_per_tensor_10, 1e-05), kwargs = {})
2025-03-21T20:30:48.1016302Z     %quantize_per_tensor_166 : [num_users=3] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%rms_norm_2, 0.0002292444696649909, 31927, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1017909Z     %dequantize_per_tensor_379 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_166, 0.0002292444696649909, 31927, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1019538Z     %dequantize_per_tensor_380 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_166, 0.0002292444696649909, 31927, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1021165Z     %dequantize_per_tensor_381 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_166, 0.0002292444696649909, 31927, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1022483Z     %unsqueeze_7 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_381, -1), kwargs = {})
2025-03-21T20:30:48.1023748Z     %quantize_per_tensor_167 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_7, 0.0002292444696649909, 31927, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1025330Z     %dequantize_per_tensor_382 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_167, 0.0002292444696649909, 31927, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1026641Z     %transpose_41 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_382, 1, 2), kwargs = {})
2025-03-21T20:30:48.1027893Z     %quantize_per_tensor_168 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_41, 0.0002292444696649909, 31927, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1029471Z     %dequantize_per_tensor_383 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_168, 0.0002292444696649909, 31927, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1030846Z     %conv2d_7 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_383, %dequantize_per_tensor_11), kwargs = {})
2025-03-21T20:30:48.1032142Z     %quantize_per_tensor_169 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_7, 0.0005588589119724929, 30540, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1033872Z     %dequantize_per_tensor_384 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_169, 0.0005588589119724929, 30540, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1035188Z     %transpose_42 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_384, 1, 2), kwargs = {})
2025-03-21T20:30:48.1036450Z     %quantize_per_tensor_170 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_42, 0.0005588589119724929, 30540, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1038029Z     %dequantize_per_tensor_385 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_170, 0.0005588589119724929, 30540, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1039304Z     %squeeze_7 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_385, -1), kwargs = {})
2025-03-21T20:30:48.1040518Z     %quantize_per_tensor_171 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_7, 0.0005588589119724929, 30540, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1042234Z     %dequantize_per_tensor_386 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_171, 0.0005588589119724929, 30540, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1043567Z     %unsqueeze_8 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_380, -1), kwargs = {})
2025-03-21T20:30:48.1044831Z     %quantize_per_tensor_172 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_8, 0.0002292444696649909, 31927, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1046408Z     %dequantize_per_tensor_387 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_172, 0.0002292444696649909, 31927, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1047720Z     %transpose_43 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_387, 1, 2), kwargs = {})
2025-03-21T20:30:48.1048975Z     %quantize_per_tensor_173 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_43, 0.0002292444696649909, 31927, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1050613Z     %dequantize_per_tensor_388 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_173, 0.0002292444696649909, 31927, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1051989Z     %conv2d_8 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_388, %dequantize_per_tensor_12), kwargs = {})
2025-03-21T20:30:48.1053291Z     %quantize_per_tensor_174 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_8, 0.00035107287112623453, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1054871Z     %dequantize_per_tensor_389 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_174, 0.00035107287112623453, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1056175Z     %transpose_44 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_389, 1, 2), kwargs = {})
2025-03-21T20:30:48.1057435Z     %quantize_per_tensor_175 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_44, 0.00035107287112623453, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1059018Z     %dequantize_per_tensor_390 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_175, 0.00035107287112623453, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1059439Z     %squeeze_8 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_390, -1), kwargs = {})
2025-03-21T20:30:48.1060141Z     %quantize_per_tensor_176 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_8, 0.00035107287112623453, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1060923Z     %dequantize_per_tensor_391 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_176, 0.00035107287112623453, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1061372Z     %unsqueeze_9 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_379, -1), kwargs = {})
2025-03-21T20:30:48.1062083Z     %quantize_per_tensor_177 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_9, 0.0002292444696649909, 31927, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1062941Z     %dequantize_per_tensor_392 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_177, 0.0002292444696649909, 31927, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1063388Z     %transpose_45 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_392, 1, 2), kwargs = {})
2025-03-21T20:30:48.1064096Z     %quantize_per_tensor_178 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_45, 0.0002292444696649909, 31927, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1064869Z     %dequantize_per_tensor_393 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_178, 0.0002292444696649909, 31927, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1065368Z     %conv2d_9 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_393, %dequantize_per_tensor_13), kwargs = {})
2025-03-21T20:30:48.1066068Z     %quantize_per_tensor_179 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_9, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1066822Z     %dequantize_per_tensor_394 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_179, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1067270Z     %transpose_46 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_394, 1, 2), kwargs = {})
2025-03-21T20:30:48.1067969Z     %quantize_per_tensor_180 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_46, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1068751Z     %dequantize_per_tensor_395 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_180, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1069161Z     %squeeze_9 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_395, -1), kwargs = {})
2025-03-21T20:30:48.1069865Z     %quantize_per_tensor_181 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_9, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1070622Z     %dequantize_per_tensor_396 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_181, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1071075Z     %view_12 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_386, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.1071760Z     %quantize_per_tensor_182 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_12, 0.0005588589119724929, 30540, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1072531Z     %dequantize_per_tensor_397 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_182, 0.0005588589119724929, 30540, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1072966Z     %view_13 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_391, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.1073659Z     %quantize_per_tensor_183 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_13, 0.00035107287112623453, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1074472Z     %dequantize_per_tensor_398 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_183, 0.00035107287112623453, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1074967Z     %view_14 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_396, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.1075642Z     %quantize_per_tensor_184 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_14, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1076409Z     %dequantize_per_tensor_399 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_184, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1076887Z     %_to_copy_2 : [num_users=1] = call_function[target=torch.ops.aten._to_copy.default](args = (%dequantize_per_tensor_397,), kwargs = {dtype: torch.float32})
2025-03-21T20:30:48.1077593Z     %quantize_per_tensor_185 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%_to_copy_2, 0.0005588589119724929, 30540, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1078351Z     %dequantize_per_tensor_400 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_185, 0.0005588589119724929, 30540, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1078804Z     %view_15 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_400, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:30:48.1079483Z     %quantize_per_tensor_186 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_15, 0.0005588589119724929, 30540, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1080255Z     %dequantize_per_tensor_401 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_186, 0.0005588589119724929, 30540, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1080655Z     %unbind_2 : [num_users=2] = call_function[target=torch.ops.aten.unbind.int](args = (%dequantize_per_tensor_401, -1), kwargs = {})
2025-03-21T20:30:48.1080969Z     %getitem_4 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_2, 0), kwargs = {})
2025-03-21T20:30:48.1081284Z     %getitem_5 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_2, 1), kwargs = {})
2025-03-21T20:30:48.1081981Z     %quantize_per_tensor_187 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_4, 0.00031485746148973703, 24746, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1082755Z     %dequantize_per_tensor_402 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_187, 0.00031485746148973703, 24746, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1083520Z     %dequantize_per_tensor_403 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_187, 0.00031485746148973703, 24746, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1084215Z     %quantize_per_tensor_188 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_5, 0.0005588589119724929, 30540, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1084976Z     %dequantize_per_tensor_404 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_188, 0.0005588589119724929, 30540, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1085786Z     %dequantize_per_tensor_405 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_188, 0.0005588589119724929, 30540, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1086307Z     %_to_copy_3 : [num_users=1] = call_function[target=torch.ops.aten._to_copy.default](args = (%dequantize_per_tensor_398,), kwargs = {dtype: torch.float32})
2025-03-21T20:30:48.1087002Z     %quantize_per_tensor_189 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%_to_copy_3, 0.00035107287112623453, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1087766Z     %dequantize_per_tensor_406 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_189, 0.00035107287112623453, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1088217Z     %view_16 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_406, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:30:48.1088908Z     %quantize_per_tensor_190 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_16, 0.00035107287112623453, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1089742Z     %dequantize_per_tensor_407 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_190, 0.00035107287112623453, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1090144Z     %unbind_3 : [num_users=2] = call_function[target=torch.ops.aten.unbind.int](args = (%dequantize_per_tensor_407, -1), kwargs = {})
2025-03-21T20:30:48.1090466Z     %getitem_6 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_3, 0), kwargs = {})
2025-03-21T20:30:48.1090777Z     %getitem_7 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_3, 1), kwargs = {})
2025-03-21T20:30:48.1091483Z     %quantize_per_tensor_191 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_6, 0.00035107287112623453, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1092255Z     %dequantize_per_tensor_408 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_191, 0.00035107287112623453, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1093029Z     %dequantize_per_tensor_409 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_191, 0.00035107287112623453, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1093720Z     %quantize_per_tensor_192 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_7, 0.0003347279562149197, 34945, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1094496Z     %dequantize_per_tensor_410 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_192, 0.0003347279562149197, 34945, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1095254Z     %dequantize_per_tensor_411 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_192, 0.0003347279562149197, 34945, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1095696Z     %view_17 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_161, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:30:48.1096372Z     %quantize_per_tensor_193 : [num_users=4] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_17, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1097192Z     %dequantize_per_tensor_412 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_193, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1097996Z     %dequantize_per_tensor_413 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_193, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1098766Z     %dequantize_per_tensor_414 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_193, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1099522Z     %dequantize_per_tensor_415 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_193, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1099957Z     %view_18 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_173, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:30:48.1100639Z     %quantize_per_tensor_194 : [num_users=4] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_18, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1101410Z     %dequantize_per_tensor_416 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_194, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1102165Z     %dequantize_per_tensor_417 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_194, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1102932Z     %dequantize_per_tensor_418 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_194, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1103697Z     %dequantize_per_tensor_419 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_194, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1104175Z     %mul_11 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_403, %dequantize_per_tensor_415), kwargs = {})
2025-03-21T20:30:48.1104858Z     %quantize_per_tensor_195 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_11, 0.00031216273782774806, 24881, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1105640Z     %dequantize_per_tensor_420 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_195, 0.00031216273782774806, 24881, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1106108Z     %mul_12 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_404, %dequantize_per_tensor_418), kwargs = {})
2025-03-21T20:30:48.1106803Z     %quantize_per_tensor_196 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_12, 0.00018542019824963063, 32753, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1107566Z     %dequantize_per_tensor_421 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_196, 0.00018542019824963063, 32753, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1108044Z     %sub_2 : [num_users=1] = call_function[target=torch.ops.aten.sub.Tensor](args = (%dequantize_per_tensor_420, %dequantize_per_tensor_421), kwargs = {})
2025-03-21T20:30:48.1108763Z     %quantize_per_tensor_197 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%sub_2, 0.0003158242325298488, 26127, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1109579Z     %dequantize_per_tensor_422 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_197, 0.0003158242325298488, 26127, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1110046Z     %mul_13 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_402, %dequantize_per_tensor_419), kwargs = {})
2025-03-21T20:30:48.1110736Z     %quantize_per_tensor_198 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_13, 0.00020952976774424314, 32714, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1111501Z     %dequantize_per_tensor_423 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_198, 0.00020952976774424314, 32714, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1111981Z     %mul_14 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_405, %dequantize_per_tensor_414), kwargs = {})
2025-03-21T20:30:48.1112662Z     %quantize_per_tensor_199 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_14, 0.0005582913290709257, 30556, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1113432Z     %dequantize_per_tensor_424 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_199, 0.0005582913290709257, 30556, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1113896Z     %add_5 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_423, %dequantize_per_tensor_424), kwargs = {})
2025-03-21T20:30:48.1114577Z     %quantize_per_tensor_200 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_5, 0.0005553436931222677, 30616, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1115341Z     %dequantize_per_tensor_425 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_200, 0.0005553436931222677, 30616, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1115815Z     %mul_15 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_409, %dequantize_per_tensor_413), kwargs = {})
2025-03-21T20:30:48.1116493Z     %quantize_per_tensor_201 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_15, 0.00035014102468267083, 33669, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1117269Z     %dequantize_per_tensor_426 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_201, 0.00035014102468267083, 33669, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1117736Z     %mul_16 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_410, %dequantize_per_tensor_416), kwargs = {})
2025-03-21T20:30:48.1118420Z     %quantize_per_tensor_202 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_16, 0.0002225427160738036, 32972, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1119182Z     %dequantize_per_tensor_427 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_202, 0.0002225427160738036, 32972, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1119654Z     %sub_3 : [num_users=1] = call_function[target=torch.ops.aten.sub.Tensor](args = (%dequantize_per_tensor_426, %dequantize_per_tensor_427), kwargs = {})
2025-03-21T20:30:48.1120378Z     %quantize_per_tensor_203 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%sub_3, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1121207Z     %dequantize_per_tensor_428 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_203, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1121672Z     %mul_17 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_408, %dequantize_per_tensor_417), kwargs = {})
2025-03-21T20:30:48.1122355Z     %quantize_per_tensor_204 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_17, 0.0002190972154494375, 28074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1123116Z     %dequantize_per_tensor_429 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_204, 0.0002190972154494375, 28074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1123596Z     %mul_18 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_411, %dequantize_per_tensor_412), kwargs = {})
2025-03-21T20:30:48.1124279Z     %quantize_per_tensor_205 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_18, 0.00033182575134560466, 34828, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1125054Z     %dequantize_per_tensor_430 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_205, 0.00033182575134560466, 34828, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1125517Z     %add_6 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_429, %dequantize_per_tensor_430), kwargs = {})
2025-03-21T20:30:48.1126200Z     %quantize_per_tensor_206 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_6, 0.0003313907072879374, 34832, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1126962Z     %dequantize_per_tensor_431 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_206, 0.0003313907072879374, 34832, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1127483Z     %stack_2 : [num_users=1] = call_function[target=torch.ops.aten.stack.default](args = ([%dequantize_per_tensor_422, %dequantize_per_tensor_425], -1), kwargs = {})
2025-03-21T20:30:48.1128162Z     %quantize_per_tensor_207 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%stack_2, 0.0005553436931222677, 30616, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1128933Z     %dequantize_per_tensor_432 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_207, 0.0005553436931222677, 30616, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1129427Z     %view_19 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_432, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.1130121Z     %quantize_per_tensor_208 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_19, 0.0005553436931222677, 30616, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1130878Z     %dequantize_per_tensor_433 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_208, 0.0005553436931222677, 30616, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1131396Z     %stack_3 : [num_users=1] = call_function[target=torch.ops.aten.stack.default](args = ([%dequantize_per_tensor_428, %dequantize_per_tensor_431], -1), kwargs = {})
2025-03-21T20:30:48.1132128Z     %quantize_per_tensor_209 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%stack_3, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1133126Z     %dequantize_per_tensor_434 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_209, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1133559Z     %view_20 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_434, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.1134252Z     %quantize_per_tensor_210 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_20, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1135021Z     %dequantize_per_tensor_435 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_210, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1135521Z     %type_as_2 : [num_users=1] = call_function[target=torch.ops.aten.type_as.default](args = (%dequantize_per_tensor_433, %dequantize_per_tensor_397), kwargs = {})
2025-03-21T20:30:48.1136211Z     %quantize_per_tensor_211 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%type_as_2, 0.0005553436931222677, 30616, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1136981Z     %dequantize_per_tensor_436 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_211, 0.0005553436931222677, 30616, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1137468Z     %type_as_3 : [num_users=1] = call_function[target=torch.ops.aten.type_as.default](args = (%dequantize_per_tensor_435, %dequantize_per_tensor_398), kwargs = {})
2025-03-21T20:30:48.1138172Z     %quantize_per_tensor_212 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%type_as_3, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1138939Z     %dequantize_per_tensor_437 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_212, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1139381Z     %transpose_47 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_436, 1, 2), kwargs = {})
2025-03-21T20:30:48.1140088Z     %quantize_per_tensor_213 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_47, 0.0005553436931222677, 30616, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1140856Z     %dequantize_per_tensor_438 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_213, 0.0005553436931222677, 30616, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1141482Z     %index_put_2 : [num_users=1] = call_function[target=torch.ops.aten.index_put.default](args = (%dequantize_per_tensor_116, [None, %attn_options_input_pos], %dequantize_per_tensor_437), kwargs = {})
2025-03-21T20:30:48.1142187Z     %quantize_per_tensor_214 : [num_users=13] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_put_2, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1142952Z     %dequantize_per_tensor_439 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_214, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1143799Z     %dequantize_per_tensor_440 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_214, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1144622Z     %dequantize_per_tensor_441 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_214, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1145397Z     %dequantize_per_tensor_442 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_214, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1146158Z     %dequantize_per_tensor_443 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_214, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1146932Z     %dequantize_per_tensor_444 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_214, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1147693Z     %dequantize_per_tensor_445 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_214, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1148463Z     %dequantize_per_tensor_446 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_214, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1149224Z     %dequantize_per_tensor_447 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_214, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1149998Z     %dequantize_per_tensor_448 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_214, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1150765Z     %dequantize_per_tensor_449 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_214, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1151532Z     %dequantize_per_tensor_450 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_214, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1152298Z     %dequantize_per_tensor_451 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_214, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1152935Z     %index_put_3 : [num_users=1] = call_function[target=torch.ops.aten.index_put.default](args = (%dequantize_per_tensor_117, [None, %attn_options_input_pos], %dequantize_per_tensor_399), kwargs = {})
2025-03-21T20:30:48.1153633Z     %quantize_per_tensor_215 : [num_users=13] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_put_3, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1154402Z     %dequantize_per_tensor_452 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_215, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1155152Z     %dequantize_per_tensor_453 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_215, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1155960Z     %dequantize_per_tensor_454 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_215, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1156759Z     %dequantize_per_tensor_455 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_215, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1157523Z     %dequantize_per_tensor_456 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_215, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1158275Z     %dequantize_per_tensor_457 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_215, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1159042Z     %dequantize_per_tensor_458 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_215, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1159793Z     %dequantize_per_tensor_459 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_215, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1160557Z     %dequantize_per_tensor_460 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_215, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1161308Z     %dequantize_per_tensor_461 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_215, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1162072Z     %dequantize_per_tensor_462 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_215, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1162830Z     %dequantize_per_tensor_463 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_215, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1163590Z     %dequantize_per_tensor_464 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_215, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1164028Z     %transpose_48 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_451, 1, 2), kwargs = {})
2025-03-21T20:30:48.1164747Z     %quantize_per_tensor_216 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_48, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1165517Z     %dequantize_per_tensor_465 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_216, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1165929Z     %select_48 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_465, 0, 0), kwargs = {})
2025-03-21T20:30:48.1166627Z     %quantize_per_tensor_217 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_48, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1167405Z     %dequantize_per_tensor_466 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_217, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1167914Z     %select_49 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_466, 0, 0), kwargs = {})
2025-03-21T20:30:48.1168623Z     %quantize_per_tensor_218 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_49, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1169445Z     %dequantize_per_tensor_467 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_218, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1169896Z     %transpose_49 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_450, 1, 2), kwargs = {})
2025-03-21T20:30:48.1170612Z     %quantize_per_tensor_219 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_49, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1171400Z     %dequantize_per_tensor_468 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_219, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1171805Z     %select_50 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_468, 0, 0), kwargs = {})
2025-03-21T20:30:48.1172514Z     %quantize_per_tensor_220 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_50, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1173282Z     %dequantize_per_tensor_469 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_220, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1173701Z     %select_51 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_469, 0, 1), kwargs = {})
2025-03-21T20:30:48.1174397Z     %quantize_per_tensor_221 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_51, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1175174Z     %dequantize_per_tensor_470 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_221, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1175609Z     %transpose_50 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_449, 1, 2), kwargs = {})
2025-03-21T20:30:48.1176329Z     %quantize_per_tensor_222 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_50, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1177094Z     %dequantize_per_tensor_471 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_222, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1177508Z     %select_52 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_471, 0, 0), kwargs = {})
2025-03-21T20:30:48.1178204Z     %quantize_per_tensor_223 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_52, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1178981Z     %dequantize_per_tensor_472 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_223, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1179428Z     %select_53 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_472, 0, 2), kwargs = {})
2025-03-21T20:30:48.1180181Z     %quantize_per_tensor_224 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_53, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1180943Z     %dequantize_per_tensor_473 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_224, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1181387Z     %transpose_51 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_448, 1, 2), kwargs = {})
2025-03-21T20:30:48.1182093Z     %quantize_per_tensor_225 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_51, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1182877Z     %dequantize_per_tensor_474 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_225, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1183278Z     %select_54 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_474, 0, 0), kwargs = {})
2025-03-21T20:30:48.1183981Z     %quantize_per_tensor_226 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_54, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1184748Z     %dequantize_per_tensor_475 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_226, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1185162Z     %select_55 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_475, 0, 3), kwargs = {})
2025-03-21T20:30:48.1185862Z     %quantize_per_tensor_227 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_55, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1186623Z     %dequantize_per_tensor_476 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_227, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1187068Z     %transpose_52 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_447, 1, 2), kwargs = {})
2025-03-21T20:30:48.1187773Z     %quantize_per_tensor_228 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_52, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1188558Z     %dequantize_per_tensor_477 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_228, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1188955Z     %select_56 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_477, 0, 0), kwargs = {})
2025-03-21T20:30:48.1189664Z     %quantize_per_tensor_229 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_56, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1190424Z     %dequantize_per_tensor_478 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_229, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1190904Z     %select_57 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_478, 0, 4), kwargs = {})
2025-03-21T20:30:48.1191648Z     %quantize_per_tensor_230 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_57, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1192424Z     %dequantize_per_tensor_479 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_230, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1192861Z     %transpose_53 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_446, 1, 2), kwargs = {})
2025-03-21T20:30:48.1193576Z     %quantize_per_tensor_231 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_53, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1194350Z     %dequantize_per_tensor_480 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_231, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1194758Z     %select_58 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_480, 0, 0), kwargs = {})
2025-03-21T20:30:48.1195455Z     %quantize_per_tensor_232 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_58, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1196229Z     %dequantize_per_tensor_481 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_232, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1196634Z     %select_59 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_481, 0, 5), kwargs = {})
2025-03-21T20:30:48.1197340Z     %quantize_per_tensor_233 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_59, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1198105Z     %dequantize_per_tensor_482 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_233, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1198559Z     %transpose_54 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_445, 1, 2), kwargs = {})
2025-03-21T20:30:48.1199266Z     %quantize_per_tensor_234 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_54, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1200045Z     %dequantize_per_tensor_483 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_234, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1200448Z     %select_60 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_483, 0, 0), kwargs = {})
2025-03-21T20:30:48.1201145Z     %quantize_per_tensor_235 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_60, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1201909Z     %dequantize_per_tensor_484 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_235, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1202370Z     %select_61 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_484, 0, 6), kwargs = {})
2025-03-21T20:30:48.1203114Z     %quantize_per_tensor_236 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_61, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1203890Z     %dequantize_per_tensor_485 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_236, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1204325Z     %transpose_55 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_444, 1, 2), kwargs = {})
2025-03-21T20:30:48.1205043Z     %quantize_per_tensor_237 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_55, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1205811Z     %dequantize_per_tensor_486 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_237, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1206231Z     %select_62 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_486, 0, 0), kwargs = {})
2025-03-21T20:30:48.1206934Z     %quantize_per_tensor_238 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_62, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1207712Z     %dequantize_per_tensor_487 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_238, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1208117Z     %select_63 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_487, 0, 7), kwargs = {})
2025-03-21T20:30:48.1208829Z     %quantize_per_tensor_239 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_63, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1209655Z     %dequantize_per_tensor_488 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_239, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1210107Z     %transpose_56 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_443, 1, 2), kwargs = {})
2025-03-21T20:30:48.1210817Z     %quantize_per_tensor_240 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_56, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1211602Z     %dequantize_per_tensor_489 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_240, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1212012Z     %select_64 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_489, 0, 0), kwargs = {})
2025-03-21T20:30:48.1212717Z     %quantize_per_tensor_241 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_64, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1213481Z     %dequantize_per_tensor_490 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_241, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1213893Z     %select_65 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_490, 0, 8), kwargs = {})
2025-03-21T20:30:48.1214701Z     %quantize_per_tensor_242 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_65, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1215482Z     %dequantize_per_tensor_491 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_242, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1215920Z     %transpose_57 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_442, 1, 2), kwargs = {})
2025-03-21T20:30:48.1216640Z     %quantize_per_tensor_243 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_57, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1217406Z     %dequantize_per_tensor_492 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_243, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1217824Z     %select_66 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_492, 0, 0), kwargs = {})
2025-03-21T20:30:48.1218519Z     %quantize_per_tensor_244 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_66, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1219299Z     %dequantize_per_tensor_493 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_244, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1219700Z     %select_67 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_493, 0, 9), kwargs = {})
2025-03-21T20:30:48.1220414Z     %quantize_per_tensor_245 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_67, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1221179Z     %dequantize_per_tensor_494 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_245, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1221626Z     %transpose_58 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_441, 1, 2), kwargs = {})
2025-03-21T20:30:48.1222334Z     %quantize_per_tensor_246 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_58, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1223113Z     %dequantize_per_tensor_495 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_246, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1223519Z     %select_68 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_495, 0, 0), kwargs = {})
2025-03-21T20:30:48.1224221Z     %quantize_per_tensor_247 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_68, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1224984Z     %dequantize_per_tensor_496 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_247, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1225400Z     %select_69 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_496, 0, 10), kwargs = {})
2025-03-21T20:30:48.1226187Z     %quantize_per_tensor_248 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_69, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1226967Z     %dequantize_per_tensor_497 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_248, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1227400Z     %transpose_59 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_440, 1, 2), kwargs = {})
2025-03-21T20:30:48.1228108Z     %quantize_per_tensor_249 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_59, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1228884Z     %dequantize_per_tensor_498 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_249, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1229294Z     %select_70 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_498, 0, 0), kwargs = {})
2025-03-21T20:30:48.1229997Z     %quantize_per_tensor_250 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_70, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1230764Z     %dequantize_per_tensor_499 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_250, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1231182Z     %select_71 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_499, 0, 11), kwargs = {})
2025-03-21T20:30:48.1231876Z     %quantize_per_tensor_251 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_71, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1232847Z     %dequantize_per_tensor_500 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_251, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1234310Z     %cat_2 : [num_users=1] = call_function[target=torch.ops.aten.cat.default](args = ([%dequantize_per_tensor_467, %dequantize_per_tensor_470, %dequantize_per_tensor_473, %dequantize_per_tensor_476, %dequantize_per_tensor_479, %dequantize_per_tensor_482, %dequantize_per_tensor_485, %dequantize_per_tensor_488, %dequantize_per_tensor_491, %dequantize_per_tensor_494, %dequantize_per_tensor_497, %dequantize_per_tensor_500],), kwargs = {})
2025-03-21T20:30:48.1234992Z     %quantize_per_tensor_252 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%cat_2, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1235775Z     %dequantize_per_tensor_501 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_252, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1236218Z     %view_21 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_501, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:30:48.1236916Z     %quantize_per_tensor_253 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_21, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1237760Z     %dequantize_per_tensor_502 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_253, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1238286Z     %transpose_60 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_464, 1, 2), kwargs = {})
2025-03-21T20:30:48.1238987Z     %quantize_per_tensor_254 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_60, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1239760Z     %dequantize_per_tensor_503 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_254, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1240165Z     %select_72 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_503, 0, 0), kwargs = {})
2025-03-21T20:30:48.1240867Z     %quantize_per_tensor_255 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_72, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1241626Z     %dequantize_per_tensor_504 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_255, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1242026Z     %select_73 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_504, 0, 0), kwargs = {})
2025-03-21T20:30:48.1242724Z     %quantize_per_tensor_256 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_73, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1243485Z     %dequantize_per_tensor_505 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_256, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1243939Z     %transpose_61 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_463, 1, 2), kwargs = {})
2025-03-21T20:30:48.1244637Z     %quantize_per_tensor_257 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_61, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1245404Z     %dequantize_per_tensor_506 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_257, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1245802Z     %select_74 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_506, 0, 0), kwargs = {})
2025-03-21T20:30:48.1246496Z     %quantize_per_tensor_258 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_74, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1247256Z     %dequantize_per_tensor_507 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_258, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1247671Z     %select_75 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_507, 0, 1), kwargs = {})
2025-03-21T20:30:48.1248356Z     %quantize_per_tensor_259 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_75, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1249125Z     %dequantize_per_tensor_508 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_259, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1249725Z     %transpose_62 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_462, 1, 2), kwargs = {})
2025-03-21T20:30:48.1250435Z     %quantize_per_tensor_260 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_62, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1251193Z     %dequantize_per_tensor_509 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_260, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1251607Z     %select_76 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_509, 0, 0), kwargs = {})
2025-03-21T20:30:48.1252296Z     %quantize_per_tensor_261 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_76, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1253065Z     %dequantize_per_tensor_510 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_261, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1253467Z     %select_77 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_510, 0, 2), kwargs = {})
2025-03-21T20:30:48.1254170Z     %quantize_per_tensor_262 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_77, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1254926Z     %dequantize_per_tensor_511 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_262, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1255378Z     %transpose_63 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_461, 1, 2), kwargs = {})
2025-03-21T20:30:48.1256078Z     %quantize_per_tensor_263 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_63, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1256842Z     %dequantize_per_tensor_512 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_263, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1257245Z     %select_78 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_512, 0, 0), kwargs = {})
2025-03-21T20:30:48.1257944Z     %quantize_per_tensor_264 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_78, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1258704Z     %dequantize_per_tensor_513 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_264, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1259120Z     %select_79 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_513, 0, 3), kwargs = {})
2025-03-21T20:30:48.1259800Z     %quantize_per_tensor_265 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_79, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1260565Z     %dequantize_per_tensor_514 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_265, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1261097Z     %transpose_64 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_460, 1, 2), kwargs = {})
2025-03-21T20:30:48.1261810Z     %quantize_per_tensor_266 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_64, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1262566Z     %dequantize_per_tensor_515 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_266, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1262981Z     %select_80 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_515, 0, 0), kwargs = {})
2025-03-21T20:30:48.1263664Z     %quantize_per_tensor_267 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_80, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1264449Z     %dequantize_per_tensor_516 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_267, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1264856Z     %select_81 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_516, 0, 4), kwargs = {})
2025-03-21T20:30:48.1265556Z     %quantize_per_tensor_268 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_81, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1266316Z     %dequantize_per_tensor_517 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_268, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1266773Z     %transpose_65 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_459, 1, 2), kwargs = {})
2025-03-21T20:30:48.1267480Z     %quantize_per_tensor_269 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_65, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1268254Z     %dequantize_per_tensor_518 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_269, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1268659Z     %select_82 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_518, 0, 0), kwargs = {})
2025-03-21T20:30:48.1269359Z     %quantize_per_tensor_270 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_82, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1270124Z     %dequantize_per_tensor_519 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_270, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1270542Z     %select_83 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_519, 0, 5), kwargs = {})
2025-03-21T20:30:48.1271229Z     %quantize_per_tensor_271 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_83, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1272001Z     %dequantize_per_tensor_520 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_271, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1272482Z     %transpose_66 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_458, 1, 2), kwargs = {})
2025-03-21T20:30:48.1273239Z     %quantize_per_tensor_272 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_66, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1273993Z     %dequantize_per_tensor_521 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_272, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1274409Z     %select_84 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_521, 0, 0), kwargs = {})
2025-03-21T20:30:48.1275094Z     %quantize_per_tensor_273 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_84, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1275873Z     %dequantize_per_tensor_522 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_273, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1276276Z     %select_85 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_522, 0, 6), kwargs = {})
2025-03-21T20:30:48.1276969Z     %quantize_per_tensor_274 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_85, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1277724Z     %dequantize_per_tensor_523 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_274, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1278176Z     %transpose_67 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_457, 1, 2), kwargs = {})
2025-03-21T20:30:48.1278880Z     %quantize_per_tensor_275 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_67, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1279637Z     %dequantize_per_tensor_524 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_275, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1280052Z     %select_86 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_524, 0, 0), kwargs = {})
2025-03-21T20:30:48.1280736Z     %quantize_per_tensor_276 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_86, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1281513Z     %dequantize_per_tensor_525 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_276, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1281920Z     %select_87 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_525, 0, 7), kwargs = {})
2025-03-21T20:30:48.1282615Z     %quantize_per_tensor_277 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_87, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1283376Z     %dequantize_per_tensor_526 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_277, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1283823Z     %transpose_68 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_456, 1, 2), kwargs = {})
2025-03-21T20:30:48.1284622Z     %quantize_per_tensor_278 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_68, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1285388Z     %dequantize_per_tensor_527 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_278, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1285792Z     %select_88 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_527, 0, 0), kwargs = {})
2025-03-21T20:30:48.1286487Z     %quantize_per_tensor_279 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_88, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1287246Z     %dequantize_per_tensor_528 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_279, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1287661Z     %select_89 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_528, 0, 8), kwargs = {})
2025-03-21T20:30:48.1288342Z     %quantize_per_tensor_280 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_89, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1289112Z     %dequantize_per_tensor_529 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_280, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1289631Z     %transpose_69 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_455, 1, 2), kwargs = {})
2025-03-21T20:30:48.1290350Z     %quantize_per_tensor_281 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_69, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1291108Z     %dequantize_per_tensor_530 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_281, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1291525Z     %select_90 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_530, 0, 0), kwargs = {})
2025-03-21T20:30:48.1292208Z     %quantize_per_tensor_282 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_90, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1292979Z     %dequantize_per_tensor_531 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_282, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1293383Z     %select_91 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_531, 0, 9), kwargs = {})
2025-03-21T20:30:48.1294077Z     %quantize_per_tensor_283 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_91, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1294834Z     %dequantize_per_tensor_532 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_283, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1295276Z     %transpose_70 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_454, 1, 2), kwargs = {})
2025-03-21T20:30:48.1296092Z     %quantize_per_tensor_284 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_70, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1296858Z     %dequantize_per_tensor_533 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_284, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1297262Z     %select_92 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_533, 0, 0), kwargs = {})
2025-03-21T20:30:48.1297961Z     %quantize_per_tensor_285 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_92, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1298720Z     %dequantize_per_tensor_534 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_285, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1299141Z     %select_93 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_534, 0, 10), kwargs = {})
2025-03-21T20:30:48.1299826Z     %quantize_per_tensor_286 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_93, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1300594Z     %dequantize_per_tensor_535 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_286, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1301029Z     %transpose_71 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_453, 1, 2), kwargs = {})
2025-03-21T20:30:48.1301749Z     %quantize_per_tensor_287 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_71, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1302512Z     %dequantize_per_tensor_536 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_287, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1302932Z     %select_94 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_536, 0, 0), kwargs = {})
2025-03-21T20:30:48.1303617Z     %quantize_per_tensor_288 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_94, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1304390Z     %dequantize_per_tensor_537 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_288, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1304805Z     %select_95 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_537, 0, 11), kwargs = {})
2025-03-21T20:30:48.1305503Z     %quantize_per_tensor_289 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_95, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1306259Z     %dequantize_per_tensor_538 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_289, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1307765Z     %cat_3 : [num_users=1] = call_function[target=torch.ops.aten.cat.default](args = ([%dequantize_per_tensor_505, %dequantize_per_tensor_508, %dequantize_per_tensor_511, %dequantize_per_tensor_514, %dequantize_per_tensor_517, %dequantize_per_tensor_520, %dequantize_per_tensor_523, %dequantize_per_tensor_526, %dequantize_per_tensor_529, %dequantize_per_tensor_532, %dequantize_per_tensor_535, %dequantize_per_tensor_538],), kwargs = {})
2025-03-21T20:30:48.1308482Z     %quantize_per_tensor_290 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%cat_3, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1309253Z     %dequantize_per_tensor_539 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_290, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1309690Z     %view_22 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_539, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:30:48.1310383Z     %quantize_per_tensor_291 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_22, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1311143Z     %dequantize_per_tensor_540 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_291, 8.02720314823091e-05, 34074, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1311917Z     %quantize_per_tensor_292 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%dequantize_per_tensor_540, 8.347312541445717e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.1312681Z     %dequantize_per_tensor_541 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_292, 8.347312541445717e-05, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.1313183Z     %index_3 : [num_users=1] = call_function[target=torch.ops.aten.index.Tensor](args = (%dequantize_per_tensor_118, [%attn_options_input_pos]), kwargs = {})
2025-03-21T20:30:48.1313874Z     %quantize_per_tensor_293 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_3, 0.0038910505827516317, 65535, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1314653Z     %dequantize_per_tensor_542 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_293, 0.0038910505827516317, 65535, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1315100Z     %transpose_72 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_502, -2, -1), kwargs = {})
2025-03-21T20:30:48.1315817Z     %quantize_per_tensor_294 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_72, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1316586Z     %dequantize_per_tensor_543 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_294, 0.00035046463017351925, 33692, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1317360Z     %quantize_per_tensor_295 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%dequantize_per_tensor_543, 0.00036035533412359655, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.1318132Z     %dequantize_per_tensor_544 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_295, 0.00036035533412359655, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.1318644Z     %matmul_2 : [num_users=1] = call_function[target=torch.ops.aten.matmul.default](args = (%dequantize_per_tensor_438, %dequantize_per_tensor_544), kwargs = {})
2025-03-21T20:30:48.1319381Z     %quantize_per_tensor_296 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%matmul_2, 0.003841349622234702, 41763, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1320202Z     %dequantize_per_tensor_545 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_296, 0.003841349622234702, 41763, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1320940Z     %dequantize_per_tensor_546 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param150, 1.9073777366429567e-06, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1321420Z     %mul_19 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_545, %dequantize_per_tensor_546), kwargs = {})
2025-03-21T20:30:48.1322104Z     %quantize_per_tensor_297 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_19, 0.00048016870277933776, 41763, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1322888Z     %dequantize_per_tensor_547 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_297, 0.00048016870277933776, 41763, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1323359Z     %add_7 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_547, %dequantize_per_tensor_542), kwargs = {})
2025-03-21T20:30:48.1324042Z     %quantize_per_tensor_298 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_7, 0.004258564207702875, 62855, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1324801Z     %dequantize_per_tensor_548 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_298, 0.004258564207702875, 62855, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1325231Z     %softmax_1 : [num_users=1] = call_function[target=torch.ops.aten.softmax.int](args = (%dequantize_per_tensor_548, -1), kwargs = {})
2025-03-21T20:30:48.1325917Z     %quantize_per_tensor_299 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%softmax_1, 1.5259021893143654e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1326682Z     %dequantize_per_tensor_549 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_299, 1.5259021893143654e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1327183Z     %matmul_3 : [num_users=1] = call_function[target=torch.ops.aten.matmul.default](args = (%dequantize_per_tensor_549, %dequantize_per_tensor_541), kwargs = {})
2025-03-21T20:30:48.1327888Z     %quantize_per_tensor_300 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%matmul_3, 5.015738497604616e-05, 34187, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1328656Z     %dequantize_per_tensor_550 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_300, 5.015738497604616e-05, 34187, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1329109Z     %transpose_73 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_550, 1, 2), kwargs = {})
2025-03-21T20:30:48.1329916Z     %quantize_per_tensor_301 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_73, 5.015738497604616e-05, 34187, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1330695Z     %dequantize_per_tensor_551 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_301, 5.015738497604616e-05, 34187, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1331223Z     %view_23 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_551, [1, 1, 768]), kwargs = {})
2025-03-21T20:30:48.1331914Z     %quantize_per_tensor_302 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_23, 5.015738497604616e-05, 34187, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1332854Z     %dequantize_per_tensor_552 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_302, 5.015738497604616e-05, 34187, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1333322Z     %unsqueeze_10 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_552, -1), kwargs = {})
2025-03-21T20:30:48.1334032Z     %quantize_per_tensor_303 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_10, 5.015738497604616e-05, 34187, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1334814Z     %dequantize_per_tensor_553 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_303, 5.015738497604616e-05, 34187, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1335252Z     %transpose_74 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_553, 1, 2), kwargs = {})
2025-03-21T20:30:48.1335971Z     %quantize_per_tensor_304 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_74, 5.015738497604616e-05, 34187, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1336731Z     %dequantize_per_tensor_554 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_304, 5.015738497604616e-05, 34187, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1337251Z     %conv2d_10 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_554, %dequantize_per_tensor_14), kwargs = {})
2025-03-21T20:30:48.1337943Z     %quantize_per_tensor_305 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_10, 6.624962406931445e-05, 32697, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1338720Z     %dequantize_per_tensor_555 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_305, 6.624962406931445e-05, 32697, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1339159Z     %transpose_75 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_555, 1, 2), kwargs = {})
2025-03-21T20:30:48.1339878Z     %quantize_per_tensor_306 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_75, 6.624962406931445e-05, 32697, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1340639Z     %dequantize_per_tensor_556 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_306, 6.624962406931445e-05, 32697, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1341065Z     %squeeze_10 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_556, -1), kwargs = {})
2025-03-21T20:30:48.1341758Z     %quantize_per_tensor_307 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_10, 6.624962406931445e-05, 32697, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1342534Z     %dequantize_per_tensor_557 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_307, 6.624962406931445e-05, 32697, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1343163Z     %add_8 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_377, %dequantize_per_tensor_557), kwargs = {})
2025-03-21T20:30:48.1343843Z     %quantize_per_tensor_308 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_8, 0.00016923173097893596, 27235, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1344626Z     %dequantize_per_tensor_558 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_308, 0.00016923173097893596, 27235, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1345400Z     %dequantize_per_tensor_559 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_308, 0.00016923173097893596, 27235, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1345956Z     %rms_norm_3 : [num_users=1] = call_function[target=torch.ops.aten.rms_norm.default](args = (%dequantize_per_tensor_559, [768], %dequantize_per_tensor_15, 1e-05), kwargs = {})
2025-03-21T20:30:48.1346654Z     %quantize_per_tensor_309 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%rms_norm_3, 0.00021398279932327569, 31590, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1347432Z     %dequantize_per_tensor_560 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_309, 0.00021398279932327569, 31590, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1348209Z     %dequantize_per_tensor_561 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_309, 0.00021398279932327569, 31590, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1348666Z     %unsqueeze_11 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_561, -1), kwargs = {})
2025-03-21T20:30:48.1349376Z     %quantize_per_tensor_310 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_11, 0.00021398279932327569, 31590, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1350156Z     %dequantize_per_tensor_562 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_310, 0.00021398279932327569, 31590, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1350594Z     %transpose_76 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_562, 1, 2), kwargs = {})
2025-03-21T20:30:48.1351320Z     %quantize_per_tensor_311 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_76, 0.00021398279932327569, 31590, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1352093Z     %dequantize_per_tensor_563 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_311, 0.00021398279932327569, 31590, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1352606Z     %conv2d_11 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_563, %dequantize_per_tensor_16), kwargs = {})
2025-03-21T20:30:48.1353302Z     %quantize_per_tensor_312 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_11, 0.00014935866056475788, 27447, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1354082Z     %dequantize_per_tensor_564 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_312, 0.00014935866056475788, 27447, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1354567Z     %transpose_77 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_564, 1, 2), kwargs = {})
2025-03-21T20:30:48.1355334Z     %quantize_per_tensor_313 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_77, 0.00014935866056475788, 27447, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1356107Z     %dequantize_per_tensor_565 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_313, 0.00014935866056475788, 27447, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1356531Z     %squeeze_11 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_565, -1), kwargs = {})
2025-03-21T20:30:48.1357232Z     %quantize_per_tensor_314 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_11, 0.00014935866056475788, 27447, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1358015Z     %dequantize_per_tensor_566 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_314, 0.00014935866056475788, 27447, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1358782Z     %dequantize_per_tensor_567 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_314, 0.00014935866056475788, 27447, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1359212Z     %sigmoid_1 : [num_users=1] = call_function[target=torch.ops.aten.sigmoid.default](args = (%dequantize_per_tensor_567,), kwargs = {})
2025-03-21T20:30:48.1359873Z     %quantize_per_tensor_315 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%sigmoid_1, 1.52587890625e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1360630Z     %dequantize_per_tensor_568 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_315, 1.52587890625e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1361103Z     %mul_20 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_566, %dequantize_per_tensor_568), kwargs = {})
2025-03-21T20:30:48.1361787Z     %quantize_per_tensor_316 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_20, 9.076054266188294e-05, 3068, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1362549Z     %dequantize_per_tensor_569 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_316, 9.076054266188294e-05, 3068, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1363010Z     %unsqueeze_12 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_560, -1), kwargs = {})
2025-03-21T20:30:48.1363731Z     %quantize_per_tensor_317 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_12, 0.00021398279932327569, 31590, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1364516Z     %dequantize_per_tensor_570 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_317, 0.00021398279932327569, 31590, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1364955Z     %transpose_78 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_570, 1, 2), kwargs = {})
2025-03-21T20:30:48.1365681Z     %quantize_per_tensor_318 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_78, 0.00021398279932327569, 31590, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1366499Z     %dequantize_per_tensor_571 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_318, 0.00021398279932327569, 31590, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1367057Z     %conv2d_12 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_571, %dequantize_per_tensor_17), kwargs = {})
2025-03-21T20:30:48.1367755Z     %quantize_per_tensor_319 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_12, 0.00023316948499996215, 31553, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1368538Z     %dequantize_per_tensor_572 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_319, 0.00023316948499996215, 31553, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1368977Z     %transpose_79 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_572, 1, 2), kwargs = {})
2025-03-21T20:30:48.1369770Z     %quantize_per_tensor_320 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_79, 0.00023316948499996215, 31553, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1370543Z     %dequantize_per_tensor_573 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_320, 0.00023316948499996215, 31553, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1370968Z     %squeeze_12 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_573, -1), kwargs = {})
2025-03-21T20:30:48.1371666Z     %quantize_per_tensor_321 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_12, 0.00023316948499996215, 31553, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1372451Z     %dequantize_per_tensor_574 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_321, 0.00023316948499996215, 31553, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1372919Z     %mul_21 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_569, %dequantize_per_tensor_574), kwargs = {})
2025-03-21T20:30:48.1373611Z     %quantize_per_tensor_322 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_21, 0.0009241419611498713, 33256, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1374374Z     %dequantize_per_tensor_575 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_322, 0.0009241419611498713, 33256, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1374841Z     %unsqueeze_13 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_575, -1), kwargs = {})
2025-03-21T20:30:48.1375555Z     %quantize_per_tensor_323 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_13, 0.0009241419611498713, 33256, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1376334Z     %dequantize_per_tensor_576 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_323, 0.0009241419611498713, 33256, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1376776Z     %transpose_80 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_576, 1, 2), kwargs = {})
2025-03-21T20:30:48.1377497Z     %quantize_per_tensor_324 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_80, 0.0009241419611498713, 33256, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1378335Z     %dequantize_per_tensor_577 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_324, 0.0009241419611498713, 33256, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1378890Z     %conv2d_13 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_577, %dequantize_per_tensor_18), kwargs = {})
2025-03-21T20:30:48.1379580Z     %quantize_per_tensor_325 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_13, 0.0008836374618113041, 9331, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1380354Z     %dequantize_per_tensor_578 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_325, 0.0008836374618113041, 9331, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1380788Z     %transpose_81 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_578, 1, 2), kwargs = {})
2025-03-21T20:30:48.1381511Z     %quantize_per_tensor_326 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_81, 0.0008836374618113041, 9331, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1382268Z     %dequantize_per_tensor_579 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_326, 0.0008836374618113041, 9331, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1382688Z     %squeeze_13 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_579, -1), kwargs = {})
2025-03-21T20:30:48.1383379Z     %quantize_per_tensor_327 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_13, 0.0008836374618113041, 9331, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1384157Z     %dequantize_per_tensor_580 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_327, 0.0008836374618113041, 9331, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1384628Z     %add_9 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_558, %dequantize_per_tensor_580), kwargs = {})
2025-03-21T20:30:48.1385313Z     %quantize_per_tensor_328 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_9, 0.0010317935375496745, 12458, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1386076Z     %dequantize_per_tensor_581 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_328, 0.0010317935375496745, 12458, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1386854Z     %dequantize_per_tensor_582 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_328, 0.0010317935375496745, 12458, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1387393Z     %rms_norm_4 : [num_users=1] = call_function[target=torch.ops.aten.rms_norm.default](args = (%dequantize_per_tensor_582, [768], %dequantize_per_tensor_19, 1e-05), kwargs = {})
2025-03-21T20:30:48.1388101Z     %quantize_per_tensor_329 : [num_users=3] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%rms_norm_4, 0.0003308423620183021, 21627, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1388859Z     %dequantize_per_tensor_583 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_329, 0.0003308423620183021, 21627, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1389633Z     %dequantize_per_tensor_584 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_329, 0.0003308423620183021, 21627, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1390498Z     %dequantize_per_tensor_585 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_329, 0.0003308423620183021, 21627, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1390966Z     %unsqueeze_14 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_585, -1), kwargs = {})
2025-03-21T20:30:48.1391673Z     %quantize_per_tensor_330 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_14, 0.0003308423620183021, 21627, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1392449Z     %dequantize_per_tensor_586 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_330, 0.0003308423620183021, 21627, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1392887Z     %transpose_82 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_586, 1, 2), kwargs = {})
2025-03-21T20:30:48.1393606Z     %quantize_per_tensor_331 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_82, 0.0003308423620183021, 21627, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1394367Z     %dequantize_per_tensor_587 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_331, 0.0003308423620183021, 21627, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1394879Z     %conv2d_14 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_587, %dequantize_per_tensor_20), kwargs = {})
2025-03-21T20:30:48.1395572Z     %quantize_per_tensor_332 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_14, 0.00036216730950400233, 19231, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1396359Z     %dequantize_per_tensor_588 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_332, 0.00036216730950400233, 19231, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1396794Z     %transpose_83 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_588, 1, 2), kwargs = {})
2025-03-21T20:30:48.1397513Z     %quantize_per_tensor_333 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_83, 0.00036216730950400233, 19231, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1398281Z     %dequantize_per_tensor_589 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_333, 0.00036216730950400233, 19231, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1398705Z     %squeeze_14 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_589, -1), kwargs = {})
2025-03-21T20:30:48.1399409Z     %quantize_per_tensor_334 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_14, 0.00036216730950400233, 19231, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1400186Z     %dequantize_per_tensor_590 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_334, 0.00036216730950400233, 19231, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1400637Z     %unsqueeze_15 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_584, -1), kwargs = {})
2025-03-21T20:30:48.1401354Z     %quantize_per_tensor_335 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_15, 0.0003308423620183021, 21627, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1402219Z     %dequantize_per_tensor_591 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_335, 0.0003308423620183021, 21627, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1402673Z     %transpose_84 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_591, 1, 2), kwargs = {})
2025-03-21T20:30:48.1403378Z     %quantize_per_tensor_336 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_84, 0.0003308423620183021, 21627, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1404154Z     %dequantize_per_tensor_592 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_336, 0.0003308423620183021, 21627, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1404660Z     %conv2d_15 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_592, %dequantize_per_tensor_21), kwargs = {})
2025-03-21T20:30:48.1405375Z     %quantize_per_tensor_337 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_15, 0.00037646826240234077, 30723, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1406146Z     %dequantize_per_tensor_593 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_337, 0.00037646826240234077, 30723, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1406583Z     %transpose_85 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_593, 1, 2), kwargs = {})
2025-03-21T20:30:48.1407303Z     %quantize_per_tensor_338 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_85, 0.00037646826240234077, 30723, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1408077Z     %dequantize_per_tensor_594 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_338, 0.00037646826240234077, 30723, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1408500Z     %squeeze_15 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_594, -1), kwargs = {})
2025-03-21T20:30:48.1409198Z     %quantize_per_tensor_339 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_15, 0.00037646826240234077, 30723, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1410039Z     %dequantize_per_tensor_595 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_339, 0.00037646826240234077, 30723, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1410495Z     %unsqueeze_16 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_583, -1), kwargs = {})
2025-03-21T20:30:48.1411212Z     %quantize_per_tensor_340 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_16, 0.0003308423620183021, 21627, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1411980Z     %dequantize_per_tensor_596 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_340, 0.0003308423620183021, 21627, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1412430Z     %transpose_86 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_596, 1, 2), kwargs = {})
2025-03-21T20:30:48.1413136Z     %quantize_per_tensor_341 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_86, 0.0003308423620183021, 21627, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1414013Z     %dequantize_per_tensor_597 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_341, 0.0003308423620183021, 21627, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1414514Z     %conv2d_16 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_597, %dequantize_per_tensor_22), kwargs = {})
2025-03-21T20:30:48.1415213Z     %quantize_per_tensor_342 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_16, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1415977Z     %dequantize_per_tensor_598 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_342, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1416426Z     %transpose_87 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_598, 1, 2), kwargs = {})
2025-03-21T20:30:48.1417135Z     %quantize_per_tensor_343 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_87, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1417910Z     %dequantize_per_tensor_599 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_343, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1418321Z     %squeeze_16 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_599, -1), kwargs = {})
2025-03-21T20:30:48.1419031Z     %quantize_per_tensor_344 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_16, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1419799Z     %dequantize_per_tensor_600 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_344, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1420249Z     %view_24 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_590, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.1420939Z     %quantize_per_tensor_345 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_24, 0.00036216730950400233, 19231, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1421720Z     %dequantize_per_tensor_601 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_345, 0.00036216730950400233, 19231, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1422156Z     %view_25 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_595, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.1422855Z     %quantize_per_tensor_346 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_25, 0.00037646826240234077, 30723, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1423623Z     %dequantize_per_tensor_602 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_346, 0.00037646826240234077, 30723, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1424065Z     %view_26 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_600, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.1424746Z     %quantize_per_tensor_347 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_26, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1425628Z     %dequantize_per_tensor_603 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_347, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1426107Z     %_to_copy_4 : [num_users=1] = call_function[target=torch.ops.aten._to_copy.default](args = (%dequantize_per_tensor_601,), kwargs = {dtype: torch.float32})
2025-03-21T20:30:48.1426812Z     %quantize_per_tensor_348 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%_to_copy_4, 0.00036216730950400233, 19231, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1427581Z     %dequantize_per_tensor_604 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_348, 0.00036216730950400233, 19231, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1428036Z     %view_27 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_604, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:30:48.1428725Z     %quantize_per_tensor_349 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_27, 0.00036216730950400233, 19231, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1429502Z     %dequantize_per_tensor_605 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_349, 0.00036216730950400233, 19231, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1429902Z     %unbind_4 : [num_users=2] = call_function[target=torch.ops.aten.unbind.int](args = (%dequantize_per_tensor_605, -1), kwargs = {})
2025-03-21T20:30:48.1430232Z     %getitem_8 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_4, 0), kwargs = {})
2025-03-21T20:30:48.1430548Z     %getitem_9 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_4, 1), kwargs = {})
2025-03-21T20:30:48.1431256Z     %quantize_per_tensor_350 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_8, 0.0002881281834561378, 24173, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1432020Z     %dequantize_per_tensor_606 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_350, 0.0002881281834561378, 24173, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1432999Z     %dequantize_per_tensor_607 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_350, 0.0002881281834561378, 24173, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1433708Z     %quantize_per_tensor_351 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_9, 0.00034527943353168666, 16967, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1434493Z     %dequantize_per_tensor_608 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_351, 0.00034527943353168666, 16967, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1435255Z     %dequantize_per_tensor_609 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_351, 0.00034527943353168666, 16967, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1435748Z     %_to_copy_5 : [num_users=1] = call_function[target=torch.ops.aten._to_copy.default](args = (%dequantize_per_tensor_602,), kwargs = {dtype: torch.float32})
2025-03-21T20:30:48.1436440Z     %quantize_per_tensor_352 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%_to_copy_5, 0.00037646826240234077, 30723, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1437374Z     %dequantize_per_tensor_610 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_352, 0.00037646826240234077, 30723, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1437821Z     %view_28 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_610, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:30:48.1438515Z     %quantize_per_tensor_353 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_28, 0.00037646826240234077, 30723, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1439282Z     %dequantize_per_tensor_611 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_353, 0.00037646826240234077, 30723, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1439703Z     %unbind_5 : [num_users=2] = call_function[target=torch.ops.aten.unbind.int](args = (%dequantize_per_tensor_611, -1), kwargs = {})
2025-03-21T20:30:48.1440022Z     %getitem_10 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_5, 0), kwargs = {})
2025-03-21T20:30:48.1440348Z     %getitem_11 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_5, 1), kwargs = {})
2025-03-21T20:30:48.1441045Z     %quantize_per_tensor_354 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_10, 0.00029378890758380294, 23361, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1441823Z     %dequantize_per_tensor_612 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_354, 0.00029378890758380294, 23361, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1442589Z     %dequantize_per_tensor_613 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_354, 0.00029378890758380294, 23361, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1443303Z     %quantize_per_tensor_355 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_11, 0.00037646826240234077, 30723, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1444072Z     %dequantize_per_tensor_614 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_355, 0.00037646826240234077, 30723, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1444852Z     %dequantize_per_tensor_615 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_355, 0.00037646826240234077, 30723, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1445277Z     %view_29 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_160, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:30:48.1445971Z     %quantize_per_tensor_356 : [num_users=4] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_29, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1446738Z     %dequantize_per_tensor_616 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_356, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1447510Z     %dequantize_per_tensor_617 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_356, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1448267Z     %dequantize_per_tensor_618 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_356, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1449131Z     %dequantize_per_tensor_619 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_356, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1449623Z     %view_30 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_172, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:30:48.1450320Z     %quantize_per_tensor_357 : [num_users=4] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_30, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1451078Z     %dequantize_per_tensor_620 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_357, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1451857Z     %dequantize_per_tensor_621 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_357, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1452619Z     %dequantize_per_tensor_622 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_357, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1453388Z     %dequantize_per_tensor_623 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_357, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1453854Z     %mul_22 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_607, %dequantize_per_tensor_619), kwargs = {})
2025-03-21T20:30:48.1454549Z     %quantize_per_tensor_358 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_22, 0.0002832972095347941, 23707, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1455312Z     %dequantize_per_tensor_624 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_358, 0.0002832972095347941, 23707, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1455794Z     %mul_23 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_608, %dequantize_per_tensor_622), kwargs = {})
2025-03-21T20:30:48.1456476Z     %quantize_per_tensor_359 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_23, 0.00015349165187217295, 32189, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1457261Z     %dequantize_per_tensor_625 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_359, 0.00015349165187217295, 32189, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1457726Z     %sub_4 : [num_users=1] = call_function[target=torch.ops.aten.sub.Tensor](args = (%dequantize_per_tensor_624, %dequantize_per_tensor_625), kwargs = {})
2025-03-21T20:30:48.1458404Z     %quantize_per_tensor_360 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%sub_4, 0.000280614010989666, 23955, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1459165Z     %dequantize_per_tensor_626 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_360, 0.000280614010989666, 23955, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1459640Z     %mul_24 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_606, %dequantize_per_tensor_623), kwargs = {})
2025-03-21T20:30:48.1460369Z     %quantize_per_tensor_361 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_24, 0.00019744332530535758, 33781, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1461189Z     %dequantize_per_tensor_627 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_361, 0.00019744332530535758, 33781, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1461668Z     %mul_25 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_609, %dequantize_per_tensor_618), kwargs = {})
2025-03-21T20:30:48.1462348Z     %quantize_per_tensor_362 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_25, 0.0003398616099730134, 16524, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1463130Z     %dequantize_per_tensor_628 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_362, 0.0003398616099730134, 16524, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1463599Z     %add_10 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_627, %dequantize_per_tensor_628), kwargs = {})
2025-03-21T20:30:48.1464290Z     %quantize_per_tensor_363 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_10, 0.0003456322301644832, 18868, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1465056Z     %dequantize_per_tensor_629 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_363, 0.0003456322301644832, 18868, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1465536Z     %mul_26 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_613, %dequantize_per_tensor_617), kwargs = {})
2025-03-21T20:30:48.1466217Z     %quantize_per_tensor_364 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_26, 0.0002919230901170522, 23481, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1466992Z     %dequantize_per_tensor_630 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_364, 0.0002919230901170522, 23481, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1467464Z     %mul_27 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_614, %dequantize_per_tensor_620), kwargs = {})
2025-03-21T20:30:48.1468154Z     %quantize_per_tensor_365 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_27, 0.00021678538178093731, 35772, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1468923Z     %dequantize_per_tensor_631 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_365, 0.00021678538178093731, 35772, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1469399Z     %sub_5 : [num_users=1] = call_function[target=torch.ops.aten.sub.Tensor](args = (%dequantize_per_tensor_630, %dequantize_per_tensor_631), kwargs = {})
2025-03-21T20:30:48.1470071Z     %quantize_per_tensor_366 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%sub_5, 0.0002932342467829585, 23779, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1470842Z     %dequantize_per_tensor_632 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_366, 0.0002932342467829585, 23779, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1471310Z     %mul_28 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_612, %dequantize_per_tensor_621), kwargs = {})
2025-03-21T20:30:48.1472043Z     %quantize_per_tensor_367 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_28, 0.0001832414127420634, 33825, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1472860Z     %dequantize_per_tensor_633 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_367, 0.0001832414127420634, 33825, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1473335Z     %mul_29 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_615, %dequantize_per_tensor_616), kwargs = {})
2025-03-21T20:30:48.1474013Z     %quantize_per_tensor_368 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_29, 0.0003678293142002076, 31068, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1474788Z     %dequantize_per_tensor_634 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_368, 0.0003678293142002076, 31068, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1475255Z     %add_11 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_633, %dequantize_per_tensor_634), kwargs = {})
2025-03-21T20:30:48.1475951Z     %quantize_per_tensor_369 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_11, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1476716Z     %dequantize_per_tensor_635 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_369, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1477235Z     %stack_4 : [num_users=1] = call_function[target=torch.ops.aten.stack.default](args = ([%dequantize_per_tensor_626, %dequantize_per_tensor_629], -1), kwargs = {})
2025-03-21T20:30:48.1477922Z     %quantize_per_tensor_370 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%stack_4, 0.0003486985806375742, 19278, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1478697Z     %dequantize_per_tensor_636 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_370, 0.0003486985806375742, 19278, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1479132Z     %view_31 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_636, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.1479825Z     %quantize_per_tensor_371 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_31, 0.0003486985806375742, 19278, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1480591Z     %dequantize_per_tensor_637 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_371, 0.0003486985806375742, 19278, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1481114Z     %stack_5 : [num_users=1] = call_function[target=torch.ops.aten.stack.default](args = ([%dequantize_per_tensor_632, %dequantize_per_tensor_635], -1), kwargs = {})
2025-03-21T20:30:48.1481803Z     %quantize_per_tensor_372 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%stack_5, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1482580Z     %dequantize_per_tensor_638 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_372, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1483015Z     %view_32 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_638, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.1483806Z     %quantize_per_tensor_373 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_32, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1484578Z     %dequantize_per_tensor_639 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_373, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1485078Z     %type_as_4 : [num_users=1] = call_function[target=torch.ops.aten.type_as.default](args = (%dequantize_per_tensor_637, %dequantize_per_tensor_601), kwargs = {})
2025-03-21T20:30:48.1485760Z     %quantize_per_tensor_374 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%type_as_4, 0.0003486985806375742, 19278, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1486540Z     %dequantize_per_tensor_640 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_374, 0.0003486985806375742, 19278, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1487034Z     %type_as_5 : [num_users=1] = call_function[target=torch.ops.aten.type_as.default](args = (%dequantize_per_tensor_639, %dequantize_per_tensor_602), kwargs = {})
2025-03-21T20:30:48.1487735Z     %quantize_per_tensor_375 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%type_as_5, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1488501Z     %dequantize_per_tensor_641 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_375, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1488950Z     %transpose_88 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_640, 1, 2), kwargs = {})
2025-03-21T20:30:48.1489723Z     %quantize_per_tensor_376 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_88, 0.0003486985806375742, 19278, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1490502Z     %dequantize_per_tensor_642 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_376, 0.0003486985806375742, 19278, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1491126Z     %index_put_4 : [num_users=1] = call_function[target=torch.ops.aten.index_put.default](args = (%dequantize_per_tensor_119, [None, %attn_options_input_pos], %dequantize_per_tensor_641), kwargs = {})
2025-03-21T20:30:48.1491846Z     %quantize_per_tensor_377 : [num_users=13] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_put_4, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1492631Z     %dequantize_per_tensor_643 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_377, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1493408Z     %dequantize_per_tensor_644 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_377, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1494172Z     %dequantize_per_tensor_645 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_377, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1494947Z     %dequantize_per_tensor_646 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_377, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1495811Z     %dequantize_per_tensor_647 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_377, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1496596Z     %dequantize_per_tensor_648 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_377, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1497360Z     %dequantize_per_tensor_649 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_377, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1498137Z     %dequantize_per_tensor_650 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_377, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1498911Z     %dequantize_per_tensor_651 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_377, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1499687Z     %dequantize_per_tensor_652 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_377, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1500456Z     %dequantize_per_tensor_653 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_377, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1501234Z     %dequantize_per_tensor_654 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_377, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1502004Z     %dequantize_per_tensor_655 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_377, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1502639Z     %index_put_5 : [num_users=1] = call_function[target=torch.ops.aten.index_put.default](args = (%dequantize_per_tensor_120, [None, %attn_options_input_pos], %dequantize_per_tensor_603), kwargs = {})
2025-03-21T20:30:48.1503339Z     %quantize_per_tensor_378 : [num_users=13] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_put_5, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1504112Z     %dequantize_per_tensor_656 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_378, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1504880Z     %dequantize_per_tensor_657 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_378, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1505655Z     %dequantize_per_tensor_658 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_378, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1506415Z     %dequantize_per_tensor_659 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_378, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1507226Z     %dequantize_per_tensor_660 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_378, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1508029Z     %dequantize_per_tensor_661 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_378, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1508802Z     %dequantize_per_tensor_662 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_378, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1509562Z     %dequantize_per_tensor_663 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_378, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1510334Z     %dequantize_per_tensor_664 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_378, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1511093Z     %dequantize_per_tensor_665 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_378, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1511862Z     %dequantize_per_tensor_666 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_378, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1512620Z     %dequantize_per_tensor_667 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_378, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1513393Z     %dequantize_per_tensor_668 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_378, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1513834Z     %transpose_89 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_655, 1, 2), kwargs = {})
2025-03-21T20:30:48.1514555Z     %quantize_per_tensor_379 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_89, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1515322Z     %dequantize_per_tensor_669 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_379, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1515737Z     %select_96 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_669, 0, 0), kwargs = {})
2025-03-21T20:30:48.1516438Z     %quantize_per_tensor_380 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_96, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1517217Z     %dequantize_per_tensor_670 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_380, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1517618Z     %select_97 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_670, 0, 0), kwargs = {})
2025-03-21T20:30:48.1518324Z     %quantize_per_tensor_381 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_97, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1519144Z     %dequantize_per_tensor_671 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_381, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1519640Z     %transpose_90 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_654, 1, 2), kwargs = {})
2025-03-21T20:30:48.1520351Z     %quantize_per_tensor_382 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_90, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1521127Z     %dequantize_per_tensor_672 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_382, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1521531Z     %select_98 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_672, 0, 0), kwargs = {})
2025-03-21T20:30:48.1522238Z     %quantize_per_tensor_383 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_98, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1523011Z     %dequantize_per_tensor_673 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_383, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1523422Z     %select_99 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_673, 0, 1), kwargs = {})
2025-03-21T20:30:48.1524117Z     %quantize_per_tensor_384 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_99, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1524896Z     %dequantize_per_tensor_674 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_384, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1525333Z     %transpose_91 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_653, 1, 2), kwargs = {})
2025-03-21T20:30:48.1526058Z     %quantize_per_tensor_385 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_91, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1526823Z     %dequantize_per_tensor_675 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_385, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1527243Z     %select_100 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_675, 0, 0), kwargs = {})
2025-03-21T20:30:48.1527944Z     %quantize_per_tensor_386 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_100, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1528730Z     %dequantize_per_tensor_676 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_386, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1529136Z     %select_101 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_676, 0, 2), kwargs = {})
2025-03-21T20:30:48.1529907Z     %quantize_per_tensor_387 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_101, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1530730Z     %dequantize_per_tensor_677 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_387, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1531225Z     %transpose_92 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_652, 1, 2), kwargs = {})
2025-03-21T20:30:48.1531934Z     %quantize_per_tensor_388 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_92, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1532888Z     %dequantize_per_tensor_678 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_388, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1533300Z     %select_102 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_678, 0, 0), kwargs = {})
2025-03-21T20:30:48.1534019Z     %quantize_per_tensor_389 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_102, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1534790Z     %dequantize_per_tensor_679 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_389, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1535209Z     %select_103 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_679, 0, 3), kwargs = {})
2025-03-21T20:30:48.1535909Z     %quantize_per_tensor_390 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_103, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1536691Z     %dequantize_per_tensor_680 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_390, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1537133Z     %transpose_93 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_651, 1, 2), kwargs = {})
2025-03-21T20:30:48.1537853Z     %quantize_per_tensor_391 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_93, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1538618Z     %dequantize_per_tensor_681 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_391, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1539037Z     %select_104 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_681, 0, 0), kwargs = {})
2025-03-21T20:30:48.1539740Z     %quantize_per_tensor_392 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_104, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1540523Z     %dequantize_per_tensor_682 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_392, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1540931Z     %select_105 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_682, 0, 4), kwargs = {})
2025-03-21T20:30:48.1541641Z     %quantize_per_tensor_393 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_105, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1542409Z     %dequantize_per_tensor_683 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_393, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1542997Z     %transpose_94 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_650, 1, 2), kwargs = {})
2025-03-21T20:30:48.1543709Z     %quantize_per_tensor_394 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_94, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1544490Z     %dequantize_per_tensor_684 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_394, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1544902Z     %select_106 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_684, 0, 0), kwargs = {})
2025-03-21T20:30:48.1545619Z     %quantize_per_tensor_395 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_106, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1546388Z     %dequantize_per_tensor_685 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_395, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1546807Z     %select_107 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_685, 0, 5), kwargs = {})
2025-03-21T20:30:48.1547509Z     %quantize_per_tensor_396 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_107, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1548290Z     %dequantize_per_tensor_686 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_396, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1548733Z     %transpose_95 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_649, 1, 2), kwargs = {})
2025-03-21T20:30:48.1549457Z     %quantize_per_tensor_397 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_95, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1550223Z     %dequantize_per_tensor_687 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_397, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1550651Z     %select_108 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_687, 0, 0), kwargs = {})
2025-03-21T20:30:48.1551355Z     %quantize_per_tensor_398 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_108, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1552142Z     %dequantize_per_tensor_688 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_398, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1552552Z     %select_109 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_688, 0, 6), kwargs = {})
2025-03-21T20:30:48.1553267Z     %quantize_per_tensor_399 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_109, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1554040Z     %dequantize_per_tensor_689 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_399, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1554616Z     %transpose_96 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_648, 1, 2), kwargs = {})
2025-03-21T20:30:48.1555331Z     %quantize_per_tensor_400 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_96, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1556114Z     %dequantize_per_tensor_690 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_400, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1556526Z     %select_110 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_690, 0, 0), kwargs = {})
2025-03-21T20:30:48.1557232Z     %quantize_per_tensor_401 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_110, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1558016Z     %dequantize_per_tensor_691 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_401, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1558424Z     %select_111 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_691, 0, 7), kwargs = {})
2025-03-21T20:30:48.1559140Z     %quantize_per_tensor_402 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_111, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1559907Z     %dequantize_per_tensor_692 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_402, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1560364Z     %transpose_97 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_647, 1, 2), kwargs = {})
2025-03-21T20:30:48.1561078Z     %quantize_per_tensor_403 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_97, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1561865Z     %dequantize_per_tensor_693 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_403, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1562280Z     %select_112 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_693, 0, 0), kwargs = {})
2025-03-21T20:30:48.1562999Z     %quantize_per_tensor_404 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_112, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1563779Z     %dequantize_per_tensor_694 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_404, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1564206Z     %select_113 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_694, 0, 8), kwargs = {})
2025-03-21T20:30:48.1564911Z     %quantize_per_tensor_405 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_113, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1565700Z     %dequantize_per_tensor_695 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_405, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1566246Z     %transpose_98 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_646, 1, 2), kwargs = {})
2025-03-21T20:30:48.1566969Z     %quantize_per_tensor_406 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_98, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1567736Z     %dequantize_per_tensor_696 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_406, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1568159Z     %select_114 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_696, 0, 0), kwargs = {})
2025-03-21T20:30:48.1568859Z     %quantize_per_tensor_407 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_114, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1569694Z     %dequantize_per_tensor_697 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_407, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1570102Z     %select_115 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_697, 0, 9), kwargs = {})
2025-03-21T20:30:48.1570811Z     %quantize_per_tensor_408 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_115, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1571582Z     %dequantize_per_tensor_698 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_408, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1572033Z     %transpose_99 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_645, 1, 2), kwargs = {})
2025-03-21T20:30:48.1572746Z     %quantize_per_tensor_409 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_99, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1573524Z     %dequantize_per_tensor_699 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_409, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1573932Z     %select_116 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_699, 0, 0), kwargs = {})
2025-03-21T20:30:48.1574641Z     %quantize_per_tensor_410 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_116, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1575413Z     %dequantize_per_tensor_700 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_410, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1575836Z     %select_117 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_700, 0, 10), kwargs = {})
2025-03-21T20:30:48.1576534Z     %quantize_per_tensor_411 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_117, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1577310Z     %dequantize_per_tensor_701 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_411, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1577823Z     %transpose_100 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_644, 1, 2), kwargs = {})
2025-03-21T20:30:48.1578600Z     %quantize_per_tensor_412 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_100, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1579368Z     %dequantize_per_tensor_702 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_412, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1579787Z     %select_118 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_702, 0, 0), kwargs = {})
2025-03-21T20:30:48.1580485Z     %quantize_per_tensor_413 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_118, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1581271Z     %dequantize_per_tensor_703 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_413, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1581684Z     %select_119 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_703, 0, 11), kwargs = {})
2025-03-21T20:30:48.1582397Z     %quantize_per_tensor_414 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_119, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1583165Z     %dequantize_per_tensor_704 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_414, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1584621Z     %cat_4 : [num_users=1] = call_function[target=torch.ops.aten.cat.default](args = ([%dequantize_per_tensor_671, %dequantize_per_tensor_674, %dequantize_per_tensor_677, %dequantize_per_tensor_680, %dequantize_per_tensor_683, %dequantize_per_tensor_686, %dequantize_per_tensor_689, %dequantize_per_tensor_692, %dequantize_per_tensor_695, %dequantize_per_tensor_698, %dequantize_per_tensor_701, %dequantize_per_tensor_704],), kwargs = {})
2025-03-21T20:30:48.1585304Z     %quantize_per_tensor_415 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%cat_4, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1586089Z     %dequantize_per_tensor_705 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_415, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1586535Z     %view_33 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_705, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:30:48.1587236Z     %quantize_per_tensor_416 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_33, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1588003Z     %dequantize_per_tensor_706 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_416, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1588460Z     %transpose_101 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_668, 1, 2), kwargs = {})
2025-03-21T20:30:48.1589174Z     %quantize_per_tensor_417 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_101, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1590041Z     %dequantize_per_tensor_707 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_417, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1590453Z     %select_120 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_707, 0, 0), kwargs = {})
2025-03-21T20:30:48.1591160Z     %quantize_per_tensor_418 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_120, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1591920Z     %dequantize_per_tensor_708 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_418, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1592349Z     %select_121 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_708, 0, 0), kwargs = {})
2025-03-21T20:30:48.1593049Z     %quantize_per_tensor_419 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_121, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1593820Z     %dequantize_per_tensor_709 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_419, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1594263Z     %transpose_102 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_667, 1, 2), kwargs = {})
2025-03-21T20:30:48.1594983Z     %quantize_per_tensor_420 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_102, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1595748Z     %dequantize_per_tensor_710 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_420, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1596173Z     %select_122 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_710, 0, 0), kwargs = {})
2025-03-21T20:30:48.1596867Z     %quantize_per_tensor_421 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_122, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1597640Z     %dequantize_per_tensor_711 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_421, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1598050Z     %select_123 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_711, 0, 1), kwargs = {})
2025-03-21T20:30:48.1598766Z     %quantize_per_tensor_422 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_123, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1599530Z     %dequantize_per_tensor_712 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_422, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1599984Z     %transpose_103 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_666, 1, 2), kwargs = {})
2025-03-21T20:30:48.1600700Z     %quantize_per_tensor_423 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_103, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1601525Z     %dequantize_per_tensor_713 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_423, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1601993Z     %select_124 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_713, 0, 0), kwargs = {})
2025-03-21T20:30:48.1602701Z     %quantize_per_tensor_424 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_124, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1603465Z     %dequantize_per_tensor_714 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_424, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1603887Z     %select_125 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_714, 0, 2), kwargs = {})
2025-03-21T20:30:48.1604590Z     %quantize_per_tensor_425 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_125, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1605363Z     %dequantize_per_tensor_715 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_425, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1605805Z     %transpose_104 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_665, 1, 2), kwargs = {})
2025-03-21T20:30:48.1606526Z     %quantize_per_tensor_426 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_104, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1607287Z     %dequantize_per_tensor_716 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_426, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1607714Z     %select_126 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_716, 0, 0), kwargs = {})
2025-03-21T20:30:48.1608409Z     %quantize_per_tensor_427 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_126, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1609184Z     %dequantize_per_tensor_717 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_427, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1609653Z     %select_127 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_717, 0, 3), kwargs = {})
2025-03-21T20:30:48.1610371Z     %quantize_per_tensor_428 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_127, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1611133Z     %dequantize_per_tensor_718 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_428, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1611587Z     %transpose_105 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_664, 1, 2), kwargs = {})
2025-03-21T20:30:48.1612295Z     %quantize_per_tensor_429 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_105, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1613119Z     %dequantize_per_tensor_719 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_429, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1613578Z     %select_128 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_719, 0, 0), kwargs = {})
2025-03-21T20:30:48.1614275Z     %quantize_per_tensor_430 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_128, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1615054Z     %dequantize_per_tensor_720 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_430, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1615465Z     %select_129 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_720, 0, 4), kwargs = {})
2025-03-21T20:30:48.1616176Z     %quantize_per_tensor_431 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_129, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1616938Z     %dequantize_per_tensor_721 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_431, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1617389Z     %transpose_106 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_663, 1, 2), kwargs = {})
2025-03-21T20:30:48.1618097Z     %quantize_per_tensor_432 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_106, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1618875Z     %dequantize_per_tensor_722 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_432, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1619288Z     %select_130 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_722, 0, 0), kwargs = {})
2025-03-21T20:30:48.1619994Z     %quantize_per_tensor_433 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_130, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1620753Z     %dequantize_per_tensor_723 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_433, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1621172Z     %select_131 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_723, 0, 5), kwargs = {})
2025-03-21T20:30:48.1621869Z     %quantize_per_tensor_434 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_131, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1622645Z     %dequantize_per_tensor_724 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_434, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1623087Z     %transpose_107 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_662, 1, 2), kwargs = {})
2025-03-21T20:30:48.1623814Z     %quantize_per_tensor_435 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_107, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1624621Z     %dequantize_per_tensor_725 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_435, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1625085Z     %select_132 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_725, 0, 0), kwargs = {})
2025-03-21T20:30:48.1625780Z     %quantize_per_tensor_436 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_132, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1626553Z     %dequantize_per_tensor_726 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_436, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1626961Z     %select_133 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_726, 0, 6), kwargs = {})
2025-03-21T20:30:48.1627669Z     %quantize_per_tensor_437 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_133, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1628439Z     %dequantize_per_tensor_727 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_437, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1628890Z     %transpose_108 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_661, 1, 2), kwargs = {})
2025-03-21T20:30:48.1629597Z     %quantize_per_tensor_438 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_108, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1630374Z     %dequantize_per_tensor_728 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_438, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1630787Z     %select_134 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_728, 0, 0), kwargs = {})
2025-03-21T20:30:48.1631492Z     %quantize_per_tensor_439 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_134, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1632398Z     %dequantize_per_tensor_729 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_439, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1632833Z     %select_135 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_729, 0, 7), kwargs = {})
2025-03-21T20:30:48.1633529Z     %quantize_per_tensor_440 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_135, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1634310Z     %dequantize_per_tensor_730 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_440, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1634748Z     %transpose_109 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_660, 1, 2), kwargs = {})
2025-03-21T20:30:48.1635471Z     %quantize_per_tensor_441 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_109, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1636314Z     %dequantize_per_tensor_731 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_441, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1636796Z     %select_136 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_731, 0, 0), kwargs = {})
2025-03-21T20:30:48.1637490Z     %quantize_per_tensor_442 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_136, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1638264Z     %dequantize_per_tensor_732 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_442, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1638672Z     %select_137 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_732, 0, 8), kwargs = {})
2025-03-21T20:30:48.1639381Z     %quantize_per_tensor_443 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_137, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1640145Z     %dequantize_per_tensor_733 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_443, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1640598Z     %transpose_110 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_659, 1, 2), kwargs = {})
2025-03-21T20:30:48.1641309Z     %quantize_per_tensor_444 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_110, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1642085Z     %dequantize_per_tensor_734 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_444, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1642497Z     %select_138 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_734, 0, 0), kwargs = {})
2025-03-21T20:30:48.1643207Z     %quantize_per_tensor_445 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_138, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1643971Z     %dequantize_per_tensor_735 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_445, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1644395Z     %select_139 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_735, 0, 9), kwargs = {})
2025-03-21T20:30:48.1645091Z     %quantize_per_tensor_446 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_139, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1645869Z     %dequantize_per_tensor_736 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_446, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1646309Z     %transpose_111 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_658, 1, 2), kwargs = {})
2025-03-21T20:30:48.1647031Z     %quantize_per_tensor_447 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_111, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1647839Z     %dequantize_per_tensor_737 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_447, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1648321Z     %select_140 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_737, 0, 0), kwargs = {})
2025-03-21T20:30:48.1649014Z     %quantize_per_tensor_448 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_140, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1649841Z     %dequantize_per_tensor_738 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_448, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1650252Z     %select_141 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_738, 0, 10), kwargs = {})
2025-03-21T20:30:48.1650965Z     %quantize_per_tensor_449 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_141, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1651727Z     %dequantize_per_tensor_739 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_449, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1652182Z     %transpose_112 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_657, 1, 2), kwargs = {})
2025-03-21T20:30:48.1652892Z     %quantize_per_tensor_450 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_112, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1653671Z     %dequantize_per_tensor_740 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_450, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1654084Z     %select_142 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_740, 0, 0), kwargs = {})
2025-03-21T20:30:48.1654783Z     %quantize_per_tensor_451 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_142, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1655556Z     %dequantize_per_tensor_741 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_451, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1655970Z     %select_143 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_741, 0, 11), kwargs = {})
2025-03-21T20:30:48.1656684Z     %quantize_per_tensor_452 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_143, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1657450Z     %dequantize_per_tensor_742 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_452, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1658909Z     %cat_5 : [num_users=1] = call_function[target=torch.ops.aten.cat.default](args = ([%dequantize_per_tensor_709, %dequantize_per_tensor_712, %dequantize_per_tensor_715, %dequantize_per_tensor_718, %dequantize_per_tensor_721, %dequantize_per_tensor_724, %dequantize_per_tensor_727, %dequantize_per_tensor_730, %dequantize_per_tensor_733, %dequantize_per_tensor_736, %dequantize_per_tensor_739, %dequantize_per_tensor_742],), kwargs = {})
2025-03-21T20:30:48.1659653Z     %quantize_per_tensor_453 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%cat_5, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1660469Z     %dequantize_per_tensor_743 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_453, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1660928Z     %view_34 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_743, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:30:48.1661614Z     %quantize_per_tensor_454 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_34, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1662393Z     %dequantize_per_tensor_744 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_454, 9.550915274303406e-05, 30065, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1663170Z     %quantize_per_tensor_455 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%dequantize_per_tensor_744, 0.00010338902211515233, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.1663962Z     %dequantize_per_tensor_745 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_455, 0.00010338902211515233, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.1664453Z     %index_4 : [num_users=1] = call_function[target=torch.ops.aten.index.Tensor](args = (%dequantize_per_tensor_121, [%attn_options_input_pos]), kwargs = {})
2025-03-21T20:30:48.1665160Z     %quantize_per_tensor_456 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_4, 0.0038910505827516317, 65535, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1665929Z     %dequantize_per_tensor_746 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_456, 0.0038910505827516317, 65535, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1666401Z     %transpose_113 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_706, -2, -1), kwargs = {})
2025-03-21T20:30:48.1667120Z     %quantize_per_tensor_457 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_113, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1667901Z     %dequantize_per_tensor_747 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_457, 0.00036907364847138524, 31320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1668665Z     %quantize_per_tensor_458 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%dequantize_per_tensor_747, 0.00038538043736480176, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.1669454Z     %dequantize_per_tensor_748 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_458, 0.00038538043736480176, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.1669962Z     %matmul_4 : [num_users=1] = call_function[target=torch.ops.aten.matmul.default](args = (%dequantize_per_tensor_642, %dequantize_per_tensor_748), kwargs = {})
2025-03-21T20:30:48.1670666Z     %quantize_per_tensor_459 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%matmul_4, 0.004083077888935804, 41914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1671427Z     %dequantize_per_tensor_749 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_459, 0.004083077888935804, 41914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1672268Z     %dequantize_per_tensor_750 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param151, 1.9073777366429567e-06, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1672738Z     %mul_30 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_749, %dequantize_per_tensor_750), kwargs = {})
2025-03-21T20:30:48.1673428Z     %quantize_per_tensor_460 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_30, 0.0005103847361169755, 41914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1674189Z     %dequantize_per_tensor_751 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_460, 0.0005103847361169755, 41914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1674672Z     %add_12 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_751, %dequantize_per_tensor_746), kwargs = {})
2025-03-21T20:30:48.1675353Z     %quantize_per_tensor_461 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_12, 0.0043187374249100685, 62811, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1676129Z     %dequantize_per_tensor_752 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_461, 0.0043187374249100685, 62811, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1676542Z     %softmax_2 : [num_users=1] = call_function[target=torch.ops.aten.softmax.int](args = (%dequantize_per_tensor_752, -1), kwargs = {})
2025-03-21T20:30:48.1677243Z     %quantize_per_tensor_462 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%softmax_2, 1.5259021893143654e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1678006Z     %dequantize_per_tensor_753 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_462, 1.5259021893143654e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1678513Z     %matmul_5 : [num_users=1] = call_function[target=torch.ops.aten.matmul.default](args = (%dequantize_per_tensor_753, %dequantize_per_tensor_745), kwargs = {})
2025-03-21T20:30:48.1679217Z     %quantize_per_tensor_463 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%matmul_5, 5.6490640417905524e-05, 31487, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1679985Z     %dequantize_per_tensor_754 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_463, 5.6490640417905524e-05, 31487, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1680443Z     %transpose_114 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_754, 1, 2), kwargs = {})
2025-03-21T20:30:48.1681160Z     %quantize_per_tensor_464 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_114, 5.6490640417905524e-05, 31487, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1681939Z     %dequantize_per_tensor_755 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_464, 5.6490640417905524e-05, 31487, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1682363Z     %view_35 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_755, [1, 1, 768]), kwargs = {})
2025-03-21T20:30:48.1683058Z     %quantize_per_tensor_465 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_35, 5.6490640417905524e-05, 31487, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1683921Z     %dequantize_per_tensor_756 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_465, 5.6490640417905524e-05, 31487, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1684387Z     %unsqueeze_17 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_756, -1), kwargs = {})
2025-03-21T20:30:48.1685095Z     %quantize_per_tensor_466 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_17, 5.6490640417905524e-05, 31487, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1685873Z     %dequantize_per_tensor_757 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_466, 5.6490640417905524e-05, 31487, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1686316Z     %transpose_115 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_757, 1, 2), kwargs = {})
2025-03-21T20:30:48.1687047Z     %quantize_per_tensor_467 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_115, 5.6490640417905524e-05, 31487, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1687815Z     %dequantize_per_tensor_758 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_467, 5.6490640417905524e-05, 31487, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1688324Z     %conv2d_17 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_758, %dequantize_per_tensor_23), kwargs = {})
2025-03-21T20:30:48.1689021Z     %quantize_per_tensor_468 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_17, 0.00010611177276587114, 33703, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1689860Z     %dequantize_per_tensor_759 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_468, 0.00010611177276587114, 33703, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1690300Z     %transpose_116 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_759, 1, 2), kwargs = {})
2025-03-21T20:30:48.1691032Z     %quantize_per_tensor_469 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_116, 0.00010611177276587114, 33703, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1691800Z     %dequantize_per_tensor_760 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_469, 0.00010611177276587114, 33703, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1692230Z     %squeeze_17 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_760, -1), kwargs = {})
2025-03-21T20:30:48.1692924Z     %quantize_per_tensor_470 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_17, 0.00010611177276587114, 33703, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1693700Z     %dequantize_per_tensor_761 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_470, 0.00010611177276587114, 33703, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1694164Z     %add_13 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_581, %dequantize_per_tensor_761), kwargs = {})
2025-03-21T20:30:48.1694916Z     %quantize_per_tensor_471 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_13, 0.001073345891200006, 11837, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1695722Z     %dequantize_per_tensor_762 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_471, 0.001073345891200006, 11837, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1696489Z     %dequantize_per_tensor_763 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_471, 0.001073345891200006, 11837, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1697033Z     %rms_norm_5 : [num_users=1] = call_function[target=torch.ops.aten.rms_norm.default](args = (%dequantize_per_tensor_763, [768], %dequantize_per_tensor_24, 1e-05), kwargs = {})
2025-03-21T20:30:48.1697746Z     %quantize_per_tensor_472 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%rms_norm_5, 0.00031091910204850137, 15960, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1698523Z     %dequantize_per_tensor_764 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_472, 0.00031091910204850137, 15960, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1699303Z     %dequantize_per_tensor_765 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_472, 0.00031091910204850137, 15960, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1699759Z     %unsqueeze_18 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_765, -1), kwargs = {})
2025-03-21T20:30:48.1700485Z     %quantize_per_tensor_473 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_18, 0.00031091910204850137, 15960, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1701257Z     %dequantize_per_tensor_766 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_473, 0.00031091910204850137, 15960, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1701717Z     %transpose_117 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_766, 1, 2), kwargs = {})
2025-03-21T20:30:48.1702431Z     %quantize_per_tensor_474 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_117, 0.00031091910204850137, 15960, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1703212Z     %dequantize_per_tensor_767 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_474, 0.00031091910204850137, 15960, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1703712Z     %conv2d_18 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_767, %dequantize_per_tensor_25), kwargs = {})
2025-03-21T20:30:48.1704424Z     %quantize_per_tensor_475 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_18, 0.00018055648251902312, 33284, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1705195Z     %dequantize_per_tensor_768 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_475, 0.00018055648251902312, 33284, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1705644Z     %transpose_118 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_768, 1, 2), kwargs = {})
2025-03-21T20:30:48.1706356Z     %quantize_per_tensor_476 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_118, 0.00018055648251902312, 33284, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1707187Z     %dequantize_per_tensor_769 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_476, 0.00018055648251902312, 33284, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1707641Z     %squeeze_18 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_769, -1), kwargs = {})
2025-03-21T20:30:48.1708351Z     %quantize_per_tensor_477 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_18, 0.00018055648251902312, 33284, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1709125Z     %dequantize_per_tensor_770 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_477, 0.00018055648251902312, 33284, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1709912Z     %dequantize_per_tensor_771 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_477, 0.00018055648251902312, 33284, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1710339Z     %sigmoid_2 : [num_users=1] = call_function[target=torch.ops.aten.sigmoid.default](args = (%dequantize_per_tensor_771,), kwargs = {})
2025-03-21T20:30:48.1711018Z     %quantize_per_tensor_478 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%sigmoid_2, 1.52587890625e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1711760Z     %dequantize_per_tensor_772 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_478, 1.52587890625e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1712242Z     %mul_31 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_770, %dequantize_per_tensor_772), kwargs = {})
2025-03-21T20:30:48.1712924Z     %quantize_per_tensor_479 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_31, 9.284297266276553e-05, 2999, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1713705Z     %dequantize_per_tensor_773 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_479, 9.284297266276553e-05, 2999, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1714160Z     %unsqueeze_19 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_764, -1), kwargs = {})
2025-03-21T20:30:48.1714888Z     %quantize_per_tensor_480 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_19, 0.00031091910204850137, 15960, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1715662Z     %dequantize_per_tensor_774 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_480, 0.00031091910204850137, 15960, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1716118Z     %transpose_119 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_774, 1, 2), kwargs = {})
2025-03-21T20:30:48.1716833Z     %quantize_per_tensor_481 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_119, 0.00031091910204850137, 15960, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1717614Z     %dequantize_per_tensor_775 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_481, 0.00031091910204850137, 15960, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1718114Z     %conv2d_19 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_775, %dequantize_per_tensor_26), kwargs = {})
2025-03-21T20:30:48.1718864Z     %quantize_per_tensor_482 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_19, 0.00019716951646842062, 31579, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1719676Z     %dequantize_per_tensor_776 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_482, 0.00019716951646842062, 31579, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1720132Z     %transpose_120 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_776, 1, 2), kwargs = {})
2025-03-21T20:30:48.1720849Z     %quantize_per_tensor_483 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_120, 0.00019716951646842062, 31579, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1721632Z     %dequantize_per_tensor_777 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_483, 0.00019716951646842062, 31579, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1722046Z     %squeeze_19 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_777, -1), kwargs = {})
2025-03-21T20:30:48.1722760Z     %quantize_per_tensor_484 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_19, 0.00019716951646842062, 31579, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1723526Z     %dequantize_per_tensor_778 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_484, 0.00019716951646842062, 31579, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1724010Z     %mul_32 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_773, %dequantize_per_tensor_778), kwargs = {})
2025-03-21T20:30:48.1724689Z     %quantize_per_tensor_485 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_32, 0.0009127886733040214, 36679, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1725467Z     %dequantize_per_tensor_779 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_485, 0.0009127886733040214, 36679, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1725917Z     %unsqueeze_20 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_779, -1), kwargs = {})
2025-03-21T20:30:48.1726630Z     %quantize_per_tensor_486 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_20, 0.0009127886733040214, 36679, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1727394Z     %dequantize_per_tensor_780 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_486, 0.0009127886733040214, 36679, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1727850Z     %transpose_121 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_780, 1, 2), kwargs = {})
2025-03-21T20:30:48.1728560Z     %quantize_per_tensor_487 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_121, 0.0009127886733040214, 36679, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1729391Z     %dequantize_per_tensor_781 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_487, 0.0009127886733040214, 36679, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1729897Z     %conv2d_20 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_781, %dequantize_per_tensor_27), kwargs = {})
2025-03-21T20:30:48.1730708Z     %quantize_per_tensor_488 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_20, 0.0011877048527821898, 2626, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1731467Z     %dequantize_per_tensor_782 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_488, 0.0011877048527821898, 2626, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1731924Z     %transpose_122 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_782, 1, 2), kwargs = {})
2025-03-21T20:30:48.1732796Z     %quantize_per_tensor_489 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_122, 0.0011877048527821898, 2626, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1733576Z     %dequantize_per_tensor_783 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_489, 0.0011877048527821898, 2626, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1733992Z     %squeeze_20 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_783, -1), kwargs = {})
2025-03-21T20:30:48.1734702Z     %quantize_per_tensor_490 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_20, 0.0011877048527821898, 2626, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1735459Z     %dequantize_per_tensor_784 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_490, 0.0011877048527821898, 2626, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1735926Z     %add_14 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_762, %dequantize_per_tensor_784), kwargs = {})
2025-03-21T20:30:48.1736617Z     %quantize_per_tensor_491 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_14, 0.0020524393767118454, 7490, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1737382Z     %dequantize_per_tensor_785 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_491, 0.0020524393767118454, 7490, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1738157Z     %dequantize_per_tensor_786 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_491, 0.0020524393767118454, 7490, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1738698Z     %rms_norm_6 : [num_users=1] = call_function[target=torch.ops.aten.rms_norm.default](args = (%dequantize_per_tensor_786, [768], %dequantize_per_tensor_28, 1e-05), kwargs = {})
2025-03-21T20:30:48.1739410Z     %quantize_per_tensor_492 : [num_users=3] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%rms_norm_6, 0.00036565581103786826, 25893, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1740182Z     %dequantize_per_tensor_787 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_492, 0.00036565581103786826, 25893, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1740963Z     %dequantize_per_tensor_788 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_492, 0.00036565581103786826, 25893, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1741739Z     %dequantize_per_tensor_789 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_492, 0.00036565581103786826, 25893, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1742284Z     %unsqueeze_21 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_789, -1), kwargs = {})
2025-03-21T20:30:48.1743081Z     %quantize_per_tensor_493 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_21, 0.00036565581103786826, 25893, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1743859Z     %dequantize_per_tensor_790 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_493, 0.00036565581103786826, 25893, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1744301Z     %transpose_123 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_790, 1, 2), kwargs = {})
2025-03-21T20:30:48.1745027Z     %quantize_per_tensor_494 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_123, 0.00036565581103786826, 25893, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1745801Z     %dequantize_per_tensor_791 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_494, 0.00036565581103786826, 25893, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1746317Z     %conv2d_21 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_791, %dequantize_per_tensor_29), kwargs = {})
2025-03-21T20:30:48.1747013Z     %quantize_per_tensor_495 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_21, 0.00035187334287911654, 29898, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1747794Z     %dequantize_per_tensor_792 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_495, 0.00035187334287911654, 29898, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1748238Z     %transpose_124 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_792, 1, 2), kwargs = {})
2025-03-21T20:30:48.1748974Z     %quantize_per_tensor_496 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_124, 0.00035187334287911654, 29898, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1749740Z     %dequantize_per_tensor_793 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_496, 0.00035187334287911654, 29898, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1750165Z     %squeeze_21 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_793, -1), kwargs = {})
2025-03-21T20:30:48.1750865Z     %quantize_per_tensor_497 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_21, 0.00035187334287911654, 29898, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1751651Z     %dequantize_per_tensor_794 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_497, 0.00035187334287911654, 29898, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1752107Z     %unsqueeze_22 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_788, -1), kwargs = {})
2025-03-21T20:30:48.1752825Z     %quantize_per_tensor_498 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_22, 0.00036565581103786826, 25893, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1753593Z     %dequantize_per_tensor_795 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_498, 0.00036565581103786826, 25893, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1754092Z     %transpose_125 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_795, 1, 2), kwargs = {})
2025-03-21T20:30:48.1754853Z     %quantize_per_tensor_499 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_125, 0.00036565581103786826, 25893, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1755633Z     %dequantize_per_tensor_796 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_499, 0.00036565581103786826, 25893, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1756137Z     %conv2d_22 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_796, %dequantize_per_tensor_30), kwargs = {})
2025-03-21T20:30:48.1756844Z     %quantize_per_tensor_500 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_22, 0.00039280077908188105, 32440, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1757618Z     %dequantize_per_tensor_797 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_500, 0.00039280077908188105, 32440, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1758072Z     %transpose_126 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_797, 1, 2), kwargs = {})
2025-03-21T20:30:48.1758786Z     %quantize_per_tensor_501 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_126, 0.00039280077908188105, 32440, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1759567Z     %dequantize_per_tensor_798 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_501, 0.00039280077908188105, 32440, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1759982Z     %squeeze_22 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_798, -1), kwargs = {})
2025-03-21T20:30:48.1760697Z     %quantize_per_tensor_502 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_22, 0.00039280077908188105, 32440, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1761461Z     %dequantize_per_tensor_799 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_502, 0.00039280077908188105, 32440, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1761928Z     %unsqueeze_23 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_787, -1), kwargs = {})
2025-03-21T20:30:48.1762636Z     %quantize_per_tensor_503 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_23, 0.00036565581103786826, 25893, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1763419Z     %dequantize_per_tensor_800 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_503, 0.00036565581103786826, 25893, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1790889Z     %transpose_127 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_800, 1, 2), kwargs = {})
2025-03-21T20:30:48.1791747Z     %quantize_per_tensor_504 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_127, 0.00036565581103786826, 25893, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1792526Z     %dequantize_per_tensor_801 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_504, 0.00036565581103786826, 25893, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1793188Z     %conv2d_23 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_801, %dequantize_per_tensor_31), kwargs = {})
2025-03-21T20:30:48.1793944Z     %quantize_per_tensor_505 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_23, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1794728Z     %dequantize_per_tensor_802 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_505, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1795172Z     %transpose_128 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_802, 1, 2), kwargs = {})
2025-03-21T20:30:48.1795909Z     %quantize_per_tensor_506 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_128, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1796681Z     %dequantize_per_tensor_803 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_506, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1797110Z     %squeeze_23 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_803, -1), kwargs = {})
2025-03-21T20:30:48.1797807Z     %quantize_per_tensor_507 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_23, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1798587Z     %dequantize_per_tensor_804 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_507, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1799031Z     %view_36 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_794, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.1799730Z     %quantize_per_tensor_508 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_36, 0.00035187334287911654, 29898, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1800490Z     %dequantize_per_tensor_805 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_508, 0.00035187334287911654, 29898, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1800937Z     %view_37 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_799, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.1801620Z     %quantize_per_tensor_509 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_37, 0.00039280077908188105, 32440, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1802407Z     %dequantize_per_tensor_806 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_509, 0.00039280077908188105, 32440, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1802843Z     %view_38 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_804, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.1803541Z     %quantize_per_tensor_510 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_38, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1804306Z     %dequantize_per_tensor_807 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_510, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1804841Z     %_to_copy_6 : [num_users=1] = call_function[target=torch.ops.aten._to_copy.default](args = (%dequantize_per_tensor_805,), kwargs = {dtype: torch.float32})
2025-03-21T20:30:48.1805597Z     %quantize_per_tensor_511 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%_to_copy_6, 0.00035187334287911654, 29898, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1806379Z     %dequantize_per_tensor_808 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_511, 0.00035187334287911654, 29898, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1806823Z     %view_39 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_808, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:30:48.1807525Z     %quantize_per_tensor_512 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_39, 0.00035187334287911654, 29898, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1808296Z     %dequantize_per_tensor_809 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_512, 0.00035187334287911654, 29898, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1808710Z     %unbind_6 : [num_users=2] = call_function[target=torch.ops.aten.unbind.int](args = (%dequantize_per_tensor_809, -1), kwargs = {})
2025-03-21T20:30:48.1809027Z     %getitem_12 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_6, 0), kwargs = {})
2025-03-21T20:30:48.1809422Z     %getitem_13 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_6, 1), kwargs = {})
2025-03-21T20:30:48.1810138Z     %quantize_per_tensor_513 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_12, 0.00035187334287911654, 29898, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1810916Z     %dequantize_per_tensor_810 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_513, 0.00035187334287911654, 29898, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1811693Z     %dequantize_per_tensor_811 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_513, 0.00035187334287911654, 29898, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1812384Z     %quantize_per_tensor_514 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_13, 0.0003007998166140169, 27134, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1813165Z     %dequantize_per_tensor_812 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_514, 0.0003007998166140169, 27134, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1813950Z     %dequantize_per_tensor_813 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_514, 0.0003007998166140169, 27134, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1814427Z     %_to_copy_7 : [num_users=1] = call_function[target=torch.ops.aten._to_copy.default](args = (%dequantize_per_tensor_806,), kwargs = {dtype: torch.float32})
2025-03-21T20:30:48.1815115Z     %quantize_per_tensor_515 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%_to_copy_7, 0.00039280077908188105, 32440, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1815893Z     %dequantize_per_tensor_814 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_515, 0.00039280077908188105, 32440, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1816391Z     %view_40 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_814, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:30:48.1817136Z     %quantize_per_tensor_516 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_40, 0.00039280077908188105, 32440, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1817904Z     %dequantize_per_tensor_815 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_516, 0.00039280077908188105, 32440, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1818320Z     %unbind_7 : [num_users=2] = call_function[target=torch.ops.aten.unbind.int](args = (%dequantize_per_tensor_815, -1), kwargs = {})
2025-03-21T20:30:48.1818634Z     %getitem_14 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_7, 0), kwargs = {})
2025-03-21T20:30:48.1818958Z     %getitem_15 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_7, 1), kwargs = {})
2025-03-21T20:30:48.1819657Z     %quantize_per_tensor_517 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_14, 0.0003777415840886533, 31121, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1820435Z     %dequantize_per_tensor_816 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_517, 0.0003777415840886533, 31121, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1821194Z     %dequantize_per_tensor_817 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_517, 0.0003777415840886533, 31121, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1821900Z     %quantize_per_tensor_518 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_15, 0.00037405197508633137, 34066, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1822670Z     %dequantize_per_tensor_818 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_518, 0.00037405197508633137, 34066, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1823450Z     %dequantize_per_tensor_819 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_518, 0.00037405197508633137, 34066, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1823880Z     %view_41 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_159, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:30:48.1824573Z     %quantize_per_tensor_519 : [num_users=4] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_41, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1825338Z     %dequantize_per_tensor_820 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_519, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1826113Z     %dequantize_per_tensor_821 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_519, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1826870Z     %dequantize_per_tensor_822 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_519, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1827635Z     %dequantize_per_tensor_823 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_519, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1828111Z     %view_42 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_171, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:30:48.1828850Z     %quantize_per_tensor_520 : [num_users=4] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_42, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1829609Z     %dequantize_per_tensor_824 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_520, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1830382Z     %dequantize_per_tensor_825 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_520, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1831140Z     %dequantize_per_tensor_826 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_520, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1831915Z     %dequantize_per_tensor_827 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_520, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1832584Z     %mul_33 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_811, %dequantize_per_tensor_823), kwargs = {})
2025-03-21T20:30:48.1833282Z     %quantize_per_tensor_521 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_33, 0.00034635368501767516, 29709, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1834054Z     %dequantize_per_tensor_828 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_521, 0.00034635368501767516, 29709, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1834539Z     %mul_34 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_812, %dequantize_per_tensor_826), kwargs = {})
2025-03-21T20:30:48.1835222Z     %quantize_per_tensor_522 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_34, 0.00016881964984349906, 32450, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1836003Z     %dequantize_per_tensor_829 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_522, 0.00016881964984349906, 32450, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1836469Z     %sub_6 : [num_users=1] = call_function[target=torch.ops.aten.sub.Tensor](args = (%dequantize_per_tensor_828, %dequantize_per_tensor_829), kwargs = {})
2025-03-21T20:30:48.1837159Z     %quantize_per_tensor_523 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%sub_6, 0.0003396201936993748, 29394, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1837925Z     %dequantize_per_tensor_830 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_523, 0.0003396201936993748, 29394, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1838403Z     %mul_35 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_810, %dequantize_per_tensor_827), kwargs = {})
2025-03-21T20:30:48.1839083Z     %quantize_per_tensor_524 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_35, 0.0001840081822592765, 33501, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1839950Z     %dequantize_per_tensor_831 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_524, 0.0001840081822592765, 33501, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1840479Z     %mul_36 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_813, %dequantize_per_tensor_822), kwargs = {})
2025-03-21T20:30:48.1841169Z     %quantize_per_tensor_525 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_36, 0.00029949701274745166, 27196, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1841934Z     %dequantize_per_tensor_832 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_525, 0.00029949701274745166, 27196, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1842411Z     %add_15 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_831, %dequantize_per_tensor_832), kwargs = {})
2025-03-21T20:30:48.1843096Z     %quantize_per_tensor_526 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_15, 0.0002954587689600885, 27289, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1843880Z     %dequantize_per_tensor_833 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_526, 0.0002954587689600885, 27289, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1844347Z     %mul_37 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_817, %dequantize_per_tensor_821), kwargs = {})
2025-03-21T20:30:48.1845046Z     %quantize_per_tensor_527 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_37, 0.00037480672472156584, 31015, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1845819Z     %dequantize_per_tensor_834 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_527, 0.00037480672472156584, 31015, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1846305Z     %mul_38 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_818, %dequantize_per_tensor_824), kwargs = {})
2025-03-21T20:30:48.1846986Z     %quantize_per_tensor_528 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_38, 0.0001904213277157396, 33744, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1847770Z     %dequantize_per_tensor_835 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_528, 0.0001904213277157396, 33744, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1848236Z     %sub_7 : [num_users=1] = call_function[target=torch.ops.aten.sub.Tensor](args = (%dequantize_per_tensor_834, %dequantize_per_tensor_835), kwargs = {})
2025-03-21T20:30:48.1848929Z     %quantize_per_tensor_529 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%sub_7, 0.0003823137958534062, 31137, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1849753Z     %dequantize_per_tensor_836 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_529, 0.0003823137958534062, 31137, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1850236Z     %mul_39 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_816, %dequantize_per_tensor_825), kwargs = {})
2025-03-21T20:30:48.1850917Z     %quantize_per_tensor_530 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_39, 0.00017462005780544132, 35580, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1851750Z     %dequantize_per_tensor_837 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_530, 0.00017462005780544132, 35580, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1852274Z     %mul_40 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_819, %dequantize_per_tensor_820), kwargs = {})
2025-03-21T20:30:48.1852970Z     %quantize_per_tensor_531 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_40, 0.00036741403164342046, 33632, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1853737Z     %dequantize_per_tensor_838 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_531, 0.00036741403164342046, 33632, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1854216Z     %add_16 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_837, %dequantize_per_tensor_838), kwargs = {})
2025-03-21T20:30:48.1854902Z     %quantize_per_tensor_532 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_16, 0.00036854256177321076, 33858, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1855686Z     %dequantize_per_tensor_839 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_532, 0.00036854256177321076, 33858, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1856199Z     %stack_6 : [num_users=1] = call_function[target=torch.ops.aten.stack.default](args = ([%dequantize_per_tensor_830, %dequantize_per_tensor_833], -1), kwargs = {})
2025-03-21T20:30:48.1856897Z     %quantize_per_tensor_533 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%stack_6, 0.0003396201936993748, 29394, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1857662Z     %dequantize_per_tensor_840 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_533, 0.0003396201936993748, 29394, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1858114Z     %view_43 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_840, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.1858794Z     %quantize_per_tensor_534 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_43, 0.0003396201936993748, 29394, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1859567Z     %dequantize_per_tensor_841 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_534, 0.0003396201936993748, 29394, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1860077Z     %stack_7 : [num_users=1] = call_function[target=torch.ops.aten.stack.default](args = ([%dequantize_per_tensor_836, %dequantize_per_tensor_839], -1), kwargs = {})
2025-03-21T20:30:48.1860780Z     %quantize_per_tensor_535 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%stack_7, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1861546Z     %dequantize_per_tensor_842 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_535, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1861991Z     %view_44 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_842, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.1862668Z     %quantize_per_tensor_536 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_44, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1863489Z     %dequantize_per_tensor_843 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_536, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1864027Z     %type_as_6 : [num_users=1] = call_function[target=torch.ops.aten.type_as.default](args = (%dequantize_per_tensor_841, %dequantize_per_tensor_805), kwargs = {})
2025-03-21T20:30:48.1864724Z     %quantize_per_tensor_537 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%type_as_6, 0.0003396201936993748, 29394, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1865486Z     %dequantize_per_tensor_844 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_537, 0.0003396201936993748, 29394, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1865992Z     %type_as_7 : [num_users=1] = call_function[target=torch.ops.aten.type_as.default](args = (%dequantize_per_tensor_843, %dequantize_per_tensor_806), kwargs = {})
2025-03-21T20:30:48.1866685Z     %quantize_per_tensor_538 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%type_as_7, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1867459Z     %dequantize_per_tensor_845 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_538, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1867901Z     %transpose_129 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_844, 1, 2), kwargs = {})
2025-03-21T20:30:48.1868628Z     %quantize_per_tensor_539 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_129, 0.0003396201936993748, 29394, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1869395Z     %dequantize_per_tensor_846 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_539, 0.0003396201936993748, 29394, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1870034Z     %index_put_6 : [num_users=1] = call_function[target=torch.ops.aten.index_put.default](args = (%dequantize_per_tensor_122, [None, %attn_options_input_pos], %dequantize_per_tensor_845), kwargs = {})
2025-03-21T20:30:48.1870731Z     %quantize_per_tensor_540 : [num_users=13] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_put_6, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1871505Z     %dequantize_per_tensor_847 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_540, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1872268Z     %dequantize_per_tensor_848 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_540, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1873041Z     %dequantize_per_tensor_849 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_540, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1873799Z     %dequantize_per_tensor_850 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_540, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1874573Z     %dequantize_per_tensor_851 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_540, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1875374Z     %dequantize_per_tensor_852 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_540, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1876190Z     %dequantize_per_tensor_853 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_540, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1876948Z     %dequantize_per_tensor_854 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_540, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1877725Z     %dequantize_per_tensor_855 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_540, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1878489Z     %dequantize_per_tensor_856 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_540, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1879264Z     %dequantize_per_tensor_857 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_540, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1880020Z     %dequantize_per_tensor_858 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_540, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1880793Z     %dequantize_per_tensor_859 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_540, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1881423Z     %index_put_7 : [num_users=1] = call_function[target=torch.ops.aten.index_put.default](args = (%dequantize_per_tensor_123, [None, %attn_options_input_pos], %dequantize_per_tensor_807), kwargs = {})
2025-03-21T20:30:48.1882141Z     %quantize_per_tensor_541 : [num_users=13] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_put_7, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1882908Z     %dequantize_per_tensor_860 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_541, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1883685Z     %dequantize_per_tensor_861 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_541, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1884453Z     %dequantize_per_tensor_862 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_541, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1885234Z     %dequantize_per_tensor_863 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_541, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1885997Z     %dequantize_per_tensor_864 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_541, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1886777Z     %dequantize_per_tensor_865 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_541, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1887638Z     %dequantize_per_tensor_866 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_541, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1888416Z     %dequantize_per_tensor_867 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_541, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1889176Z     %dequantize_per_tensor_868 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_541, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1890042Z     %dequantize_per_tensor_869 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_541, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1890817Z     %dequantize_per_tensor_870 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_541, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1891593Z     %dequantize_per_tensor_871 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_541, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1892352Z     %dequantize_per_tensor_872 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_541, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1892805Z     %transpose_130 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_859, 1, 2), kwargs = {})
2025-03-21T20:30:48.1893522Z     %quantize_per_tensor_542 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_130, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1894300Z     %dequantize_per_tensor_873 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_542, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1894709Z     %select_144 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_873, 0, 0), kwargs = {})
2025-03-21T20:30:48.1895422Z     %quantize_per_tensor_543 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_144, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1896188Z     %dequantize_per_tensor_874 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_543, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1896613Z     %select_145 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_874, 0, 0), kwargs = {})
2025-03-21T20:30:48.1897309Z     %quantize_per_tensor_544 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_145, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1898087Z     %dequantize_per_tensor_875 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_544, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1898526Z     %transpose_131 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_858, 1, 2), kwargs = {})
2025-03-21T20:30:48.1899313Z     %quantize_per_tensor_545 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_131, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1900122Z     %dequantize_per_tensor_876 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_545, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1900549Z     %select_146 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_876, 0, 0), kwargs = {})
2025-03-21T20:30:48.1901245Z     %quantize_per_tensor_546 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_146, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1902024Z     %dequantize_per_tensor_877 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_546, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1902433Z     %select_147 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_877, 0, 1), kwargs = {})
2025-03-21T20:30:48.1903140Z     %quantize_per_tensor_547 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_147, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1903903Z     %dequantize_per_tensor_878 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_547, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1904361Z     %transpose_132 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_857, 1, 2), kwargs = {})
2025-03-21T20:30:48.1905075Z     %quantize_per_tensor_548 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_132, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1905852Z     %dequantize_per_tensor_879 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_548, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1906261Z     %select_148 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_879, 0, 0), kwargs = {})
2025-03-21T20:30:48.1906971Z     %quantize_per_tensor_549 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_148, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1907734Z     %dequantize_per_tensor_880 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_549, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1908158Z     %select_149 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_880, 0, 2), kwargs = {})
2025-03-21T20:30:48.1908853Z     %quantize_per_tensor_550 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_149, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1909628Z     %dequantize_per_tensor_881 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_550, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1910068Z     %transpose_133 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_856, 1, 2), kwargs = {})
2025-03-21T20:30:48.1910835Z     %quantize_per_tensor_551 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_133, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1911644Z     %dequantize_per_tensor_882 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_551, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1912067Z     %select_150 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_882, 0, 0), kwargs = {})
2025-03-21T20:30:48.1912762Z     %quantize_per_tensor_552 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_150, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1913539Z     %dequantize_per_tensor_883 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_552, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1913954Z     %select_151 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_883, 0, 3), kwargs = {})
2025-03-21T20:30:48.1914663Z     %quantize_per_tensor_553 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_151, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1915425Z     %dequantize_per_tensor_884 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_553, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1915877Z     %transpose_134 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_855, 1, 2), kwargs = {})
2025-03-21T20:30:48.1916593Z     %quantize_per_tensor_554 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_134, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1917372Z     %dequantize_per_tensor_885 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_554, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1917783Z     %select_152 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_885, 0, 0), kwargs = {})
2025-03-21T20:30:48.1918479Z     %quantize_per_tensor_555 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_152, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1919261Z     %dequantize_per_tensor_886 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_555, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1919672Z     %select_153 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_886, 0, 4), kwargs = {})
2025-03-21T20:30:48.1920380Z     %quantize_per_tensor_556 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_153, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1921144Z     %dequantize_per_tensor_887 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_556, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1921601Z     %transpose_135 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_854, 1, 2), kwargs = {})
2025-03-21T20:30:48.1922354Z     %quantize_per_tensor_557 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_135, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1923176Z     %dequantize_per_tensor_888 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_557, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1923584Z     %select_154 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_888, 0, 0), kwargs = {})
2025-03-21T20:30:48.1924293Z     %quantize_per_tensor_558 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_154, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1925054Z     %dequantize_per_tensor_889 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_558, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1925486Z     %select_155 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_889, 0, 5), kwargs = {})
2025-03-21T20:30:48.1926181Z     %quantize_per_tensor_559 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_155, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1926957Z     %dequantize_per_tensor_890 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_559, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1927396Z     %transpose_136 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_853, 1, 2), kwargs = {})
2025-03-21T20:30:48.1928120Z     %quantize_per_tensor_560 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_136, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1928889Z     %dequantize_per_tensor_891 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_560, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1929367Z     %select_156 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_891, 0, 0), kwargs = {})
2025-03-21T20:30:48.1930064Z     %quantize_per_tensor_561 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_156, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1930840Z     %dequantize_per_tensor_892 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_561, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1931255Z     %select_157 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_892, 0, 6), kwargs = {})
2025-03-21T20:30:48.1931963Z     %quantize_per_tensor_562 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_157, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1932908Z     %dequantize_per_tensor_893 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_562, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1933367Z     %transpose_137 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_852, 1, 2), kwargs = {})
2025-03-21T20:30:48.1934171Z     %quantize_per_tensor_563 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_137, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1935010Z     %dequantize_per_tensor_894 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_563, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1935417Z     %select_158 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_894, 0, 0), kwargs = {})
2025-03-21T20:30:48.1936127Z     %quantize_per_tensor_564 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_158, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1936887Z     %dequantize_per_tensor_895 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_564, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1937317Z     %select_159 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_895, 0, 7), kwargs = {})
2025-03-21T20:30:48.1938009Z     %quantize_per_tensor_565 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_159, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1938784Z     %dequantize_per_tensor_896 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_565, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1939222Z     %transpose_138 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_851, 1, 2), kwargs = {})
2025-03-21T20:30:48.1939947Z     %quantize_per_tensor_566 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_138, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1940714Z     %dequantize_per_tensor_897 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_566, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1941135Z     %select_160 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_897, 0, 0), kwargs = {})
2025-03-21T20:30:48.1941830Z     %quantize_per_tensor_567 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_160, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1942607Z     %dequantize_per_tensor_898 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_567, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1943021Z     %select_161 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_898, 0, 8), kwargs = {})
2025-03-21T20:30:48.1943727Z     %quantize_per_tensor_568 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_161, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1944491Z     %dequantize_per_tensor_899 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_568, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1944949Z     %transpose_139 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_850, 1, 2), kwargs = {})
2025-03-21T20:30:48.1945721Z     %quantize_per_tensor_569 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_139, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1946549Z     %dequantize_per_tensor_900 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_569, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1946958Z     %select_162 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_900, 0, 0), kwargs = {})
2025-03-21T20:30:48.1947672Z     %quantize_per_tensor_570 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_162, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1948437Z     %dequantize_per_tensor_901 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_570, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1948863Z     %select_163 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_901, 0, 9), kwargs = {})
2025-03-21T20:30:48.1949564Z     %quantize_per_tensor_571 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_163, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1950343Z     %dequantize_per_tensor_902 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_571, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1950787Z     %transpose_140 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_849, 1, 2), kwargs = {})
2025-03-21T20:30:48.1951512Z     %quantize_per_tensor_572 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_140, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1952279Z     %dequantize_per_tensor_903 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_572, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1952706Z     %select_164 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_903, 0, 0), kwargs = {})
2025-03-21T20:30:48.1953401Z     %quantize_per_tensor_573 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_164, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1954176Z     %dequantize_per_tensor_904 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_573, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1954589Z     %select_165 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_904, 0, 10), kwargs = {})
2025-03-21T20:30:48.1955304Z     %quantize_per_tensor_574 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_165, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1956061Z     %dequantize_per_tensor_905 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_574, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1956517Z     %transpose_141 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_848, 1, 2), kwargs = {})
2025-03-21T20:30:48.1957224Z     %quantize_per_tensor_575 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_141, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1958119Z     %dequantize_per_tensor_906 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_575, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1958531Z     %select_166 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_906, 0, 0), kwargs = {})
2025-03-21T20:30:48.1959222Z     %quantize_per_tensor_576 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_166, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1959999Z     %dequantize_per_tensor_907 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_576, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1960416Z     %select_167 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_907, 0, 11), kwargs = {})
2025-03-21T20:30:48.1961128Z     %quantize_per_tensor_577 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_167, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1961890Z     %dequantize_per_tensor_908 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_577, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1963345Z     %cat_6 : [num_users=1] = call_function[target=torch.ops.aten.cat.default](args = ([%dequantize_per_tensor_875, %dequantize_per_tensor_878, %dequantize_per_tensor_881, %dequantize_per_tensor_884, %dequantize_per_tensor_887, %dequantize_per_tensor_890, %dequantize_per_tensor_893, %dequantize_per_tensor_896, %dequantize_per_tensor_899, %dequantize_per_tensor_902, %dequantize_per_tensor_905, %dequantize_per_tensor_908],), kwargs = {})
2025-03-21T20:30:48.1964039Z     %quantize_per_tensor_578 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%cat_6, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1964800Z     %dequantize_per_tensor_909 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_578, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1965250Z     %view_45 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_909, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:30:48.1965929Z     %quantize_per_tensor_579 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_45, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1966708Z     %dequantize_per_tensor_910 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_579, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1967151Z     %transpose_142 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_872, 1, 2), kwargs = {})
2025-03-21T20:30:48.1967881Z     %quantize_per_tensor_580 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_142, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1968647Z     %dequantize_per_tensor_911 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_580, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1969066Z     %select_168 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_911, 0, 0), kwargs = {})
2025-03-21T20:30:48.1969928Z     %quantize_per_tensor_581 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_168, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1970720Z     %dequantize_per_tensor_912 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_581, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1971129Z     %select_169 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_912, 0, 0), kwargs = {})
2025-03-21T20:30:48.1971830Z     %quantize_per_tensor_582 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_169, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1972612Z     %dequantize_per_tensor_913 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_582, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1973058Z     %transpose_143 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_871, 1, 2), kwargs = {})
2025-03-21T20:30:48.1973788Z     %quantize_per_tensor_583 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_143, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1974557Z     %dequantize_per_tensor_914 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_583, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1974980Z     %select_170 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_914, 0, 0), kwargs = {})
2025-03-21T20:30:48.1975685Z     %quantize_per_tensor_584 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_170, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1976463Z     %dequantize_per_tensor_915 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_584, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1976872Z     %select_171 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_915, 0, 1), kwargs = {})
2025-03-21T20:30:48.1977584Z     %quantize_per_tensor_585 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_171, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1978356Z     %dequantize_per_tensor_916 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_585, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1978814Z     %transpose_144 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_870, 1, 2), kwargs = {})
2025-03-21T20:30:48.1979529Z     %quantize_per_tensor_586 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_144, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1980307Z     %dequantize_per_tensor_917 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_586, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1980716Z     %select_172 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_917, 0, 0), kwargs = {})
2025-03-21T20:30:48.1981534Z     %quantize_per_tensor_587 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_172, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1982302Z     %dequantize_per_tensor_918 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_587, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1982724Z     %select_173 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_918, 0, 2), kwargs = {})
2025-03-21T20:30:48.1983425Z     %quantize_per_tensor_588 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_173, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1984206Z     %dequantize_per_tensor_919 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_588, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1984651Z     %transpose_145 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_869, 1, 2), kwargs = {})
2025-03-21T20:30:48.1985382Z     %quantize_per_tensor_589 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_145, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1986150Z     %dequantize_per_tensor_920 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_589, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1986575Z     %select_174 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_920, 0, 0), kwargs = {})
2025-03-21T20:30:48.1987284Z     %quantize_per_tensor_590 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_174, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1988064Z     %dequantize_per_tensor_921 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_590, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1988476Z     %select_175 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_921, 0, 3), kwargs = {})
2025-03-21T20:30:48.1989187Z     %quantize_per_tensor_591 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_175, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1989960Z     %dequantize_per_tensor_922 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_591, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1990417Z     %transpose_146 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_868, 1, 2), kwargs = {})
2025-03-21T20:30:48.1991133Z     %quantize_per_tensor_592 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_146, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1991912Z     %dequantize_per_tensor_923 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_592, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1992321Z     %select_176 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_923, 0, 0), kwargs = {})
2025-03-21T20:30:48.1993126Z     %quantize_per_tensor_593 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_176, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1993895Z     %dequantize_per_tensor_924 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_593, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1994317Z     %select_177 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_924, 0, 4), kwargs = {})
2025-03-21T20:30:48.1995014Z     %quantize_per_tensor_594 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_177, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1995793Z     %dequantize_per_tensor_925 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_594, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1996234Z     %transpose_147 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_867, 1, 2), kwargs = {})
2025-03-21T20:30:48.1996965Z     %quantize_per_tensor_595 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_147, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1997734Z     %dequantize_per_tensor_926 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_595, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1998155Z     %select_178 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_926, 0, 0), kwargs = {})
2025-03-21T20:30:48.1998860Z     %quantize_per_tensor_596 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_178, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.1999634Z     %dequantize_per_tensor_927 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_596, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2000040Z     %select_179 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_927, 0, 5), kwargs = {})
2025-03-21T20:30:48.2000752Z     %quantize_per_tensor_597 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_179, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2001520Z     %dequantize_per_tensor_928 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_597, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2001976Z     %transpose_148 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_866, 1, 2), kwargs = {})
2025-03-21T20:30:48.2002691Z     %quantize_per_tensor_598 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_148, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2003470Z     %dequantize_per_tensor_929 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_598, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2003877Z     %select_180 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_929, 0, 0), kwargs = {})
2025-03-21T20:30:48.2004684Z     %quantize_per_tensor_599 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_180, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2005451Z     %dequantize_per_tensor_930 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_599, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2005875Z     %select_181 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_930, 0, 6), kwargs = {})
2025-03-21T20:30:48.2006572Z     %quantize_per_tensor_600 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_181, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2007356Z     %dequantize_per_tensor_931 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_600, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2007801Z     %transpose_149 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_865, 1, 2), kwargs = {})
2025-03-21T20:30:48.2008530Z     %quantize_per_tensor_601 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_149, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2009358Z     %dequantize_per_tensor_932 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_601, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2009777Z     %select_182 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_932, 0, 0), kwargs = {})
2025-03-21T20:30:48.2010481Z     %quantize_per_tensor_602 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_182, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2011264Z     %dequantize_per_tensor_933 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_602, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2011671Z     %select_183 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_933, 0, 7), kwargs = {})
2025-03-21T20:30:48.2012383Z     %quantize_per_tensor_603 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_183, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2013150Z     %dequantize_per_tensor_934 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_603, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2013607Z     %transpose_150 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_864, 1, 2), kwargs = {})
2025-03-21T20:30:48.2014321Z     %quantize_per_tensor_604 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_150, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2015100Z     %dequantize_per_tensor_935 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_604, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2015506Z     %select_184 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_935, 0, 0), kwargs = {})
2025-03-21T20:30:48.2016261Z     %quantize_per_tensor_605 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_184, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2017125Z     %dequantize_per_tensor_936 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_605, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2017535Z     %select_185 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_936, 0, 8), kwargs = {})
2025-03-21T20:30:48.2018243Z     %quantize_per_tensor_606 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_185, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2019011Z     %dequantize_per_tensor_937 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_606, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2019470Z     %transpose_151 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_863, 1, 2), kwargs = {})
2025-03-21T20:30:48.2020184Z     %quantize_per_tensor_607 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_151, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2020964Z     %dequantize_per_tensor_938 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_607, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2021373Z     %select_186 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_938, 0, 0), kwargs = {})
2025-03-21T20:30:48.2022089Z     %quantize_per_tensor_608 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_186, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2022860Z     %dequantize_per_tensor_939 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_608, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2023279Z     %select_187 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_939, 0, 9), kwargs = {})
2025-03-21T20:30:48.2023974Z     %quantize_per_tensor_609 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_187, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2024761Z     %dequantize_per_tensor_940 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_609, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2025200Z     %transpose_152 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_862, 1, 2), kwargs = {})
2025-03-21T20:30:48.2025924Z     %quantize_per_tensor_610 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_152, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2026689Z     %dequantize_per_tensor_941 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_610, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2027110Z     %select_188 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_941, 0, 0), kwargs = {})
2025-03-21T20:30:48.2027854Z     %quantize_per_tensor_611 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_188, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2028691Z     %dequantize_per_tensor_942 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_611, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2029100Z     %select_189 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_942, 0, 10), kwargs = {})
2025-03-21T20:30:48.2029810Z     %quantize_per_tensor_612 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_189, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2030573Z     %dequantize_per_tensor_943 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_612, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2031029Z     %transpose_153 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_861, 1, 2), kwargs = {})
2025-03-21T20:30:48.2031741Z     %quantize_per_tensor_613 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_153, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2032722Z     %dequantize_per_tensor_944 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_613, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2033128Z     %select_190 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_944, 0, 0), kwargs = {})
2025-03-21T20:30:48.2033845Z     %quantize_per_tensor_614 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_190, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2034610Z     %dequantize_per_tensor_945 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_614, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2035034Z     %select_191 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_945, 0, 11), kwargs = {})
2025-03-21T20:30:48.2035731Z     %quantize_per_tensor_615 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_191, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2036524Z     %dequantize_per_tensor_946 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_615, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2037966Z     %cat_7 : [num_users=1] = call_function[target=torch.ops.aten.cat.default](args = ([%dequantize_per_tensor_913, %dequantize_per_tensor_916, %dequantize_per_tensor_919, %dequantize_per_tensor_922, %dequantize_per_tensor_925, %dequantize_per_tensor_928, %dequantize_per_tensor_931, %dequantize_per_tensor_934, %dequantize_per_tensor_937, %dequantize_per_tensor_940, %dequantize_per_tensor_943, %dequantize_per_tensor_946],), kwargs = {})
2025-03-21T20:30:48.2038658Z     %quantize_per_tensor_616 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%cat_7, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2039426Z     %dequantize_per_tensor_947 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_616, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2040018Z     %view_46 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_947, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:30:48.2040701Z     %quantize_per_tensor_617 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_46, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2041477Z     %dequantize_per_tensor_948 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_617, 0.00011123115109512582, 26424, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2042233Z     %quantize_per_tensor_618 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%dequantize_per_tensor_948, 0.0001327675417996943, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.2043018Z     %dequantize_per_tensor_949 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_618, 0.0001327675417996943, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.2047889Z     %index_5 : [num_users=1] = call_function[target=torch.ops.aten.index.Tensor](args = (%dequantize_per_tensor_124, [%attn_options_input_pos]), kwargs = {})
2025-03-21T20:30:48.2048597Z     %quantize_per_tensor_619 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_5, 0.0038910505827516317, 65535, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2049427Z     %dequantize_per_tensor_950 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_619, 0.0038910505827516317, 65535, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2049915Z     %transpose_154 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_910, -2, -1), kwargs = {})
2025-03-21T20:30:48.2050636Z     %quantize_per_tensor_620 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_154, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2051440Z     %dequantize_per_tensor_951 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_620, 0.0003910682280547917, 31907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2052215Z     %quantize_per_tensor_621 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%dequantize_per_tensor_951, 0.00040133832953870296, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.2052992Z     %dequantize_per_tensor_952 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_621, 0.00040133832953870296, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.2053511Z     %matmul_6 : [num_users=1] = call_function[target=torch.ops.aten.matmul.default](args = (%dequantize_per_tensor_846, %dequantize_per_tensor_952), kwargs = {})
2025-03-21T20:30:48.2054207Z     %quantize_per_tensor_622 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%matmul_6, 0.0038027865812182426, 39476, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2054987Z     %dequantize_per_tensor_953 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_622, 0.0038027865812182426, 39476, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2055732Z     %dequantize_per_tensor_954 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param152, 1.9073777366429567e-06, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2056332Z     %mul_41 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_953, %dequantize_per_tensor_954), kwargs = {})
2025-03-21T20:30:48.2057019Z     %quantize_per_tensor_623 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_41, 0.00047534832265228033, 39476, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2057803Z     %dequantize_per_tensor_955 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_623, 0.00047534832265228033, 39476, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2058267Z     %add_17 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_955, %dequantize_per_tensor_950), kwargs = {})
2025-03-21T20:30:48.2058954Z     %quantize_per_tensor_624 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_17, 0.004309757146984339, 62661, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2059717Z     %dequantize_per_tensor_956 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_624, 0.004309757146984339, 62661, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2060202Z     %softmax_3 : [num_users=1] = call_function[target=torch.ops.aten.softmax.int](args = (%dequantize_per_tensor_956, -1), kwargs = {})
2025-03-21T20:30:48.2060884Z     %quantize_per_tensor_625 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%softmax_3, 1.5259021893143654e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2061644Z     %dequantize_per_tensor_957 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_625, 1.5259021893143654e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2062149Z     %matmul_7 : [num_users=1] = call_function[target=torch.ops.aten.matmul.default](args = (%dequantize_per_tensor_957, %dequantize_per_tensor_949), kwargs = {})
2025-03-21T20:30:48.2062846Z     %quantize_per_tensor_626 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%matmul_7, 6.451566150644794e-05, 32814, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2063609Z     %dequantize_per_tensor_958 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_626, 6.451566150644794e-05, 32814, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2064061Z     %transpose_155 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_958, 1, 2), kwargs = {})
2025-03-21T20:30:48.2064774Z     %quantize_per_tensor_627 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_155, 6.451566150644794e-05, 32814, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2065551Z     %dequantize_per_tensor_959 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_627, 6.451566150644794e-05, 32814, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2065975Z     %view_47 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_959, [1, 1, 768]), kwargs = {})
2025-03-21T20:30:48.2066664Z     %quantize_per_tensor_628 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_47, 6.451566150644794e-05, 32814, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2067425Z     %dequantize_per_tensor_960 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_628, 6.451566150644794e-05, 32814, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2067962Z     %unsqueeze_24 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_960, -1), kwargs = {})
2025-03-21T20:30:48.2068664Z     %quantize_per_tensor_629 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_24, 6.451566150644794e-05, 32814, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2069440Z     %dequantize_per_tensor_961 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_629, 6.451566150644794e-05, 32814, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2069877Z     %transpose_156 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_961, 1, 2), kwargs = {})
2025-03-21T20:30:48.2070601Z     %quantize_per_tensor_630 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_156, 6.451566150644794e-05, 32814, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2071364Z     %dequantize_per_tensor_962 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_630, 6.451566150644794e-05, 32814, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2071914Z     %conv2d_24 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_962, %dequantize_per_tensor_32), kwargs = {})
2025-03-21T20:30:48.2072599Z     %quantize_per_tensor_631 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_24, 5.919613249716349e-05, 40616, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2073369Z     %dequantize_per_tensor_963 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_631, 5.919613249716349e-05, 40616, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2073813Z     %transpose_157 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_963, 1, 2), kwargs = {})
2025-03-21T20:30:48.2074533Z     %quantize_per_tensor_632 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_157, 5.919613249716349e-05, 40616, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2075296Z     %dequantize_per_tensor_964 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_632, 5.919613249716349e-05, 40616, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2075717Z     %squeeze_24 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_964, -1), kwargs = {})
2025-03-21T20:30:48.2076411Z     %quantize_per_tensor_633 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_24, 5.919613249716349e-05, 40616, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2077182Z     %dequantize_per_tensor_965 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_633, 5.919613249716349e-05, 40616, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2077646Z     %add_18 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_785, %dequantize_per_tensor_965), kwargs = {})
2025-03-21T20:30:48.2078334Z     %quantize_per_tensor_634 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_18, 0.0020493771880865097, 7471, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2079089Z     %dequantize_per_tensor_966 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_634, 0.0020493771880865097, 7471, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2080427Z     %dequantize_per_tensor_967 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_634, 0.0020493771880865097, 7471, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2080968Z     %rms_norm_7 : [num_users=1] = call_function[target=torch.ops.aten.rms_norm.default](args = (%dequantize_per_tensor_967, [768], %dequantize_per_tensor_33, 1e-05), kwargs = {})
2025-03-21T20:30:48.2081676Z     %quantize_per_tensor_635 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%rms_norm_7, 0.00031500012846663594, 14572, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2082459Z     %dequantize_per_tensor_968 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_635, 0.00031500012846663594, 14572, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2083402Z     %dequantize_per_tensor_969 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_635, 0.00031500012846663594, 14572, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2083906Z     %unsqueeze_25 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_969, -1), kwargs = {})
2025-03-21T20:30:48.2084629Z     %quantize_per_tensor_636 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_25, 0.00031500012846663594, 14572, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2085393Z     %dequantize_per_tensor_970 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_636, 0.00031500012846663594, 14572, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2085850Z     %transpose_158 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_970, 1, 2), kwargs = {})
2025-03-21T20:30:48.2086570Z     %quantize_per_tensor_637 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_158, 0.00031500012846663594, 14572, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2087353Z     %dequantize_per_tensor_971 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_637, 0.00031500012846663594, 14572, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2087851Z     %conv2d_25 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_971, %dequantize_per_tensor_34), kwargs = {})
2025-03-21T20:30:48.2088555Z     %quantize_per_tensor_638 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_25, 0.00022086942044552416, 31371, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2089387Z     %dequantize_per_tensor_972 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_638, 0.00022086942044552416, 31371, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2089846Z     %transpose_159 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_972, 1, 2), kwargs = {})
2025-03-21T20:30:48.2090561Z     %quantize_per_tensor_639 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_159, 0.00022086942044552416, 31371, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2091345Z     %dequantize_per_tensor_973 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_639, 0.00022086942044552416, 31371, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2091816Z     %squeeze_25 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_973, -1), kwargs = {})
2025-03-21T20:30:48.2092543Z     %quantize_per_tensor_640 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_25, 0.00022086942044552416, 31371, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2093325Z     %dequantize_per_tensor_974 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_640, 0.00022086942044552416, 31371, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2094099Z     %dequantize_per_tensor_975 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_640, 0.00022086942044552416, 31371, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2094520Z     %sigmoid_3 : [num_users=1] = call_function[target=torch.ops.aten.sigmoid.default](args = (%dequantize_per_tensor_975,), kwargs = {})
2025-03-21T20:30:48.2095192Z     %quantize_per_tensor_641 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%sigmoid_3, 1.52587890625e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2095961Z     %dequantize_per_tensor_976 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_641, 1.52587890625e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2096425Z     %mul_42 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_974, %dequantize_per_tensor_976), kwargs = {})
2025-03-21T20:30:48.2097113Z     %quantize_per_tensor_642 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_42, 0.00011932865891139954, 2334, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2097877Z     %dequantize_per_tensor_977 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_642, 0.00011932865891139954, 2334, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2098339Z     %unsqueeze_26 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_968, -1), kwargs = {})
2025-03-21T20:30:48.2099049Z     %quantize_per_tensor_643 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_26, 0.00031500012846663594, 14572, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2099823Z     %dequantize_per_tensor_978 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_643, 0.00031500012846663594, 14572, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2100267Z     %transpose_160 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_978, 1, 2), kwargs = {})
2025-03-21T20:30:48.2100993Z     %quantize_per_tensor_644 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_160, 0.00031500012846663594, 14572, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2101763Z     %dequantize_per_tensor_979 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_644, 0.00031500012846663594, 14572, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2102272Z     %conv2d_26 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_979, %dequantize_per_tensor_35), kwargs = {})
2025-03-21T20:30:48.2102965Z     %quantize_per_tensor_645 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_26, 0.00024752813624218106, 33708, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2103780Z     %dequantize_per_tensor_980 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_645, 0.00024752813624218106, 33708, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2104243Z     %transpose_161 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_980, 1, 2), kwargs = {})
2025-03-21T20:30:48.2104971Z     %quantize_per_tensor_646 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_161, 0.00024752813624218106, 33708, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2105738Z     %dequantize_per_tensor_981 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_646, 0.00024752813624218106, 33708, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2106158Z     %squeeze_26 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_981, -1), kwargs = {})
2025-03-21T20:30:48.2106861Z     %quantize_per_tensor_647 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_26, 0.00024752813624218106, 33708, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2107666Z     %dequantize_per_tensor_982 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_647, 0.00024752813624218106, 33708, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2108133Z     %mul_43 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_977, %dequantize_per_tensor_982), kwargs = {})
2025-03-21T20:30:48.2108817Z     %quantize_per_tensor_648 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_43, 0.0006538353045471013, 38748, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2109580Z     %dequantize_per_tensor_983 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_648, 0.0006538353045471013, 38748, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2110043Z     %unsqueeze_27 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_983, -1), kwargs = {})
2025-03-21T20:30:48.2110752Z     %quantize_per_tensor_649 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_27, 0.0006538353045471013, 38748, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2111521Z     %dequantize_per_tensor_984 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_649, 0.0006538353045471013, 38748, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2111962Z     %transpose_162 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_984, 1, 2), kwargs = {})
2025-03-21T20:30:48.2112686Z     %quantize_per_tensor_650 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_162, 0.0006538353045471013, 38748, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2113448Z     %dequantize_per_tensor_985 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_650, 0.0006538353045471013, 38748, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2113961Z     %conv2d_27 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_985, %dequantize_per_tensor_36), kwargs = {})
2025-03-21T20:30:48.2114639Z     %quantize_per_tensor_651 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_27, 0.000476505549158901, 4992, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2115448Z     %dequantize_per_tensor_986 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_651, 0.000476505549158901, 4992, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2115912Z     %transpose_163 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_986, 1, 2), kwargs = {})
2025-03-21T20:30:48.2116621Z     %quantize_per_tensor_652 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_163, 0.000476505549158901, 4992, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2117376Z     %dequantize_per_tensor_987 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_652, 0.000476505549158901, 4992, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2117797Z     %squeeze_27 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_987, -1), kwargs = {})
2025-03-21T20:30:48.2118490Z     %quantize_per_tensor_653 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_27, 0.000476505549158901, 4992, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2119291Z     %dequantize_per_tensor_988 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_653, 0.000476505549158901, 4992, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2119754Z     %add_19 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_966, %dequantize_per_tensor_988), kwargs = {})
2025-03-21T20:30:48.2120435Z     %quantize_per_tensor_654 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_19, 0.002495231805369258, 6285, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2121194Z     %dequantize_per_tensor_989 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_654, 0.002495231805369258, 6285, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2121957Z     %dequantize_per_tensor_990 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_654, 0.002495231805369258, 6285, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2122499Z     %rms_norm_8 : [num_users=1] = call_function[target=torch.ops.aten.rms_norm.default](args = (%dequantize_per_tensor_990, [768], %dequantize_per_tensor_37, 1e-05), kwargs = {})
2025-03-21T20:30:48.2123200Z     %quantize_per_tensor_655 : [num_users=3] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%rms_norm_8, 0.00039765422116033733, 28522, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2123967Z     %dequantize_per_tensor_991 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_655, 0.00039765422116033733, 28522, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2124744Z     %dequantize_per_tensor_992 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_655, 0.00039765422116033733, 28522, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2125507Z     %dequantize_per_tensor_993 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_655, 0.00039765422116033733, 28522, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2125969Z     %unsqueeze_28 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_993, -1), kwargs = {})
2025-03-21T20:30:48.2126676Z     %quantize_per_tensor_656 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_28, 0.00039765422116033733, 28522, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2127524Z     %dequantize_per_tensor_994 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_656, 0.00039765422116033733, 28522, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2127967Z     %transpose_164 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_994, 1, 2), kwargs = {})
2025-03-21T20:30:48.2128692Z     %quantize_per_tensor_657 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_164, 0.00039765422116033733, 28522, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2129530Z     %dequantize_per_tensor_995 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_657, 0.00039765422116033733, 28522, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2130047Z     %conv2d_28 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_995, %dequantize_per_tensor_38), kwargs = {})
2025-03-21T20:30:48.2130742Z     %quantize_per_tensor_658 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_28, 0.00031367456540465355, 28419, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2131550Z     %dequantize_per_tensor_996 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_658, 0.00031367456540465355, 28419, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2131996Z     %transpose_165 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_996, 1, 2), kwargs = {})
2025-03-21T20:30:48.2132934Z     %quantize_per_tensor_659 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_165, 0.00031367456540465355, 28419, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2133709Z     %dequantize_per_tensor_997 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_659, 0.00031367456540465355, 28419, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2134135Z     %squeeze_28 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_997, -1), kwargs = {})
2025-03-21T20:30:48.2134831Z     %quantize_per_tensor_660 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_28, 0.00031367456540465355, 28419, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2135605Z     %dequantize_per_tensor_998 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_660, 0.00031367456540465355, 28419, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2136059Z     %unsqueeze_29 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_992, -1), kwargs = {})
2025-03-21T20:30:48.2136777Z     %quantize_per_tensor_661 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_29, 0.00039765422116033733, 28522, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2137544Z     %dequantize_per_tensor_999 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_661, 0.00039765422116033733, 28522, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2137991Z     %transpose_166 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_999, 1, 2), kwargs = {})
2025-03-21T20:30:48.2138820Z     %quantize_per_tensor_662 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_166, 0.00039765422116033733, 28522, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2139636Z     %dequantize_per_tensor_1000 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_662, 0.00039765422116033733, 28522, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2140139Z     %conv2d_29 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_1000, %dequantize_per_tensor_39), kwargs = {})
2025-03-21T20:30:48.2140839Z     %quantize_per_tensor_663 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_29, 0.0004061445069964975, 31842, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2141605Z     %dequantize_per_tensor_1001 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_663, 0.0004061445069964975, 31842, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2142061Z     %transpose_167 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1001, 1, 2), kwargs = {})
2025-03-21T20:30:48.2142774Z     %quantize_per_tensor_664 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_167, 0.0004061445069964975, 31842, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2143616Z     %dequantize_per_tensor_1002 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_664, 0.0004061445069964975, 31842, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2144029Z     %squeeze_29 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_1002, -1), kwargs = {})
2025-03-21T20:30:48.2144734Z     %quantize_per_tensor_665 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_29, 0.0004061445069964975, 31842, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2145500Z     %dequantize_per_tensor_1003 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_665, 0.0004061445069964975, 31842, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2145965Z     %unsqueeze_30 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_991, -1), kwargs = {})
2025-03-21T20:30:48.2146672Z     %quantize_per_tensor_666 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_30, 0.00039765422116033733, 28522, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2147459Z     %dequantize_per_tensor_1004 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_666, 0.00039765422116033733, 28522, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2147908Z     %transpose_168 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1004, 1, 2), kwargs = {})
2025-03-21T20:30:48.2148631Z     %quantize_per_tensor_667 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_168, 0.00039765422116033733, 28522, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2149405Z     %dequantize_per_tensor_1005 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_667, 0.00039765422116033733, 28522, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2149918Z     %conv2d_30 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_1005, %dequantize_per_tensor_40), kwargs = {})
2025-03-21T20:30:48.2150659Z     %quantize_per_tensor_668 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_30, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2151466Z     %dequantize_per_tensor_1006 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_668, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2151910Z     %transpose_169 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1006, 1, 2), kwargs = {})
2025-03-21T20:30:48.2152626Z     %quantize_per_tensor_669 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_169, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2153408Z     %dequantize_per_tensor_1007 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_669, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2153830Z     %squeeze_30 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_1007, -1), kwargs = {})
2025-03-21T20:30:48.2154544Z     %quantize_per_tensor_670 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_30, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2155354Z     %dequantize_per_tensor_1008 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_670, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2155803Z     %view_48 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_998, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.2156496Z     %quantize_per_tensor_671 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_48, 0.00031367456540465355, 28419, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2157283Z     %dequantize_per_tensor_1009 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_671, 0.00031367456540465355, 28419, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2157725Z     %view_49 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1003, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.2158417Z     %quantize_per_tensor_672 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_49, 0.0004061445069964975, 31842, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2159189Z     %dequantize_per_tensor_1010 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_672, 0.0004061445069964975, 31842, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2159640Z     %view_50 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1008, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.2160325Z     %quantize_per_tensor_673 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_50, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2161110Z     %dequantize_per_tensor_1011 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_673, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2161588Z     %_to_copy_8 : [num_users=1] = call_function[target=torch.ops.aten._to_copy.default](args = (%dequantize_per_tensor_1009,), kwargs = {dtype: torch.float32})
2025-03-21T20:30:48.2162338Z     %quantize_per_tensor_674 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%_to_copy_8, 0.00031367456540465355, 28419, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2163145Z     %dequantize_per_tensor_1012 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_674, 0.00031367456540465355, 28419, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2163607Z     %view_51 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1012, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:30:48.2164289Z     %quantize_per_tensor_675 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_51, 0.00031367456540465355, 28419, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2165073Z     %dequantize_per_tensor_1013 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_675, 0.00031367456540465355, 28419, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2165480Z     %unbind_8 : [num_users=2] = call_function[target=torch.ops.aten.unbind.int](args = (%dequantize_per_tensor_1013, -1), kwargs = {})
2025-03-21T20:30:48.2165803Z     %getitem_16 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_8, 0), kwargs = {})
2025-03-21T20:30:48.2166142Z     %getitem_17 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_8, 1), kwargs = {})
2025-03-21T20:30:48.2166852Z     %quantize_per_tensor_676 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_16, 0.00031367456540465355, 28419, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2167628Z     %dequantize_per_tensor_1014 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_676, 0.00031367456540465355, 28419, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2168411Z     %dequantize_per_tensor_1015 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_676, 0.00031367456540465355, 28419, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2169112Z     %quantize_per_tensor_677 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_17, 0.00029694687691517174, 29660, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2169953Z     %dequantize_per_tensor_1016 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_677, 0.00029694687691517174, 29660, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2170724Z     %dequantize_per_tensor_1017 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_677, 0.00029694687691517174, 29660, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2171222Z     %_to_copy_9 : [num_users=1] = call_function[target=torch.ops.aten._to_copy.default](args = (%dequantize_per_tensor_1010,), kwargs = {dtype: torch.float32})
2025-03-21T20:30:48.2171912Z     %quantize_per_tensor_678 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%_to_copy_9, 0.0004061445069964975, 31842, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2172694Z     %dequantize_per_tensor_1018 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_678, 0.0004061445069964975, 31842, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2173140Z     %view_52 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1018, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:30:48.2173885Z     %quantize_per_tensor_679 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_52, 0.0004061445069964975, 31842, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2174678Z     %dequantize_per_tensor_1019 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_679, 0.0004061445069964975, 31842, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2175095Z     %unbind_9 : [num_users=2] = call_function[target=torch.ops.aten.unbind.int](args = (%dequantize_per_tensor_1019, -1), kwargs = {})
2025-03-21T20:30:48.2175403Z     %getitem_18 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_9, 0), kwargs = {})
2025-03-21T20:30:48.2175721Z     %getitem_19 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_9, 1), kwargs = {})
2025-03-21T20:30:48.2176418Z     %quantize_per_tensor_680 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_18, 0.00040076454752124846, 31390, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2177203Z     %dequantize_per_tensor_1020 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_680, 0.00040076454752124846, 31390, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2177999Z     %dequantize_per_tensor_1021 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_680, 0.00040076454752124846, 31390, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2178705Z     %quantize_per_tensor_681 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_19, 0.0003823413862846792, 33824, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2179471Z     %dequantize_per_tensor_1022 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_681, 0.0003823413862846792, 33824, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2180251Z     %dequantize_per_tensor_1023 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_681, 0.0003823413862846792, 33824, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2180683Z     %view_53 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_158, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:30:48.2181373Z     %quantize_per_tensor_682 : [num_users=4] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_53, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2182140Z     %dequantize_per_tensor_1024 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_682, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2182915Z     %dequantize_per_tensor_1025 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_682, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2183680Z     %dequantize_per_tensor_1026 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_682, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2184460Z     %dequantize_per_tensor_1027 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_682, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2184888Z     %view_54 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_170, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:30:48.2185624Z     %quantize_per_tensor_683 : [num_users=4] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_54, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2186413Z     %dequantize_per_tensor_1028 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_683, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2187190Z     %dequantize_per_tensor_1029 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_683, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2187951Z     %dequantize_per_tensor_1030 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_683, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2188727Z     %dequantize_per_tensor_1031 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_683, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2189199Z     %mul_44 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1015, %dequantize_per_tensor_1027), kwargs = {})
2025-03-21T20:30:48.2189913Z     %quantize_per_tensor_684 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_44, 0.0003092595434281975, 28515, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2190679Z     %dequantize_per_tensor_1032 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_684, 0.0003092595434281975, 28515, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2191160Z     %mul_45 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1016, %dequantize_per_tensor_1030), kwargs = {})
2025-03-21T20:30:48.2191845Z     %quantize_per_tensor_685 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_45, 0.00020828904234804213, 31612, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2192632Z     %dequantize_per_tensor_1033 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_685, 0.00020828904234804213, 31612, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2193098Z     %sub_8 : [num_users=1] = call_function[target=torch.ops.aten.sub.Tensor](args = (%dequantize_per_tensor_1032, %dequantize_per_tensor_1033), kwargs = {})
2025-03-21T20:30:48.2193788Z     %quantize_per_tensor_686 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%sub_8, 0.00030704005621373653, 28921, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2194563Z     %dequantize_per_tensor_1034 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_686, 0.00030704005621373653, 28921, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2195045Z     %mul_46 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1014, %dequantize_per_tensor_1031), kwargs = {})
2025-03-21T20:30:48.2195729Z     %quantize_per_tensor_687 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_46, 0.00016941409558057785, 33259, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2196512Z     %dequantize_per_tensor_1035 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_687, 0.00016941409558057785, 33259, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2196982Z     %mul_47 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1017, %dequantize_per_tensor_1026), kwargs = {})
2025-03-21T20:30:48.2197743Z     %quantize_per_tensor_688 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_47, 0.00029095596983097494, 29320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2198517Z     %dequantize_per_tensor_1036 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_688, 0.00029095596983097494, 29320, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2198996Z     %add_20 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_1035, %dequantize_per_tensor_1036), kwargs = {})
2025-03-21T20:30:48.2199667Z     %quantize_per_tensor_689 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_20, 0.00028711769846268, 29314, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2200442Z     %dequantize_per_tensor_1037 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_689, 0.00028711769846268, 29314, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2200913Z     %mul_48 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1021, %dequantize_per_tensor_1025), kwargs = {})
2025-03-21T20:30:48.2201630Z     %quantize_per_tensor_690 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_48, 0.0003889426589012146, 30723, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2202395Z     %dequantize_per_tensor_1038 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_690, 0.0003889426589012146, 30723, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2202874Z     %mul_49 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1022, %dequantize_per_tensor_1028), kwargs = {})
2025-03-21T20:30:48.2203558Z     %quantize_per_tensor_691 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_49, 0.00020149449119344354, 31475, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2204342Z     %dequantize_per_tensor_1039 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_691, 0.00020149449119344354, 31475, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2204809Z     %sub_9 : [num_users=1] = call_function[target=torch.ops.aten.sub.Tensor](args = (%dequantize_per_tensor_1038, %dequantize_per_tensor_1039), kwargs = {})
2025-03-21T20:30:48.2205497Z     %quantize_per_tensor_692 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%sub_9, 0.0003881677403114736, 30645, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2206267Z     %dequantize_per_tensor_1040 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_692, 0.0003881677403114736, 30645, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2206750Z     %mul_50 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1020, %dequantize_per_tensor_1029), kwargs = {})
2025-03-21T20:30:48.2207426Z     %quantize_per_tensor_693 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_50, 0.00017219017900060862, 30798, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2208203Z     %dequantize_per_tensor_1041 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_693, 0.00017219017900060862, 30798, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2208733Z     %mul_51 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1023, %dequantize_per_tensor_1024), kwargs = {})
2025-03-21T20:30:48.2209503Z     %quantize_per_tensor_694 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_51, 0.0003756027726922184, 33266, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2210274Z     %dequantize_per_tensor_1042 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_694, 0.0003756027726922184, 33266, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2210754Z     %add_21 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_1041, %dequantize_per_tensor_1042), kwargs = {})
2025-03-21T20:30:48.2211434Z     %quantize_per_tensor_695 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_21, 0.00038093022885732353, 33710, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2212224Z     %dequantize_per_tensor_1043 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_695, 0.00038093022885732353, 33710, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2212774Z     %stack_8 : [num_users=1] = call_function[target=torch.ops.aten.stack.default](args = ([%dequantize_per_tensor_1034, %dequantize_per_tensor_1037], -1), kwargs = {})
2025-03-21T20:30:48.2213462Z     %quantize_per_tensor_696 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%stack_8, 0.00030704005621373653, 28921, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2214244Z     %dequantize_per_tensor_1044 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_696, 0.00030704005621373653, 28921, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2214685Z     %view_55 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1044, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.2215382Z     %quantize_per_tensor_697 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_55, 0.00030704005621373653, 28921, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2216163Z     %dequantize_per_tensor_1045 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_697, 0.00030704005621373653, 28921, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2216693Z     %stack_9 : [num_users=1] = call_function[target=torch.ops.aten.stack.default](args = ([%dequantize_per_tensor_1040, %dequantize_per_tensor_1043], -1), kwargs = {})
2025-03-21T20:30:48.2217379Z     %quantize_per_tensor_698 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%stack_9, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2218167Z     %dequantize_per_tensor_1046 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_698, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2218604Z     %view_56 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1046, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.2219297Z     %quantize_per_tensor_699 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_56, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2220063Z     %dequantize_per_tensor_1047 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_699, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2220616Z     %type_as_8 : [num_users=1] = call_function[target=torch.ops.aten.type_as.default](args = (%dequantize_per_tensor_1045, %dequantize_per_tensor_1009), kwargs = {})
2025-03-21T20:30:48.2221331Z     %quantize_per_tensor_700 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%type_as_8, 0.00030704005621373653, 28921, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2222113Z     %dequantize_per_tensor_1048 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_700, 0.00030704005621373653, 28921, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2222607Z     %type_as_9 : [num_users=1] = call_function[target=torch.ops.aten.type_as.default](args = (%dequantize_per_tensor_1047, %dequantize_per_tensor_1010), kwargs = {})
2025-03-21T20:30:48.2223311Z     %quantize_per_tensor_701 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%type_as_9, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2224081Z     %dequantize_per_tensor_1049 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_701, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2224564Z     %transpose_170 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1048, 1, 2), kwargs = {})
2025-03-21T20:30:48.2225276Z     %quantize_per_tensor_702 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_170, 0.00030704005621373653, 28921, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2226056Z     %dequantize_per_tensor_1050 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_702, 0.00030704005621373653, 28921, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2226689Z     %index_put_8 : [num_users=1] = call_function[target=torch.ops.aten.index_put.default](args = (%dequantize_per_tensor_125, [None, %attn_options_input_pos], %dequantize_per_tensor_1049), kwargs = {})
2025-03-21T20:30:48.2227403Z     %quantize_per_tensor_703 : [num_users=13] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_put_8, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2228172Z     %dequantize_per_tensor_1051 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_703, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2228954Z     %dequantize_per_tensor_1052 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_703, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2229727Z     %dequantize_per_tensor_1053 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_703, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2230510Z     %dequantize_per_tensor_1054 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_703, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2231276Z     %dequantize_per_tensor_1055 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_703, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2232052Z     %dequantize_per_tensor_1056 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_703, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2233110Z     %dequantize_per_tensor_1057 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_703, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2233899Z     %dequantize_per_tensor_1058 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_703, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2234678Z     %dequantize_per_tensor_1059 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_703, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2235442Z     %dequantize_per_tensor_1060 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_703, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2236229Z     %dequantize_per_tensor_1061 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_703, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2237033Z     %dequantize_per_tensor_1062 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_703, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2237818Z     %dequantize_per_tensor_1063 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_703, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2238442Z     %index_put_9 : [num_users=1] = call_function[target=torch.ops.aten.index_put.default](args = (%dequantize_per_tensor_126, [None, %attn_options_input_pos], %dequantize_per_tensor_1011), kwargs = {})
2025-03-21T20:30:48.2239163Z     %quantize_per_tensor_704 : [num_users=13] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_put_9, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2239939Z     %dequantize_per_tensor_1064 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_704, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2240716Z     %dequantize_per_tensor_1065 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_704, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2241481Z     %dequantize_per_tensor_1066 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_704, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2242262Z     %dequantize_per_tensor_1067 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_704, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2243033Z     %dequantize_per_tensor_1068 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_704, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2243815Z     %dequantize_per_tensor_1069 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_704, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2244631Z     %dequantize_per_tensor_1070 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_704, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2245442Z     %dequantize_per_tensor_1071 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_704, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2246210Z     %dequantize_per_tensor_1072 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_704, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2246989Z     %dequantize_per_tensor_1073 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_704, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2247758Z     %dequantize_per_tensor_1074 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_704, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2248530Z     %dequantize_per_tensor_1075 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_704, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2249395Z     %dequantize_per_tensor_1076 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_704, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2249857Z     %transpose_171 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1063, 1, 2), kwargs = {})
2025-03-21T20:30:48.2250576Z     %quantize_per_tensor_705 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_171, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2251368Z     %dequantize_per_tensor_1077 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_705, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2251784Z     %select_192 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1077, 0, 0), kwargs = {})
2025-03-21T20:30:48.2252500Z     %quantize_per_tensor_706 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_192, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2253277Z     %dequantize_per_tensor_1078 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_706, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2253710Z     %select_193 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1078, 0, 0), kwargs = {})
2025-03-21T20:30:48.2254419Z     %quantize_per_tensor_707 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_193, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2255214Z     %dequantize_per_tensor_1079 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_707, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2255663Z     %transpose_172 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1062, 1, 2), kwargs = {})
2025-03-21T20:30:48.2256396Z     %quantize_per_tensor_708 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_172, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2257259Z     %dequantize_per_tensor_1080 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_708, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2257691Z     %select_194 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1080, 0, 0), kwargs = {})
2025-03-21T20:30:48.2258395Z     %quantize_per_tensor_709 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_194, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2259187Z     %dequantize_per_tensor_1081 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_709, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2259608Z     %select_195 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1081, 0, 1), kwargs = {})
2025-03-21T20:30:48.2260325Z     %quantize_per_tensor_710 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_195, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2261124Z     %dequantize_per_tensor_1082 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_710, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2261580Z     %transpose_173 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1061, 1, 2), kwargs = {})
2025-03-21T20:30:48.2262296Z     %quantize_per_tensor_711 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_173, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2263089Z     %dequantize_per_tensor_1083 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_711, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2263504Z     %select_196 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1083, 0, 0), kwargs = {})
2025-03-21T20:30:48.2264216Z     %quantize_per_tensor_712 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_196, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2264991Z     %dequantize_per_tensor_1084 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_712, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2265418Z     %select_197 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1084, 0, 2), kwargs = {})
2025-03-21T20:30:48.2266122Z     %quantize_per_tensor_713 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_197, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2266907Z     %dequantize_per_tensor_1085 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_713, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2267349Z     %transpose_174 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1060, 1, 2), kwargs = {})
2025-03-21T20:30:48.2268074Z     %quantize_per_tensor_714 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_174, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2268915Z     %dequantize_per_tensor_1086 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_714, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2269341Z     %select_198 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1086, 0, 0), kwargs = {})
2025-03-21T20:30:48.2270040Z     %quantize_per_tensor_715 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_198, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2270824Z     %dequantize_per_tensor_1087 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_715, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2271239Z     %select_199 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1087, 0, 3), kwargs = {})
2025-03-21T20:30:48.2271951Z     %quantize_per_tensor_716 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_199, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2272752Z     %dequantize_per_tensor_1088 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_716, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2273209Z     %transpose_175 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1059, 1, 2), kwargs = {})
2025-03-21T20:30:48.2273922Z     %quantize_per_tensor_717 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_175, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2274707Z     %dequantize_per_tensor_1089 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_717, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2275125Z     %select_200 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1089, 0, 0), kwargs = {})
2025-03-21T20:30:48.2275832Z     %quantize_per_tensor_718 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_200, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2276603Z     %dequantize_per_tensor_1090 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_718, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2277028Z     %select_201 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1090, 0, 4), kwargs = {})
2025-03-21T20:30:48.2277726Z     %quantize_per_tensor_719 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_201, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2278511Z     %dequantize_per_tensor_1091 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_719, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2278953Z     %transpose_176 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1058, 1, 2), kwargs = {})
2025-03-21T20:30:48.2279679Z     %quantize_per_tensor_720 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_176, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2280521Z     %dequantize_per_tensor_1092 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_720, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2280948Z     %select_202 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1092, 0, 0), kwargs = {})
2025-03-21T20:30:48.2281646Z     %quantize_per_tensor_721 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_202, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2282432Z     %dequantize_per_tensor_1093 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_721, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2282846Z     %select_203 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1093, 0, 5), kwargs = {})
2025-03-21T20:30:48.2283558Z     %quantize_per_tensor_722 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_203, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2284354Z     %dequantize_per_tensor_1094 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_722, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2284809Z     %transpose_177 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1057, 1, 2), kwargs = {})
2025-03-21T20:30:48.2285523Z     %quantize_per_tensor_723 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_177, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2286317Z     %dequantize_per_tensor_1095 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_723, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2286736Z     %select_204 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1095, 0, 0), kwargs = {})
2025-03-21T20:30:48.2287446Z     %quantize_per_tensor_724 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_204, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2288217Z     %dequantize_per_tensor_1096 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_724, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2288646Z     %select_205 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1096, 0, 6), kwargs = {})
2025-03-21T20:30:48.2289403Z     %quantize_per_tensor_725 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_205, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2290193Z     %dequantize_per_tensor_1097 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_725, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2290638Z     %transpose_178 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1056, 1, 2), kwargs = {})
2025-03-21T20:30:48.2291355Z     %quantize_per_tensor_726 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_178, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2292220Z     %dequantize_per_tensor_1098 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_726, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2292642Z     %select_206 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1098, 0, 0), kwargs = {})
2025-03-21T20:30:48.2293357Z     %quantize_per_tensor_727 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_206, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2294127Z     %dequantize_per_tensor_1099 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_727, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2294553Z     %select_207 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1099, 0, 7), kwargs = {})
2025-03-21T20:30:48.2295253Z     %quantize_per_tensor_728 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_207, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2296072Z     %dequantize_per_tensor_1100 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_728, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2296516Z     %transpose_179 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1055, 1, 2), kwargs = {})
2025-03-21T20:30:48.2297245Z     %quantize_per_tensor_729 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_179, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2298021Z     %dequantize_per_tensor_1101 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_729, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2298444Z     %select_208 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1101, 0, 0), kwargs = {})
2025-03-21T20:30:48.2299142Z     %quantize_per_tensor_730 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_208, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2299924Z     %dequantize_per_tensor_1102 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_730, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2300339Z     %select_209 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1102, 0, 8), kwargs = {})
2025-03-21T20:30:48.2301053Z     %quantize_per_tensor_731 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_209, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2301822Z     %dequantize_per_tensor_1103 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_731, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2302274Z     %transpose_180 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1054, 1, 2), kwargs = {})
2025-03-21T20:30:48.2302991Z     %quantize_per_tensor_732 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_180, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2303846Z     %dequantize_per_tensor_1104 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_732, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2304261Z     %select_210 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1104, 0, 0), kwargs = {})
2025-03-21T20:30:48.2304970Z     %quantize_per_tensor_733 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_210, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2305742Z     %dequantize_per_tensor_1105 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_733, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2306167Z     %select_211 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1105, 0, 9), kwargs = {})
2025-03-21T20:30:48.2306868Z     %quantize_per_tensor_734 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_211, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2307677Z     %dequantize_per_tensor_1106 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_734, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2308119Z     %transpose_181 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1053, 1, 2), kwargs = {})
2025-03-21T20:30:48.2308845Z     %quantize_per_tensor_735 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_181, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2309622Z     %dequantize_per_tensor_1107 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_735, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2310045Z     %select_212 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1107, 0, 0), kwargs = {})
2025-03-21T20:30:48.2310746Z     %quantize_per_tensor_736 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_212, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2311527Z     %dequantize_per_tensor_1108 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_736, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2311943Z     %select_213 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1108, 0, 10), kwargs = {})
2025-03-21T20:30:48.2312656Z     %quantize_per_tensor_737 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_213, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2313431Z     %dequantize_per_tensor_1109 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_737, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2313886Z     %transpose_182 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1052, 1, 2), kwargs = {})
2025-03-21T20:30:48.2314598Z     %quantize_per_tensor_738 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_182, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2315452Z     %dequantize_per_tensor_1110 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_738, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2315864Z     %select_214 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1110, 0, 0), kwargs = {})
2025-03-21T20:30:48.2316576Z     %quantize_per_tensor_739 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_214, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2317344Z     %dequantize_per_tensor_1111 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_739, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2317774Z     %select_215 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1111, 0, 11), kwargs = {})
2025-03-21T20:30:48.2318471Z     %quantize_per_tensor_740 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_215, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2319278Z     %dequantize_per_tensor_1112 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_740, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2320770Z     %cat_8 : [num_users=1] = call_function[target=torch.ops.aten.cat.default](args = ([%dequantize_per_tensor_1079, %dequantize_per_tensor_1082, %dequantize_per_tensor_1085, %dequantize_per_tensor_1088, %dequantize_per_tensor_1091, %dequantize_per_tensor_1094, %dequantize_per_tensor_1097, %dequantize_per_tensor_1100, %dequantize_per_tensor_1103, %dequantize_per_tensor_1106, %dequantize_per_tensor_1109, %dequantize_per_tensor_1112],), kwargs = {})
2025-03-21T20:30:48.2321467Z     %quantize_per_tensor_741 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%cat_8, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2322239Z     %dequantize_per_tensor_1113 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_741, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2322693Z     %view_57 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1113, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:30:48.2323374Z     %quantize_per_tensor_742 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_57, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2324160Z     %dequantize_per_tensor_1114 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_742, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2324606Z     %transpose_183 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1076, 1, 2), kwargs = {})
2025-03-21T20:30:48.2325331Z     %quantize_per_tensor_743 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_183, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2326100Z     %dequantize_per_tensor_1115 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_743, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2326522Z     %select_216 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1115, 0, 0), kwargs = {})
2025-03-21T20:30:48.2327308Z     %quantize_per_tensor_744 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_216, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2328096Z     %dequantize_per_tensor_1116 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_744, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2328505Z     %select_217 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1116, 0, 0), kwargs = {})
2025-03-21T20:30:48.2329216Z     %quantize_per_tensor_745 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_217, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2330046Z     %dequantize_per_tensor_1117 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_745, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2330506Z     %transpose_184 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1075, 1, 2), kwargs = {})
2025-03-21T20:30:48.2331248Z     %quantize_per_tensor_746 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_184, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2332032Z     %dequantize_per_tensor_1118 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_746, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2332596Z     %select_218 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1118, 0, 0), kwargs = {})
2025-03-21T20:30:48.2333316Z     %quantize_per_tensor_747 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_218, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2334088Z     %dequantize_per_tensor_1119 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_747, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2334512Z     %select_219 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1119, 0, 1), kwargs = {})
2025-03-21T20:30:48.2335211Z     %quantize_per_tensor_748 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_219, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2335997Z     %dequantize_per_tensor_1120 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_748, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2336442Z     %transpose_185 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1074, 1, 2), kwargs = {})
2025-03-21T20:30:48.2337169Z     %quantize_per_tensor_749 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_185, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2337943Z     %dequantize_per_tensor_1121 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_749, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2338367Z     %select_220 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1121, 0, 0), kwargs = {})
2025-03-21T20:30:48.2339182Z     %quantize_per_tensor_750 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_220, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2339973Z     %dequantize_per_tensor_1122 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_750, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2340383Z     %select_221 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1122, 0, 2), kwargs = {})
2025-03-21T20:30:48.2341095Z     %quantize_per_tensor_751 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_221, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2341873Z     %dequantize_per_tensor_1123 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_751, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2342331Z     %transpose_186 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1073, 1, 2), kwargs = {})
2025-03-21T20:30:48.2343081Z     %quantize_per_tensor_752 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_186, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2343867Z     %dequantize_per_tensor_1124 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_752, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2344275Z     %select_222 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1124, 0, 0), kwargs = {})
2025-03-21T20:30:48.2344993Z     %quantize_per_tensor_753 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_222, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2345766Z     %dequantize_per_tensor_1125 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_753, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2346192Z     %select_223 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1125, 0, 3), kwargs = {})
2025-03-21T20:30:48.2346889Z     %quantize_per_tensor_754 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_223, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2347676Z     %dequantize_per_tensor_1126 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_754, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2348122Z     %transpose_187 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1072, 1, 2), kwargs = {})
2025-03-21T20:30:48.2348852Z     %quantize_per_tensor_755 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_187, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2349627Z     %dequantize_per_tensor_1127 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_755, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2350053Z     %select_224 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1127, 0, 0), kwargs = {})
2025-03-21T20:30:48.2350821Z     %quantize_per_tensor_756 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_224, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2351611Z     %dequantize_per_tensor_1128 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_756, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2352023Z     %select_225 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1128, 0, 4), kwargs = {})
2025-03-21T20:30:48.2352721Z     %quantize_per_tensor_757 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_225, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2353513Z     %dequantize_per_tensor_1129 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_757, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2353962Z     %transpose_188 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1071, 1, 2), kwargs = {})
2025-03-21T20:30:48.2354722Z     %quantize_per_tensor_758 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_188, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2355498Z     %dequantize_per_tensor_1130 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_758, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2355926Z     %select_226 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1130, 0, 0), kwargs = {})
2025-03-21T20:30:48.2356635Z     %quantize_per_tensor_759 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_226, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2357428Z     %dequantize_per_tensor_1131 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_759, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2357845Z     %select_227 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1131, 0, 5), kwargs = {})
2025-03-21T20:30:48.2358562Z     %quantize_per_tensor_760 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_227, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2359344Z     %dequantize_per_tensor_1132 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_760, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2359803Z     %transpose_189 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1070, 1, 2), kwargs = {})
2025-03-21T20:30:48.2360524Z     %quantize_per_tensor_761 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_189, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2361309Z     %dequantize_per_tensor_1133 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_761, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2361720Z     %select_228 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1133, 0, 0), kwargs = {})
2025-03-21T20:30:48.2362521Z     %quantize_per_tensor_762 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_228, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2363300Z     %dequantize_per_tensor_1134 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_762, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2363726Z     %select_229 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1134, 0, 6), kwargs = {})
2025-03-21T20:30:48.2364426Z     %quantize_per_tensor_763 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_229, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2365214Z     %dequantize_per_tensor_1135 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_763, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2365662Z     %transpose_190 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1069, 1, 2), kwargs = {})
2025-03-21T20:30:48.2366418Z     %quantize_per_tensor_764 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_190, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2367192Z     %dequantize_per_tensor_1136 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_764, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2367619Z     %select_230 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1136, 0, 0), kwargs = {})
2025-03-21T20:30:48.2368323Z     %quantize_per_tensor_765 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_230, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2369113Z     %dequantize_per_tensor_1137 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_765, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2369588Z     %select_231 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1137, 0, 7), kwargs = {})
2025-03-21T20:30:48.2370306Z     %quantize_per_tensor_766 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_231, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2371084Z     %dequantize_per_tensor_1138 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_766, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2371542Z     %transpose_191 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1068, 1, 2), kwargs = {})
2025-03-21T20:30:48.2372260Z     %quantize_per_tensor_767 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_191, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2373046Z     %dequantize_per_tensor_1139 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_767, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2373459Z     %select_232 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1139, 0, 0), kwargs = {})
2025-03-21T20:30:48.2374251Z     %quantize_per_tensor_768 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_232, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2375028Z     %dequantize_per_tensor_1140 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_768, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2375453Z     %select_233 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1140, 0, 8), kwargs = {})
2025-03-21T20:30:48.2376155Z     %quantize_per_tensor_769 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_233, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2376946Z     %dequantize_per_tensor_1141 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_769, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2377394Z     %transpose_192 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1067, 1, 2), kwargs = {})
2025-03-21T20:30:48.2378150Z     %quantize_per_tensor_770 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_192, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2378925Z     %dequantize_per_tensor_1142 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_770, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2379350Z     %select_234 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1142, 0, 0), kwargs = {})
2025-03-21T20:30:48.2380058Z     %quantize_per_tensor_771 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_234, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2380846Z     %dequantize_per_tensor_1143 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_771, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2381260Z     %select_235 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1143, 0, 9), kwargs = {})
2025-03-21T20:30:48.2381975Z     %quantize_per_tensor_772 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_235, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2382748Z     %dequantize_per_tensor_1144 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_772, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2383208Z     %transpose_193 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1066, 1, 2), kwargs = {})
2025-03-21T20:30:48.2383925Z     %quantize_per_tensor_773 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_193, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2384711Z     %dequantize_per_tensor_1145 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_773, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2385122Z     %select_236 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1145, 0, 0), kwargs = {})
2025-03-21T20:30:48.2385913Z     %quantize_per_tensor_774 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_236, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2386687Z     %dequantize_per_tensor_1146 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_774, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2389021Z     %select_237 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1146, 0, 10), kwargs = {})
2025-03-21T20:30:48.2389749Z     %quantize_per_tensor_775 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_237, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2390527Z     %dequantize_per_tensor_1147 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_775, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2390985Z     %transpose_194 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1065, 1, 2), kwargs = {})
2025-03-21T20:30:48.2391743Z     %quantize_per_tensor_776 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_194, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2392558Z     %dequantize_per_tensor_1148 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_776, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2392972Z     %select_238 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1148, 0, 0), kwargs = {})
2025-03-21T20:30:48.2393687Z     %quantize_per_tensor_777 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_238, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2394464Z     %dequantize_per_tensor_1149 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_777, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2394890Z     %select_239 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1149, 0, 11), kwargs = {})
2025-03-21T20:30:48.2395595Z     %quantize_per_tensor_778 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_239, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2396381Z     %dequantize_per_tensor_1150 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_778, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2397881Z     %cat_9 : [num_users=1] = call_function[target=torch.ops.aten.cat.default](args = ([%dequantize_per_tensor_1117, %dequantize_per_tensor_1120, %dequantize_per_tensor_1123, %dequantize_per_tensor_1126, %dequantize_per_tensor_1129, %dequantize_per_tensor_1132, %dequantize_per_tensor_1135, %dequantize_per_tensor_1138, %dequantize_per_tensor_1141, %dequantize_per_tensor_1144, %dequantize_per_tensor_1147, %dequantize_per_tensor_1150],), kwargs = {})
2025-03-21T20:30:48.2398578Z     %quantize_per_tensor_779 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%cat_9, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2399384Z     %dequantize_per_tensor_1151 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_779, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2399865Z     %view_58 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1151, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:30:48.2400557Z     %quantize_per_tensor_780 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_58, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2401393Z     %dequantize_per_tensor_1152 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_780, 0.00012666585098486394, 35736, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2402161Z     %quantize_per_tensor_781 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%dequantize_per_tensor_1152, 0.00013814217527396977, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.2402958Z     %dequantize_per_tensor_1153 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_781, 0.00013814217527396977, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.2403468Z     %index_6 : [num_users=1] = call_function[target=torch.ops.aten.index.Tensor](args = (%dequantize_per_tensor_127, [%attn_options_input_pos]), kwargs = {})
2025-03-21T20:30:48.2404169Z     %quantize_per_tensor_782 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_6, 0.0038910505827516317, 65535, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2404936Z     %dequantize_per_tensor_1154 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_782, 0.0038910505827516317, 65535, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2405406Z     %transpose_195 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1114, -2, -1), kwargs = {})
2025-03-21T20:30:48.2406120Z     %quantize_per_tensor_783 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_195, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2406905Z     %dequantize_per_tensor_1155 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_783, 0.00040260335663333535, 31896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2407670Z     %quantize_per_tensor_784 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%dequantize_per_tensor_1155, 0.0004133212787564844, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.2408453Z     %dequantize_per_tensor_1156 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_784, 0.0004133212787564844, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.2408965Z     %matmul_8 : [num_users=1] = call_function[target=torch.ops.aten.matmul.default](args = (%dequantize_per_tensor_1050, %dequantize_per_tensor_1156), kwargs = {})
2025-03-21T20:30:48.2409741Z     %quantize_per_tensor_785 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%matmul_8, 0.0038901909720152617, 41062, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2410516Z     %dequantize_per_tensor_1157 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_785, 0.0038901909720152617, 41062, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2411299Z     %dequantize_per_tensor_1158 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param153, 1.9073777366429567e-06, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2411798Z     %mul_52 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1157, %dequantize_per_tensor_1158), kwargs = {})
2025-03-21T20:30:48.2412488Z     %quantize_per_tensor_786 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_52, 0.0004862738715019077, 41062, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2413290Z     %dequantize_per_tensor_1159 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_786, 0.0004862738715019077, 41062, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2413774Z     %add_22 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_1159, %dequantize_per_tensor_1154), kwargs = {})
2025-03-21T20:30:48.2414447Z     %quantize_per_tensor_787 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_22, 0.004292679484933615, 62763, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2415225Z     %dequantize_per_tensor_1160 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_787, 0.004292679484933615, 62763, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2415663Z     %softmax_4 : [num_users=1] = call_function[target=torch.ops.aten.softmax.int](args = (%dequantize_per_tensor_1160, -1), kwargs = {})
2025-03-21T20:30:48.2416358Z     %quantize_per_tensor_788 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%softmax_4, 1.5259021893143654e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2417125Z     %dequantize_per_tensor_1161 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_788, 1.5259021893143654e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2417648Z     %matmul_9 : [num_users=1] = call_function[target=torch.ops.aten.matmul.default](args = (%dequantize_per_tensor_1161, %dequantize_per_tensor_1153), kwargs = {})
2025-03-21T20:30:48.2418335Z     %quantize_per_tensor_789 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%matmul_9, 7.019092299742624e-05, 30970, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2419114Z     %dequantize_per_tensor_1162 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_789, 7.019092299742624e-05, 30970, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2419559Z     %transpose_196 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1162, 1, 2), kwargs = {})
2025-03-21T20:30:48.2420282Z     %quantize_per_tensor_790 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_196, 7.019092299742624e-05, 30970, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2421054Z     %dequantize_per_tensor_1163 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_790, 7.019092299742624e-05, 30970, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2421493Z     %view_59 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1163, [1, 1, 768]), kwargs = {})
2025-03-21T20:30:48.2422177Z     %quantize_per_tensor_791 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_59, 7.019092299742624e-05, 30970, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2422979Z     %dequantize_per_tensor_1164 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_791, 7.019092299742624e-05, 30970, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2423461Z     %unsqueeze_31 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_1164, -1), kwargs = {})
2025-03-21T20:30:48.2424179Z     %quantize_per_tensor_792 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_31, 7.019092299742624e-05, 30970, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2424972Z     %dequantize_per_tensor_1165 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_792, 7.019092299742624e-05, 30970, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2425429Z     %transpose_197 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1165, 1, 2), kwargs = {})
2025-03-21T20:30:48.2426143Z     %quantize_per_tensor_793 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_197, 7.019092299742624e-05, 30970, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2426923Z     %dequantize_per_tensor_1166 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_793, 7.019092299742624e-05, 30970, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2427462Z     %conv2d_31 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_1166, %dequantize_per_tensor_41), kwargs = {})
2025-03-21T20:30:48.2428164Z     %quantize_per_tensor_794 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_31, 5.287839303491637e-05, 36634, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2428931Z     %dequantize_per_tensor_1167 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_794, 5.287839303491637e-05, 36634, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2429386Z     %transpose_198 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1167, 1, 2), kwargs = {})
2025-03-21T20:30:48.2430095Z     %quantize_per_tensor_795 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_198, 5.287839303491637e-05, 36634, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2430877Z     %dequantize_per_tensor_1168 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_795, 5.287839303491637e-05, 36634, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2431292Z     %squeeze_31 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_1168, -1), kwargs = {})
2025-03-21T20:30:48.2431998Z     %quantize_per_tensor_796 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_31, 5.287839303491637e-05, 36634, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2432965Z     %dequantize_per_tensor_1169 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_796, 5.287839303491637e-05, 36634, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2433447Z     %add_23 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_989, %dequantize_per_tensor_1169), kwargs = {})
2025-03-21T20:30:48.2434120Z     %quantize_per_tensor_797 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_23, 0.0024935125838965178, 6282, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2434951Z     %dequantize_per_tensor_1170 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_797, 0.0024935125838965178, 6282, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2435745Z     %dequantize_per_tensor_1171 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_797, 0.0024935125838965178, 6282, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2436305Z     %rms_norm_9 : [num_users=1] = call_function[target=torch.ops.aten.rms_norm.default](args = (%dequantize_per_tensor_1171, [768], %dequantize_per_tensor_42, 1e-05), kwargs = {})
2025-03-21T20:30:48.2437039Z     %quantize_per_tensor_798 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%rms_norm_9, 0.0003157795872539282, 17787, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2437823Z     %dequantize_per_tensor_1172 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_798, 0.0003157795872539282, 17787, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2438588Z     %dequantize_per_tensor_1173 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_798, 0.0003157795872539282, 17787, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2439094Z     %unsqueeze_32 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_1173, -1), kwargs = {})
2025-03-21T20:30:48.2439803Z     %quantize_per_tensor_799 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_32, 0.0003157795872539282, 17787, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2440580Z     %dequantize_per_tensor_1174 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_799, 0.0003157795872539282, 17787, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2441026Z     %transpose_199 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1174, 1, 2), kwargs = {})
2025-03-21T20:30:48.2441747Z     %quantize_per_tensor_800 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_199, 0.0003157795872539282, 17787, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2442519Z     %dequantize_per_tensor_1175 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_800, 0.0003157795872539282, 17787, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2443033Z     %conv2d_32 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_1175, %dequantize_per_tensor_43), kwargs = {})
2025-03-21T20:30:48.2443727Z     %quantize_per_tensor_801 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_32, 0.00021449536143336445, 27755, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2444512Z     %dequantize_per_tensor_1176 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_801, 0.00021449536143336445, 27755, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2444957Z     %transpose_200 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1176, 1, 2), kwargs = {})
2025-03-21T20:30:48.2445685Z     %quantize_per_tensor_802 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_200, 0.00021449536143336445, 27755, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2446453Z     %dequantize_per_tensor_1177 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_802, 0.00021449536143336445, 27755, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2446929Z     %squeeze_32 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_1177, -1), kwargs = {})
2025-03-21T20:30:48.2447626Z     %quantize_per_tensor_803 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_32, 0.00021449536143336445, 27755, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2448432Z     %dequantize_per_tensor_1178 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_803, 0.00021449536143336445, 27755, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2449204Z     %dequantize_per_tensor_1179 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_803, 0.00021449536143336445, 27755, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2449697Z     %sigmoid_4 : [num_users=1] = call_function[target=torch.ops.aten.sigmoid.default](args = (%dequantize_per_tensor_1179,), kwargs = {})
2025-03-21T20:30:48.2450367Z     %quantize_per_tensor_804 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%sigmoid_4, 1.52587890625e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2451148Z     %dequantize_per_tensor_1180 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_804, 1.52587890625e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2451622Z     %mul_53 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1178, %dequantize_per_tensor_1180), kwargs = {})
2025-03-21T20:30:48.2452306Z     %quantize_per_tensor_805 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_53, 0.0001278657728107646, 2178, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2453076Z     %dequantize_per_tensor_1181 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_805, 0.0001278657728107646, 2178, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2453545Z     %unsqueeze_33 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_1172, -1), kwargs = {})
2025-03-21T20:30:48.2454251Z     %quantize_per_tensor_806 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_33, 0.0003157795872539282, 17787, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2455031Z     %dequantize_per_tensor_1182 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_806, 0.0003157795872539282, 17787, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2455474Z     %transpose_201 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1182, 1, 2), kwargs = {})
2025-03-21T20:30:48.2456187Z     %quantize_per_tensor_807 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_201, 0.0003157795872539282, 17787, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2456969Z     %dequantize_per_tensor_1183 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_807, 0.0003157795872539282, 17787, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2457476Z     %conv2d_33 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_1183, %dequantize_per_tensor_44), kwargs = {})
2025-03-21T20:30:48.2458179Z     %quantize_per_tensor_808 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_33, 0.0002493332722224295, 30131, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2459005Z     %dequantize_per_tensor_1184 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_808, 0.0002493332722224295, 30131, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2459466Z     %transpose_202 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1184, 1, 2), kwargs = {})
2025-03-21T20:30:48.2460205Z     %quantize_per_tensor_809 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_202, 0.0002493332722224295, 30131, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2460989Z     %dequantize_per_tensor_1185 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_809, 0.0002493332722224295, 30131, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2461406Z     %squeeze_33 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_1185, -1), kwargs = {})
2025-03-21T20:30:48.2462121Z     %quantize_per_tensor_810 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_33, 0.0002493332722224295, 30131, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2462915Z     %dequantize_per_tensor_1186 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_810, 0.0002493332722224295, 30131, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2463404Z     %mul_54 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1181, %dequantize_per_tensor_1186), kwargs = {})
2025-03-21T20:30:48.2464085Z     %quantize_per_tensor_811 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_54, 0.0006259557558223605, 32226, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2464867Z     %dequantize_per_tensor_1187 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_811, 0.0006259557558223605, 32226, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2465324Z     %unsqueeze_34 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_1187, -1), kwargs = {})
2025-03-21T20:30:48.2466041Z     %quantize_per_tensor_812 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_34, 0.0006259557558223605, 32226, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2466809Z     %dequantize_per_tensor_1188 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_812, 0.0006259557558223605, 32226, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2467265Z     %transpose_203 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1188, 1, 2), kwargs = {})
2025-03-21T20:30:48.2467977Z     %quantize_per_tensor_813 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_203, 0.0006259557558223605, 32226, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2468757Z     %dequantize_per_tensor_1189 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_813, 0.0006259557558223605, 32226, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2469261Z     %conv2d_34 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_1189, %dequantize_per_tensor_45), kwargs = {})
2025-03-21T20:30:48.2469959Z     %quantize_per_tensor_814 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_34, 0.0005451498436741531, 6186, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2470770Z     %dequantize_per_tensor_1190 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_814, 0.0005451498436741531, 6186, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2471228Z     %transpose_204 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1190, 1, 2), kwargs = {})
2025-03-21T20:30:48.2471970Z     %quantize_per_tensor_815 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_204, 0.0005451498436741531, 6186, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2472748Z     %dequantize_per_tensor_1191 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_815, 0.0005451498436741531, 6186, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2473163Z     %squeeze_34 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_1191, -1), kwargs = {})
2025-03-21T20:30:48.2473867Z     %quantize_per_tensor_816 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_34, 0.0005451498436741531, 6186, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2474660Z     %dequantize_per_tensor_1192 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_816, 0.0005451498436741531, 6186, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2475150Z     %add_24 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_1170, %dequantize_per_tensor_1192), kwargs = {})
2025-03-21T20:30:48.2475824Z     %quantize_per_tensor_817 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_24, 0.0026261727325618267, 6169, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2476599Z     %dequantize_per_tensor_1193 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_817, 0.0026261727325618267, 6169, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2477365Z     %dequantize_per_tensor_1194 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_817, 0.0026261727325618267, 6169, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2477925Z     %rms_norm_10 : [num_users=1] = call_function[target=torch.ops.aten.rms_norm.default](args = (%dequantize_per_tensor_1194, [768], %dequantize_per_tensor_46, 1e-05), kwargs = {})
2025-03-21T20:30:48.2478615Z     %quantize_per_tensor_818 : [num_users=3] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%rms_norm_10, 0.000380539771867916, 30682, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2479395Z     %dequantize_per_tensor_1195 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_818, 0.000380539771867916, 30682, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2480159Z     %dequantize_per_tensor_1196 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_818, 0.000380539771867916, 30682, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2480932Z     %dequantize_per_tensor_1197 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_818, 0.000380539771867916, 30682, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2481391Z     %unsqueeze_35 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_1197, -1), kwargs = {})
2025-03-21T20:30:48.2482127Z     %quantize_per_tensor_819 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_35, 0.000380539771867916, 30682, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2482915Z     %dequantize_per_tensor_1198 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_819, 0.000380539771867916, 30682, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2483371Z     %transpose_205 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1198, 1, 2), kwargs = {})
2025-03-21T20:30:48.2484105Z     %quantize_per_tensor_820 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_205, 0.000380539771867916, 30682, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2484886Z     %dequantize_per_tensor_1199 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_820, 0.000380539771867916, 30682, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2485393Z     %conv2d_35 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_1199, %dequantize_per_tensor_47), kwargs = {})
2025-03-21T20:30:48.2486121Z     %quantize_per_tensor_821 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_35, 0.0003648563288152218, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2486892Z     %dequantize_per_tensor_1200 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_821, 0.0003648563288152218, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2487349Z     %transpose_206 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1200, 1, 2), kwargs = {})
2025-03-21T20:30:48.2488065Z     %quantize_per_tensor_822 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_206, 0.0003648563288152218, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2488849Z     %dequantize_per_tensor_1201 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_822, 0.0003648563288152218, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2489350Z     %squeeze_35 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_1201, -1), kwargs = {})
2025-03-21T20:30:48.2490063Z     %quantize_per_tensor_823 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_35, 0.0003648563288152218, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2490835Z     %dequantize_per_tensor_1202 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_823, 0.0003648563288152218, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2491308Z     %unsqueeze_36 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_1196, -1), kwargs = {})
2025-03-21T20:30:48.2492010Z     %quantize_per_tensor_824 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_36, 0.000380539771867916, 30682, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2492789Z     %dequantize_per_tensor_1203 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_824, 0.000380539771867916, 30682, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2493233Z     %transpose_207 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1203, 1, 2), kwargs = {})
2025-03-21T20:30:48.2493986Z     %quantize_per_tensor_825 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_207, 0.000380539771867916, 30682, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2494772Z     %dequantize_per_tensor_1204 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_825, 0.000380539771867916, 30682, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2495289Z     %conv2d_36 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_1204, %dequantize_per_tensor_48), kwargs = {})
2025-03-21T20:30:48.2496004Z     %quantize_per_tensor_826 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_36, 0.0004354633274488151, 30890, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2496791Z     %dequantize_per_tensor_1205 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_826, 0.0004354633274488151, 30890, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2497240Z     %transpose_208 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1205, 1, 2), kwargs = {})
2025-03-21T20:30:48.2497986Z     %quantize_per_tensor_827 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_208, 0.0004354633274488151, 30890, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2498758Z     %dequantize_per_tensor_1206 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_827, 0.0004354633274488151, 30890, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2499185Z     %squeeze_36 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_1206, -1), kwargs = {})
2025-03-21T20:30:48.2499884Z     %quantize_per_tensor_828 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_36, 0.0004354633274488151, 30890, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2500671Z     %dequantize_per_tensor_1207 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_828, 0.0004354633274488151, 30890, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2501131Z     %unsqueeze_37 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_1195, -1), kwargs = {})
2025-03-21T20:30:48.2501846Z     %quantize_per_tensor_829 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_37, 0.000380539771867916, 30682, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2502608Z     %dequantize_per_tensor_1208 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_829, 0.000380539771867916, 30682, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2503063Z     %transpose_209 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1208, 1, 2), kwargs = {})
2025-03-21T20:30:48.2503770Z     %quantize_per_tensor_830 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_209, 0.000380539771867916, 30682, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2504544Z     %dequantize_per_tensor_1209 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_830, 0.000380539771867916, 30682, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2505048Z     %conv2d_37 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_1209, %dequantize_per_tensor_49), kwargs = {})
2025-03-21T20:30:48.2505801Z     %quantize_per_tensor_831 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_37, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2506572Z     %dequantize_per_tensor_1210 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_831, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2507024Z     %transpose_210 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1210, 1, 2), kwargs = {})
2025-03-21T20:30:48.2507756Z     %quantize_per_tensor_832 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_210, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2508539Z     %dequantize_per_tensor_1211 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_832, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2508954Z     %squeeze_37 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_1211, -1), kwargs = {})
2025-03-21T20:30:48.2509684Z     %quantize_per_tensor_833 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_37, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2510454Z     %dequantize_per_tensor_1212 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_833, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2510901Z     %view_60 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1202, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.2511585Z     %quantize_per_tensor_834 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_60, 0.0003648563288152218, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2512364Z     %dequantize_per_tensor_1213 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_834, 0.0003648563288152218, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2512797Z     %view_61 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1207, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.2513482Z     %quantize_per_tensor_835 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_61, 0.0004354633274488151, 30890, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2514266Z     %dequantize_per_tensor_1214 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_835, 0.0004354633274488151, 30890, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2514703Z     %view_62 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1212, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.2515400Z     %quantize_per_tensor_836 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_62, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2516170Z     %dequantize_per_tensor_1215 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_836, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2516661Z     %_to_copy_10 : [num_users=1] = call_function[target=torch.ops.aten._to_copy.default](args = (%dequantize_per_tensor_1213,), kwargs = {dtype: torch.float32})
2025-03-21T20:30:48.2517439Z     %quantize_per_tensor_837 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%_to_copy_10, 0.0003648563288152218, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2518225Z     %dequantize_per_tensor_1216 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_837, 0.0003648563288152218, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2518695Z     %view_63 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1216, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:30:48.2519390Z     %quantize_per_tensor_838 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_63, 0.0003648563288152218, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2520162Z     %dequantize_per_tensor_1217 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_838, 0.0003648563288152218, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2520579Z     %unbind_10 : [num_users=2] = call_function[target=torch.ops.aten.unbind.int](args = (%dequantize_per_tensor_1217, -1), kwargs = {})
2025-03-21T20:30:48.2520920Z     %getitem_20 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_10, 0), kwargs = {})
2025-03-21T20:30:48.2521246Z     %getitem_21 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_10, 1), kwargs = {})
2025-03-21T20:30:48.2521945Z     %quantize_per_tensor_839 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_20, 0.00027893035439774394, 29335, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2522730Z     %dequantize_per_tensor_1218 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_839, 0.00027893035439774394, 29335, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2523503Z     %dequantize_per_tensor_1219 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_839, 0.00027893035439774394, 29335, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2524208Z     %quantize_per_tensor_840 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_21, 0.0003648563288152218, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2524976Z     %dequantize_per_tensor_1220 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_840, 0.0003648563288152218, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2525752Z     %dequantize_per_tensor_1221 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_840, 0.0003648563288152218, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2526236Z     %_to_copy_11 : [num_users=1] = call_function[target=torch.ops.aten._to_copy.default](args = (%dequantize_per_tensor_1214,), kwargs = {dtype: torch.float32})
2025-03-21T20:30:48.2526938Z     %quantize_per_tensor_841 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%_to_copy_11, 0.0004354633274488151, 30890, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2527707Z     %dequantize_per_tensor_1222 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_841, 0.0004354633274488151, 30890, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2528165Z     %view_64 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1222, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:30:48.2528868Z     %quantize_per_tensor_842 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_64, 0.0004354633274488151, 30890, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2529730Z     %dequantize_per_tensor_1223 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_842, 0.0004354633274488151, 30890, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2530138Z     %unbind_11 : [num_users=2] = call_function[target=torch.ops.aten.unbind.int](args = (%dequantize_per_tensor_1223, -1), kwargs = {})
2025-03-21T20:30:48.2530501Z     %getitem_22 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_11, 0), kwargs = {})
2025-03-21T20:30:48.2530818Z     %getitem_23 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_11, 1), kwargs = {})
2025-03-21T20:30:48.2531534Z     %quantize_per_tensor_843 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_22, 0.00038958649383857846, 30696, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2532469Z     %dequantize_per_tensor_1224 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_843, 0.00038958649383857846, 30696, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2533317Z     %dequantize_per_tensor_1225 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_843, 0.00038958649383857846, 30696, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2534019Z     %quantize_per_tensor_844 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_23, 0.0004354633274488151, 30890, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2534806Z     %dequantize_per_tensor_1226 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_844, 0.0004354633274488151, 30890, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2535575Z     %dequantize_per_tensor_1227 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_844, 0.0004354633274488151, 30890, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2536024Z     %view_65 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_157, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:30:48.2536711Z     %quantize_per_tensor_845 : [num_users=4] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_65, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2537495Z     %dequantize_per_tensor_1228 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_845, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2538263Z     %dequantize_per_tensor_1229 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_845, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2539047Z     %dequantize_per_tensor_1230 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_845, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2539814Z     %dequantize_per_tensor_1231 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_845, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2540258Z     %view_66 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_169, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:30:48.2541003Z     %quantize_per_tensor_846 : [num_users=4] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_66, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2541788Z     %dequantize_per_tensor_1232 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_846, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2542582Z     %dequantize_per_tensor_1233 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_846, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2543363Z     %dequantize_per_tensor_1234 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_846, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2544134Z     %dequantize_per_tensor_1235 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_846, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2544646Z     %mul_55 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1219, %dequantize_per_tensor_1231), kwargs = {})
2025-03-21T20:30:48.2545326Z     %quantize_per_tensor_847 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_55, 0.0002772713196463883, 29395, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2546104Z     %dequantize_per_tensor_1236 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_847, 0.0002772713196463883, 29395, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2546578Z     %mul_56 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1220, %dequantize_per_tensor_1234), kwargs = {})
2025-03-21T20:30:48.2547271Z     %quantize_per_tensor_848 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_56, 0.00015570834511891007, 31919, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2548046Z     %dequantize_per_tensor_1237 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_848, 0.00015570834511891007, 31919, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2548529Z     %sub_10 : [num_users=1] = call_function[target=torch.ops.aten.sub.Tensor](args = (%dequantize_per_tensor_1236, %dequantize_per_tensor_1237), kwargs = {})
2025-03-21T20:30:48.2549210Z     %quantize_per_tensor_849 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%sub_10, 0.00027773523470386863, 29312, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2549996Z     %dequantize_per_tensor_1238 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_849, 0.00027773523470386863, 29312, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2550466Z     %mul_57 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1218, %dequantize_per_tensor_1235), kwargs = {})
2025-03-21T20:30:48.2551160Z     %quantize_per_tensor_850 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_57, 0.00017529382603242993, 34419, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2551928Z     %dequantize_per_tensor_1239 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_850, 0.00017529382603242993, 34419, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2552436Z     %mul_58 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1221, %dequantize_per_tensor_1230), kwargs = {})
2025-03-21T20:30:48.2553135Z     %quantize_per_tensor_851 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_58, 0.0003621247597038746, 32927, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2553916Z     %dequantize_per_tensor_1240 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_851, 0.0003621247597038746, 32927, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2554411Z     %add_25 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_1239, %dequantize_per_tensor_1240), kwargs = {})
2025-03-21T20:30:48.2555103Z     %quantize_per_tensor_852 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_25, 0.0003545602085068822, 32712, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2555872Z     %dequantize_per_tensor_1241 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_852, 0.0003545602085068822, 32712, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2556378Z     %mul_59 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1225, %dequantize_per_tensor_1229), kwargs = {})
2025-03-21T20:30:48.2557058Z     %quantize_per_tensor_853 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_59, 0.00038680178113281727, 30861, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2557844Z     %dequantize_per_tensor_1242 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_853, 0.00038680178113281727, 30861, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2558322Z     %mul_60 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1226, %dequantize_per_tensor_1232), kwargs = {})
2025-03-21T20:30:48.2559019Z     %quantize_per_tensor_854 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_60, 0.00020304229110479355, 35220, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2559799Z     %dequantize_per_tensor_1243 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_854, 0.00020304229110479355, 35220, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2560284Z     %sub_11 : [num_users=1] = call_function[target=torch.ops.aten.sub.Tensor](args = (%dequantize_per_tensor_1242, %dequantize_per_tensor_1243), kwargs = {})
2025-03-21T20:30:48.2560962Z     %quantize_per_tensor_855 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%sub_11, 0.000387135281926021, 30644, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2561742Z     %dequantize_per_tensor_1244 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_855, 0.000387135281926021, 30644, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2562216Z     %mul_61 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1224, %dequantize_per_tensor_1233), kwargs = {})
2025-03-21T20:30:48.2562916Z     %quantize_per_tensor_856 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_61, 0.00019716918177437037, 32534, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2563689Z     %dequantize_per_tensor_1245 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_856, 0.00019716918177437037, 32534, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2564236Z     %mul_62 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1227, %dequantize_per_tensor_1228), kwargs = {})
2025-03-21T20:30:48.2564918Z     %quantize_per_tensor_857 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_62, 0.00042476155795156956, 31446, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2565727Z     %dequantize_per_tensor_1246 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_857, 0.00042476155795156956, 31446, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2566200Z     %add_26 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_1245, %dequantize_per_tensor_1246), kwargs = {})
2025-03-21T20:30:48.2566893Z     %quantize_per_tensor_858 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_26, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2567661Z     %dequantize_per_tensor_1247 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_858, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2568219Z     %stack_10 : [num_users=1] = call_function[target=torch.ops.aten.stack.default](args = ([%dequantize_per_tensor_1238, %dequantize_per_tensor_1241], -1), kwargs = {})
2025-03-21T20:30:48.2568908Z     %quantize_per_tensor_859 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%stack_10, 0.0003545602085068822, 32712, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2569753Z     %dequantize_per_tensor_1248 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_859, 0.0003545602085068822, 32712, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2570195Z     %view_67 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1248, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.2570890Z     %quantize_per_tensor_860 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_67, 0.0003545602085068822, 32712, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2571658Z     %dequantize_per_tensor_1249 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_860, 0.0003545602085068822, 32712, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2572193Z     %stack_11 : [num_users=1] = call_function[target=torch.ops.aten.stack.default](args = ([%dequantize_per_tensor_1244, %dequantize_per_tensor_1247], -1), kwargs = {})
2025-03-21T20:30:48.2572880Z     %quantize_per_tensor_861 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%stack_11, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2573666Z     %dequantize_per_tensor_1250 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_861, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2574105Z     %view_68 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1250, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.2574804Z     %quantize_per_tensor_862 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_68, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2575606Z     %dequantize_per_tensor_1251 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_862, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2576143Z     %type_as_10 : [num_users=1] = call_function[target=torch.ops.aten.type_as.default](args = (%dequantize_per_tensor_1249, %dequantize_per_tensor_1213), kwargs = {})
2025-03-21T20:30:48.2576835Z     %quantize_per_tensor_863 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%type_as_10, 0.0003545602085068822, 32712, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2577639Z     %dequantize_per_tensor_1252 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_863, 0.0003545602085068822, 32712, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2578138Z     %type_as_11 : [num_users=1] = call_function[target=torch.ops.aten.type_as.default](args = (%dequantize_per_tensor_1251, %dequantize_per_tensor_1214), kwargs = {})
2025-03-21T20:30:48.2578828Z     %quantize_per_tensor_864 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%type_as_11, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2579608Z     %dequantize_per_tensor_1253 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_864, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2580079Z     %transpose_211 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1252, 1, 2), kwargs = {})
2025-03-21T20:30:48.2580802Z     %quantize_per_tensor_865 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_211, 0.0003545602085068822, 32712, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2581572Z     %dequantize_per_tensor_1254 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_865, 0.0003545602085068822, 32712, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2582209Z     %index_put_10 : [num_users=1] = call_function[target=torch.ops.aten.index_put.default](args = (%dequantize_per_tensor_128, [None, %attn_options_input_pos], %dequantize_per_tensor_1253), kwargs = {})
2025-03-21T20:30:48.2582917Z     %quantize_per_tensor_866 : [num_users=13] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_put_10, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2583696Z     %dequantize_per_tensor_1255 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_866, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2584480Z     %dequantize_per_tensor_1256 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_866, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2585244Z     %dequantize_per_tensor_1257 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_866, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2586023Z     %dequantize_per_tensor_1258 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_866, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2586788Z     %dequantize_per_tensor_1259 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_866, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2587589Z     %dequantize_per_tensor_1260 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_866, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2588382Z     %dequantize_per_tensor_1261 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_866, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2589159Z     %dequantize_per_tensor_1262 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_866, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2589957Z     %dequantize_per_tensor_1263 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_866, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2590739Z     %dequantize_per_tensor_1264 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_866, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2591506Z     %dequantize_per_tensor_1265 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_866, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2592313Z     %dequantize_per_tensor_1266 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_866, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2593077Z     %dequantize_per_tensor_1267 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_866, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2593725Z     %index_put_11 : [num_users=1] = call_function[target=torch.ops.aten.index_put.default](args = (%dequantize_per_tensor_129, [None, %attn_options_input_pos], %dequantize_per_tensor_1215), kwargs = {})
2025-03-21T20:30:48.2594429Z     %quantize_per_tensor_867 : [num_users=13] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_put_11, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2595216Z     %dequantize_per_tensor_1268 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_867, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2595984Z     %dequantize_per_tensor_1269 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_867, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2596770Z     %dequantize_per_tensor_1270 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_867, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2597538Z     %dequantize_per_tensor_1271 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_867, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2598324Z     %dequantize_per_tensor_1272 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_867, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2599091Z     %dequantize_per_tensor_1273 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_867, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2599898Z     %dequantize_per_tensor_1274 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_867, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2600693Z     %dequantize_per_tensor_1275 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_867, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2601496Z     %dequantize_per_tensor_1276 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_867, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2602267Z     %dequantize_per_tensor_1277 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_867, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2603052Z     %dequantize_per_tensor_1278 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_867, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2603857Z     %dequantize_per_tensor_1279 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_867, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2604642Z     %dequantize_per_tensor_1280 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_867, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2605089Z     %transpose_212 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1267, 1, 2), kwargs = {})
2025-03-21T20:30:48.2605817Z     %quantize_per_tensor_868 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_212, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2606587Z     %dequantize_per_tensor_1281 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_868, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2607019Z     %select_240 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1281, 0, 0), kwargs = {})
2025-03-21T20:30:48.2607720Z     %quantize_per_tensor_869 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_240, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2608504Z     %dequantize_per_tensor_1282 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_869, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2608919Z     %select_241 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1282, 0, 0), kwargs = {})
2025-03-21T20:30:48.2609689Z     %quantize_per_tensor_870 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_241, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2610460Z     %dequantize_per_tensor_1283 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_870, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2610919Z     %transpose_213 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1266, 1, 2), kwargs = {})
2025-03-21T20:30:48.2611660Z     %quantize_per_tensor_871 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_213, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2612467Z     %dequantize_per_tensor_1284 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_871, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2612880Z     %select_242 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1284, 0, 0), kwargs = {})
2025-03-21T20:30:48.2613617Z     %quantize_per_tensor_872 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_242, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2614385Z     %dequantize_per_tensor_1285 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_872, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2614811Z     %select_243 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1285, 0, 1), kwargs = {})
2025-03-21T20:30:48.2615534Z     %quantize_per_tensor_873 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_243, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2616315Z     %dequantize_per_tensor_1286 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_873, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2616759Z     %transpose_214 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1265, 1, 2), kwargs = {})
2025-03-21T20:30:48.2617483Z     %quantize_per_tensor_874 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_214, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2618251Z     %dequantize_per_tensor_1287 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_874, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2618679Z     %select_244 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1287, 0, 0), kwargs = {})
2025-03-21T20:30:48.2619375Z     %quantize_per_tensor_875 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_244, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2620155Z     %dequantize_per_tensor_1288 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_875, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2620569Z     %select_245 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1288, 0, 2), kwargs = {})
2025-03-21T20:30:48.2621276Z     %quantize_per_tensor_876 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_245, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2622047Z     %dequantize_per_tensor_1289 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_876, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2622506Z     %transpose_215 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1264, 1, 2), kwargs = {})
2025-03-21T20:30:48.2623236Z     %quantize_per_tensor_877 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_215, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2624038Z     %dequantize_per_tensor_1290 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_877, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2624448Z     %select_246 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1290, 0, 0), kwargs = {})
2025-03-21T20:30:48.2625174Z     %quantize_per_tensor_878 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_246, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2625946Z     %dequantize_per_tensor_1291 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_878, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2626372Z     %select_247 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1291, 0, 3), kwargs = {})
2025-03-21T20:30:48.2627066Z     %quantize_per_tensor_879 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_247, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2627878Z     %dequantize_per_tensor_1292 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_879, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2628322Z     %transpose_216 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1263, 1, 2), kwargs = {})
2025-03-21T20:30:48.2629034Z     %quantize_per_tensor_880 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_216, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2629816Z     %dequantize_per_tensor_1293 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_880, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2630227Z     %select_248 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1293, 0, 0), kwargs = {})
2025-03-21T20:30:48.2630935Z     %quantize_per_tensor_881 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_248, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2631702Z     %dequantize_per_tensor_1294 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_881, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2632129Z     %select_249 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1294, 0, 4), kwargs = {})
2025-03-21T20:30:48.2632994Z     %quantize_per_tensor_882 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_249, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2633783Z     %dequantize_per_tensor_1295 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_882, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2634227Z     %transpose_217 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1262, 1, 2), kwargs = {})
2025-03-21T20:30:48.2635008Z     %quantize_per_tensor_883 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_217, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2635807Z     %dequantize_per_tensor_1296 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_883, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2636233Z     %select_250 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1296, 0, 0), kwargs = {})
2025-03-21T20:30:48.2636958Z     %quantize_per_tensor_884 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_250, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2637744Z     %dequantize_per_tensor_1297 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_884, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2638162Z     %select_251 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1297, 0, 5), kwargs = {})
2025-03-21T20:30:48.2638869Z     %quantize_per_tensor_885 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_251, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2639676Z     %dequantize_per_tensor_1298 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_885, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2640128Z     %transpose_218 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1261, 1, 2), kwargs = {})
2025-03-21T20:30:48.2640839Z     %quantize_per_tensor_886 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_218, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2641624Z     %dequantize_per_tensor_1299 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_886, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2642038Z     %select_252 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1299, 0, 0), kwargs = {})
2025-03-21T20:30:48.2642747Z     %quantize_per_tensor_887 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_252, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2643513Z     %dequantize_per_tensor_1300 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_887, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2643940Z     %select_253 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1300, 0, 6), kwargs = {})
2025-03-21T20:30:48.2644632Z     %quantize_per_tensor_888 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_253, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2645412Z     %dequantize_per_tensor_1301 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_888, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2645858Z     %transpose_219 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1260, 1, 2), kwargs = {})
2025-03-21T20:30:48.2646604Z     %quantize_per_tensor_889 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_219, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2647396Z     %dequantize_per_tensor_1302 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_889, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2647820Z     %select_254 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1302, 0, 0), kwargs = {})
2025-03-21T20:30:48.2648550Z     %quantize_per_tensor_890 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_254, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2649390Z     %dequantize_per_tensor_1303 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_890, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2649809Z     %select_255 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1303, 0, 7), kwargs = {})
2025-03-21T20:30:48.2650519Z     %quantize_per_tensor_891 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_255, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2651316Z     %dequantize_per_tensor_1304 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_891, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2651778Z     %transpose_220 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1259, 1, 2), kwargs = {})
2025-03-21T20:30:48.2652491Z     %quantize_per_tensor_892 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_220, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2653276Z     %dequantize_per_tensor_1305 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_892, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2653690Z     %select_256 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1305, 0, 0), kwargs = {})
2025-03-21T20:30:48.2654401Z     %quantize_per_tensor_893 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_256, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2655168Z     %dequantize_per_tensor_1306 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_893, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2655597Z     %select_257 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1306, 0, 8), kwargs = {})
2025-03-21T20:30:48.2656289Z     %quantize_per_tensor_894 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_257, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2657069Z     %dequantize_per_tensor_1307 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_894, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2657512Z     %transpose_221 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1258, 1, 2), kwargs = {})
2025-03-21T20:30:48.2658236Z     %quantize_per_tensor_895 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_221, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2659057Z     %dequantize_per_tensor_1308 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_895, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2659483Z     %select_258 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1308, 0, 0), kwargs = {})
2025-03-21T20:30:48.2660203Z     %quantize_per_tensor_896 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_258, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2660988Z     %dequantize_per_tensor_1309 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_896, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2661404Z     %select_259 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1309, 0, 9), kwargs = {})
2025-03-21T20:30:48.2662114Z     %quantize_per_tensor_897 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_259, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2662909Z     %dequantize_per_tensor_1310 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_897, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2663369Z     %transpose_222 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1257, 1, 2), kwargs = {})
2025-03-21T20:30:48.2664080Z     %quantize_per_tensor_898 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_222, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2664865Z     %dequantize_per_tensor_1311 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_898, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2665279Z     %select_260 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1311, 0, 0), kwargs = {})
2025-03-21T20:30:48.2665991Z     %quantize_per_tensor_899 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_260, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2666755Z     %dequantize_per_tensor_1312 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_899, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2667185Z     %select_261 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1312, 0, 10), kwargs = {})
2025-03-21T20:30:48.2667881Z     %quantize_per_tensor_900 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_261, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2668661Z     %dequantize_per_tensor_1313 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_900, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2669106Z     %transpose_223 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1256, 1, 2), kwargs = {})
2025-03-21T20:30:48.2669825Z     %quantize_per_tensor_901 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_223, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2670642Z     %dequantize_per_tensor_1314 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_901, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2671069Z     %select_262 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1314, 0, 0), kwargs = {})
2025-03-21T20:30:48.2671785Z     %quantize_per_tensor_902 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_262, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2672564Z     %dequantize_per_tensor_1315 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_902, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2672979Z     %select_263 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1315, 0, 11), kwargs = {})
2025-03-21T20:30:48.2673675Z     %quantize_per_tensor_903 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_263, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2674479Z     %dequantize_per_tensor_1316 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_903, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2675989Z     %cat_10 : [num_users=1] = call_function[target=torch.ops.aten.cat.default](args = ([%dequantize_per_tensor_1283, %dequantize_per_tensor_1286, %dequantize_per_tensor_1289, %dequantize_per_tensor_1292, %dequantize_per_tensor_1295, %dequantize_per_tensor_1298, %dequantize_per_tensor_1301, %dequantize_per_tensor_1304, %dequantize_per_tensor_1307, %dequantize_per_tensor_1310, %dequantize_per_tensor_1313, %dequantize_per_tensor_1316],), kwargs = {})
2025-03-21T20:30:48.2676669Z     %quantize_per_tensor_904 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%cat_10, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2677449Z     %dequantize_per_tensor_1317 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_904, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2677893Z     %view_69 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1317, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:30:48.2678585Z     %quantize_per_tensor_905 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_69, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2679355Z     %dequantize_per_tensor_1318 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_905, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2679811Z     %transpose_224 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1280, 1, 2), kwargs = {})
2025-03-21T20:30:48.2680522Z     %quantize_per_tensor_906 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_224, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2681304Z     %dequantize_per_tensor_1319 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_906, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2681740Z     %select_264 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1319, 0, 0), kwargs = {})
2025-03-21T20:30:48.2682470Z     %quantize_per_tensor_907 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_264, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2683238Z     %dequantize_per_tensor_1320 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_907, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2683684Z     %select_265 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1320, 0, 0), kwargs = {})
2025-03-21T20:30:48.2684379Z     %quantize_per_tensor_908 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_265, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2685160Z     %dequantize_per_tensor_1321 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_908, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2685629Z     %transpose_225 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1279, 1, 2), kwargs = {})
2025-03-21T20:30:48.2686347Z     %quantize_per_tensor_909 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_225, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2687117Z     %dequantize_per_tensor_1322 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_909, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2687543Z     %select_266 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1322, 0, 0), kwargs = {})
2025-03-21T20:30:48.2688241Z     %quantize_per_tensor_910 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_266, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2689010Z     %dequantize_per_tensor_1323 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_910, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2689501Z     %select_267 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1323, 0, 1), kwargs = {})
2025-03-21T20:30:48.2690199Z     %quantize_per_tensor_911 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_267, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2690986Z     %dequantize_per_tensor_1324 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_911, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2691434Z     %transpose_226 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1278, 1, 2), kwargs = {})
2025-03-21T20:30:48.2692155Z     %quantize_per_tensor_912 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_226, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2692924Z     %dequantize_per_tensor_1325 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_912, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2693348Z     %select_268 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1325, 0, 0), kwargs = {})
2025-03-21T20:30:48.2694105Z     %quantize_per_tensor_913 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_268, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2694890Z     %dequantize_per_tensor_1326 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_913, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2695329Z     %select_269 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1326, 0, 2), kwargs = {})
2025-03-21T20:30:48.2696035Z     %quantize_per_tensor_914 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_269, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2696803Z     %dequantize_per_tensor_1327 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_914, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2697259Z     %transpose_227 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1277, 1, 2), kwargs = {})
2025-03-21T20:30:48.2698016Z     %quantize_per_tensor_915 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_227, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2698802Z     %dequantize_per_tensor_1328 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_915, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2699212Z     %select_270 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1328, 0, 0), kwargs = {})
2025-03-21T20:30:48.2699922Z     %quantize_per_tensor_916 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_270, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2700693Z     %dequantize_per_tensor_1329 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_916, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2701119Z     %select_271 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1329, 0, 3), kwargs = {})
2025-03-21T20:30:48.2701816Z     %quantize_per_tensor_917 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_271, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2702605Z     %dequantize_per_tensor_1330 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_917, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2703052Z     %transpose_228 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1276, 1, 2), kwargs = {})
2025-03-21T20:30:48.2703781Z     %quantize_per_tensor_918 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_228, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2704553Z     %dequantize_per_tensor_1331 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_918, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2704975Z     %select_272 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1331, 0, 0), kwargs = {})
2025-03-21T20:30:48.2705721Z     %quantize_per_tensor_919 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_272, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2706502Z     %dequantize_per_tensor_1332 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_919, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2706939Z     %select_273 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1332, 0, 4), kwargs = {})
2025-03-21T20:30:48.2707648Z     %quantize_per_tensor_920 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_273, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2708417Z     %dequantize_per_tensor_1333 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_920, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2708875Z     %transpose_229 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1275, 1, 2), kwargs = {})
2025-03-21T20:30:48.2709611Z     %quantize_per_tensor_921 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_229, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2710391Z     %dequantize_per_tensor_1334 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_921, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2710802Z     %select_274 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1334, 0, 0), kwargs = {})
2025-03-21T20:30:48.2711515Z     %quantize_per_tensor_922 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_274, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2712284Z     %dequantize_per_tensor_1335 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_922, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2712712Z     %select_275 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1335, 0, 5), kwargs = {})
2025-03-21T20:30:48.2713406Z     %quantize_per_tensor_923 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_275, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2714190Z     %dequantize_per_tensor_1336 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_923, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2714637Z     %transpose_230 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1274, 1, 2), kwargs = {})
2025-03-21T20:30:48.2715361Z     %quantize_per_tensor_924 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_230, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2716134Z     %dequantize_per_tensor_1337 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_924, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2716557Z     %select_276 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1337, 0, 0), kwargs = {})
2025-03-21T20:30:48.2717300Z     %quantize_per_tensor_925 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_276, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2718086Z     %dequantize_per_tensor_1338 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_925, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2718520Z     %select_277 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1338, 0, 6), kwargs = {})
2025-03-21T20:30:48.2719232Z     %quantize_per_tensor_926 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_277, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2720002Z     %dequantize_per_tensor_1339 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_926, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2720461Z     %transpose_231 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1273, 1, 2), kwargs = {})
2025-03-21T20:30:48.2721195Z     %quantize_per_tensor_927 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_231, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2721975Z     %dequantize_per_tensor_1340 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_927, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2722388Z     %select_278 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1340, 0, 0), kwargs = {})
2025-03-21T20:30:48.2723098Z     %quantize_per_tensor_928 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_278, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2723862Z     %dequantize_per_tensor_1341 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_928, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2724288Z     %select_279 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1341, 0, 7), kwargs = {})
2025-03-21T20:30:48.2724983Z     %quantize_per_tensor_929 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_279, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2725759Z     %dequantize_per_tensor_1342 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_929, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2726202Z     %transpose_232 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1272, 1, 2), kwargs = {})
2025-03-21T20:30:48.2726927Z     %quantize_per_tensor_930 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_232, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2727695Z     %dequantize_per_tensor_1343 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_930, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2728120Z     %select_280 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1343, 0, 0), kwargs = {})
2025-03-21T20:30:48.2728863Z     %quantize_per_tensor_931 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_280, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2729698Z     %dequantize_per_tensor_1344 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_931, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2730108Z     %select_281 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1344, 0, 8), kwargs = {})
2025-03-21T20:30:48.2730839Z     %quantize_per_tensor_932 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_281, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2731609Z     %dequantize_per_tensor_1345 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_932, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2732069Z     %transpose_233 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1271, 1, 2), kwargs = {})
2025-03-21T20:30:48.2732981Z     %quantize_per_tensor_933 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_233, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2733764Z     %dequantize_per_tensor_1346 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_933, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2734173Z     %select_282 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1346, 0, 0), kwargs = {})
2025-03-21T20:30:48.2734868Z     %quantize_per_tensor_934 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_282, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2735649Z     %dequantize_per_tensor_1347 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_934, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2736061Z     %select_283 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1347, 0, 9), kwargs = {})
2025-03-21T20:30:48.2736770Z     %quantize_per_tensor_935 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_283, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2737537Z     %dequantize_per_tensor_1348 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_935, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2737992Z     %transpose_234 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1270, 1, 2), kwargs = {})
2025-03-21T20:30:48.2738701Z     %quantize_per_tensor_936 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_234, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2739471Z     %dequantize_per_tensor_1349 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_936, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2739881Z     %select_284 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1349, 0, 0), kwargs = {})
2025-03-21T20:30:48.2740647Z     %quantize_per_tensor_937 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_284, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2741445Z     %dequantize_per_tensor_1350 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_937, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2741876Z     %select_285 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1350, 0, 10), kwargs = {})
2025-03-21T20:30:48.2743167Z     %quantize_per_tensor_938 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_285, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2744753Z     %dequantize_per_tensor_1351 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_938, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2746104Z     %transpose_235 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1269, 1, 2), kwargs = {})
2025-03-21T20:30:48.2747418Z     %quantize_per_tensor_939 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_235, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2749015Z     %dequantize_per_tensor_1352 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_939, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2750304Z     %select_286 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1352, 0, 0), kwargs = {})
2025-03-21T20:30:48.2751544Z     %quantize_per_tensor_940 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_286, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2753124Z     %dequantize_per_tensor_1353 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_940, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2754427Z     %select_287 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1353, 0, 11), kwargs = {})
2025-03-21T20:30:48.2755655Z     %quantize_per_tensor_941 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_287, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2757235Z     %dequantize_per_tensor_1354 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_941, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2759661Z     %cat_11 : [num_users=1] = call_function[target=torch.ops.aten.cat.default](args = ([%dequantize_per_tensor_1321, %dequantize_per_tensor_1324, %dequantize_per_tensor_1327, %dequantize_per_tensor_1330, %dequantize_per_tensor_1333, %dequantize_per_tensor_1336, %dequantize_per_tensor_1339, %dequantize_per_tensor_1342, %dequantize_per_tensor_1345, %dequantize_per_tensor_1348, %dequantize_per_tensor_1351, %dequantize_per_tensor_1354],), kwargs = {})
2025-03-21T20:30:48.2761954Z     %quantize_per_tensor_942 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%cat_11, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2763546Z     %dequantize_per_tensor_1355 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_942, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2764900Z     %view_70 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1355, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:30:48.2766137Z     %quantize_per_tensor_943 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_70, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2767727Z     %dequantize_per_tensor_1356 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_943, 0.0001254916423931718, 28364, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2769431Z     %quantize_per_tensor_944 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%dequantize_per_tensor_1356, 0.00014235699200071394, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.2771090Z     %dequantize_per_tensor_1357 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_944, 0.00014235699200071394, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.2772492Z     %index_7 : [num_users=1] = call_function[target=torch.ops.aten.index.Tensor](args = (%dequantize_per_tensor_130, [%attn_options_input_pos]), kwargs = {})
2025-03-21T20:30:48.2773780Z     %quantize_per_tensor_945 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_7, 0.0038910505827516317, 65535, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2775348Z     %dequantize_per_tensor_1358 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_945, 0.0038910505827516317, 65535, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2776684Z     %transpose_236 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1318, -2, -1), kwargs = {})
2025-03-21T20:30:48.2777966Z     %quantize_per_tensor_946 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_236, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2779561Z     %dequantize_per_tensor_1359 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_946, 0.0004216498928144574, 32136, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2781214Z     %quantize_per_tensor_947 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%dequantize_per_tensor_1359, 0.00042978691635653377, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.2793078Z     %dequantize_per_tensor_1360 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_947, 0.00042978691635653377, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.2794524Z     %matmul_10 : [num_users=1] = call_function[target=torch.ops.aten.matmul.default](args = (%dequantize_per_tensor_1254, %dequantize_per_tensor_1360), kwargs = {})
2025-03-21T20:30:48.2795858Z     %quantize_per_tensor_948 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%matmul_10, 0.0038201091811060905, 40308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2797440Z     %dequantize_per_tensor_1361 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_948, 0.0038201091811060905, 40308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2799161Z     %dequantize_per_tensor_1362 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param154, 1.9073777366429567e-06, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2800533Z     %mul_63 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1361, %dequantize_per_tensor_1362), kwargs = {})
2025-03-21T20:30:48.2801794Z     %quantize_per_tensor_949 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_63, 0.0004775136476382613, 40308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2803396Z     %dequantize_per_tensor_1363 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_949, 0.0004775136476382613, 40308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2804753Z     %add_27 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_1363, %dequantize_per_tensor_1358), kwargs = {})
2025-03-21T20:30:48.2806020Z     %quantize_per_tensor_950 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_27, 0.004275546874850988, 62718, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2807571Z     %dequantize_per_tensor_1364 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_950, 0.004275546874850988, 62718, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2808898Z     %softmax_5 : [num_users=1] = call_function[target=torch.ops.aten.softmax.int](args = (%dequantize_per_tensor_1364, -1), kwargs = {})
2025-03-21T20:30:48.2810221Z     %quantize_per_tensor_951 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%softmax_5, 1.5259021893143654e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2811792Z     %dequantize_per_tensor_1365 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_951, 1.5259021893143654e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2813178Z     %matmul_11 : [num_users=1] = call_function[target=torch.ops.aten.matmul.default](args = (%dequantize_per_tensor_1365, %dequantize_per_tensor_1357), kwargs = {})
2025-03-21T20:30:48.2814501Z     %quantize_per_tensor_952 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%matmul_11, 7.123954856069759e-05, 34216, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2816081Z     %dequantize_per_tensor_1366 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_952, 7.123954856069759e-05, 34216, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2817410Z     %transpose_237 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1366, 1, 2), kwargs = {})
2025-03-21T20:30:48.2818683Z     %quantize_per_tensor_953 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_237, 7.123954856069759e-05, 34216, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2820275Z     %dequantize_per_tensor_1367 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_953, 7.123954856069759e-05, 34216, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2821575Z     %view_71 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1367, [1, 1, 768]), kwargs = {})
2025-03-21T20:30:48.2822799Z     %quantize_per_tensor_954 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_71, 7.123954856069759e-05, 34216, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2824397Z     %dequantize_per_tensor_1368 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_954, 7.123954856069759e-05, 34216, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2825782Z     %unsqueeze_38 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_1368, -1), kwargs = {})
2025-03-21T20:30:48.2827064Z     %quantize_per_tensor_955 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_38, 7.123954856069759e-05, 34216, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2828681Z     %dequantize_per_tensor_1369 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_955, 7.123954856069759e-05, 34216, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2830008Z     %transpose_238 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1369, 1, 2), kwargs = {})
2025-03-21T20:30:48.2831280Z     %quantize_per_tensor_956 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_238, 7.123954856069759e-05, 34216, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2833071Z     %dequantize_per_tensor_1370 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_956, 7.123954856069759e-05, 34216, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2834533Z     %conv2d_38 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_1370, %dequantize_per_tensor_50), kwargs = {})
2025-03-21T20:30:48.2835845Z     %quantize_per_tensor_957 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_38, 4.46785670646932e-05, 25383, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2837410Z     %dequantize_per_tensor_1371 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_957, 4.46785670646932e-05, 25383, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2838721Z     %transpose_239 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1371, 1, 2), kwargs = {})
2025-03-21T20:30:48.2839987Z     %quantize_per_tensor_958 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_239, 4.46785670646932e-05, 25383, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2841568Z     %dequantize_per_tensor_1372 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_958, 4.46785670646932e-05, 25383, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2842860Z     %squeeze_38 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_1372, -1), kwargs = {})
2025-03-21T20:30:48.2844080Z     %quantize_per_tensor_959 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_38, 4.46785670646932e-05, 25383, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2845650Z     %dequantize_per_tensor_1373 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_959, 4.46785670646932e-05, 25383, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2847006Z     %add_28 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_1193, %dequantize_per_tensor_1373), kwargs = {})
2025-03-21T20:30:48.2848267Z     %quantize_per_tensor_960 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_28, 0.0026234339457005262, 6156, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2849927Z     %dequantize_per_tensor_1374 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_960, 0.0026234339457005262, 6156, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2851609Z     %dequantize_per_tensor_1375 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_960, 0.0026234339457005262, 6156, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2853037Z     %rms_norm_11 : [num_users=1] = call_function[target=torch.ops.aten.rms_norm.default](args = (%dequantize_per_tensor_1375, [768], %dequantize_per_tensor_51, 1e-05), kwargs = {})
2025-03-21T20:30:48.2854428Z     %quantize_per_tensor_961 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%rms_norm_11, 0.0003379492845851928, 19066, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2855996Z     %dequantize_per_tensor_1376 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_961, 0.0003379492845851928, 19066, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2857653Z     %dequantize_per_tensor_1377 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_961, 0.0003379492845851928, 19066, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2859018Z     %unsqueeze_39 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_1377, -1), kwargs = {})
2025-03-21T20:30:48.2860297Z     %quantize_per_tensor_962 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_39, 0.0003379492845851928, 19066, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2861890Z     %dequantize_per_tensor_1378 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_962, 0.0003379492845851928, 19066, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2863226Z     %transpose_240 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1378, 1, 2), kwargs = {})
2025-03-21T20:30:48.2864501Z     %quantize_per_tensor_963 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_240, 0.0003379492845851928, 19066, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2866100Z     %dequantize_per_tensor_1379 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_963, 0.0003379492845851928, 19066, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2867487Z     %conv2d_39 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_1379, %dequantize_per_tensor_52), kwargs = {})
2025-03-21T20:30:48.2868808Z     %quantize_per_tensor_964 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_39, 0.00017915855278261006, 28370, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2870393Z     %dequantize_per_tensor_1380 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_964, 0.00017915855278261006, 28370, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2871726Z     %transpose_241 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1380, 1, 2), kwargs = {})
2025-03-21T20:30:48.2873003Z     %quantize_per_tensor_965 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_241, 0.00017915855278261006, 28370, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2874594Z     %dequantize_per_tensor_1381 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_965, 0.00017915855278261006, 28370, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2875943Z     %squeeze_39 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_1381, -1), kwargs = {})
2025-03-21T20:30:48.2877178Z     %quantize_per_tensor_966 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_39, 0.00017915855278261006, 28370, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2878772Z     %dequantize_per_tensor_1382 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_966, 0.00017915855278261006, 28370, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2880454Z     %dequantize_per_tensor_1383 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_966, 0.00017915855278261006, 28370, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2881772Z     %sigmoid_5 : [num_users=1] = call_function[target=torch.ops.aten.sigmoid.default](args = (%dequantize_per_tensor_1383,), kwargs = {})
2025-03-21T20:30:48.2882989Z     %quantize_per_tensor_967 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%sigmoid_5, 1.52587890625e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2884538Z     %dequantize_per_tensor_1384 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_967, 1.52587890625e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2885869Z     %mul_64 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1382, %dequantize_per_tensor_1384), kwargs = {})
2025-03-21T20:30:48.2887138Z     %quantize_per_tensor_968 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_64, 0.00010571902384981513, 2634, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2888708Z     %dequantize_per_tensor_1385 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_968, 0.00010571902384981513, 2634, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2890112Z     %unsqueeze_40 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_1376, -1), kwargs = {})
2025-03-21T20:30:48.2891376Z     %quantize_per_tensor_969 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_40, 0.0003379492845851928, 19066, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2892960Z     %dequantize_per_tensor_1386 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_969, 0.0003379492845851928, 19066, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2894291Z     %transpose_242 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1386, 1, 2), kwargs = {})
2025-03-21T20:30:48.2895566Z     %quantize_per_tensor_970 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_242, 0.0003379492845851928, 19066, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2897164Z     %dequantize_per_tensor_1387 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_970, 0.0003379492845851928, 19066, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2898550Z     %conv2d_40 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_1387, %dequantize_per_tensor_53), kwargs = {})
2025-03-21T20:30:48.2899855Z     %quantize_per_tensor_971 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_40, 0.0002466057485435158, 42095, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2901484Z     %dequantize_per_tensor_1388 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_971, 0.0002466057485435158, 42095, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2902818Z     %transpose_243 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1388, 1, 2), kwargs = {})
2025-03-21T20:30:48.2904121Z     %quantize_per_tensor_972 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_243, 0.0002466057485435158, 42095, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2905718Z     %dequantize_per_tensor_1389 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_972, 0.0002466057485435158, 42095, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2907020Z     %squeeze_40 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_1389, -1), kwargs = {})
2025-03-21T20:30:48.2908240Z     %quantize_per_tensor_973 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_40, 0.0002466057485435158, 42095, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2909876Z     %dequantize_per_tensor_1390 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_973, 0.0002466057485435158, 42095, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2911241Z     %mul_65 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1385, %dequantize_per_tensor_1390), kwargs = {})
2025-03-21T20:30:48.2912507Z     %quantize_per_tensor_974 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_65, 0.0003100545145571232, 27801, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2914069Z     %dequantize_per_tensor_1391 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_974, 0.0003100545145571232, 27801, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2915418Z     %unsqueeze_41 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_1391, -1), kwargs = {})
2025-03-21T20:30:48.2916701Z     %quantize_per_tensor_975 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_41, 0.0003100545145571232, 27801, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2918287Z     %dequantize_per_tensor_1392 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_975, 0.0003100545145571232, 27801, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2919621Z     %transpose_244 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1392, 1, 2), kwargs = {})
2025-03-21T20:30:48.2920896Z     %quantize_per_tensor_976 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_244, 0.0003100545145571232, 27801, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2922493Z     %dequantize_per_tensor_1393 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_976, 0.0003100545145571232, 27801, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2923887Z     %conv2d_41 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_1393, %dequantize_per_tensor_54), kwargs = {})
2025-03-21T20:30:48.2925200Z     %quantize_per_tensor_977 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_41, 0.00021493309759534895, 11862, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2926820Z     %dequantize_per_tensor_1394 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_977, 0.00021493309759534895, 11862, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2928159Z     %transpose_245 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1394, 1, 2), kwargs = {})
2025-03-21T20:30:48.2929533Z     %quantize_per_tensor_978 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_245, 0.00021493309759534895, 11862, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2931144Z     %dequantize_per_tensor_1395 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_978, 0.00021493309759534895, 11862, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2932613Z     %squeeze_41 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_1395, -1), kwargs = {})
2025-03-21T20:30:48.2933850Z     %quantize_per_tensor_979 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_41, 0.00021493309759534895, 11862, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2935486Z     %dequantize_per_tensor_1396 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_979, 0.00021493309759534895, 11862, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2936849Z     %add_29 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_1374, %dequantize_per_tensor_1396), kwargs = {})
2025-03-21T20:30:48.2938106Z     %quantize_per_tensor_980 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_29, 0.002668527187779546, 5953, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2939659Z     %dequantize_per_tensor_1397 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_980, 0.002668527187779546, 5953, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2941296Z     %dequantize_per_tensor_1398 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_980, 0.002668527187779546, 5953, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2942718Z     %rms_norm_12 : [num_users=1] = call_function[target=torch.ops.aten.rms_norm.default](args = (%dequantize_per_tensor_1398, [768], %dequantize_per_tensor_55, 1e-05), kwargs = {})
2025-03-21T20:30:48.2944058Z     %quantize_per_tensor_981 : [num_users=3] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%rms_norm_12, 0.0004216353117953986, 31504, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2945635Z     %dequantize_per_tensor_1399 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_981, 0.0004216353117953986, 31504, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2947291Z     %dequantize_per_tensor_1400 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_981, 0.0004216353117953986, 31504, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2948946Z     %dequantize_per_tensor_1401 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_981, 0.0004216353117953986, 31504, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2950283Z     %unsqueeze_42 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_1401, -1), kwargs = {})
2025-03-21T20:30:48.2951595Z     %quantize_per_tensor_982 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_42, 0.0004216353117953986, 31504, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2953217Z     %dequantize_per_tensor_1402 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_982, 0.0004216353117953986, 31504, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2954546Z     %transpose_246 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1402, 1, 2), kwargs = {})
2025-03-21T20:30:48.2955848Z     %quantize_per_tensor_983 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_246, 0.0004216353117953986, 31504, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2957443Z     %dequantize_per_tensor_1403 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_983, 0.0004216353117953986, 31504, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2958832Z     %conv2d_42 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_1403, %dequantize_per_tensor_56), kwargs = {})
2025-03-21T20:30:48.2960168Z     %quantize_per_tensor_984 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_42, 0.00036033670767210424, 26444, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2961754Z     %dequantize_per_tensor_1404 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_984, 0.00036033670767210424, 26444, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2963093Z     %transpose_247 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1404, 1, 2), kwargs = {})
2025-03-21T20:30:48.2964359Z     %quantize_per_tensor_985 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_247, 0.00036033670767210424, 26444, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2965962Z     %dequantize_per_tensor_1405 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_985, 0.00036033670767210424, 26444, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2967262Z     %squeeze_42 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_1405, -1), kwargs = {})
2025-03-21T20:30:48.2968488Z     %quantize_per_tensor_986 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_42, 0.00036033670767210424, 26444, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2970141Z     %dequantize_per_tensor_1406 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_986, 0.00036033670767210424, 26444, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2971483Z     %unsqueeze_43 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_1400, -1), kwargs = {})
2025-03-21T20:30:48.2972760Z     %quantize_per_tensor_987 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_43, 0.0004216353117953986, 31504, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2974353Z     %dequantize_per_tensor_1407 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_987, 0.0004216353117953986, 31504, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2975678Z     %transpose_248 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1407, 1, 2), kwargs = {})
2025-03-21T20:30:48.2976969Z     %quantize_per_tensor_988 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_248, 0.0004216353117953986, 31504, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2978584Z     %dequantize_per_tensor_1408 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_988, 0.0004216353117953986, 31504, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2979974Z     %conv2d_43 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_1408, %dequantize_per_tensor_57), kwargs = {})
2025-03-21T20:30:48.2981296Z     %quantize_per_tensor_989 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_43, 0.00046843686141073704, 34413, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2982885Z     %dequantize_per_tensor_1409 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_989, 0.00046843686141073704, 34413, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2984217Z     %transpose_249 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1409, 1, 2), kwargs = {})
2025-03-21T20:30:48.2985514Z     %quantize_per_tensor_990 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_249, 0.00046843686141073704, 34413, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2987117Z     %dequantize_per_tensor_1410 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_990, 0.00046843686141073704, 34413, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2988418Z     %squeeze_43 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_1410, -1), kwargs = {})
2025-03-21T20:30:48.2989651Z     %quantize_per_tensor_991 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_43, 0.00046843686141073704, 34413, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2991236Z     %dequantize_per_tensor_1411 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_991, 0.00046843686141073704, 34413, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2992586Z     %unsqueeze_44 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_1399, -1), kwargs = {})
2025-03-21T20:30:48.2993868Z     %quantize_per_tensor_992 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_44, 0.0004216353117953986, 31504, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2995457Z     %dequantize_per_tensor_1412 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_992, 0.0004216353117953986, 31504, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2996789Z     %transpose_250 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1412, 1, 2), kwargs = {})
2025-03-21T20:30:48.2998048Z     %quantize_per_tensor_993 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_250, 0.0004216353117953986, 31504, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.2999644Z     %dequantize_per_tensor_1413 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_993, 0.0004216353117953986, 31504, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3001029Z     %conv2d_44 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_1413, %dequantize_per_tensor_58), kwargs = {})
2025-03-21T20:30:48.3002391Z     %quantize_per_tensor_994 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_44, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3003979Z     %dequantize_per_tensor_1414 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_994, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3005312Z     %transpose_251 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1414, 1, 2), kwargs = {})
2025-03-21T20:30:48.3006607Z     %quantize_per_tensor_995 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_251, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3008220Z     %dequantize_per_tensor_1415 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_995, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3009586Z     %squeeze_44 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_1415, -1), kwargs = {})
2025-03-21T20:30:48.3010857Z     %quantize_per_tensor_996 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_44, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3012458Z     %dequantize_per_tensor_1416 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_996, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3013788Z     %view_72 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1406, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.3015018Z     %quantize_per_tensor_997 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_72, 0.00036033670767210424, 26444, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3016591Z     %dequantize_per_tensor_1417 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_997, 0.00036033670767210424, 26444, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3017919Z     %view_73 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1411, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.3019160Z     %quantize_per_tensor_998 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_73, 0.00046843686141073704, 34413, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3020736Z     %dequantize_per_tensor_1418 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_998, 0.00046843686141073704, 34413, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3022060Z     %view_74 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1416, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.3023299Z     %quantize_per_tensor_999 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_74, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3024877Z     %dequantize_per_tensor_1419 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_999, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3026245Z     %_to_copy_12 : [num_users=1] = call_function[target=torch.ops.aten._to_copy.default](args = (%dequantize_per_tensor_1417,), kwargs = {dtype: torch.float32})
2025-03-21T20:30:48.3027606Z     %quantize_per_tensor_1000 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%_to_copy_12, 0.00036033670767210424, 26444, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3029206Z     %dequantize_per_tensor_1420 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1000, 0.00036033670767210424, 26444, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3030572Z     %view_75 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1420, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:30:48.3031819Z     %quantize_per_tensor_1001 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_75, 0.00036033670767210424, 26444, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3033597Z     %dequantize_per_tensor_1421 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1001, 0.00036033670767210424, 26444, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3034912Z     %unbind_12 : [num_users=2] = call_function[target=torch.ops.aten.unbind.int](args = (%dequantize_per_tensor_1421, -1), kwargs = {})
2025-03-21T20:30:48.3035798Z     %getitem_24 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_12, 0), kwargs = {})
2025-03-21T20:30:48.3036547Z     %getitem_25 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_12, 1), kwargs = {})
2025-03-21T20:30:48.3037684Z     %quantize_per_tensor_1002 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_24, 0.0002986950858030468, 31901, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3039275Z     %dequantize_per_tensor_1422 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1002, 0.0002986950858030468, 31901, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3040924Z     %dequantize_per_tensor_1423 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1002, 0.0002986950858030468, 31901, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3042507Z     %quantize_per_tensor_1003 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_25, 0.0003436956903897226, 24551, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3044085Z     %dequantize_per_tensor_1424 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1003, 0.0003436956903897226, 24551, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3045736Z     %dequantize_per_tensor_1425 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1003, 0.0003436956903897226, 24551, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3047099Z     %_to_copy_13 : [num_users=1] = call_function[target=torch.ops.aten._to_copy.default](args = (%dequantize_per_tensor_1418,), kwargs = {dtype: torch.float32})
2025-03-21T20:30:48.3048385Z     %quantize_per_tensor_1004 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%_to_copy_13, 0.00046843686141073704, 34413, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3050032Z     %dequantize_per_tensor_1426 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1004, 0.00046843686141073704, 34413, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3051371Z     %view_76 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1426, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:30:48.3052692Z     %quantize_per_tensor_1005 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_76, 0.00046843686141073704, 34413, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3054268Z     %dequantize_per_tensor_1427 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1005, 0.00046843686141073704, 34413, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3055559Z     %unbind_13 : [num_users=2] = call_function[target=torch.ops.aten.unbind.int](args = (%dequantize_per_tensor_1427, -1), kwargs = {})
2025-03-21T20:30:48.3056449Z     %getitem_26 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_13, 0), kwargs = {})
2025-03-21T20:30:48.3057194Z     %getitem_27 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_13, 1), kwargs = {})
2025-03-21T20:30:48.3058319Z     %quantize_per_tensor_1006 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_26, 0.0004310147778596729, 31711, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3059905Z     %dequantize_per_tensor_1428 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1006, 0.0004310147778596729, 31711, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3061584Z     %dequantize_per_tensor_1429 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1006, 0.0004310147778596729, 31711, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3063160Z     %quantize_per_tensor_1007 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_27, 0.00046482981997542083, 34680, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3064758Z     %dequantize_per_tensor_1430 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1007, 0.00046482981997542083, 34680, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3066418Z     %dequantize_per_tensor_1431 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1007, 0.00046482981997542083, 34680, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3067735Z     %view_77 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_156, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:30:48.3068966Z     %quantize_per_tensor_1008 : [num_users=4] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_77, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3070533Z     %dequantize_per_tensor_1432 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1008, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3072178Z     %dequantize_per_tensor_1433 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1008, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3073825Z     %dequantize_per_tensor_1434 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1008, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3075471Z     %dequantize_per_tensor_1435 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1008, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3076782Z     %view_78 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_168, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:30:48.3078052Z     %quantize_per_tensor_1009 : [num_users=4] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_78, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3079619Z     %dequantize_per_tensor_1436 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1009, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3081287Z     %dequantize_per_tensor_1437 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1009, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3082932Z     %dequantize_per_tensor_1438 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1009, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3084580Z     %dequantize_per_tensor_1439 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1009, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3085946Z     %mul_66 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1423, %dequantize_per_tensor_1435), kwargs = {})
2025-03-21T20:30:48.3087208Z     %quantize_per_tensor_1010 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_66, 0.0002917187812272459, 32599, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3088767Z     %dequantize_per_tensor_1440 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1010, 0.0002917187812272459, 32599, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3090211Z     %mul_67 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1424, %dequantize_per_tensor_1438), kwargs = {})
2025-03-21T20:30:48.3091478Z     %quantize_per_tensor_1011 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_67, 0.00021490042854566127, 31703, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3093056Z     %dequantize_per_tensor_1441 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1011, 0.00021490042854566127, 31703, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3094415Z     %sub_12 : [num_users=1] = call_function[target=torch.ops.aten.sub.Tensor](args = (%dequantize_per_tensor_1440, %dequantize_per_tensor_1441), kwargs = {})
2025-03-21T20:30:48.3095682Z     %quantize_per_tensor_1012 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%sub_12, 0.0002888002200052142, 33000, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3097246Z     %dequantize_per_tensor_1442 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1012, 0.0002888002200052142, 33000, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3098604Z     %mul_68 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1422, %dequantize_per_tensor_1439), kwargs = {})
2025-03-21T20:30:48.3099870Z     %quantize_per_tensor_1013 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_68, 0.00015702449309173971, 33148, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3101441Z     %dequantize_per_tensor_1443 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1013, 0.00015702449309173971, 33148, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3102841Z     %mul_69 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1425, %dequantize_per_tensor_1434), kwargs = {})
2025-03-21T20:30:48.3104106Z     %quantize_per_tensor_1014 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_69, 0.00033834765781648457, 24827, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3105704Z     %dequantize_per_tensor_1444 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1014, 0.00033834765781648457, 24827, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3107064Z     %add_30 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_1443, %dequantize_per_tensor_1444), kwargs = {})
2025-03-21T20:30:48.3108334Z     %quantize_per_tensor_1015 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_30, 0.00033126529888249934, 25134, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3109897Z     %dequantize_per_tensor_1445 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1015, 0.00033126529888249934, 25134, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3111278Z     %mul_70 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1429, %dequantize_per_tensor_1433), kwargs = {})
2025-03-21T20:30:48.3112547Z     %quantize_per_tensor_1016 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_70, 0.00042510710773058236, 32035, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3114119Z     %dequantize_per_tensor_1446 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1016, 0.00042510710773058236, 32035, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3115477Z     %mul_71 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1430, %dequantize_per_tensor_1436), kwargs = {})
2025-03-21T20:30:48.3116749Z     %quantize_per_tensor_1017 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_71, 0.00023940755636431277, 32509, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3118318Z     %dequantize_per_tensor_1447 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1017, 0.00023940755636431277, 32509, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3119671Z     %sub_13 : [num_users=1] = call_function[target=torch.ops.aten.sub.Tensor](args = (%dequantize_per_tensor_1446, %dequantize_per_tensor_1447), kwargs = {})
2025-03-21T20:30:48.3120923Z     %quantize_per_tensor_1018 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%sub_13, 0.0004331881063990295, 31428, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3122486Z     %dequantize_per_tensor_1448 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1018, 0.0004331881063990295, 31428, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3123839Z     %mul_72 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1428, %dequantize_per_tensor_1437), kwargs = {})
2025-03-21T20:30:48.3125100Z     %quantize_per_tensor_1019 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_72, 0.00021039359853602946, 32216, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3126705Z     %dequantize_per_tensor_1449 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1019, 0.00021039359853602946, 32216, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3128083Z     %mul_73 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1431, %dequantize_per_tensor_1432), kwargs = {})
2025-03-21T20:30:48.3129405Z     %quantize_per_tensor_1020 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_73, 0.00045264922664500773, 34909, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3131002Z     %dequantize_per_tensor_1450 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1020, 0.00045264922664500773, 34909, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3132544Z     %add_31 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_1449, %dequantize_per_tensor_1450), kwargs = {})
2025-03-21T20:30:48.3133813Z     %quantize_per_tensor_1021 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_31, 0.0004520940419752151, 35209, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3135375Z     %dequantize_per_tensor_1451 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1021, 0.0004520940419752151, 35209, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3136828Z     %stack_12 : [num_users=1] = call_function[target=torch.ops.aten.stack.default](args = ([%dequantize_per_tensor_1442, %dequantize_per_tensor_1445], -1), kwargs = {})
2025-03-21T20:30:48.3138144Z     %quantize_per_tensor_1022 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%stack_12, 0.00034964593942277133, 27258, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3139723Z     %dequantize_per_tensor_1452 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1022, 0.00034964593942277133, 27258, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3141044Z     %view_79 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1452, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.3142276Z     %quantize_per_tensor_1023 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_79, 0.00034964593942277133, 27258, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3143855Z     %dequantize_per_tensor_1453 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1023, 0.00034964593942277133, 27258, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3145267Z     %stack_13 : [num_users=1] = call_function[target=torch.ops.aten.stack.default](args = ([%dequantize_per_tensor_1448, %dequantize_per_tensor_1451], -1), kwargs = {})
2025-03-21T20:30:48.3146583Z     %quantize_per_tensor_1024 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%stack_13, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3148143Z     %dequantize_per_tensor_1454 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1024, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3149454Z     %view_80 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1454, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.3150686Z     %quantize_per_tensor_1025 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_80, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3152277Z     %dequantize_per_tensor_1455 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1025, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3153688Z     %type_as_12 : [num_users=1] = call_function[target=torch.ops.aten.type_as.default](args = (%dequantize_per_tensor_1453, %dequantize_per_tensor_1417), kwargs = {})
2025-03-21T20:30:48.3154995Z     %quantize_per_tensor_1026 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%type_as_12, 0.00034964593942277133, 27258, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3156601Z     %dequantize_per_tensor_1456 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1026, 0.00034964593942277133, 27258, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3157986Z     %type_as_13 : [num_users=1] = call_function[target=torch.ops.aten.type_as.default](args = (%dequantize_per_tensor_1455, %dequantize_per_tensor_1418), kwargs = {})
2025-03-21T20:30:48.3159293Z     %quantize_per_tensor_1027 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%type_as_13, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3160886Z     %dequantize_per_tensor_1457 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1027, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3162208Z     %transpose_252 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1456, 1, 2), kwargs = {})
2025-03-21T20:30:48.3163479Z     %quantize_per_tensor_1028 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_252, 0.00034964593942277133, 27258, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3165082Z     %dequantize_per_tensor_1458 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1028, 0.00034964593942277133, 27258, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3166602Z     %index_put_12 : [num_users=1] = call_function[target=torch.ops.aten.index_put.default](args = (%dequantize_per_tensor_131, [None, %attn_options_input_pos], %dequantize_per_tensor_1457), kwargs = {})
2025-03-21T20:30:48.3168059Z     %quantize_per_tensor_1029 : [num_users=13] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_put_12, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3169702Z     %dequantize_per_tensor_1459 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1029, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3171362Z     %dequantize_per_tensor_1460 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1029, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3173012Z     %dequantize_per_tensor_1461 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1029, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3174666Z     %dequantize_per_tensor_1462 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1029, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3176318Z     %dequantize_per_tensor_1463 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1029, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3177985Z     %dequantize_per_tensor_1464 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1029, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3179657Z     %dequantize_per_tensor_1465 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1029, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3181324Z     %dequantize_per_tensor_1466 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1029, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3182966Z     %dequantize_per_tensor_1467 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1029, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3184613Z     %dequantize_per_tensor_1468 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1029, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3186277Z     %dequantize_per_tensor_1469 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1029, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3187927Z     %dequantize_per_tensor_1470 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1029, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3189578Z     %dequantize_per_tensor_1471 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1029, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3191089Z     %index_put_13 : [num_users=1] = call_function[target=torch.ops.aten.index_put.default](args = (%dequantize_per_tensor_132, [None, %attn_options_input_pos], %dequantize_per_tensor_1419), kwargs = {})
2025-03-21T20:30:48.3192539Z     %quantize_per_tensor_1030 : [num_users=13] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_put_13, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3194131Z     %dequantize_per_tensor_1472 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1030, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3195791Z     %dequantize_per_tensor_1473 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1030, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3197448Z     %dequantize_per_tensor_1474 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1030, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3199103Z     %dequantize_per_tensor_1475 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1030, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3200761Z     %dequantize_per_tensor_1476 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1030, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3202418Z     %dequantize_per_tensor_1477 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1030, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3204127Z     %dequantize_per_tensor_1478 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1030, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3205787Z     %dequantize_per_tensor_1479 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1030, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3207455Z     %dequantize_per_tensor_1480 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1030, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3209115Z     %dequantize_per_tensor_1481 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1030, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3210854Z     %dequantize_per_tensor_1482 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1030, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3212552Z     %dequantize_per_tensor_1483 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1030, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3214214Z     %dequantize_per_tensor_1484 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1030, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3215544Z     %transpose_253 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1471, 1, 2), kwargs = {})
2025-03-21T20:30:48.3216810Z     %quantize_per_tensor_1031 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_253, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3218396Z     %dequantize_per_tensor_1485 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1031, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3219690Z     %select_288 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1485, 0, 0), kwargs = {})
2025-03-21T20:30:48.3220911Z     %quantize_per_tensor_1032 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_288, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3222478Z     %dequantize_per_tensor_1486 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1032, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3223766Z     %select_289 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1486, 0, 0), kwargs = {})
2025-03-21T20:30:48.3224987Z     %quantize_per_tensor_1033 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_289, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3226551Z     %dequantize_per_tensor_1487 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1033, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3227876Z     %transpose_254 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1470, 1, 2), kwargs = {})
2025-03-21T20:30:48.3229191Z     %quantize_per_tensor_1034 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_254, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3230782Z     %dequantize_per_tensor_1488 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1034, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3232118Z     %select_290 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1488, 0, 0), kwargs = {})
2025-03-21T20:30:48.3233526Z     %quantize_per_tensor_1035 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_290, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3235115Z     %dequantize_per_tensor_1489 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1035, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3236418Z     %select_291 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1489, 0, 1), kwargs = {})
2025-03-21T20:30:48.3237714Z     %quantize_per_tensor_1036 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_291, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3239300Z     %dequantize_per_tensor_1490 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1036, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3240638Z     %transpose_255 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1469, 1, 2), kwargs = {})
2025-03-21T20:30:48.3241920Z     %quantize_per_tensor_1037 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_255, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3243502Z     %dequantize_per_tensor_1491 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1037, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3244795Z     %select_292 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1491, 0, 0), kwargs = {})
2025-03-21T20:30:48.3246023Z     %quantize_per_tensor_1038 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_292, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3247603Z     %dequantize_per_tensor_1492 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1038, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3248896Z     %select_293 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1492, 0, 2), kwargs = {})
2025-03-21T20:30:48.3250181Z     %quantize_per_tensor_1039 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_293, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3251764Z     %dequantize_per_tensor_1493 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1039, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3253104Z     %transpose_256 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1468, 1, 2), kwargs = {})
2025-03-21T20:30:48.3254473Z     %quantize_per_tensor_1040 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_256, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3256077Z     %dequantize_per_tensor_1494 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1040, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3257384Z     %select_294 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1494, 0, 0), kwargs = {})
2025-03-21T20:30:48.3258647Z     %quantize_per_tensor_1041 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_294, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3260212Z     %dequantize_per_tensor_1495 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1041, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3261515Z     %select_295 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1495, 0, 3), kwargs = {})
2025-03-21T20:30:48.3262768Z     %quantize_per_tensor_1042 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_295, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3264351Z     %dequantize_per_tensor_1496 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1042, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3265673Z     %transpose_257 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1467, 1, 2), kwargs = {})
2025-03-21T20:30:48.3266944Z     %quantize_per_tensor_1043 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_257, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3268536Z     %dequantize_per_tensor_1497 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1043, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3269837Z     %select_296 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1497, 0, 0), kwargs = {})
2025-03-21T20:30:48.3271056Z     %quantize_per_tensor_1044 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_296, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3272622Z     %dequantize_per_tensor_1498 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1044, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3273919Z     %select_297 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1498, 0, 4), kwargs = {})
2025-03-21T20:30:48.3275144Z     %quantize_per_tensor_1045 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_297, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3276719Z     %dequantize_per_tensor_1499 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1045, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3278050Z     %transpose_258 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1466, 1, 2), kwargs = {})
2025-03-21T20:30:48.3279342Z     %quantize_per_tensor_1046 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_258, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3280957Z     %dequantize_per_tensor_1500 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1046, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3282253Z     %select_298 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1500, 0, 0), kwargs = {})
2025-03-21T20:30:48.3283501Z     %quantize_per_tensor_1047 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_298, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3285079Z     %dequantize_per_tensor_1501 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1047, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3286368Z     %select_299 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1501, 0, 5), kwargs = {})
2025-03-21T20:30:48.3287617Z     %quantize_per_tensor_1048 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_299, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3289193Z     %dequantize_per_tensor_1502 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1048, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3290584Z     %transpose_259 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1465, 1, 2), kwargs = {})
2025-03-21T20:30:48.3291850Z     %quantize_per_tensor_1049 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_259, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3293438Z     %dequantize_per_tensor_1503 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1049, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3294741Z     %select_300 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1503, 0, 0), kwargs = {})
2025-03-21T20:30:48.3295971Z     %quantize_per_tensor_1050 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_300, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3297554Z     %dequantize_per_tensor_1504 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1050, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3298859Z     %select_301 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1504, 0, 6), kwargs = {})
2025-03-21T20:30:48.3300090Z     %quantize_per_tensor_1051 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_301, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3301668Z     %dequantize_per_tensor_1505 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1051, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3303005Z     %transpose_260 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1464, 1, 2), kwargs = {})
2025-03-21T20:30:48.3304316Z     %quantize_per_tensor_1052 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_260, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3305946Z     %dequantize_per_tensor_1506 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1052, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3307249Z     %select_302 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1506, 0, 0), kwargs = {})
2025-03-21T20:30:48.3308516Z     %quantize_per_tensor_1053 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_302, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3310095Z     %dequantize_per_tensor_1507 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1053, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3311394Z     %select_303 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1507, 0, 7), kwargs = {})
2025-03-21T20:30:48.3312653Z     %quantize_per_tensor_1054 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_303, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3314239Z     %dequantize_per_tensor_1508 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1054, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3315572Z     %transpose_261 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1463, 1, 2), kwargs = {})
2025-03-21T20:30:48.3316844Z     %quantize_per_tensor_1055 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_261, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3318440Z     %dequantize_per_tensor_1509 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1055, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3319737Z     %select_304 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1509, 0, 0), kwargs = {})
2025-03-21T20:30:48.3320965Z     %quantize_per_tensor_1056 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_304, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3322550Z     %dequantize_per_tensor_1510 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1056, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3323847Z     %select_305 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1510, 0, 8), kwargs = {})
2025-03-21T20:30:48.3325077Z     %quantize_per_tensor_1057 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_305, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3326647Z     %dequantize_per_tensor_1511 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1057, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3327977Z     %transpose_262 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1462, 1, 2), kwargs = {})
2025-03-21T20:30:48.3329328Z     %quantize_per_tensor_1058 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_262, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3330958Z     %dequantize_per_tensor_1512 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1058, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3333732Z     %select_306 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1512, 0, 0), kwargs = {})
2025-03-21T20:30:48.3335057Z     %quantize_per_tensor_1059 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_306, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3336641Z     %dequantize_per_tensor_1513 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1059, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3337943Z     %select_307 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1513, 0, 9), kwargs = {})
2025-03-21T20:30:48.3339208Z     %quantize_per_tensor_1060 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_307, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3340787Z     %dequantize_per_tensor_1514 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1060, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3342122Z     %transpose_263 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1461, 1, 2), kwargs = {})
2025-03-21T20:30:48.3343395Z     %quantize_per_tensor_1061 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_263, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3344977Z     %dequantize_per_tensor_1515 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1061, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3346271Z     %select_308 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1515, 0, 0), kwargs = {})
2025-03-21T20:30:48.3347502Z     %quantize_per_tensor_1062 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_308, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3349083Z     %dequantize_per_tensor_1516 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1062, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3350381Z     %select_309 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1516, 0, 10), kwargs = {})
2025-03-21T20:30:48.3351606Z     %quantize_per_tensor_1063 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_309, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3353191Z     %dequantize_per_tensor_1517 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1063, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3354520Z     %transpose_264 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1460, 1, 2), kwargs = {})
2025-03-21T20:30:48.3355828Z     %quantize_per_tensor_1064 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_264, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3357461Z     %dequantize_per_tensor_1518 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1064, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3358764Z     %select_310 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1518, 0, 0), kwargs = {})
2025-03-21T20:30:48.3360023Z     %quantize_per_tensor_1065 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_310, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3361598Z     %dequantize_per_tensor_1519 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1065, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3362911Z     %select_311 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1519, 0, 11), kwargs = {})
2025-03-21T20:30:48.3364163Z     %quantize_per_tensor_1066 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_311, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3365738Z     %dequantize_per_tensor_1520 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1066, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3368113Z     %cat_12 : [num_users=1] = call_function[target=torch.ops.aten.cat.default](args = ([%dequantize_per_tensor_1487, %dequantize_per_tensor_1490, %dequantize_per_tensor_1493, %dequantize_per_tensor_1496, %dequantize_per_tensor_1499, %dequantize_per_tensor_1502, %dequantize_per_tensor_1505, %dequantize_per_tensor_1508, %dequantize_per_tensor_1511, %dequantize_per_tensor_1514, %dequantize_per_tensor_1517, %dequantize_per_tensor_1520],), kwargs = {})
2025-03-21T20:30:48.3370464Z     %quantize_per_tensor_1067 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%cat_12, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3372031Z     %dequantize_per_tensor_1521 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1067, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3373365Z     %view_81 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1521, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:30:48.3374612Z     %quantize_per_tensor_1068 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_81, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3376186Z     %dequantize_per_tensor_1522 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1068, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3377513Z     %transpose_265 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1484, 1, 2), kwargs = {})
2025-03-21T20:30:48.3378792Z     %quantize_per_tensor_1069 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_265, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3380401Z     %dequantize_per_tensor_1523 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1069, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3381765Z     %select_312 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1523, 0, 0), kwargs = {})
2025-03-21T20:30:48.3382989Z     %quantize_per_tensor_1070 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_312, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3384611Z     %dequantize_per_tensor_1524 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1070, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3385916Z     %select_313 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1524, 0, 0), kwargs = {})
2025-03-21T20:30:48.3387148Z     %quantize_per_tensor_1071 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_313, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3388740Z     %dequantize_per_tensor_1525 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1071, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3390102Z     %transpose_266 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1483, 1, 2), kwargs = {})
2025-03-21T20:30:48.3391381Z     %quantize_per_tensor_1072 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_266, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3392989Z     %dequantize_per_tensor_1526 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1072, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3394299Z     %select_314 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1526, 0, 0), kwargs = {})
2025-03-21T20:30:48.3395529Z     %quantize_per_tensor_1073 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_314, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3397134Z     %dequantize_per_tensor_1527 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1073, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3398436Z     %select_315 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1527, 0, 1), kwargs = {})
2025-03-21T20:30:48.3399672Z     %quantize_per_tensor_1074 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_315, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3401256Z     %dequantize_per_tensor_1528 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1074, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3402597Z     %transpose_267 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1482, 1, 2), kwargs = {})
2025-03-21T20:30:48.3403875Z     %quantize_per_tensor_1075 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_267, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3405485Z     %dequantize_per_tensor_1529 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1075, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3406858Z     %select_316 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1529, 0, 0), kwargs = {})
2025-03-21T20:30:48.3408091Z     %quantize_per_tensor_1076 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_316, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3409783Z     %dequantize_per_tensor_1530 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1076, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3411091Z     %select_317 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1530, 0, 2), kwargs = {})
2025-03-21T20:30:48.3412328Z     %quantize_per_tensor_1077 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_317, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3413921Z     %dequantize_per_tensor_1531 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1077, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3415283Z     %transpose_268 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1481, 1, 2), kwargs = {})
2025-03-21T20:30:48.3416565Z     %quantize_per_tensor_1078 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_268, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3418162Z     %dequantize_per_tensor_1532 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1078, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3419469Z     %select_318 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1532, 0, 0), kwargs = {})
2025-03-21T20:30:48.3420714Z     %quantize_per_tensor_1079 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_318, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3422318Z     %dequantize_per_tensor_1533 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1079, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3423629Z     %select_319 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1533, 0, 3), kwargs = {})
2025-03-21T20:30:48.3424872Z     %quantize_per_tensor_1080 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_319, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3426469Z     %dequantize_per_tensor_1534 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1080, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3427808Z     %transpose_269 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1480, 1, 2), kwargs = {})
2025-03-21T20:30:48.3429089Z     %quantize_per_tensor_1081 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_269, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3430705Z     %dequantize_per_tensor_1535 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1081, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3432080Z     %select_320 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1535, 0, 0), kwargs = {})
2025-03-21T20:30:48.3433522Z     %quantize_per_tensor_1082 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_320, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3435163Z     %dequantize_per_tensor_1536 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1082, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3436473Z     %select_321 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1536, 0, 4), kwargs = {})
2025-03-21T20:30:48.3437713Z     %quantize_per_tensor_1083 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_321, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3439319Z     %dequantize_per_tensor_1537 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1083, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3440694Z     %transpose_270 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1479, 1, 2), kwargs = {})
2025-03-21T20:30:48.3441976Z     %quantize_per_tensor_1084 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_270, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3443577Z     %dequantize_per_tensor_1538 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1084, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3444888Z     %select_322 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1538, 0, 0), kwargs = {})
2025-03-21T20:30:48.3446125Z     %quantize_per_tensor_1085 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_322, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3447737Z     %dequantize_per_tensor_1539 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1085, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3449047Z     %select_323 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1539, 0, 5), kwargs = {})
2025-03-21T20:30:48.3450350Z     %quantize_per_tensor_1086 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_323, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3451934Z     %dequantize_per_tensor_1540 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1086, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3453275Z     %transpose_271 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1478, 1, 2), kwargs = {})
2025-03-21T20:30:48.3454557Z     %quantize_per_tensor_1087 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_271, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3456171Z     %dequantize_per_tensor_1541 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1087, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3457567Z     %select_324 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1541, 0, 0), kwargs = {})
2025-03-21T20:30:48.3458812Z     %quantize_per_tensor_1088 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_324, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3460442Z     %dequantize_per_tensor_1542 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1088, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3461749Z     %select_325 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1542, 0, 6), kwargs = {})
2025-03-21T20:30:48.3462989Z     %quantize_per_tensor_1089 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_325, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3464586Z     %dequantize_per_tensor_1543 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1089, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3465953Z     %transpose_272 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1477, 1, 2), kwargs = {})
2025-03-21T20:30:48.3467235Z     %quantize_per_tensor_1090 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_272, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3468837Z     %dequantize_per_tensor_1544 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1090, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3470151Z     %select_326 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1544, 0, 0), kwargs = {})
2025-03-21T20:30:48.3471382Z     %quantize_per_tensor_1091 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_326, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3472173Z     %dequantize_per_tensor_1545 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1091, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3472585Z     %select_327 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1545, 0, 7), kwargs = {})
2025-03-21T20:30:48.3473306Z     %quantize_per_tensor_1092 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_327, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3474080Z     %dequantize_per_tensor_1546 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1092, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3474536Z     %transpose_273 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1476, 1, 2), kwargs = {})
2025-03-21T20:30:48.3475257Z     %quantize_per_tensor_1093 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_273, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3476043Z     %dequantize_per_tensor_1547 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1093, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3476503Z     %select_328 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1547, 0, 0), kwargs = {})
2025-03-21T20:30:48.3477222Z     %quantize_per_tensor_1094 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_328, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3478023Z     %dequantize_per_tensor_1548 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1094, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3478445Z     %select_329 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1548, 0, 8), kwargs = {})
2025-03-21T20:30:48.3479156Z     %quantize_per_tensor_1095 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_329, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3479948Z     %dequantize_per_tensor_1549 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1095, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3480419Z     %transpose_274 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1475, 1, 2), kwargs = {})
2025-03-21T20:30:48.3481150Z     %quantize_per_tensor_1096 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_274, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3481924Z     %dequantize_per_tensor_1550 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1096, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3482352Z     %select_330 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1550, 0, 0), kwargs = {})
2025-03-21T20:30:48.3483063Z     %quantize_per_tensor_1097 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_330, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3483856Z     %dequantize_per_tensor_1551 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1097, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3484266Z     %select_331 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1551, 0, 9), kwargs = {})
2025-03-21T20:30:48.3484986Z     %quantize_per_tensor_1098 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_331, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3485764Z     %dequantize_per_tensor_1552 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1098, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3486220Z     %transpose_275 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1474, 1, 2), kwargs = {})
2025-03-21T20:30:48.3486939Z     %quantize_per_tensor_1099 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_275, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3487724Z     %dequantize_per_tensor_1553 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1099, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3488201Z     %select_332 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1553, 0, 0), kwargs = {})
2025-03-21T20:30:48.3488920Z     %quantize_per_tensor_1100 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_332, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3489784Z     %dequantize_per_tensor_1554 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1100, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3490211Z     %select_333 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1554, 0, 10), kwargs = {})
2025-03-21T20:30:48.3490922Z     %quantize_per_tensor_1101 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_333, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3491711Z     %dequantize_per_tensor_1555 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1101, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3492179Z     %transpose_276 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1473, 1, 2), kwargs = {})
2025-03-21T20:30:48.3492913Z     %quantize_per_tensor_1102 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_276, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3493687Z     %dequantize_per_tensor_1556 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1102, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3494114Z     %select_334 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1556, 0, 0), kwargs = {})
2025-03-21T20:30:48.3494821Z     %quantize_per_tensor_1103 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_334, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3495613Z     %dequantize_per_tensor_1557 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1103, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3496026Z     %select_335 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1557, 0, 11), kwargs = {})
2025-03-21T20:30:48.3496742Z     %quantize_per_tensor_1104 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_335, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3497519Z     %dequantize_per_tensor_1558 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1104, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3499031Z     %cat_13 : [num_users=1] = call_function[target=torch.ops.aten.cat.default](args = ([%dequantize_per_tensor_1525, %dequantize_per_tensor_1528, %dequantize_per_tensor_1531, %dequantize_per_tensor_1534, %dequantize_per_tensor_1537, %dequantize_per_tensor_1540, %dequantize_per_tensor_1543, %dequantize_per_tensor_1546, %dequantize_per_tensor_1549, %dequantize_per_tensor_1552, %dequantize_per_tensor_1555, %dequantize_per_tensor_1558],), kwargs = {})
2025-03-21T20:30:48.3499750Z     %quantize_per_tensor_1105 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%cat_13, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3500570Z     %dequantize_per_tensor_1559 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1105, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3501016Z     %view_82 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1559, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:30:48.3501744Z     %quantize_per_tensor_1106 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_82, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3502525Z     %dequantize_per_tensor_1560 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1106, 0.00011607543274294585, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3503318Z     %quantize_per_tensor_1107 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%dequantize_per_tensor_1560, 0.00011609794455580413, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.3504124Z     %dequantize_per_tensor_1561 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1107, 0.00011609794455580413, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.3504623Z     %index_8 : [num_users=1] = call_function[target=torch.ops.aten.index.Tensor](args = (%dequantize_per_tensor_133, [%attn_options_input_pos]), kwargs = {})
2025-03-21T20:30:48.3505313Z     %quantize_per_tensor_1108 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_8, 0.0038910505827516317, 65535, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3506096Z     %dequantize_per_tensor_1562 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1108, 0.0038910505827516317, 65535, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3506548Z     %transpose_277 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1522, -2, -1), kwargs = {})
2025-03-21T20:30:48.3507273Z     %quantize_per_tensor_1109 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_277, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3508045Z     %dequantize_per_tensor_1563 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1109, 0.000468338665086776, 33988, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3508823Z     %quantize_per_tensor_1110 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%dequantize_per_tensor_1563, 0.0004857908934354782, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.3509600Z     %dequantize_per_tensor_1564 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1110, 0.0004857908934354782, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.3510121Z     %matmul_12 : [num_users=1] = call_function[target=torch.ops.aten.matmul.default](args = (%dequantize_per_tensor_1458, %dequantize_per_tensor_1564), kwargs = {})
2025-03-21T20:30:48.3510814Z     %quantize_per_tensor_1111 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%matmul_12, 0.004839103203266859, 45381, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3511640Z     %dequantize_per_tensor_1565 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1111, 0.004839103203266859, 45381, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3512407Z     %dequantize_per_tensor_1566 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param155, 1.9073777366429567e-06, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3512890Z     %mul_74 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1565, %dequantize_per_tensor_1566), kwargs = {})
2025-03-21T20:30:48.3513595Z     %quantize_per_tensor_1112 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_74, 0.0006048879004083574, 45381, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3514380Z     %dequantize_per_tensor_1567 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1112, 0.0006048879004083574, 45381, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3514853Z     %add_32 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_1567, %dequantize_per_tensor_1562), kwargs = {})
2025-03-21T20:30:48.3515541Z     %quantize_per_tensor_1113 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_32, 0.004426939878612757, 62781, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3516337Z     %dequantize_per_tensor_1568 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1113, 0.004426939878612757, 62781, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3516764Z     %softmax_6 : [num_users=1] = call_function[target=torch.ops.aten.softmax.int](args = (%dequantize_per_tensor_1568, -1), kwargs = {})
2025-03-21T20:30:48.3517456Z     %quantize_per_tensor_1114 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%softmax_6, 1.5259021893143654e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3518233Z     %dequantize_per_tensor_1569 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1114, 1.5259021893143654e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3518744Z     %matmul_13 : [num_users=1] = call_function[target=torch.ops.aten.matmul.default](args = (%dequantize_per_tensor_1569, %dequantize_per_tensor_1561), kwargs = {})
2025-03-21T20:30:48.3519453Z     %quantize_per_tensor_1115 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%matmul_13, 8.035911014303565e-05, 31531, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3520224Z     %dequantize_per_tensor_1570 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1115, 8.035911014303565e-05, 31531, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3520684Z     %transpose_278 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1570, 1, 2), kwargs = {})
2025-03-21T20:30:48.3521398Z     %quantize_per_tensor_1116 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_278, 8.035911014303565e-05, 31531, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3522186Z     %dequantize_per_tensor_1571 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1116, 8.035911014303565e-05, 31531, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3522609Z     %view_83 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1571, [1, 1, 768]), kwargs = {})
2025-03-21T20:30:48.3523328Z     %quantize_per_tensor_1117 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_83, 8.035911014303565e-05, 31531, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3524126Z     %dequantize_per_tensor_1572 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1117, 8.035911014303565e-05, 31531, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3524598Z     %unsqueeze_45 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_1572, -1), kwargs = {})
2025-03-21T20:30:48.3525331Z     %quantize_per_tensor_1118 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_45, 8.035911014303565e-05, 31531, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3526127Z     %dequantize_per_tensor_1573 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1118, 8.035911014303565e-05, 31531, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3526573Z     %transpose_279 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1573, 1, 2), kwargs = {})
2025-03-21T20:30:48.3527289Z     %quantize_per_tensor_1119 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_279, 8.035911014303565e-05, 31531, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3528113Z     %dequantize_per_tensor_1574 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1119, 8.035911014303565e-05, 31531, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3528616Z     %conv2d_45 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_1574, %dequantize_per_tensor_59), kwargs = {})
2025-03-21T20:30:48.3529389Z     %quantize_per_tensor_1120 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_45, 4.686550164478831e-05, 25382, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3530169Z     %dequantize_per_tensor_1575 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1120, 4.686550164478831e-05, 25382, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3530628Z     %transpose_280 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1575, 1, 2), kwargs = {})
2025-03-21T20:30:48.3531346Z     %quantize_per_tensor_1121 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_280, 4.686550164478831e-05, 25382, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3532132Z     %dequantize_per_tensor_1576 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1121, 4.686550164478831e-05, 25382, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3532686Z     %squeeze_45 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_1576, -1), kwargs = {})
2025-03-21T20:30:48.3533397Z     %quantize_per_tensor_1122 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_45, 4.686550164478831e-05, 25382, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3534175Z     %dequantize_per_tensor_1577 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1122, 4.686550164478831e-05, 25382, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3534660Z     %add_33 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_1397, %dequantize_per_tensor_1577), kwargs = {})
2025-03-21T20:30:48.3535389Z     %quantize_per_tensor_1123 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_33, 0.00266623985953629, 5970, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3536201Z     %dequantize_per_tensor_1578 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1123, 0.00266623985953629, 5970, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3536963Z     %dequantize_per_tensor_1579 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1123, 0.00266623985953629, 5970, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3537552Z     %rms_norm_13 : [num_users=1] = call_function[target=torch.ops.aten.rms_norm.default](args = (%dequantize_per_tensor_1579, [768], %dequantize_per_tensor_60, 1e-05), kwargs = {})
2025-03-21T20:30:48.3538261Z     %quantize_per_tensor_1124 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%rms_norm_13, 0.0003203543310519308, 20731, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3539050Z     %dequantize_per_tensor_1580 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1124, 0.0003203543310519308, 20731, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3539855Z     %dequantize_per_tensor_1581 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1124, 0.0003203543310519308, 20731, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3540329Z     %unsqueeze_46 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_1581, -1), kwargs = {})
2025-03-21T20:30:48.3541042Z     %quantize_per_tensor_1125 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_46, 0.0003203543310519308, 20731, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3541833Z     %dequantize_per_tensor_1582 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1125, 0.0003203543310519308, 20731, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3542279Z     %transpose_281 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1582, 1, 2), kwargs = {})
2025-03-21T20:30:48.3543012Z     %quantize_per_tensor_1126 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_281, 0.0003203543310519308, 20731, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3543786Z     %dequantize_per_tensor_1583 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1126, 0.0003203543310519308, 20731, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3544305Z     %conv2d_46 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_1583, %dequantize_per_tensor_61), kwargs = {})
2025-03-21T20:30:48.3545008Z     %quantize_per_tensor_1127 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_46, 0.00019273435464128852, 30017, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3545802Z     %dequantize_per_tensor_1584 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1127, 0.00019273435464128852, 30017, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3546249Z     %transpose_282 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1584, 1, 2), kwargs = {})
2025-03-21T20:30:48.3546985Z     %quantize_per_tensor_1128 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_282, 0.00019273435464128852, 30017, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3547818Z     %dequantize_per_tensor_1585 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1128, 0.00019273435464128852, 30017, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3548250Z     %squeeze_46 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_1585, -1), kwargs = {})
2025-03-21T20:30:48.3549016Z     %quantize_per_tensor_1129 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_46, 0.00019273435464128852, 30017, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3549810Z     %dequantize_per_tensor_1586 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1129, 0.00019273435464128852, 30017, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3550590Z     %dequantize_per_tensor_1587 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1129, 0.00019273435464128852, 30017, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3551053Z     %sigmoid_6 : [num_users=1] = call_function[target=torch.ops.aten.sigmoid.default](args = (%dequantize_per_tensor_1587,), kwargs = {})
2025-03-21T20:30:48.3551726Z     %quantize_per_tensor_1130 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%sigmoid_6, 1.52587890625e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3552488Z     %dequantize_per_tensor_1588 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1130, 1.52587890625e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3552961Z     %mul_75 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1586, %dequantize_per_tensor_1588), kwargs = {})
2025-03-21T20:30:48.3553667Z     %quantize_per_tensor_1131 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_75, 0.00010859330359380692, 2564, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3554441Z     %dequantize_per_tensor_1589 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1131, 0.00010859330359380692, 2564, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3554911Z     %unsqueeze_47 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_1580, -1), kwargs = {})
2025-03-21T20:30:48.3555623Z     %quantize_per_tensor_1132 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_47, 0.0003203543310519308, 20731, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3556406Z     %dequantize_per_tensor_1590 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1132, 0.0003203543310519308, 20731, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3556851Z     %transpose_283 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1590, 1, 2), kwargs = {})
2025-03-21T20:30:48.3557579Z     %quantize_per_tensor_1133 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_283, 0.0003203543310519308, 20731, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3558353Z     %dequantize_per_tensor_1591 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1133, 0.0003203543310519308, 20731, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3558898Z     %conv2d_47 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_1591, %dequantize_per_tensor_62), kwargs = {})
2025-03-21T20:30:48.3559625Z     %quantize_per_tensor_1134 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_47, 0.00018771942995954305, 34569, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3560416Z     %dequantize_per_tensor_1592 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1134, 0.00018771942995954305, 34569, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3560884Z     %transpose_284 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1592, 1, 2), kwargs = {})
2025-03-21T20:30:48.3561622Z     %quantize_per_tensor_1135 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_284, 0.00018771942995954305, 34569, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3562406Z     %dequantize_per_tensor_1593 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1135, 0.00018771942995954305, 34569, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3562857Z     %squeeze_47 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_1593, -1), kwargs = {})
2025-03-21T20:30:48.3563564Z     %quantize_per_tensor_1136 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_47, 0.00018771942995954305, 34569, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3564359Z     %dequantize_per_tensor_1594 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1136, 0.00018771942995954305, 34569, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3564839Z     %mul_76 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1589, %dequantize_per_tensor_1594), kwargs = {})
2025-03-21T20:30:48.3565542Z     %quantize_per_tensor_1137 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_76, 0.00036516462569124997, 41930, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3566324Z     %dequantize_per_tensor_1595 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1137, 0.00036516462569124997, 41930, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3566795Z     %unsqueeze_48 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_1595, -1), kwargs = {})
2025-03-21T20:30:48.3567512Z     %quantize_per_tensor_1138 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_48, 0.00036516462569124997, 41930, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3568302Z     %dequantize_per_tensor_1596 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1138, 0.00036516462569124997, 41930, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3568744Z     %transpose_285 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1596, 1, 2), kwargs = {})
2025-03-21T20:30:48.3569535Z     %quantize_per_tensor_1139 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_285, 0.00036516462569124997, 41930, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3570312Z     %dequantize_per_tensor_1597 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1139, 0.00036516462569124997, 41930, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3570867Z     %conv2d_48 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_1597, %dequantize_per_tensor_63), kwargs = {})
2025-03-21T20:30:48.3571589Z     %quantize_per_tensor_1140 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_48, 0.0002038518141489476, 13251, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3572378Z     %dequantize_per_tensor_1598 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1140, 0.0002038518141489476, 13251, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3572858Z     %transpose_286 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1598, 1, 2), kwargs = {})
2025-03-21T20:30:48.3573587Z     %quantize_per_tensor_1141 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_286, 0.0002038518141489476, 13251, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3574361Z     %dequantize_per_tensor_1599 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1141, 0.0002038518141489476, 13251, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3574814Z     %squeeze_48 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_1599, -1), kwargs = {})
2025-03-21T20:30:48.3575513Z     %quantize_per_tensor_1142 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_48, 0.0002038518141489476, 13251, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3576297Z     %dequantize_per_tensor_1600 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1142, 0.0002038518141489476, 13251, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3576769Z     %add_34 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_1578, %dequantize_per_tensor_1600), kwargs = {})
2025-03-21T20:30:48.3577460Z     %quantize_per_tensor_1143 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_34, 0.002665344625711441, 5896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3578226Z     %dequantize_per_tensor_1601 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1143, 0.002665344625711441, 5896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3579006Z     %dequantize_per_tensor_1602 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1143, 0.002665344625711441, 5896, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3579553Z     %rms_norm_14 : [num_users=1] = call_function[target=torch.ops.aten.rms_norm.default](args = (%dequantize_per_tensor_1602, [768], %dequantize_per_tensor_64, 1e-05), kwargs = {})
2025-03-21T20:30:48.3580269Z     %quantize_per_tensor_1144 : [num_users=3] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%rms_norm_14, 0.0004271493526175618, 31257, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3581043Z     %dequantize_per_tensor_1603 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1144, 0.0004271493526175618, 31257, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3581827Z     %dequantize_per_tensor_1604 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1144, 0.0004271493526175618, 31257, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3582621Z     %dequantize_per_tensor_1605 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1144, 0.0004271493526175618, 31257, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3583109Z     %unsqueeze_49 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_1605, -1), kwargs = {})
2025-03-21T20:30:48.3583821Z     %quantize_per_tensor_1145 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_49, 0.0004271493526175618, 31257, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3584628Z     %dequantize_per_tensor_1606 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1145, 0.0004271493526175618, 31257, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3585073Z     %transpose_287 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1606, 1, 2), kwargs = {})
2025-03-21T20:30:48.3585799Z     %quantize_per_tensor_1146 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_287, 0.0004271493526175618, 31257, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3586571Z     %dequantize_per_tensor_1607 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1146, 0.0004271493526175618, 31257, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3587115Z     %conv2d_49 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_1607, %dequantize_per_tensor_65), kwargs = {})
2025-03-21T20:30:48.3587818Z     %quantize_per_tensor_1147 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_49, 0.00033543823519721627, 30157, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3588616Z     %dequantize_per_tensor_1608 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1147, 0.00033543823519721627, 30157, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3589060Z     %transpose_288 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1608, 1, 2), kwargs = {})
2025-03-21T20:30:48.3589793Z     %quantize_per_tensor_1148 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_288, 0.00033543823519721627, 30157, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3590568Z     %dequantize_per_tensor_1609 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1148, 0.00033543823519721627, 30157, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3590993Z     %squeeze_49 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_1609, -1), kwargs = {})
2025-03-21T20:30:48.3591700Z     %quantize_per_tensor_1149 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_49, 0.00033543823519721627, 30157, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3592488Z     %dequantize_per_tensor_1610 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1149, 0.00033543823519721627, 30157, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3592947Z     %unsqueeze_50 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_1604, -1), kwargs = {})
2025-03-21T20:30:48.3593679Z     %quantize_per_tensor_1150 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_50, 0.0004271493526175618, 31257, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3594483Z     %dequantize_per_tensor_1611 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1150, 0.0004271493526175618, 31257, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3594965Z     %transpose_289 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1611, 1, 2), kwargs = {})
2025-03-21T20:30:48.3595683Z     %quantize_per_tensor_1151 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_289, 0.0004271493526175618, 31257, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3596494Z     %dequantize_per_tensor_1612 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1151, 0.0004271493526175618, 31257, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3596998Z     %conv2d_50 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_1612, %dequantize_per_tensor_66), kwargs = {})
2025-03-21T20:30:48.3597712Z     %quantize_per_tensor_1152 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_50, 0.00040363334119319916, 34283, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3598514Z     %dequantize_per_tensor_1613 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1152, 0.00040363334119319916, 34283, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3598972Z     %transpose_290 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1613, 1, 2), kwargs = {})
2025-03-21T20:30:48.3599695Z     %quantize_per_tensor_1153 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_290, 0.00040363334119319916, 34283, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3600487Z     %dequantize_per_tensor_1614 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1153, 0.00040363334119319916, 34283, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3600903Z     %squeeze_50 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_1614, -1), kwargs = {})
2025-03-21T20:30:48.3601610Z     %quantize_per_tensor_1154 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_50, 0.00040363334119319916, 34283, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3602401Z     %dequantize_per_tensor_1615 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1154, 0.00040363334119319916, 34283, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3602857Z     %unsqueeze_51 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_1603, -1), kwargs = {})
2025-03-21T20:30:48.3603585Z     %quantize_per_tensor_1155 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_51, 0.0004271493526175618, 31257, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3604360Z     %dequantize_per_tensor_1616 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1155, 0.0004271493526175618, 31257, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3604818Z     %transpose_291 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1616, 1, 2), kwargs = {})
2025-03-21T20:30:48.3605535Z     %quantize_per_tensor_1156 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_291, 0.0004271493526175618, 31257, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3606343Z     %dequantize_per_tensor_1617 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1156, 0.0004271493526175618, 31257, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3606870Z     %conv2d_51 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_1617, %dequantize_per_tensor_67), kwargs = {})
2025-03-21T20:30:48.3607578Z     %quantize_per_tensor_1157 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_51, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3608373Z     %dequantize_per_tensor_1618 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1157, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3608827Z     %transpose_292 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1618, 1, 2), kwargs = {})
2025-03-21T20:30:48.3609596Z     %quantize_per_tensor_1158 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_292, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3610408Z     %dequantize_per_tensor_1619 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1158, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3610821Z     %squeeze_51 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_1619, -1), kwargs = {})
2025-03-21T20:30:48.3611536Z     %quantize_per_tensor_1159 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_51, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3612308Z     %dequantize_per_tensor_1620 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1159, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3612764Z     %view_84 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1610, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.3613465Z     %quantize_per_tensor_1160 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_84, 0.00033543823519721627, 30157, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3614265Z     %dequantize_per_tensor_1621 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1160, 0.00033543823519721627, 30157, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3614702Z     %view_85 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1615, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.3615405Z     %quantize_per_tensor_1161 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_85, 0.00040363334119319916, 34283, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3616182Z     %dequantize_per_tensor_1622 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1161, 0.00040363334119319916, 34283, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3616629Z     %view_86 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1620, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.3617315Z     %quantize_per_tensor_1162 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_86, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3618129Z     %dequantize_per_tensor_1623 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1162, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3618641Z     %_to_copy_14 : [num_users=1] = call_function[target=torch.ops.aten._to_copy.default](args = (%dequantize_per_tensor_1621,), kwargs = {dtype: torch.float32})
2025-03-21T20:30:48.3619362Z     %quantize_per_tensor_1163 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%_to_copy_14, 0.00033543823519721627, 30157, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3620164Z     %dequantize_per_tensor_1624 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1163, 0.00033543823519721627, 30157, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3620622Z     %view_87 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1624, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:30:48.3621315Z     %quantize_per_tensor_1164 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_87, 0.00033543823519721627, 30157, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3622126Z     %dequantize_per_tensor_1625 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1164, 0.00033543823519721627, 30157, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3622531Z     %unbind_14 : [num_users=2] = call_function[target=torch.ops.aten.unbind.int](args = (%dequantize_per_tensor_1625, -1), kwargs = {})
2025-03-21T20:30:48.3622860Z     %getitem_28 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_14, 0), kwargs = {})
2025-03-21T20:30:48.3623171Z     %getitem_29 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_14, 1), kwargs = {})
2025-03-21T20:30:48.3623890Z     %quantize_per_tensor_1165 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_28, 0.00033543823519721627, 30157, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3624674Z     %dequantize_per_tensor_1626 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1165, 0.00033543823519721627, 30157, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3625460Z     %dequantize_per_tensor_1627 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1165, 0.00033543823519721627, 30157, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3626164Z     %quantize_per_tensor_1166 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_29, 0.00027173387934453785, 36672, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3626955Z     %dequantize_per_tensor_1628 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1166, 0.00027173387934453785, 36672, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3627729Z     %dequantize_per_tensor_1629 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1166, 0.00027173387934453785, 36672, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3628218Z     %_to_copy_15 : [num_users=1] = call_function[target=torch.ops.aten._to_copy.default](args = (%dequantize_per_tensor_1622,), kwargs = {dtype: torch.float32})
2025-03-21T20:30:48.3628916Z     %quantize_per_tensor_1167 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%_to_copy_15, 0.00040363334119319916, 34283, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3629728Z     %dequantize_per_tensor_1630 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1167, 0.00040363334119319916, 34283, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3630200Z     %view_88 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1630, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:30:48.3630905Z     %quantize_per_tensor_1168 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_88, 0.00040363334119319916, 34283, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3631705Z     %dequantize_per_tensor_1631 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1168, 0.00040363334119319916, 34283, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3632131Z     %unbind_15 : [num_users=2] = call_function[target=torch.ops.aten.unbind.int](args = (%dequantize_per_tensor_1631, -1), kwargs = {})
2025-03-21T20:30:48.3632605Z     %getitem_30 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_15, 0), kwargs = {})
2025-03-21T20:30:48.3632937Z     %getitem_31 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_15, 1), kwargs = {})
2025-03-21T20:30:48.3633697Z     %quantize_per_tensor_1169 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_30, 0.00040363334119319916, 34283, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3634490Z     %dequantize_per_tensor_1632 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1169, 0.00040363334119319916, 34283, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3635262Z     %dequantize_per_tensor_1633 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1169, 0.00040363334119319916, 34283, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3635983Z     %quantize_per_tensor_1170 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_31, 0.00034802465233951807, 38786, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3636760Z     %dequantize_per_tensor_1634 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1170, 0.00034802465233951807, 38786, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3637548Z     %dequantize_per_tensor_1635 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1170, 0.00034802465233951807, 38786, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3637977Z     %view_89 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_155, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:30:48.3638681Z     %quantize_per_tensor_1171 : [num_users=4] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_89, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3639450Z     %dequantize_per_tensor_1636 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1171, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3640237Z     %dequantize_per_tensor_1637 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1171, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3641002Z     %dequantize_per_tensor_1638 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1171, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3641849Z     %dequantize_per_tensor_1639 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1171, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3642283Z     %view_90 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_167, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:30:48.3642980Z     %quantize_per_tensor_1172 : [num_users=4] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_90, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3643781Z     %dequantize_per_tensor_1640 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1172, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3644569Z     %dequantize_per_tensor_1641 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1172, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3645340Z     %dequantize_per_tensor_1642 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1172, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3646149Z     %dequantize_per_tensor_1643 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1172, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3646620Z     %mul_77 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1627, %dequantize_per_tensor_1639), kwargs = {})
2025-03-21T20:30:48.3647315Z     %quantize_per_tensor_1173 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_77, 0.0003348104073666036, 30213, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3648089Z     %dequantize_per_tensor_1644 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1173, 0.0003348104073666036, 30213, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3648574Z     %mul_78 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1628, %dequantize_per_tensor_1642), kwargs = {})
2025-03-21T20:30:48.3649260Z     %quantize_per_tensor_1174 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_78, 0.0001602927513886243, 36040, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3650099Z     %dequantize_per_tensor_1645 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1174, 0.0001602927513886243, 36040, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3650571Z     %sub_14 : [num_users=1] = call_function[target=torch.ops.aten.sub.Tensor](args = (%dequantize_per_tensor_1644, %dequantize_per_tensor_1645), kwargs = {})
2025-03-21T20:30:48.3651266Z     %quantize_per_tensor_1175 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%sub_14, 0.0003344771103002131, 30259, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3652042Z     %dequantize_per_tensor_1646 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1175, 0.0003344771103002131, 30259, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3652526Z     %mul_79 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1626, %dequantize_per_tensor_1643), kwargs = {})
2025-03-21T20:30:48.3653269Z     %quantize_per_tensor_1176 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_79, 0.00014775632007513195, 30678, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3654088Z     %dequantize_per_tensor_1647 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1176, 0.00014775632007513195, 30678, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3654559Z     %mul_80 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1629, %dequantize_per_tensor_1638), kwargs = {})
2025-03-21T20:30:48.3655276Z     %quantize_per_tensor_1177 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_80, 0.000265473616309464, 35993, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3656050Z     %dequantize_per_tensor_1648 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1177, 0.000265473616309464, 35993, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3656537Z     %add_35 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_1647, %dequantize_per_tensor_1648), kwargs = {})
2025-03-21T20:30:48.3657244Z     %quantize_per_tensor_1178 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_35, 0.0002655599091667682, 35943, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3658030Z     %dequantize_per_tensor_1649 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1178, 0.0002655599091667682, 35943, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3658504Z     %mul_81 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1633, %dequantize_per_tensor_1637), kwargs = {})
2025-03-21T20:30:48.3659201Z     %quantize_per_tensor_1179 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_81, 0.0004010801203548908, 34212, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3659977Z     %dequantize_per_tensor_1650 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1179, 0.0004010801203548908, 34212, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3660464Z     %mul_82 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1634, %dequantize_per_tensor_1640), kwargs = {})
2025-03-21T20:30:48.3661149Z     %quantize_per_tensor_1180 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_82, 0.0001895799214253202, 36365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3661941Z     %dequantize_per_tensor_1651 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1180, 0.0001895799214253202, 36365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3662418Z     %sub_15 : [num_users=1] = call_function[target=torch.ops.aten.sub.Tensor](args = (%dequantize_per_tensor_1650, %dequantize_per_tensor_1651), kwargs = {})
2025-03-21T20:30:48.3663111Z     %quantize_per_tensor_1181 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%sub_15, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3663907Z     %dequantize_per_tensor_1652 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1181, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3664381Z     %mul_83 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1632, %dequantize_per_tensor_1641), kwargs = {})
2025-03-21T20:30:48.3665122Z     %quantize_per_tensor_1182 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_83, 0.00017923355335369706, 34002, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3665926Z     %dequantize_per_tensor_1653 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1182, 0.00017923355335369706, 34002, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3666413Z     %mul_84 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1635, %dequantize_per_tensor_1636), kwargs = {})
2025-03-21T20:30:48.3667130Z     %quantize_per_tensor_1183 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_84, 0.00034465600037947297, 38891, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3667927Z     %dequantize_per_tensor_1654 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1183, 0.00034465600037947297, 38891, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3668402Z     %add_36 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_1653, %dequantize_per_tensor_1654), kwargs = {})
2025-03-21T20:30:48.3669128Z     %quantize_per_tensor_1184 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_36, 0.0003462613676674664, 38962, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3669906Z     %dequantize_per_tensor_1655 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1184, 0.0003462613676674664, 38962, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3670442Z     %stack_14 : [num_users=1] = call_function[target=torch.ops.aten.stack.default](args = ([%dequantize_per_tensor_1646, %dequantize_per_tensor_1649], -1), kwargs = {})
2025-03-21T20:30:48.3671137Z     %quantize_per_tensor_1185 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%stack_14, 0.0003344771103002131, 30259, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3671923Z     %dequantize_per_tensor_1656 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1185, 0.0003344771103002131, 30259, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3672360Z     %view_91 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1656, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.3673058Z     %quantize_per_tensor_1186 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_91, 0.0003344771103002131, 30259, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3673829Z     %dequantize_per_tensor_1657 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1186, 0.0003344771103002131, 30259, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3674362Z     %stack_15 : [num_users=1] = call_function[target=torch.ops.aten.stack.default](args = ([%dequantize_per_tensor_1652, %dequantize_per_tensor_1655], -1), kwargs = {})
2025-03-21T20:30:48.3675064Z     %quantize_per_tensor_1187 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%stack_15, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3675851Z     %dequantize_per_tensor_1658 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1187, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3676291Z     %view_92 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1658, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.3677042Z     %quantize_per_tensor_1188 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_92, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3677821Z     %dequantize_per_tensor_1659 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1188, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3678356Z     %type_as_14 : [num_users=1] = call_function[target=torch.ops.aten.type_as.default](args = (%dequantize_per_tensor_1657, %dequantize_per_tensor_1621), kwargs = {})
2025-03-21T20:30:48.3679050Z     %quantize_per_tensor_1189 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%type_as_14, 0.0003344771103002131, 30259, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3679837Z     %dequantize_per_tensor_1660 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1189, 0.0003344771103002131, 30259, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3680362Z     %type_as_15 : [num_users=1] = call_function[target=torch.ops.aten.type_as.default](args = (%dequantize_per_tensor_1659, %dequantize_per_tensor_1622), kwargs = {})
2025-03-21T20:30:48.3681073Z     %quantize_per_tensor_1190 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%type_as_15, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3681849Z     %dequantize_per_tensor_1661 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1190, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3682306Z     %transpose_293 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1660, 1, 2), kwargs = {})
2025-03-21T20:30:48.3683026Z     %quantize_per_tensor_1191 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_293, 0.0003344771103002131, 30259, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3683812Z     %dequantize_per_tensor_1662 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1191, 0.0003344771103002131, 30259, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3684443Z     %index_put_14 : [num_users=1] = call_function[target=torch.ops.aten.index_put.default](args = (%dequantize_per_tensor_134, [None, %attn_options_input_pos], %dequantize_per_tensor_1661), kwargs = {})
2025-03-21T20:30:48.3685168Z     %quantize_per_tensor_1192 : [num_users=13] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_put_14, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3685945Z     %dequantize_per_tensor_1663 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1192, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3686730Z     %dequantize_per_tensor_1664 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1192, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3687503Z     %dequantize_per_tensor_1665 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1192, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3688321Z     %dequantize_per_tensor_1666 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1192, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3689117Z     %dequantize_per_tensor_1667 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1192, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3689995Z     %dequantize_per_tensor_1668 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1192, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3690798Z     %dequantize_per_tensor_1669 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1192, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3691593Z     %dequantize_per_tensor_1670 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1192, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3692371Z     %dequantize_per_tensor_1671 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1192, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3693185Z     %dequantize_per_tensor_1672 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1192, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3693961Z     %dequantize_per_tensor_1673 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1192, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3694748Z     %dequantize_per_tensor_1674 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1192, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3695539Z     %dequantize_per_tensor_1675 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1192, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3696171Z     %index_put_15 : [num_users=1] = call_function[target=torch.ops.aten.index_put.default](args = (%dequantize_per_tensor_135, [None, %attn_options_input_pos], %dequantize_per_tensor_1623), kwargs = {})
2025-03-21T20:30:48.3696894Z     %quantize_per_tensor_1193 : [num_users=13] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_put_15, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3697670Z     %dequantize_per_tensor_1676 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1193, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3698453Z     %dequantize_per_tensor_1677 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1193, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3699224Z     %dequantize_per_tensor_1678 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1193, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3700007Z     %dequantize_per_tensor_1679 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1193, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3700801Z     %dequantize_per_tensor_1680 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1193, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3701609Z     %dequantize_per_tensor_1681 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1193, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3702403Z     %dequantize_per_tensor_1682 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1193, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3703191Z     %dequantize_per_tensor_1683 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1193, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3703966Z     %dequantize_per_tensor_1684 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1193, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3704752Z     %dequantize_per_tensor_1685 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1193, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3705559Z     %dequantize_per_tensor_1686 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1193, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3706341Z     %dequantize_per_tensor_1687 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1193, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3707114Z     %dequantize_per_tensor_1688 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1193, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3707572Z     %transpose_294 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1675, 1, 2), kwargs = {})
2025-03-21T20:30:48.3708290Z     %quantize_per_tensor_1194 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_294, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3709079Z     %dequantize_per_tensor_1689 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1194, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3709495Z     %select_336 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1689, 0, 0), kwargs = {})
2025-03-21T20:30:48.3710213Z     %quantize_per_tensor_1195 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_336, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3710994Z     %dequantize_per_tensor_1690 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1195, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3711418Z     %select_337 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1690, 0, 0), kwargs = {})
2025-03-21T20:30:48.3712126Z     %quantize_per_tensor_1196 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_337, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3712965Z     %dequantize_per_tensor_1691 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1196, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3713411Z     %transpose_295 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1674, 1, 2), kwargs = {})
2025-03-21T20:30:48.3714143Z     %quantize_per_tensor_1197 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_295, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3714952Z     %dequantize_per_tensor_1692 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1197, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3715379Z     %select_338 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1692, 0, 0), kwargs = {})
2025-03-21T20:30:48.3716088Z     %quantize_per_tensor_1198 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_338, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3716903Z     %dequantize_per_tensor_1693 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1198, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3717314Z     %select_339 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1693, 0, 1), kwargs = {})
2025-03-21T20:30:48.3718033Z     %quantize_per_tensor_1199 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_339, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3718813Z     %dequantize_per_tensor_1694 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1199, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3719270Z     %transpose_296 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1673, 1, 2), kwargs = {})
2025-03-21T20:30:48.3719986Z     %quantize_per_tensor_1200 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_296, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3720774Z     %dequantize_per_tensor_1695 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1200, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3721186Z     %select_340 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1695, 0, 0), kwargs = {})
2025-03-21T20:30:48.3721895Z     %quantize_per_tensor_1201 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_340, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3722682Z     %dequantize_per_tensor_1696 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1201, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3723094Z     %select_341 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1696, 0, 2), kwargs = {})
2025-03-21T20:30:48.3723809Z     %quantize_per_tensor_1202 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_341, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3724637Z     %dequantize_per_tensor_1697 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1202, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3725096Z     %transpose_297 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1672, 1, 2), kwargs = {})
2025-03-21T20:30:48.3725815Z     %quantize_per_tensor_1203 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_297, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3726626Z     %dequantize_per_tensor_1698 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1203, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3727039Z     %select_342 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1698, 0, 0), kwargs = {})
2025-03-21T20:30:48.3727758Z     %quantize_per_tensor_1204 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_342, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3728560Z     %dequantize_per_tensor_1699 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1204, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3728983Z     %select_343 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1699, 0, 3), kwargs = {})
2025-03-21T20:30:48.3729747Z     %quantize_per_tensor_1205 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_343, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3730536Z     %dequantize_per_tensor_1700 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1205, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3731026Z     %transpose_298 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1671, 1, 2), kwargs = {})
2025-03-21T20:30:48.3731760Z     %quantize_per_tensor_1206 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_298, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3732661Z     %dequantize_per_tensor_1701 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1206, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3733089Z     %select_344 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1701, 0, 0), kwargs = {})
2025-03-21T20:30:48.3733796Z     %quantize_per_tensor_1207 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_344, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3734587Z     %dequantize_per_tensor_1702 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1207, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3734998Z     %select_345 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1702, 0, 4), kwargs = {})
2025-03-21T20:30:48.3735719Z     %quantize_per_tensor_1208 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_345, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3736586Z     %dequantize_per_tensor_1703 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1208, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3737045Z     %transpose_299 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1670, 1, 2), kwargs = {})
2025-03-21T20:30:48.3737801Z     %quantize_per_tensor_1209 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_299, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3738587Z     %dequantize_per_tensor_1704 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1209, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3739001Z     %select_346 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1704, 0, 0), kwargs = {})
2025-03-21T20:30:48.3739714Z     %quantize_per_tensor_1210 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_346, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3740526Z     %dequantize_per_tensor_1705 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1210, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3740947Z     %select_347 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1705, 0, 5), kwargs = {})
2025-03-21T20:30:48.3741654Z     %quantize_per_tensor_1211 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_347, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3742441Z     %dequantize_per_tensor_1706 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1211, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3742883Z     %transpose_300 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1669, 1, 2), kwargs = {})
2025-03-21T20:30:48.3743615Z     %quantize_per_tensor_1212 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_300, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3744389Z     %dequantize_per_tensor_1707 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1212, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3744810Z     %select_348 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1707, 0, 0), kwargs = {})
2025-03-21T20:30:48.3745516Z     %quantize_per_tensor_1213 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_348, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3746308Z     %dequantize_per_tensor_1708 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1213, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3746719Z     %select_349 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1708, 0, 6), kwargs = {})
2025-03-21T20:30:48.3747436Z     %quantize_per_tensor_1214 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_349, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3748264Z     %dequantize_per_tensor_1709 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1214, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3748718Z     %transpose_301 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1668, 1, 2), kwargs = {})
2025-03-21T20:30:48.3749470Z     %quantize_per_tensor_1215 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_301, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3750260Z     %dequantize_per_tensor_1710 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1215, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3750674Z     %select_350 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1710, 0, 0), kwargs = {})
2025-03-21T20:30:48.3751397Z     %quantize_per_tensor_1216 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_350, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3752198Z     %dequantize_per_tensor_1711 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1216, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3752626Z     %select_351 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1711, 0, 7), kwargs = {})
2025-03-21T20:30:48.3753333Z     %quantize_per_tensor_1217 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_351, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3754128Z     %dequantize_per_tensor_1712 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1217, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3754571Z     %transpose_302 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1667, 1, 2), kwargs = {})
2025-03-21T20:30:48.3755304Z     %quantize_per_tensor_1218 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_302, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3756081Z     %dequantize_per_tensor_1713 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1218, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3756509Z     %select_352 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1713, 0, 0), kwargs = {})
2025-03-21T20:30:48.3757215Z     %quantize_per_tensor_1219 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_352, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3758006Z     %dequantize_per_tensor_1714 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1219, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3758417Z     %select_353 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1714, 0, 8), kwargs = {})
2025-03-21T20:30:48.3759132Z     %quantize_per_tensor_1220 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_353, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3759957Z     %dequantize_per_tensor_1715 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1220, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3760411Z     %transpose_303 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1666, 1, 2), kwargs = {})
2025-03-21T20:30:48.3761154Z     %quantize_per_tensor_1221 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_303, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3761946Z     %dequantize_per_tensor_1716 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1221, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3762359Z     %select_354 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1716, 0, 0), kwargs = {})
2025-03-21T20:30:48.3763077Z     %quantize_per_tensor_1222 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_354, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3763885Z     %dequantize_per_tensor_1717 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1222, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3764312Z     %select_355 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1717, 0, 9), kwargs = {})
2025-03-21T20:30:48.3765026Z     %quantize_per_tensor_1223 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_355, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3765822Z     %dequantize_per_tensor_1718 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1223, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3766270Z     %transpose_304 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1665, 1, 2), kwargs = {})
2025-03-21T20:30:48.3767012Z     %quantize_per_tensor_1224 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_304, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3767794Z     %dequantize_per_tensor_1719 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1224, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3768225Z     %select_356 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1719, 0, 0), kwargs = {})
2025-03-21T20:30:48.3768938Z     %quantize_per_tensor_1225 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_356, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3769802Z     %dequantize_per_tensor_1720 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1225, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3770225Z     %select_357 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1720, 0, 10), kwargs = {})
2025-03-21T20:30:48.3770936Z     %quantize_per_tensor_1226 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_357, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3771783Z     %dequantize_per_tensor_1721 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1226, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3772230Z     %transpose_305 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1664, 1, 2), kwargs = {})
2025-03-21T20:30:48.3772984Z     %quantize_per_tensor_1227 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_305, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3773767Z     %dequantize_per_tensor_1722 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1227, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3774195Z     %select_358 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1722, 0, 0), kwargs = {})
2025-03-21T20:30:48.3774904Z     %quantize_per_tensor_1228 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_358, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3775727Z     %dequantize_per_tensor_1723 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1228, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3776140Z     %select_359 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1723, 0, 11), kwargs = {})
2025-03-21T20:30:48.3776862Z     %quantize_per_tensor_1229 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_359, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3777646Z     %dequantize_per_tensor_1724 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1229, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3779155Z     %cat_14 : [num_users=1] = call_function[target=torch.ops.aten.cat.default](args = ([%dequantize_per_tensor_1691, %dequantize_per_tensor_1694, %dequantize_per_tensor_1697, %dequantize_per_tensor_1700, %dequantize_per_tensor_1703, %dequantize_per_tensor_1706, %dequantize_per_tensor_1709, %dequantize_per_tensor_1712, %dequantize_per_tensor_1715, %dequantize_per_tensor_1718, %dequantize_per_tensor_1721, %dequantize_per_tensor_1724],), kwargs = {})
2025-03-21T20:30:48.3779859Z     %quantize_per_tensor_1230 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%cat_14, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3780640Z     %dequantize_per_tensor_1725 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1230, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3781102Z     %view_93 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1725, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:30:48.3781795Z     %quantize_per_tensor_1231 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_93, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3782587Z     %dequantize_per_tensor_1726 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1231, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3783061Z     %transpose_306 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1688, 1, 2), kwargs = {})
2025-03-21T20:30:48.3783812Z     %quantize_per_tensor_1232 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_306, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3784588Z     %dequantize_per_tensor_1727 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1232, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3785038Z     %select_360 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1727, 0, 0), kwargs = {})
2025-03-21T20:30:48.3785740Z     %quantize_per_tensor_1233 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_360, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3786526Z     %dequantize_per_tensor_1728 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1233, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3786961Z     %select_361 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1728, 0, 0), kwargs = {})
2025-03-21T20:30:48.3787660Z     %quantize_per_tensor_1234 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_361, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3788449Z     %dequantize_per_tensor_1729 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1234, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3788896Z     %transpose_307 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1687, 1, 2), kwargs = {})
2025-03-21T20:30:48.3789621Z     %quantize_per_tensor_1235 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_307, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3790392Z     %dequantize_per_tensor_1730 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1235, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3790817Z     %select_362 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1730, 0, 0), kwargs = {})
2025-03-21T20:30:48.3791513Z     %quantize_per_tensor_1236 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_362, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3792297Z     %dequantize_per_tensor_1731 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1236, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3792710Z     %select_363 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1731, 0, 1), kwargs = {})
2025-03-21T20:30:48.3793426Z     %quantize_per_tensor_1237 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_363, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3794195Z     %dequantize_per_tensor_1732 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1237, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3794648Z     %transpose_308 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1686, 1, 2), kwargs = {})
2025-03-21T20:30:48.3795424Z     %quantize_per_tensor_1238 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_308, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3796208Z     %dequantize_per_tensor_1733 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1238, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3796640Z     %select_364 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1733, 0, 0), kwargs = {})
2025-03-21T20:30:48.3797352Z     %quantize_per_tensor_1239 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_364, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3798126Z     %dequantize_per_tensor_1734 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1239, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3798548Z     %select_365 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1734, 0, 2), kwargs = {})
2025-03-21T20:30:48.3799274Z     %quantize_per_tensor_1240 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_365, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3800060Z     %dequantize_per_tensor_1735 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1240, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3800503Z     %transpose_309 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1685, 1, 2), kwargs = {})
2025-03-21T20:30:48.3801230Z     %quantize_per_tensor_1241 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_309, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3802007Z     %dequantize_per_tensor_1736 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1241, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3802434Z     %select_366 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1736, 0, 0), kwargs = {})
2025-03-21T20:30:48.3803137Z     %quantize_per_tensor_1242 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_366, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3803929Z     %dequantize_per_tensor_1737 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1242, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3804343Z     %select_367 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1737, 0, 3), kwargs = {})
2025-03-21T20:30:48.3805056Z     %quantize_per_tensor_1243 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_367, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3805834Z     %dequantize_per_tensor_1738 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1243, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3806290Z     %transpose_310 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1684, 1, 2), kwargs = {})
2025-03-21T20:30:48.3807055Z     %quantize_per_tensor_1244 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_310, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3807846Z     %dequantize_per_tensor_1739 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1244, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3808281Z     %select_368 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1739, 0, 0), kwargs = {})
2025-03-21T20:30:48.3808997Z     %quantize_per_tensor_1245 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_368, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3809831Z     %dequantize_per_tensor_1740 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1245, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3810255Z     %select_369 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1740, 0, 4), kwargs = {})
2025-03-21T20:30:48.3810984Z     %quantize_per_tensor_1246 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_369, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3811773Z     %dequantize_per_tensor_1741 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1246, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3812214Z     %transpose_311 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1683, 1, 2), kwargs = {})
2025-03-21T20:30:48.3812945Z     %quantize_per_tensor_1247 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_311, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3813717Z     %dequantize_per_tensor_1742 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1247, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3814144Z     %select_370 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1742, 0, 0), kwargs = {})
2025-03-21T20:30:48.3814845Z     %quantize_per_tensor_1248 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_370, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3815628Z     %dequantize_per_tensor_1743 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1248, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3816039Z     %select_371 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1743, 0, 5), kwargs = {})
2025-03-21T20:30:48.3816747Z     %quantize_per_tensor_1249 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_371, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3817520Z     %dequantize_per_tensor_1744 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1249, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3817976Z     %transpose_312 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1682, 1, 2), kwargs = {})
2025-03-21T20:30:48.3818739Z     %quantize_per_tensor_1250 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_312, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3819525Z     %dequantize_per_tensor_1745 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1250, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3819959Z     %select_372 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1745, 0, 0), kwargs = {})
2025-03-21T20:30:48.3820672Z     %quantize_per_tensor_1251 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_372, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3821447Z     %dequantize_per_tensor_1746 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1251, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3821871Z     %select_373 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1746, 0, 6), kwargs = {})
2025-03-21T20:30:48.3822592Z     %quantize_per_tensor_1252 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_373, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3823381Z     %dequantize_per_tensor_1747 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1252, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3823822Z     %transpose_313 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1681, 1, 2), kwargs = {})
2025-03-21T20:30:48.3824555Z     %quantize_per_tensor_1253 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_313, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3825329Z     %dequantize_per_tensor_1748 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1253, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3825753Z     %select_374 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1748, 0, 0), kwargs = {})
2025-03-21T20:30:48.3826456Z     %quantize_per_tensor_1254 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_374, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3827240Z     %dequantize_per_tensor_1749 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1254, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3827653Z     %select_375 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1749, 0, 7), kwargs = {})
2025-03-21T20:30:48.3828367Z     %quantize_per_tensor_1255 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_375, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3829135Z     %dequantize_per_tensor_1750 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1255, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3829595Z     %transpose_314 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1680, 1, 2), kwargs = {})
2025-03-21T20:30:48.3830362Z     %quantize_per_tensor_1256 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_314, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3831148Z     %dequantize_per_tensor_1751 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1256, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3831581Z     %select_376 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1751, 0, 0), kwargs = {})
2025-03-21T20:30:48.3832406Z     %quantize_per_tensor_1257 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_376, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3833194Z     %dequantize_per_tensor_1752 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1257, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3833605Z     %select_377 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1752, 0, 8), kwargs = {})
2025-03-21T20:30:48.3834394Z     %quantize_per_tensor_1258 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_377, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3835168Z     %dequantize_per_tensor_1753 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1258, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3835626Z     %transpose_315 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1679, 1, 2), kwargs = {})
2025-03-21T20:30:48.3836345Z     %quantize_per_tensor_1259 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_315, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3837134Z     %dequantize_per_tensor_1754 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1259, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3837547Z     %select_378 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1754, 0, 0), kwargs = {})
2025-03-21T20:30:48.3838262Z     %quantize_per_tensor_1260 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_378, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3839034Z     %dequantize_per_tensor_1755 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1260, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3839457Z     %select_379 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1755, 0, 9), kwargs = {})
2025-03-21T20:30:48.3840157Z     %quantize_per_tensor_1261 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_379, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3840944Z     %dequantize_per_tensor_1756 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1261, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3841385Z     %transpose_316 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1678, 1, 2), kwargs = {})
2025-03-21T20:30:48.3842186Z     %quantize_per_tensor_1262 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_316, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3842959Z     %dequantize_per_tensor_1757 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1262, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3843411Z     %select_380 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1757, 0, 0), kwargs = {})
2025-03-21T20:30:48.3844111Z     %quantize_per_tensor_1263 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_380, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3844898Z     %dequantize_per_tensor_1758 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1263, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3845315Z     %select_381 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1758, 0, 10), kwargs = {})
2025-03-21T20:30:48.3846048Z     %quantize_per_tensor_1264 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_381, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3846819Z     %dequantize_per_tensor_1759 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1264, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3847273Z     %transpose_317 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1677, 1, 2), kwargs = {})
2025-03-21T20:30:48.3847991Z     %quantize_per_tensor_1265 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_317, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3848781Z     %dequantize_per_tensor_1760 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1265, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3849192Z     %select_382 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1760, 0, 0), kwargs = {})
2025-03-21T20:30:48.3849962Z     %quantize_per_tensor_1266 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_382, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3850736Z     %dequantize_per_tensor_1761 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1266, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3851166Z     %select_383 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1761, 0, 11), kwargs = {})
2025-03-21T20:30:48.3851866Z     %quantize_per_tensor_1267 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_383, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3852651Z     %dequantize_per_tensor_1762 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1267, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3854169Z     %cat_15 : [num_users=1] = call_function[target=torch.ops.aten.cat.default](args = ([%dequantize_per_tensor_1729, %dequantize_per_tensor_1732, %dequantize_per_tensor_1735, %dequantize_per_tensor_1738, %dequantize_per_tensor_1741, %dequantize_per_tensor_1744, %dequantize_per_tensor_1747, %dequantize_per_tensor_1750, %dequantize_per_tensor_1753, %dequantize_per_tensor_1756, %dequantize_per_tensor_1759, %dequantize_per_tensor_1762],), kwargs = {})
2025-03-21T20:30:48.3854891Z     %quantize_per_tensor_1268 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%cat_15, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3855689Z     %dequantize_per_tensor_1763 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1268, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3856144Z     %view_94 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1763, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:30:48.3856835Z     %quantize_per_tensor_1269 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_94, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3857623Z     %dequantize_per_tensor_1764 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1269, 0.0001613850035937503, 35011, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3858419Z     %quantize_per_tensor_1270 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%dequantize_per_tensor_1764, 0.0001724382018437609, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.3859206Z     %dequantize_per_tensor_1765 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1270, 0.0001724382018437609, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.3859692Z     %index_9 : [num_users=1] = call_function[target=torch.ops.aten.index.Tensor](args = (%dequantize_per_tensor_136, [%attn_options_input_pos]), kwargs = {})
2025-03-21T20:30:48.3860394Z     %quantize_per_tensor_1271 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_9, 0.0038910505827516317, 65535, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3861170Z     %dequantize_per_tensor_1766 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1271, 0.0038910505827516317, 65535, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3861634Z     %transpose_318 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1726, -2, -1), kwargs = {})
2025-03-21T20:30:48.3862355Z     %quantize_per_tensor_1272 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_318, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3863146Z     %dequantize_per_tensor_1767 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1272, 0.00039715005550533533, 34049, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3863916Z     %quantize_per_tensor_1273 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%dequantize_per_tensor_1767, 0.0004126892308704555, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.3864710Z     %dequantize_per_tensor_1768 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1273, 0.0004126892308704555, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.3865224Z     %matmul_14 : [num_users=1] = call_function[target=torch.ops.aten.matmul.default](args = (%dequantize_per_tensor_1662, %dequantize_per_tensor_1768), kwargs = {})
2025-03-21T20:30:48.3865983Z     %quantize_per_tensor_1274 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%matmul_14, 0.0034391621593385935, 32661, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3866764Z     %dequantize_per_tensor_1769 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1274, 0.0034391621593385935, 32661, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3867545Z     %dequantize_per_tensor_1770 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param156, 1.9073777366429567e-06, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3868022Z     %mul_85 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1769, %dequantize_per_tensor_1770), kwargs = {})
2025-03-21T20:30:48.3868724Z     %quantize_per_tensor_1275 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_85, 0.0004298952699173242, 32661, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3869501Z     %dequantize_per_tensor_1771 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1275, 0.0004298952699173242, 32661, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3870012Z     %add_37 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_1771, %dequantize_per_tensor_1766), kwargs = {})
2025-03-21T20:30:48.3870698Z     %quantize_per_tensor_1276 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_37, 0.004289415664970875, 62271, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3871480Z     %dequantize_per_tensor_1772 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1276, 0.004289415664970875, 62271, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3871896Z     %softmax_7 : [num_users=1] = call_function[target=torch.ops.aten.softmax.int](args = (%dequantize_per_tensor_1772, -1), kwargs = {})
2025-03-21T20:30:48.3878233Z     %quantize_per_tensor_1277 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%softmax_7, 1.5259021893143654e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3879091Z     %dequantize_per_tensor_1773 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1277, 1.5259021893143654e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3879623Z     %matmul_15 : [num_users=1] = call_function[target=torch.ops.aten.matmul.default](args = (%dequantize_per_tensor_1773, %dequantize_per_tensor_1765), kwargs = {})
2025-03-21T20:30:48.3880332Z     %quantize_per_tensor_1278 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%matmul_15, 0.00010833422857103869, 34577, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3881129Z     %dequantize_per_tensor_1774 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1278, 0.00010833422857103869, 34577, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3881571Z     %transpose_319 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1774, 1, 2), kwargs = {})
2025-03-21T20:30:48.3882306Z     %quantize_per_tensor_1279 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_319, 0.00010833422857103869, 34577, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3883160Z     %dequantize_per_tensor_1775 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1279, 0.00010833422857103869, 34577, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3883636Z     %view_95 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1775, [1, 1, 768]), kwargs = {})
2025-03-21T20:30:48.3884326Z     %quantize_per_tensor_1280 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_95, 0.00010833422857103869, 34577, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3885151Z     %dequantize_per_tensor_1776 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1280, 0.00010833422857103869, 34577, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3885612Z     %unsqueeze_52 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_1776, -1), kwargs = {})
2025-03-21T20:30:48.3886344Z     %quantize_per_tensor_1281 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_52, 0.00010833422857103869, 34577, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3887160Z     %dequantize_per_tensor_1777 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1281, 0.00010833422857103869, 34577, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3887610Z     %transpose_320 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1777, 1, 2), kwargs = {})
2025-03-21T20:30:48.3888331Z     %quantize_per_tensor_1282 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_320, 0.00010833422857103869, 34577, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3889128Z     %dequantize_per_tensor_1778 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1282, 0.00010833422857103869, 34577, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3889744Z     %conv2d_52 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_1778, %dequantize_per_tensor_68), kwargs = {})
2025-03-21T20:30:48.3890465Z     %quantize_per_tensor_1283 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_52, 6.415071402443573e-05, 32880, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3891284Z     %dequantize_per_tensor_1779 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1283, 6.415071402443573e-05, 32880, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3891744Z     %transpose_321 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1779, 1, 2), kwargs = {})
2025-03-21T20:30:48.3892464Z     %quantize_per_tensor_1284 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_321, 6.415071402443573e-05, 32880, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3893251Z     %dequantize_per_tensor_1780 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1284, 6.415071402443573e-05, 32880, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3893668Z     %squeeze_52 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_1780, -1), kwargs = {})
2025-03-21T20:30:48.3894382Z     %quantize_per_tensor_1285 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_52, 6.415071402443573e-05, 32880, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3895186Z     %dequantize_per_tensor_1781 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1285, 6.415071402443573e-05, 32880, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3895700Z     %add_38 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_1601, %dequantize_per_tensor_1781), kwargs = {})
2025-03-21T20:30:48.3896381Z     %quantize_per_tensor_1286 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_38, 0.0026616528630256653, 5869, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3897195Z     %dequantize_per_tensor_1782 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1286, 0.0026616528630256653, 5869, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3897967Z     %dequantize_per_tensor_1783 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1286, 0.0026616528630256653, 5869, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3898526Z     %rms_norm_15 : [num_users=1] = call_function[target=torch.ops.aten.rms_norm.default](args = (%dequantize_per_tensor_1783, [768], %dequantize_per_tensor_69, 1e-05), kwargs = {})
2025-03-21T20:30:48.3899253Z     %quantize_per_tensor_1287 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%rms_norm_15, 0.0003230620641261339, 20283, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3900042Z     %dequantize_per_tensor_1784 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1287, 0.0003230620641261339, 20283, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3900813Z     %dequantize_per_tensor_1785 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1287, 0.0003230620641261339, 20283, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3901286Z     %unsqueeze_53 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_1785, -1), kwargs = {})
2025-03-21T20:30:48.3902001Z     %quantize_per_tensor_1288 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_53, 0.0003230620641261339, 20283, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3902787Z     %dequantize_per_tensor_1786 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1288, 0.0003230620641261339, 20283, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3903233Z     %transpose_322 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1786, 1, 2), kwargs = {})
2025-03-21T20:30:48.3903964Z     %quantize_per_tensor_1289 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_322, 0.0003230620641261339, 20283, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3904738Z     %dequantize_per_tensor_1787 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1289, 0.0003230620641261339, 20283, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3905253Z     %conv2d_53 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_1787, %dequantize_per_tensor_70), kwargs = {})
2025-03-21T20:30:48.3905950Z     %quantize_per_tensor_1290 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_53, 0.0002114040544256568, 29834, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3906757Z     %dequantize_per_tensor_1788 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1290, 0.0002114040544256568, 29834, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3907225Z     %transpose_323 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1788, 1, 2), kwargs = {})
2025-03-21T20:30:48.3907958Z     %quantize_per_tensor_1291 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_323, 0.0002114040544256568, 29834, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3908758Z     %dequantize_per_tensor_1789 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1291, 0.0002114040544256568, 29834, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3909189Z     %squeeze_53 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_1789, -1), kwargs = {})
2025-03-21T20:30:48.3909899Z     %quantize_per_tensor_1292 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_53, 0.0002114040544256568, 29834, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3910684Z     %dequantize_per_tensor_1790 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1292, 0.0002114040544256568, 29834, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3911478Z     %dequantize_per_tensor_1791 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1292, 0.0002114040544256568, 29834, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3911916Z     %sigmoid_7 : [num_users=1] = call_function[target=torch.ops.aten.sigmoid.default](args = (%dequantize_per_tensor_1791,), kwargs = {})
2025-03-21T20:30:48.3912591Z     %quantize_per_tensor_1293 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%sigmoid_7, 1.52587890625e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3913355Z     %dequantize_per_tensor_1792 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1293, 1.52587890625e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3913830Z     %mul_86 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1790, %dequantize_per_tensor_1792), kwargs = {})
2025-03-21T20:30:48.3914527Z     %quantize_per_tensor_1294 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_86, 0.00011935368820559233, 2333, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3915301Z     %dequantize_per_tensor_1793 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1294, 0.00011935368820559233, 2333, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3915758Z     %unsqueeze_54 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_1784, -1), kwargs = {})
2025-03-21T20:30:48.3916484Z     %quantize_per_tensor_1295 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_54, 0.0003230620641261339, 20283, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3917256Z     %dequantize_per_tensor_1794 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1295, 0.0003230620641261339, 20283, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3917708Z     %transpose_324 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1794, 1, 2), kwargs = {})
2025-03-21T20:30:48.3918449Z     %quantize_per_tensor_1296 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_324, 0.0003230620641261339, 20283, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3919260Z     %dequantize_per_tensor_1795 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1296, 0.0003230620641261339, 20283, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3919765Z     %conv2d_54 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_1795, %dequantize_per_tensor_71), kwargs = {})
2025-03-21T20:30:48.3920501Z     %quantize_per_tensor_1297 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_54, 0.00024151173420250416, 31646, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3921279Z     %dequantize_per_tensor_1796 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1297, 0.00024151173420250416, 31646, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3921739Z     %transpose_325 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1796, 1, 2), kwargs = {})
2025-03-21T20:30:48.3922455Z     %quantize_per_tensor_1298 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_325, 0.00024151173420250416, 31646, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3923269Z     %dequantize_per_tensor_1797 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1298, 0.00024151173420250416, 31646, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3923685Z     %squeeze_54 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_1797, -1), kwargs = {})
2025-03-21T20:30:48.3924404Z     %quantize_per_tensor_1299 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_54, 0.00024151173420250416, 31646, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3925185Z     %dequantize_per_tensor_1798 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1299, 0.00024151173420250416, 31646, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3925673Z     %mul_87 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1793, %dequantize_per_tensor_1798), kwargs = {})
2025-03-21T20:30:48.3926362Z     %quantize_per_tensor_1300 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_87, 0.00026427191914990544, 35887, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3927152Z     %dequantize_per_tensor_1799 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1300, 0.00026427191914990544, 35887, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3927608Z     %unsqueeze_55 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_1799, -1), kwargs = {})
2025-03-21T20:30:48.3928338Z     %quantize_per_tensor_1301 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_55, 0.00026427191914990544, 35887, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3929117Z     %dequantize_per_tensor_1800 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1301, 0.00026427191914990544, 35887, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3929650Z     %transpose_326 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1800, 1, 2), kwargs = {})
2025-03-21T20:30:48.3930406Z     %quantize_per_tensor_1302 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_326, 0.00026427191914990544, 35887, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3931239Z     %dequantize_per_tensor_1801 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1302, 0.00026427191914990544, 35887, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3931744Z     %conv2d_55 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_1801, %dequantize_per_tensor_72), kwargs = {})
2025-03-21T20:30:48.3932722Z     %quantize_per_tensor_1303 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_55, 0.00013502163346856833, 26548, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3933505Z     %dequantize_per_tensor_1802 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1303, 0.00013502163346856833, 26548, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3933966Z     %transpose_327 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1802, 1, 2), kwargs = {})
2025-03-21T20:30:48.3934722Z     %quantize_per_tensor_1304 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_327, 0.00013502163346856833, 26548, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3935515Z     %dequantize_per_tensor_1803 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1304, 0.00013502163346856833, 26548, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3935932Z     %squeeze_55 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_1803, -1), kwargs = {})
2025-03-21T20:30:48.3936656Z     %quantize_per_tensor_1305 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_55, 0.00013502163346856833, 26548, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3937430Z     %dequantize_per_tensor_1804 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1305, 0.00013502163346856833, 26548, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3937916Z     %add_39 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_1782, %dequantize_per_tensor_1804), kwargs = {})
2025-03-21T20:30:48.3938595Z     %quantize_per_tensor_1306 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_39, 0.0026549873873591423, 5846, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3939378Z     %dequantize_per_tensor_1805 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1306, 0.0026549873873591423, 5846, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3940144Z     %dequantize_per_tensor_1806 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1306, 0.0026549873873591423, 5846, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3940705Z     %rms_norm_16 : [num_users=1] = call_function[target=torch.ops.aten.rms_norm.default](args = (%dequantize_per_tensor_1806, [768], %dequantize_per_tensor_73, 1e-05), kwargs = {})
2025-03-21T20:30:48.3941407Z     %quantize_per_tensor_1307 : [num_users=3] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%rms_norm_16, 0.0004401287587825209, 30665, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3942223Z     %dequantize_per_tensor_1807 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1307, 0.0004401287587825209, 30665, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3943032Z     %dequantize_per_tensor_1808 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1307, 0.0004401287587825209, 30665, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3943815Z     %dequantize_per_tensor_1809 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1307, 0.0004401287587825209, 30665, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3944296Z     %unsqueeze_56 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_1809, -1), kwargs = {})
2025-03-21T20:30:48.3945021Z     %quantize_per_tensor_1308 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_56, 0.0004401287587825209, 30665, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3945800Z     %dequantize_per_tensor_1810 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1308, 0.0004401287587825209, 30665, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3946281Z     %transpose_328 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1810, 1, 2), kwargs = {})
2025-03-21T20:30:48.3946999Z     %quantize_per_tensor_1309 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_328, 0.0004401287587825209, 30665, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3947785Z     %dequantize_per_tensor_1811 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1309, 0.0004401287587825209, 30665, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3948290Z     %conv2d_56 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_1811, %dequantize_per_tensor_74), kwargs = {})
2025-03-21T20:30:48.3949003Z     %quantize_per_tensor_1310 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_56, 0.00033537388662807643, 31155, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3949784Z     %dequantize_per_tensor_1812 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1310, 0.00033537388662807643, 31155, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3950243Z     %transpose_329 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1812, 1, 2), kwargs = {})
2025-03-21T20:30:48.3950960Z     %quantize_per_tensor_1311 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_329, 0.00033537388662807643, 31155, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3951754Z     %dequantize_per_tensor_1813 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1311, 0.00033537388662807643, 31155, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3952172Z     %squeeze_56 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_1813, -1), kwargs = {})
2025-03-21T20:30:48.3952891Z     %quantize_per_tensor_1312 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_56, 0.00033537388662807643, 31155, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3953668Z     %dequantize_per_tensor_1814 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1312, 0.00033537388662807643, 31155, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3954159Z     %unsqueeze_57 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_1808, -1), kwargs = {})
2025-03-21T20:30:48.3954896Z     %quantize_per_tensor_1313 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_57, 0.0004401287587825209, 30665, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3955681Z     %dequantize_per_tensor_1815 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1313, 0.0004401287587825209, 30665, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3956147Z     %transpose_330 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1815, 1, 2), kwargs = {})
2025-03-21T20:30:48.3956876Z     %quantize_per_tensor_1314 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_330, 0.0004401287587825209, 30665, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3957651Z     %dequantize_per_tensor_1816 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1314, 0.0004401287587825209, 30665, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3958193Z     %conv2d_57 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_1816, %dequantize_per_tensor_75), kwargs = {})
2025-03-21T20:30:48.3958884Z     %quantize_per_tensor_1315 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_57, 0.00042168446816504, 35651, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3959663Z     %dequantize_per_tensor_1817 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1315, 0.00042168446816504, 35651, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3960109Z     %transpose_331 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1817, 1, 2), kwargs = {})
2025-03-21T20:30:48.3960831Z     %quantize_per_tensor_1316 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_331, 0.00042168446816504, 35651, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3961598Z     %dequantize_per_tensor_1818 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1316, 0.00042168446816504, 35651, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3962030Z     %squeeze_57 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_1818, -1), kwargs = {})
2025-03-21T20:30:48.3962724Z     %quantize_per_tensor_1317 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_57, 0.00042168446816504, 35651, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3963505Z     %dequantize_per_tensor_1819 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1317, 0.00042168446816504, 35651, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3963961Z     %unsqueeze_58 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_1807, -1), kwargs = {})
2025-03-21T20:30:48.3964688Z     %quantize_per_tensor_1318 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_58, 0.0004401287587825209, 30665, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3965465Z     %dequantize_per_tensor_1820 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1318, 0.0004401287587825209, 30665, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3965945Z     %transpose_332 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1820, 1, 2), kwargs = {})
2025-03-21T20:30:48.3966685Z     %quantize_per_tensor_1319 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_332, 0.0004401287587825209, 30665, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3967474Z     %dequantize_per_tensor_1821 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1319, 0.0004401287587825209, 30665, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3967999Z     %conv2d_58 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_1821, %dequantize_per_tensor_76), kwargs = {})
2025-03-21T20:30:48.3968712Z     %quantize_per_tensor_1320 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_58, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3969559Z     %dequantize_per_tensor_1822 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1320, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3970063Z     %transpose_333 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1822, 1, 2), kwargs = {})
2025-03-21T20:30:48.3970778Z     %quantize_per_tensor_1321 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_333, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3971562Z     %dequantize_per_tensor_1823 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1321, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3971981Z     %squeeze_58 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_1823, -1), kwargs = {})
2025-03-21T20:30:48.3972701Z     %quantize_per_tensor_1322 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_58, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3973477Z     %dequantize_per_tensor_1824 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1322, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3973933Z     %view_96 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1814, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.3974628Z     %quantize_per_tensor_1323 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_96, 0.00033537388662807643, 31155, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3975424Z     %dequantize_per_tensor_1825 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1323, 0.00033537388662807643, 31155, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3975865Z     %view_97 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1819, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.3976565Z     %quantize_per_tensor_1324 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_97, 0.00042168446816504, 35651, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3977337Z     %dequantize_per_tensor_1826 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1324, 0.00042168446816504, 35651, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3977853Z     %view_98 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1824, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.3978543Z     %quantize_per_tensor_1325 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_98, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3979332Z     %dequantize_per_tensor_1827 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1325, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3979832Z     %_to_copy_16 : [num_users=1] = call_function[target=torch.ops.aten._to_copy.default](args = (%dequantize_per_tensor_1825,), kwargs = {dtype: torch.float32})
2025-03-21T20:30:48.3980536Z     %quantize_per_tensor_1326 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%_to_copy_16, 0.00033537388662807643, 31155, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3981328Z     %dequantize_per_tensor_1828 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1326, 0.00033537388662807643, 31155, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3981803Z     %view_99 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1828, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:30:48.3982511Z     %quantize_per_tensor_1327 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_99, 0.00033537388662807643, 31155, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3983289Z     %dequantize_per_tensor_1829 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1327, 0.00033537388662807643, 31155, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3983709Z     %unbind_16 : [num_users=2] = call_function[target=torch.ops.aten.unbind.int](args = (%dequantize_per_tensor_1829, -1), kwargs = {})
2025-03-21T20:30:48.3984028Z     %getitem_32 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_16, 0), kwargs = {})
2025-03-21T20:30:48.3984359Z     %getitem_33 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_16, 1), kwargs = {})
2025-03-21T20:30:48.3985060Z     %quantize_per_tensor_1328 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_32, 0.0003121877380181104, 28601, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3985844Z     %dequantize_per_tensor_1830 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1328, 0.0003121877380181104, 28601, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3986616Z     %dequantize_per_tensor_1831 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1328, 0.0003121877380181104, 28601, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3987335Z     %quantize_per_tensor_1329 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_33, 0.0003160475753247738, 33060, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3988108Z     %dequantize_per_tensor_1832 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1329, 0.0003160475753247738, 33060, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3988887Z     %dequantize_per_tensor_1833 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1329, 0.0003160475753247738, 33060, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3989716Z     %_to_copy_17 : [num_users=1] = call_function[target=torch.ops.aten._to_copy.default](args = (%dequantize_per_tensor_1826,), kwargs = {dtype: torch.float32})
2025-03-21T20:30:48.3990454Z     %quantize_per_tensor_1330 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%_to_copy_17, 0.00042168446816504, 35651, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3991225Z     %dequantize_per_tensor_1834 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1330, 0.00042168446816504, 35651, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3991721Z     %view_100 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1834, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:30:48.3992407Z     %quantize_per_tensor_1331 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_100, 0.00042168446816504, 35651, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3993188Z     %dequantize_per_tensor_1835 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1331, 0.00042168446816504, 35651, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3993620Z     %unbind_17 : [num_users=2] = call_function[target=torch.ops.aten.unbind.int](args = (%dequantize_per_tensor_1835, -1), kwargs = {})
2025-03-21T20:30:48.3993949Z     %getitem_34 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_17, 0), kwargs = {})
2025-03-21T20:30:48.3994264Z     %getitem_35 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_17, 1), kwargs = {})
2025-03-21T20:30:48.3994975Z     %quantize_per_tensor_1332 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_34, 0.0003787923196796328, 32268, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3995750Z     %dequantize_per_tensor_1836 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1332, 0.0003787923196796328, 32268, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3996536Z     %dequantize_per_tensor_1837 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1332, 0.0003787923196796328, 32268, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3997240Z     %quantize_per_tensor_1333 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_35, 0.00038380088517442346, 39170, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3998035Z     %dequantize_per_tensor_1838 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1333, 0.00038380088517442346, 39170, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3998811Z     %dequantize_per_tensor_1839 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1333, 0.00038380088517442346, 39170, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.3999262Z     %view_101 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_154, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:30:48.3999959Z     %quantize_per_tensor_1334 : [num_users=4] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_101, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4000746Z     %dequantize_per_tensor_1840 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1334, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4001540Z     %dequantize_per_tensor_1841 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1334, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4002350Z     %dequantize_per_tensor_1842 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1334, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4003144Z     %dequantize_per_tensor_1843 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1334, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4003596Z     %view_102 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_166, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:30:48.4004291Z     %quantize_per_tensor_1335 : [num_users=4] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_102, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4005075Z     %dequantize_per_tensor_1844 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1335, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4005868Z     %dequantize_per_tensor_1845 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1335, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4006650Z     %dequantize_per_tensor_1846 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1335, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4007420Z     %dequantize_per_tensor_1847 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1335, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4007912Z     %mul_88 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1831, %dequantize_per_tensor_1843), kwargs = {})
2025-03-21T20:30:48.4008603Z     %quantize_per_tensor_1336 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_88, 0.00030949688516557217, 28792, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4009482Z     %dequantize_per_tensor_1848 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1336, 0.00030949688516557217, 28792, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4009958Z     %mul_89 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1832, %dequantize_per_tensor_1846), kwargs = {})
2025-03-21T20:30:48.4010664Z     %quantize_per_tensor_1337 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_89, 0.00016250982298515737, 35603, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4011444Z     %dequantize_per_tensor_1849 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1337, 0.00016250982298515737, 35603, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4011932Z     %sub_16 : [num_users=1] = call_function[target=torch.ops.aten.sub.Tensor](args = (%dequantize_per_tensor_1848, %dequantize_per_tensor_1849), kwargs = {})
2025-03-21T20:30:48.4012619Z     %quantize_per_tensor_1338 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%sub_16, 0.0003078577865380794, 28618, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4013816Z     %dequantize_per_tensor_1850 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1338, 0.0003078577865380794, 28618, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4014317Z     %mul_90 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1830, %dequantize_per_tensor_1847), kwargs = {})
2025-03-21T20:30:48.4015019Z     %quantize_per_tensor_1339 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_90, 0.00012979988241568208, 32122, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4015826Z     %dequantize_per_tensor_1851 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1339, 0.00012979988241568208, 32122, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4016313Z     %mul_91 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1833, %dequantize_per_tensor_1842), kwargs = {})
2025-03-21T20:30:48.4017000Z     %quantize_per_tensor_1340 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_91, 0.0003096680738963187, 32788, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4017809Z     %dequantize_per_tensor_1852 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1340, 0.0003096680738963187, 32788, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4018283Z     %add_40 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_1851, %dequantize_per_tensor_1852), kwargs = {})
2025-03-21T20:30:48.4018984Z     %quantize_per_tensor_1341 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_40, 0.00031102492357604206, 32893, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4019761Z     %dequantize_per_tensor_1853 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1341, 0.00031102492357604206, 32893, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4020246Z     %mul_92 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1837, %dequantize_per_tensor_1841), kwargs = {})
2025-03-21T20:30:48.4020932Z     %quantize_per_tensor_1342 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_92, 0.00037348963087424636, 32361, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4021720Z     %dequantize_per_tensor_1854 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1342, 0.00037348963087424636, 32361, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4022191Z     %mul_93 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1838, %dequantize_per_tensor_1844), kwargs = {})
2025-03-21T20:30:48.4022888Z     %quantize_per_tensor_1343 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_93, 0.00014117307728156447, 32406, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4023666Z     %dequantize_per_tensor_1855 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1343, 0.00014117307728156447, 32406, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4024154Z     %sub_17 : [num_users=1] = call_function[target=torch.ops.aten.sub.Tensor](args = (%dequantize_per_tensor_1854, %dequantize_per_tensor_1855), kwargs = {})
2025-03-21T20:30:48.4024832Z     %quantize_per_tensor_1344 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%sub_17, 0.0003733103221748024, 32559, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4025657Z     %dequantize_per_tensor_1856 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1344, 0.0003733103221748024, 32559, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4026153Z     %mul_94 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1836, %dequantize_per_tensor_1845), kwargs = {})
2025-03-21T20:30:48.4026849Z     %quantize_per_tensor_1345 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_94, 0.00018785295833367854, 29230, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4027673Z     %dequantize_per_tensor_1857 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1345, 0.00018785295833367854, 29230, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4028158Z     %mul_95 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1839, %dequantize_per_tensor_1840), kwargs = {})
2025-03-21T20:30:48.4028847Z     %quantize_per_tensor_1346 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_95, 0.00037025712663307786, 38747, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4029658Z     %dequantize_per_tensor_1858 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1346, 0.00037025712663307786, 38747, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4030134Z     %add_41 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_1857, %dequantize_per_tensor_1858), kwargs = {})
2025-03-21T20:30:48.4030831Z     %quantize_per_tensor_1347 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_41, 0.0003686967247631401, 39138, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4031606Z     %dequantize_per_tensor_1859 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1347, 0.0003686967247631401, 39138, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4032144Z     %stack_16 : [num_users=1] = call_function[target=torch.ops.aten.stack.default](args = ([%dequantize_per_tensor_1850, %dequantize_per_tensor_1853], -1), kwargs = {})
2025-03-21T20:30:48.4032982Z     %quantize_per_tensor_1348 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%stack_16, 0.0003295276255812496, 31046, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4033766Z     %dequantize_per_tensor_1860 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1348, 0.0003295276255812496, 31046, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4034209Z     %view_103 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1860, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.4034919Z     %quantize_per_tensor_1349 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_103, 0.0003295276255812496, 31046, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4035691Z     %dequantize_per_tensor_1861 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1349, 0.0003295276255812496, 31046, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4036227Z     %stack_17 : [num_users=1] = call_function[target=torch.ops.aten.stack.default](args = ([%dequantize_per_tensor_1856, %dequantize_per_tensor_1859], -1), kwargs = {})
2025-03-21T20:30:48.4036963Z     %quantize_per_tensor_1350 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%stack_17, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4037777Z     %dequantize_per_tensor_1862 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1350, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4038224Z     %view_104 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1862, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.4038953Z     %quantize_per_tensor_1351 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_104, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4039724Z     %dequantize_per_tensor_1863 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1351, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4040245Z     %type_as_16 : [num_users=1] = call_function[target=torch.ops.aten.type_as.default](args = (%dequantize_per_tensor_1861, %dequantize_per_tensor_1825), kwargs = {})
2025-03-21T20:30:48.4040938Z     %quantize_per_tensor_1352 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%type_as_16, 0.0003295276255812496, 31046, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4041756Z     %dequantize_per_tensor_1864 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1352, 0.0003295276255812496, 31046, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4042255Z     %type_as_17 : [num_users=1] = call_function[target=torch.ops.aten.type_as.default](args = (%dequantize_per_tensor_1863, %dequantize_per_tensor_1826), kwargs = {})
2025-03-21T20:30:48.4042964Z     %quantize_per_tensor_1353 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%type_as_17, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4043731Z     %dequantize_per_tensor_1865 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1353, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4044190Z     %transpose_334 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1864, 1, 2), kwargs = {})
2025-03-21T20:30:48.4044908Z     %quantize_per_tensor_1354 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_334, 0.0003295276255812496, 31046, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4045697Z     %dequantize_per_tensor_1866 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1354, 0.0003295276255812496, 31046, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4046329Z     %index_put_16 : [num_users=1] = call_function[target=torch.ops.aten.index_put.default](args = (%dequantize_per_tensor_137, [None, %attn_options_input_pos], %dequantize_per_tensor_1865), kwargs = {})
2025-03-21T20:30:48.4047050Z     %quantize_per_tensor_1355 : [num_users=13] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_put_16, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4047822Z     %dequantize_per_tensor_1867 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1355, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4048601Z     %dequantize_per_tensor_1868 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1355, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4049483Z     %dequantize_per_tensor_1869 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1355, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4050266Z     %dequantize_per_tensor_1870 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1355, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4051058Z     %dequantize_per_tensor_1871 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1355, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4051836Z     %dequantize_per_tensor_1872 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1355, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4052604Z     %dequantize_per_tensor_1873 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1355, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4053407Z     %dequantize_per_tensor_1874 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1355, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4054174Z     %dequantize_per_tensor_1875 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1355, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4054956Z     %dequantize_per_tensor_1876 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1355, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4055725Z     %dequantize_per_tensor_1877 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1355, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4056504Z     %dequantize_per_tensor_1878 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1355, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4057268Z     %dequantize_per_tensor_1879 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1355, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4057910Z     %index_put_17 : [num_users=1] = call_function[target=torch.ops.aten.index_put.default](args = (%dequantize_per_tensor_138, [None, %attn_options_input_pos], %dequantize_per_tensor_1827), kwargs = {})
2025-03-21T20:30:48.4058617Z     %quantize_per_tensor_1356 : [num_users=13] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_put_17, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4059403Z     %dequantize_per_tensor_1880 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1356, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4060172Z     %dequantize_per_tensor_1881 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1356, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4061193Z     %dequantize_per_tensor_1882 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1356, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4061992Z     %dequantize_per_tensor_1883 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1356, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4062778Z     %dequantize_per_tensor_1884 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1356, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4063576Z     %dequantize_per_tensor_1885 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1356, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4064363Z     %dequantize_per_tensor_1886 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1356, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4065130Z     %dequantize_per_tensor_1887 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1356, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4065951Z     %dequantize_per_tensor_1888 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1356, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4066722Z     %dequantize_per_tensor_1889 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1356, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4067507Z     %dequantize_per_tensor_1890 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1356, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4068276Z     %dequantize_per_tensor_1891 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1356, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4069066Z     %dequantize_per_tensor_1892 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1356, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4069511Z     %transpose_335 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1879, 1, 2), kwargs = {})
2025-03-21T20:30:48.4070238Z     %quantize_per_tensor_1357 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_335, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4071012Z     %dequantize_per_tensor_1893 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1357, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4071444Z     %select_384 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1893, 0, 0), kwargs = {})
2025-03-21T20:30:48.4072145Z     %quantize_per_tensor_1358 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_384, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4072928Z     %dequantize_per_tensor_1894 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1358, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4073399Z     %select_385 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1894, 0, 0), kwargs = {})
2025-03-21T20:30:48.4074112Z     %quantize_per_tensor_1359 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_385, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4074887Z     %dequantize_per_tensor_1895 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1359, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4075373Z     %transpose_336 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1878, 1, 2), kwargs = {})
2025-03-21T20:30:48.4076094Z     %quantize_per_tensor_1360 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_336, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4076889Z     %dequantize_per_tensor_1896 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1360, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4077330Z     %select_386 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1896, 0, 0), kwargs = {})
2025-03-21T20:30:48.4078049Z     %quantize_per_tensor_1361 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_386, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4078820Z     %dequantize_per_tensor_1897 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1361, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4079253Z     %select_387 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1897, 0, 1), kwargs = {})
2025-03-21T20:30:48.4079956Z     %quantize_per_tensor_1362 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_387, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4080745Z     %dequantize_per_tensor_1898 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1362, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4081196Z     %transpose_337 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1877, 1, 2), kwargs = {})
2025-03-21T20:30:48.4081923Z     %quantize_per_tensor_1363 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_337, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4082692Z     %dequantize_per_tensor_1899 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1363, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4083119Z     %select_388 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1899, 0, 0), kwargs = {})
2025-03-21T20:30:48.4083818Z     %quantize_per_tensor_1364 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_388, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4084598Z     %dequantize_per_tensor_1900 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1364, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4085035Z     %select_389 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1900, 0, 2), kwargs = {})
2025-03-21T20:30:48.4085767Z     %quantize_per_tensor_1365 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_389, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4086534Z     %dequantize_per_tensor_1901 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1365, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4087013Z     %transpose_338 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1876, 1, 2), kwargs = {})
2025-03-21T20:30:48.4087726Z     %quantize_per_tensor_1366 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_338, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4088509Z     %dequantize_per_tensor_1902 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1366, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4088944Z     %select_390 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1902, 0, 0), kwargs = {})
2025-03-21T20:30:48.4089715Z     %quantize_per_tensor_1367 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_390, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4090483Z     %dequantize_per_tensor_1903 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1367, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4090916Z     %select_391 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1903, 0, 3), kwargs = {})
2025-03-21T20:30:48.4091617Z     %quantize_per_tensor_1368 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_391, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4092401Z     %dequantize_per_tensor_1904 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1368, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4092846Z     %transpose_339 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1875, 1, 2), kwargs = {})
2025-03-21T20:30:48.4093571Z     %quantize_per_tensor_1369 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_339, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4094342Z     %dequantize_per_tensor_1905 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1369, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4094769Z     %select_392 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1905, 0, 0), kwargs = {})
2025-03-21T20:30:48.4095470Z     %quantize_per_tensor_1370 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_392, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4096254Z     %dequantize_per_tensor_1906 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1370, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4096692Z     %select_393 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1906, 0, 4), kwargs = {})
2025-03-21T20:30:48.4097433Z     %quantize_per_tensor_1371 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_393, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4098201Z     %dequantize_per_tensor_1907 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1371, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4098682Z     %transpose_340 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1874, 1, 2), kwargs = {})
2025-03-21T20:30:48.4099395Z     %quantize_per_tensor_1372 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_340, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4100179Z     %dequantize_per_tensor_1908 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1372, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4100615Z     %select_394 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1908, 0, 0), kwargs = {})
2025-03-21T20:30:48.4101324Z     %quantize_per_tensor_1373 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_394, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4102092Z     %dequantize_per_tensor_1909 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1373, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4102514Z     %select_395 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1909, 0, 5), kwargs = {})
2025-03-21T20:30:48.4103213Z     %quantize_per_tensor_1374 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_395, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4103992Z     %dequantize_per_tensor_1910 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1374, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4104434Z     %transpose_341 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1873, 1, 2), kwargs = {})
2025-03-21T20:30:48.4105159Z     %quantize_per_tensor_1375 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_341, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4105938Z     %dequantize_per_tensor_1911 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1375, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4106352Z     %select_396 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1911, 0, 0), kwargs = {})
2025-03-21T20:30:48.4107058Z     %quantize_per_tensor_1376 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_396, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4107827Z     %dequantize_per_tensor_1912 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1376, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4108273Z     %select_397 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1912, 0, 6), kwargs = {})
2025-03-21T20:30:48.4108996Z     %quantize_per_tensor_1377 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_397, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4109776Z     %dequantize_per_tensor_1913 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1377, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4110252Z     %transpose_342 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1872, 1, 2), kwargs = {})
2025-03-21T20:30:48.4110976Z     %quantize_per_tensor_1378 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_342, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4111748Z     %dequantize_per_tensor_1914 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1378, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4112193Z     %select_398 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1914, 0, 0), kwargs = {})
2025-03-21T20:30:48.4112893Z     %quantize_per_tensor_1379 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_398, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4113673Z     %dequantize_per_tensor_1915 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1379, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4114089Z     %select_399 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1915, 0, 7), kwargs = {})
2025-03-21T20:30:48.4114802Z     %quantize_per_tensor_1380 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_399, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4115575Z     %dequantize_per_tensor_1916 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1380, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4116033Z     %transpose_343 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1871, 1, 2), kwargs = {})
2025-03-21T20:30:48.4116746Z     %quantize_per_tensor_1381 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_343, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4117527Z     %dequantize_per_tensor_1917 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1381, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4117938Z     %select_400 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1917, 0, 0), kwargs = {})
2025-03-21T20:30:48.4118648Z     %quantize_per_tensor_1382 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_400, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4119424Z     %dequantize_per_tensor_1918 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1382, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4119871Z     %select_401 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1918, 0, 8), kwargs = {})
2025-03-21T20:30:48.4120594Z     %quantize_per_tensor_1383 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_401, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4121373Z     %dequantize_per_tensor_1919 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1383, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4121846Z     %transpose_344 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1870, 1, 2), kwargs = {})
2025-03-21T20:30:48.4122571Z     %quantize_per_tensor_1384 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_344, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4123343Z     %dequantize_per_tensor_1920 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1384, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4123788Z     %select_402 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1920, 0, 0), kwargs = {})
2025-03-21T20:30:48.4124490Z     %quantize_per_tensor_1385 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_402, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4125268Z     %dequantize_per_tensor_1921 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1385, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4125685Z     %select_403 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1921, 0, 9), kwargs = {})
2025-03-21T20:30:48.4126398Z     %quantize_per_tensor_1386 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_403, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4127170Z     %dequantize_per_tensor_1922 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1386, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4127621Z     %transpose_345 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1869, 1, 2), kwargs = {})
2025-03-21T20:30:48.4128333Z     %quantize_per_tensor_1387 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_345, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4129112Z     %dequantize_per_tensor_1923 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1387, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4129583Z     %select_404 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1923, 0, 0), kwargs = {})
2025-03-21T20:30:48.4130292Z     %quantize_per_tensor_1388 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_404, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4131059Z     %dequantize_per_tensor_1924 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1388, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4131483Z     %select_405 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1924, 0, 10), kwargs = {})
2025-03-21T20:30:48.4132426Z     %quantize_per_tensor_1389 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_405, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4133255Z     %dequantize_per_tensor_1925 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1389, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4133742Z     %transpose_346 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1868, 1, 2), kwargs = {})
2025-03-21T20:30:48.4134470Z     %quantize_per_tensor_1390 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_346, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4135238Z     %dequantize_per_tensor_1926 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1390, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4135661Z     %select_406 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1926, 0, 0), kwargs = {})
2025-03-21T20:30:48.4136391Z     %quantize_per_tensor_1391 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_406, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4137173Z     %dequantize_per_tensor_1927 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1391, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4137589Z     %select_407 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1927, 0, 11), kwargs = {})
2025-03-21T20:30:48.4138295Z     %quantize_per_tensor_1392 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_407, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4139065Z     %dequantize_per_tensor_1928 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1392, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4140570Z     %cat_16 : [num_users=1] = call_function[target=torch.ops.aten.cat.default](args = ([%dequantize_per_tensor_1895, %dequantize_per_tensor_1898, %dequantize_per_tensor_1901, %dequantize_per_tensor_1904, %dequantize_per_tensor_1907, %dequantize_per_tensor_1910, %dequantize_per_tensor_1913, %dequantize_per_tensor_1916, %dequantize_per_tensor_1919, %dequantize_per_tensor_1922, %dequantize_per_tensor_1925, %dequantize_per_tensor_1928],), kwargs = {})
2025-03-21T20:30:48.4141255Z     %quantize_per_tensor_1393 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%cat_16, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4142031Z     %dequantize_per_tensor_1929 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1393, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4142478Z     %view_105 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1929, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:30:48.4143175Z     %quantize_per_tensor_1394 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_105, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4143966Z     %dequantize_per_tensor_1930 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1394, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4144451Z     %transpose_347 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1892, 1, 2), kwargs = {})
2025-03-21T20:30:48.4145169Z     %quantize_per_tensor_1395 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_347, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4145974Z     %dequantize_per_tensor_1931 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1395, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4146388Z     %select_408 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1931, 0, 0), kwargs = {})
2025-03-21T20:30:48.4147103Z     %quantize_per_tensor_1396 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_408, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4147898Z     %dequantize_per_tensor_1932 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1396, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4148325Z     %select_409 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1932, 0, 0), kwargs = {})
2025-03-21T20:30:48.4149027Z     %quantize_per_tensor_1397 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_409, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4149812Z     %dequantize_per_tensor_1933 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1397, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4150261Z     %transpose_348 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1891, 1, 2), kwargs = {})
2025-03-21T20:30:48.4150992Z     %quantize_per_tensor_1398 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_348, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4151764Z     %dequantize_per_tensor_1934 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1398, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4152183Z     %select_410 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1934, 0, 0), kwargs = {})
2025-03-21T20:30:48.4152887Z     %quantize_per_tensor_1399 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_410, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4153669Z     %dequantize_per_tensor_1935 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1399, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4154079Z     %select_411 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1935, 0, 1), kwargs = {})
2025-03-21T20:30:48.4154797Z     %quantize_per_tensor_1400 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_411, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4155590Z     %dequantize_per_tensor_1936 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1400, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4156077Z     %transpose_349 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1890, 1, 2), kwargs = {})
2025-03-21T20:30:48.4156794Z     %quantize_per_tensor_1401 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_349, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4157596Z     %dequantize_per_tensor_1937 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1401, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4158007Z     %select_412 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1937, 0, 0), kwargs = {})
2025-03-21T20:30:48.4158708Z     %quantize_per_tensor_1402 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_412, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4159513Z     %dequantize_per_tensor_1938 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1402, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4159923Z     %select_413 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1938, 0, 2), kwargs = {})
2025-03-21T20:30:48.4160633Z     %quantize_per_tensor_1403 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_413, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4161406Z     %dequantize_per_tensor_1939 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1403, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4161869Z     %transpose_350 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1889, 1, 2), kwargs = {})
2025-03-21T20:30:48.4162586Z     %quantize_per_tensor_1404 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_350, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4163371Z     %dequantize_per_tensor_1940 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1404, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4163783Z     %select_414 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1940, 0, 0), kwargs = {})
2025-03-21T20:30:48.4164499Z     %quantize_per_tensor_1405 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_414, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4165274Z     %dequantize_per_tensor_1941 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1405, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4165696Z     %select_415 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1941, 0, 3), kwargs = {})
2025-03-21T20:30:48.4166398Z     %quantize_per_tensor_1406 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_415, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4167201Z     %dequantize_per_tensor_1942 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1406, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4167666Z     %transpose_351 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1888, 1, 2), kwargs = {})
2025-03-21T20:30:48.4168389Z     %quantize_per_tensor_1407 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_351, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4169185Z     %dequantize_per_tensor_1943 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1407, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4169669Z     %select_416 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1943, 0, 0), kwargs = {})
2025-03-21T20:30:48.4170379Z     %quantize_per_tensor_1408 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_416, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4171195Z     %dequantize_per_tensor_1944 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1408, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4171604Z     %select_417 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1944, 0, 4), kwargs = {})
2025-03-21T20:30:48.4172317Z     %quantize_per_tensor_1409 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_417, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4173093Z     %dequantize_per_tensor_1945 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1409, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4173549Z     %transpose_352 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1887, 1, 2), kwargs = {})
2025-03-21T20:30:48.4174269Z     %quantize_per_tensor_1410 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_352, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4175050Z     %dequantize_per_tensor_1946 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1410, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4175459Z     %select_418 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1946, 0, 0), kwargs = {})
2025-03-21T20:30:48.4176175Z     %quantize_per_tensor_1411 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_418, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4176951Z     %dequantize_per_tensor_1947 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1411, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4177377Z     %select_419 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1947, 0, 5), kwargs = {})
2025-03-21T20:30:48.4178080Z     %quantize_per_tensor_1412 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_419, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4179162Z     %dequantize_per_tensor_1948 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1412, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4179645Z     %transpose_353 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1886, 1, 2), kwargs = {})
2025-03-21T20:30:48.4180374Z     %quantize_per_tensor_1413 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_353, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4181173Z     %dequantize_per_tensor_1949 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1413, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4181599Z     %select_420 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1949, 0, 0), kwargs = {})
2025-03-21T20:30:48.4182304Z     %quantize_per_tensor_1414 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_420, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4183092Z     %dequantize_per_tensor_1950 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1414, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4183526Z     %select_421 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1950, 0, 6), kwargs = {})
2025-03-21T20:30:48.4184234Z     %quantize_per_tensor_1415 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_421, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4185005Z     %dequantize_per_tensor_1951 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1415, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4185459Z     %transpose_354 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1885, 1, 2), kwargs = {})
2025-03-21T20:30:48.4186174Z     %quantize_per_tensor_1416 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_354, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4186959Z     %dequantize_per_tensor_1952 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1416, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4187369Z     %select_422 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1952, 0, 0), kwargs = {})
2025-03-21T20:30:48.4188080Z     %quantize_per_tensor_1417 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_422, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4188852Z     %dequantize_per_tensor_1953 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1417, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4189272Z     %select_423 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1953, 0, 7), kwargs = {})
2025-03-21T20:30:48.4189971Z     %quantize_per_tensor_1418 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_423, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4190774Z     %dequantize_per_tensor_1954 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1418, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4191237Z     %transpose_355 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1884, 1, 2), kwargs = {})
2025-03-21T20:30:48.4191966Z     %quantize_per_tensor_1419 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_355, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4192757Z     %dequantize_per_tensor_1955 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1419, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4193180Z     %select_424 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1955, 0, 0), kwargs = {})
2025-03-21T20:30:48.4193879Z     %quantize_per_tensor_1420 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_424, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4194660Z     %dequantize_per_tensor_1956 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1420, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4195093Z     %select_425 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1956, 0, 8), kwargs = {})
2025-03-21T20:30:48.4195804Z     %quantize_per_tensor_1421 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_425, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4196574Z     %dequantize_per_tensor_1957 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1421, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4197027Z     %transpose_356 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1883, 1, 2), kwargs = {})
2025-03-21T20:30:48.4197745Z     %quantize_per_tensor_1422 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_356, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4198528Z     %dequantize_per_tensor_1958 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1422, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4198940Z     %select_426 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1958, 0, 0), kwargs = {})
2025-03-21T20:30:48.4199651Z     %quantize_per_tensor_1423 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_426, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4200424Z     %dequantize_per_tensor_1959 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1423, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4200846Z     %select_427 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1959, 0, 9), kwargs = {})
2025-03-21T20:30:48.4201546Z     %quantize_per_tensor_1424 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_427, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4202364Z     %dequantize_per_tensor_1960 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1424, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4202831Z     %transpose_357 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1882, 1, 2), kwargs = {})
2025-03-21T20:30:48.4203562Z     %quantize_per_tensor_1425 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_357, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4204354Z     %dequantize_per_tensor_1961 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1425, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4204769Z     %select_428 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1961, 0, 0), kwargs = {})
2025-03-21T20:30:48.4205485Z     %quantize_per_tensor_1426 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_428, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4206255Z     %dequantize_per_tensor_1962 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1426, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4206705Z     %select_429 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1962, 0, 10), kwargs = {})
2025-03-21T20:30:48.4207405Z     %quantize_per_tensor_1427 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_429, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4208186Z     %dequantize_per_tensor_1963 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1427, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4208630Z     %transpose_358 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1881, 1, 2), kwargs = {})
2025-03-21T20:30:48.4209430Z     %quantize_per_tensor_1428 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_358, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4210207Z     %dequantize_per_tensor_1964 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1428, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4210630Z     %select_430 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1964, 0, 0), kwargs = {})
2025-03-21T20:30:48.4211332Z     %quantize_per_tensor_1429 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_430, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4212113Z     %dequantize_per_tensor_1965 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1429, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4212528Z     %select_431 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_1965, 0, 11), kwargs = {})
2025-03-21T20:30:48.4213239Z     %quantize_per_tensor_1430 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_431, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4214042Z     %dequantize_per_tensor_1966 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1430, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4215596Z     %cat_17 : [num_users=1] = call_function[target=torch.ops.aten.cat.default](args = ([%dequantize_per_tensor_1933, %dequantize_per_tensor_1936, %dequantize_per_tensor_1939, %dequantize_per_tensor_1942, %dequantize_per_tensor_1945, %dequantize_per_tensor_1948, %dequantize_per_tensor_1951, %dequantize_per_tensor_1954, %dequantize_per_tensor_1957, %dequantize_per_tensor_1960, %dequantize_per_tensor_1963, %dequantize_per_tensor_1966],), kwargs = {})
2025-03-21T20:30:48.4216321Z     %quantize_per_tensor_1431 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%cat_17, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4217100Z     %dequantize_per_tensor_1967 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1431, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4217563Z     %view_106 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1967, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:30:48.4218284Z     %quantize_per_tensor_1432 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_106, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4219070Z     %dequantize_per_tensor_1968 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1432, 0.0001714634709060192, 32914, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4219848Z     %quantize_per_tensor_1433 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%dequantize_per_tensor_1968, 0.00017223355825990438, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.4220644Z     %dequantize_per_tensor_1969 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1433, 0.00017223355825990438, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.4221130Z     %index_10 : [num_users=1] = call_function[target=torch.ops.aten.index.Tensor](args = (%dequantize_per_tensor_139, [%attn_options_input_pos]), kwargs = {})
2025-03-21T20:30:48.4221836Z     %quantize_per_tensor_1434 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_10, 0.0038910505827516317, 65535, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4222610Z     %dequantize_per_tensor_1970 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1434, 0.0038910505827516317, 65535, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4223078Z     %transpose_359 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1930, -2, -1), kwargs = {})
2025-03-21T20:30:48.4223791Z     %quantize_per_tensor_1435 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_359, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4224564Z     %dequantize_per_tensor_1971 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1435, 0.000408027321100235, 35365, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4225347Z     %quantize_per_tensor_1436 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%dequantize_per_tensor_1971, 0.00044038108899258077, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.4226161Z     %dequantize_per_tensor_1972 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1436, 0.00044038108899258077, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.4226696Z     %matmul_16 : [num_users=1] = call_function[target=torch.ops.aten.matmul.default](args = (%dequantize_per_tensor_1866, %dequantize_per_tensor_1972), kwargs = {})
2025-03-21T20:30:48.4227405Z     %quantize_per_tensor_1437 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%matmul_16, 0.0028048588428646326, 32779, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4228201Z     %dequantize_per_tensor_1973 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1437, 0.0028048588428646326, 32779, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4228958Z     %dequantize_per_tensor_1974 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param157, 1.9073777366429567e-06, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4229434Z     %mul_96 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1973, %dequantize_per_tensor_1974), kwargs = {})
2025-03-21T20:30:48.4230143Z     %quantize_per_tensor_1438 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_96, 0.0003506073553580791, 32779, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4230925Z     %dequantize_per_tensor_1975 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1438, 0.0003506073553580791, 32779, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4231397Z     %add_42 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_1975, %dequantize_per_tensor_1970), kwargs = {})
2025-03-21T20:30:48.4232093Z     %quantize_per_tensor_1439 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_42, 0.0042004697024822235, 62801, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4233030Z     %dequantize_per_tensor_1976 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1439, 0.0042004697024822235, 62801, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4233460Z     %softmax_8 : [num_users=1] = call_function[target=torch.ops.aten.softmax.int](args = (%dequantize_per_tensor_1976, -1), kwargs = {})
2025-03-21T20:30:48.4234157Z     %quantize_per_tensor_1440 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%softmax_8, 1.5259021893143654e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4234941Z     %dequantize_per_tensor_1977 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1440, 1.5259021893143654e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4235458Z     %matmul_17 : [num_users=1] = call_function[target=torch.ops.aten.matmul.default](args = (%dequantize_per_tensor_1977, %dequantize_per_tensor_1969), kwargs = {})
2025-03-21T20:30:48.4236169Z     %quantize_per_tensor_1441 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%matmul_17, 9.857307304628193e-05, 32475, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4236943Z     %dequantize_per_tensor_1978 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1441, 9.857307304628193e-05, 32475, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4237397Z     %transpose_360 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1978, 1, 2), kwargs = {})
2025-03-21T20:30:48.4238174Z     %quantize_per_tensor_1442 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_360, 9.857307304628193e-05, 32475, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4238993Z     %dequantize_per_tensor_1979 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1442, 9.857307304628193e-05, 32475, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4239428Z     %view_107 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_1979, [1, 1, 768]), kwargs = {})
2025-03-21T20:30:48.4240162Z     %quantize_per_tensor_1443 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_107, 9.857307304628193e-05, 32475, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4240932Z     %dequantize_per_tensor_1980 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1443, 9.857307304628193e-05, 32475, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4241404Z     %unsqueeze_59 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_1980, -1), kwargs = {})
2025-03-21T20:30:48.4242155Z     %quantize_per_tensor_1444 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_59, 9.857307304628193e-05, 32475, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4242937Z     %dequantize_per_tensor_1981 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1444, 9.857307304628193e-05, 32475, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4243380Z     %transpose_361 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1981, 1, 2), kwargs = {})
2025-03-21T20:30:48.4244108Z     %quantize_per_tensor_1445 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_361, 9.857307304628193e-05, 32475, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4244876Z     %dequantize_per_tensor_1982 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1445, 9.857307304628193e-05, 32475, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4245387Z     %conv2d_59 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_1982, %dequantize_per_tensor_77), kwargs = {})
2025-03-21T20:30:48.4246084Z     %quantize_per_tensor_1446 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_59, 6.995500734774396e-05, 26018, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4246865Z     %dequantize_per_tensor_1983 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1446, 6.995500734774396e-05, 26018, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4247309Z     %transpose_362 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1983, 1, 2), kwargs = {})
2025-03-21T20:30:48.4248035Z     %quantize_per_tensor_1447 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_362, 6.995500734774396e-05, 26018, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4248803Z     %dequantize_per_tensor_1984 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1447, 6.995500734774396e-05, 26018, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4249223Z     %squeeze_59 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_1984, -1), kwargs = {})
2025-03-21T20:30:48.4250017Z     %quantize_per_tensor_1448 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_59, 6.995500734774396e-05, 26018, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4250828Z     %dequantize_per_tensor_1985 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1448, 6.995500734774396e-05, 26018, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4251301Z     %add_43 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_1805, %dequantize_per_tensor_1985), kwargs = {})
2025-03-21T20:30:48.4252015Z     %quantize_per_tensor_1449 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_43, 0.0026511913165450096, 5838, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4252788Z     %dequantize_per_tensor_1986 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1449, 0.0026511913165450096, 5838, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4253570Z     %dequantize_per_tensor_1987 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1449, 0.0026511913165450096, 5838, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4254139Z     %rms_norm_17 : [num_users=1] = call_function[target=torch.ops.aten.rms_norm.default](args = (%dequantize_per_tensor_1987, [768], %dequantize_per_tensor_78, 1e-05), kwargs = {})
2025-03-21T20:30:48.4254852Z     %quantize_per_tensor_1450 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%rms_norm_17, 0.00035757292062044144, 21055, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4255627Z     %dequantize_per_tensor_1988 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1450, 0.00035757292062044144, 21055, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4256411Z     %dequantize_per_tensor_1989 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1450, 0.00035757292062044144, 21055, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4256873Z     %unsqueeze_60 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_1989, -1), kwargs = {})
2025-03-21T20:30:48.4257595Z     %quantize_per_tensor_1451 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_60, 0.00035757292062044144, 21055, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4258371Z     %dequantize_per_tensor_1990 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1451, 0.00035757292062044144, 21055, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4258831Z     %transpose_363 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1990, 1, 2), kwargs = {})
2025-03-21T20:30:48.4259550Z     %quantize_per_tensor_1452 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_363, 0.00035757292062044144, 21055, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4260338Z     %dequantize_per_tensor_1991 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1452, 0.00035757292062044144, 21055, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4260839Z     %conv2d_60 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_1991, %dequantize_per_tensor_79), kwargs = {})
2025-03-21T20:30:48.4261574Z     %quantize_per_tensor_1453 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_60, 0.00018512652604840696, 30788, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4262371Z     %dequantize_per_tensor_1992 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1453, 0.00018512652604840696, 30788, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4262825Z     %transpose_364 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1992, 1, 2), kwargs = {})
2025-03-21T20:30:48.4263568Z     %quantize_per_tensor_1454 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_364, 0.00018512652604840696, 30788, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4264359Z     %dequantize_per_tensor_1993 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1454, 0.00018512652604840696, 30788, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4264772Z     %squeeze_60 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_1993, -1), kwargs = {})
2025-03-21T20:30:48.4265512Z     %quantize_per_tensor_1455 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_60, 0.00018512652604840696, 30788, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4266292Z     %dequantize_per_tensor_1994 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1455, 0.00018512652604840696, 30788, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4267077Z     %dequantize_per_tensor_1995 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1455, 0.00018512652604840696, 30788, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4267504Z     %sigmoid_8 : [num_users=1] = call_function[target=torch.ops.aten.sigmoid.default](args = (%dequantize_per_tensor_1995,), kwargs = {})
2025-03-21T20:30:48.4268184Z     %quantize_per_tensor_1456 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%sigmoid_8, 1.52587890625e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4268931Z     %dequantize_per_tensor_1996 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1456, 1.52587890625e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4269416Z     %mul_97 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1994, %dequantize_per_tensor_1996), kwargs = {})
2025-03-21T20:30:48.4270098Z     %quantize_per_tensor_1457 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_97, 0.00010224587458651513, 2723, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4270884Z     %dequantize_per_tensor_1997 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1457, 0.00010224587458651513, 2723, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4271340Z     %unsqueeze_61 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_1988, -1), kwargs = {})
2025-03-21T20:30:48.4272065Z     %quantize_per_tensor_1458 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_61, 0.00035757292062044144, 21055, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4272839Z     %dequantize_per_tensor_1998 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1458, 0.00035757292062044144, 21055, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4273341Z     %transpose_365 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_1998, 1, 2), kwargs = {})
2025-03-21T20:30:48.4274087Z     %quantize_per_tensor_1459 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_365, 0.00035757292062044144, 21055, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4274876Z     %dequantize_per_tensor_1999 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1459, 0.00035757292062044144, 21055, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4275401Z     %conv2d_61 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_1999, %dequantize_per_tensor_80), kwargs = {})
2025-03-21T20:30:48.4276113Z     %quantize_per_tensor_1460 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_61, 0.00020597278489731252, 31383, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4276889Z     %dequantize_per_tensor_2000 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1460, 0.00020597278489731252, 31383, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4277369Z     %transpose_366 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2000, 1, 2), kwargs = {})
2025-03-21T20:30:48.4278097Z     %quantize_per_tensor_1461 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_366, 0.00020597278489731252, 31383, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4278891Z     %dequantize_per_tensor_2001 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1461, 0.00020597278489731252, 31383, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4279316Z     %squeeze_61 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_2001, -1), kwargs = {})
2025-03-21T20:30:48.4280040Z     %quantize_per_tensor_1462 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_61, 0.00020597278489731252, 31383, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4280823Z     %dequantize_per_tensor_2002 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1462, 0.00020597278489731252, 31383, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4281309Z     %mul_98 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_1997, %dequantize_per_tensor_2002), kwargs = {})
2025-03-21T20:30:48.4281999Z     %quantize_per_tensor_1463 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_98, 0.00044964838889427483, 39916, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4282795Z     %dequantize_per_tensor_2003 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1463, 0.00044964838889427483, 39916, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4283256Z     %unsqueeze_62 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_2003, -1), kwargs = {})
2025-03-21T20:30:48.4283988Z     %quantize_per_tensor_1464 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_62, 0.00044964838889427483, 39916, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4284763Z     %dequantize_per_tensor_2004 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1464, 0.00044964838889427483, 39916, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4285268Z     %transpose_367 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2004, 1, 2), kwargs = {})
2025-03-21T20:30:48.4285987Z     %quantize_per_tensor_1465 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_367, 0.00044964838889427483, 39916, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4286809Z     %dequantize_per_tensor_2005 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1465, 0.00044964838889427483, 39916, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4287312Z     %conv2d_62 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_2005, %dequantize_per_tensor_81), kwargs = {})
2025-03-21T20:30:48.4288023Z     %quantize_per_tensor_1466 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_62, 0.00013728736666962504, 29642, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4288802Z     %dequantize_per_tensor_2006 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1466, 0.00013728736666962504, 29642, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4289358Z     %transpose_368 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2006, 1, 2), kwargs = {})
2025-03-21T20:30:48.4290085Z     %quantize_per_tensor_1467 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_368, 0.00013728736666962504, 29642, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4290873Z     %dequantize_per_tensor_2007 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1467, 0.00013728736666962504, 29642, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4291286Z     %squeeze_62 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_2007, -1), kwargs = {})
2025-03-21T20:30:48.4292005Z     %quantize_per_tensor_1468 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_62, 0.00013728736666962504, 29642, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4292781Z     %dequantize_per_tensor_2008 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1468, 0.00013728736666962504, 29642, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4293262Z     %add_44 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_1986, %dequantize_per_tensor_2008), kwargs = {})
2025-03-21T20:30:48.4293936Z     %quantize_per_tensor_1469 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_44, 0.002680311445146799, 6713, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4294719Z     %dequantize_per_tensor_2009 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1469, 0.002680311445146799, 6713, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4295483Z     %dequantize_per_tensor_2010 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1469, 0.002680311445146799, 6713, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4296039Z     %rms_norm_18 : [num_users=1] = call_function[target=torch.ops.aten.rms_norm.default](args = (%dequantize_per_tensor_2010, [768], %dequantize_per_tensor_82, 1e-05), kwargs = {})
2025-03-21T20:30:48.4296772Z     %quantize_per_tensor_1470 : [num_users=3] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%rms_norm_18, 0.0004660242120735347, 32140, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4297582Z     %dequantize_per_tensor_2011 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1470, 0.0004660242120735347, 32140, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4298352Z     %dequantize_per_tensor_2012 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1470, 0.0004660242120735347, 32140, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4299153Z     %dequantize_per_tensor_2013 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1470, 0.0004660242120735347, 32140, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4299610Z     %unsqueeze_63 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_2013, -1), kwargs = {})
2025-03-21T20:30:48.4300335Z     %quantize_per_tensor_1471 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_63, 0.0004660242120735347, 32140, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4301129Z     %dequantize_per_tensor_2014 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1471, 0.0004660242120735347, 32140, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4301588Z     %transpose_369 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2014, 1, 2), kwargs = {})
2025-03-21T20:30:48.4302301Z     %quantize_per_tensor_1472 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_369, 0.0004660242120735347, 32140, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4303077Z     %dequantize_per_tensor_2015 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1472, 0.0004660242120735347, 32140, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4303593Z     %conv2d_63 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_2015, %dequantize_per_tensor_83), kwargs = {})
2025-03-21T20:30:48.4304293Z     %quantize_per_tensor_1473 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_63, 0.00035828881664201617, 31639, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4305078Z     %dequantize_per_tensor_2016 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1473, 0.00035828881664201617, 31639, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4305521Z     %transpose_370 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2016, 1, 2), kwargs = {})
2025-03-21T20:30:48.4306254Z     %quantize_per_tensor_1474 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_370, 0.00035828881664201617, 31639, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4307029Z     %dequantize_per_tensor_2017 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1474, 0.00035828881664201617, 31639, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4307453Z     %squeeze_63 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_2017, -1), kwargs = {})
2025-03-21T20:30:48.4308155Z     %quantize_per_tensor_1475 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_63, 0.00035828881664201617, 31639, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4308965Z     %dequantize_per_tensor_2018 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1475, 0.00035828881664201617, 31639, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4309443Z     %unsqueeze_64 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_2012, -1), kwargs = {})
2025-03-21T20:30:48.4310165Z     %quantize_per_tensor_1476 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_64, 0.0004660242120735347, 32140, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4310980Z     %dequantize_per_tensor_2019 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1476, 0.0004660242120735347, 32140, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4311438Z     %transpose_371 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2019, 1, 2), kwargs = {})
2025-03-21T20:30:48.4312155Z     %quantize_per_tensor_1477 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_371, 0.0004660242120735347, 32140, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4312963Z     %dequantize_per_tensor_2020 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1477, 0.0004660242120735347, 32140, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4313466Z     %conv2d_64 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_2020, %dequantize_per_tensor_84), kwargs = {})
2025-03-21T20:30:48.4314173Z     %quantize_per_tensor_1478 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_64, 0.0004303281893953681, 32305, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4314950Z     %dequantize_per_tensor_2021 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1478, 0.0004303281893953681, 32305, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4315404Z     %transpose_372 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2021, 1, 2), kwargs = {})
2025-03-21T20:30:48.4316121Z     %quantize_per_tensor_1479 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_372, 0.0004303281893953681, 32305, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4316909Z     %dequantize_per_tensor_2022 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1479, 0.0004303281893953681, 32305, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4317325Z     %squeeze_64 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_2022, -1), kwargs = {})
2025-03-21T20:30:48.4318044Z     %quantize_per_tensor_1480 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_64, 0.0004303281893953681, 32305, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4318820Z     %dequantize_per_tensor_2023 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1480, 0.0004303281893953681, 32305, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4319293Z     %unsqueeze_65 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_2011, -1), kwargs = {})
2025-03-21T20:30:48.4320006Z     %quantize_per_tensor_1481 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_65, 0.0004660242120735347, 32140, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4320844Z     %dequantize_per_tensor_2024 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1481, 0.0004660242120735347, 32140, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4321294Z     %transpose_373 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2024, 1, 2), kwargs = {})
2025-03-21T20:30:48.4322046Z     %quantize_per_tensor_1482 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_373, 0.0004660242120735347, 32140, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4322821Z     %dequantize_per_tensor_2025 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1482, 0.0004660242120735347, 32140, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4323337Z     %conv2d_65 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_2025, %dequantize_per_tensor_85), kwargs = {})
2025-03-21T20:30:48.4324037Z     %quantize_per_tensor_1483 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_65, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4324849Z     %dequantize_per_tensor_2026 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1483, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4325292Z     %transpose_374 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2026, 1, 2), kwargs = {})
2025-03-21T20:30:48.4326018Z     %quantize_per_tensor_1484 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_374, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4326792Z     %dequantize_per_tensor_2027 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1484, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4327218Z     %squeeze_65 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_2027, -1), kwargs = {})
2025-03-21T20:30:48.4327919Z     %quantize_per_tensor_1485 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_65, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4328703Z     %dequantize_per_tensor_2028 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1485, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4329147Z     %view_108 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_2018, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.4329910Z     %quantize_per_tensor_1486 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_108, 0.00035828881664201617, 31639, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4330687Z     %dequantize_per_tensor_2029 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1486, 0.00035828881664201617, 31639, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4331145Z     %view_109 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_2023, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.4331837Z     %quantize_per_tensor_1487 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_109, 0.0004303281893953681, 32305, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4332864Z     %dequantize_per_tensor_2030 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1487, 0.0004303281893953681, 32305, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4333310Z     %view_110 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_2028, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.4334049Z     %quantize_per_tensor_1488 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_110, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4334824Z     %dequantize_per_tensor_2031 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1488, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4335325Z     %_to_copy_18 : [num_users=1] = call_function[target=torch.ops.aten._to_copy.default](args = (%dequantize_per_tensor_2029,), kwargs = {dtype: torch.float32})
2025-03-21T20:30:48.4336033Z     %quantize_per_tensor_1489 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%_to_copy_18, 0.00035828881664201617, 31639, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4336859Z     %dequantize_per_tensor_2032 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1489, 0.00035828881664201617, 31639, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4337312Z     %view_111 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_2032, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:30:48.4338021Z     %quantize_per_tensor_1490 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_111, 0.00035828881664201617, 31639, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4338800Z     %dequantize_per_tensor_2033 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1490, 0.00035828881664201617, 31639, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4339223Z     %unbind_18 : [num_users=2] = call_function[target=torch.ops.aten.unbind.int](args = (%dequantize_per_tensor_2033, -1), kwargs = {})
2025-03-21T20:30:48.4339540Z     %getitem_36 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_18, 0), kwargs = {})
2025-03-21T20:30:48.4339871Z     %getitem_37 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_18, 1), kwargs = {})
2025-03-21T20:30:48.4340576Z     %quantize_per_tensor_1491 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_36, 0.00035828881664201617, 31639, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4341375Z     %dequantize_per_tensor_2034 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1491, 0.00035828881664201617, 31639, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4342153Z     %dequantize_per_tensor_2035 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1491, 0.00035828881664201617, 31639, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4342875Z     %quantize_per_tensor_1492 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_37, 0.00032475838088430464, 31202, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4343649Z     %dequantize_per_tensor_2036 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1492, 0.00032475838088430464, 31202, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4344490Z     %dequantize_per_tensor_2037 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1492, 0.00032475838088430464, 31202, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4344970Z     %_to_copy_19 : [num_users=1] = call_function[target=torch.ops.aten._to_copy.default](args = (%dequantize_per_tensor_2030,), kwargs = {dtype: torch.float32})
2025-03-21T20:30:48.4345707Z     %quantize_per_tensor_1493 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%_to_copy_19, 0.0004303281893953681, 32305, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4346482Z     %dequantize_per_tensor_2038 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1493, 0.0004303281893953681, 32305, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4346953Z     %view_112 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_2038, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:30:48.4347645Z     %quantize_per_tensor_1494 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_112, 0.0004303281893953681, 32305, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4348458Z     %dequantize_per_tensor_2039 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1494, 0.0004303281893953681, 32305, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4348859Z     %unbind_19 : [num_users=2] = call_function[target=torch.ops.aten.unbind.int](args = (%dequantize_per_tensor_2039, -1), kwargs = {})
2025-03-21T20:30:48.4349194Z     %getitem_38 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_19, 0), kwargs = {})
2025-03-21T20:30:48.4349507Z     %getitem_39 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_19, 1), kwargs = {})
2025-03-21T20:30:48.4350207Z     %quantize_per_tensor_1495 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_38, 0.000411502318456769, 33783, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4350990Z     %dequantize_per_tensor_2040 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1495, 0.000411502318456769, 33783, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4351754Z     %dequantize_per_tensor_2041 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1495, 0.000411502318456769, 33783, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4352464Z     %quantize_per_tensor_1496 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_39, 0.0004275636747479439, 32090, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4353237Z     %dequantize_per_tensor_2042 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1496, 0.0004275636747479439, 32090, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4354018Z     %dequantize_per_tensor_2043 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1496, 0.0004275636747479439, 32090, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4354455Z     %view_113 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_153, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:30:48.4355158Z     %quantize_per_tensor_1497 : [num_users=4] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_113, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4355955Z     %dequantize_per_tensor_2044 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1497, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4356761Z     %dequantize_per_tensor_2045 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1497, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4357552Z     %dequantize_per_tensor_2046 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1497, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4358333Z     %dequantize_per_tensor_2047 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1497, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4358772Z     %view_114 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_165, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:30:48.4359472Z     %quantize_per_tensor_1498 : [num_users=4] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_114, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4360271Z     %dequantize_per_tensor_2048 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1498, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4361048Z     %dequantize_per_tensor_2049 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1498, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4361828Z     %dequantize_per_tensor_2050 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1498, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4362599Z     %dequantize_per_tensor_2051 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1498, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4363087Z     %mul_99 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_2035, %dequantize_per_tensor_2047), kwargs = {})
2025-03-21T20:30:48.4363768Z     %quantize_per_tensor_1499 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_99, 0.0003548612876329571, 31922, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4364540Z     %dequantize_per_tensor_2052 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1499, 0.0003548612876329571, 31922, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4365028Z     %mul_100 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_2036, %dequantize_per_tensor_2050), kwargs = {})
2025-03-21T20:30:48.4365718Z     %quantize_per_tensor_1500 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_100, 0.00014130776980891824, 32945, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4366504Z     %dequantize_per_tensor_2053 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1500, 0.00014130776980891824, 32945, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4366974Z     %sub_18 : [num_users=1] = call_function[target=torch.ops.aten.sub.Tensor](args = (%dequantize_per_tensor_2052, %dequantize_per_tensor_2053), kwargs = {})
2025-03-21T20:30:48.4367726Z     %quantize_per_tensor_1501 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%sub_18, 0.00035090342862531543, 32108, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4368504Z     %dequantize_per_tensor_2054 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1501, 0.00035090342862531543, 32108, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4369013Z     %mul_101 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_2034, %dequantize_per_tensor_2051), kwargs = {})
2025-03-21T20:30:48.4369765Z     %quantize_per_tensor_1502 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_101, 0.00016020808834582567, 31073, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4370560Z     %dequantize_per_tensor_2055 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1502, 0.00016020808834582567, 31073, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4371036Z     %mul_102 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_2037, %dequantize_per_tensor_2046), kwargs = {})
2025-03-21T20:30:48.4371765Z     %quantize_per_tensor_1503 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_102, 0.0003209649003110826, 31569, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4372538Z     %dequantize_per_tensor_2056 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1503, 0.0003209649003110826, 31569, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4373026Z     %add_45 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_2055, %dequantize_per_tensor_2056), kwargs = {})
2025-03-21T20:30:48.4373718Z     %quantize_per_tensor_1504 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_45, 0.00031776822288520634, 31840, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4374509Z     %dequantize_per_tensor_2057 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1504, 0.00031776822288520634, 31840, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4374985Z     %mul_103 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_2041, %dequantize_per_tensor_2045), kwargs = {})
2025-03-21T20:30:48.4375687Z     %quantize_per_tensor_1505 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_103, 0.00040689806337468326, 33489, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4376463Z     %dequantize_per_tensor_2058 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1505, 0.00040689806337468326, 33489, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4376950Z     %mul_104 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_2042, %dequantize_per_tensor_2048), kwargs = {})
2025-03-21T20:30:48.4377642Z     %quantize_per_tensor_1506 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_104, 0.00016605170094408095, 36087, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4378432Z     %dequantize_per_tensor_2059 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1506, 0.00016605170094408095, 36087, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4378939Z     %sub_19 : [num_users=1] = call_function[target=torch.ops.aten.sub.Tensor](args = (%dequantize_per_tensor_2058, %dequantize_per_tensor_2059), kwargs = {})
2025-03-21T20:30:48.4379663Z     %quantize_per_tensor_1507 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%sub_19, 0.0004013704019598663, 32912, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4380442Z     %dequantize_per_tensor_2060 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1507, 0.0004013704019598663, 32912, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4380955Z     %mul_105 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_2040, %dequantize_per_tensor_2049), kwargs = {})
2025-03-21T20:30:48.4381650Z     %quantize_per_tensor_1508 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_105, 0.0001810029789339751, 34754, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4382444Z     %dequantize_per_tensor_2061 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1508, 0.0001810029789339751, 34754, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4382948Z     %mul_106 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_2043, %dequantize_per_tensor_2044), kwargs = {})
2025-03-21T20:30:48.4383654Z     %quantize_per_tensor_1509 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_106, 0.00041482385131530464, 31860, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4384435Z     %dequantize_per_tensor_2062 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1509, 0.00041482385131530464, 31860, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4384924Z     %add_46 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_2061, %dequantize_per_tensor_2062), kwargs = {})
2025-03-21T20:30:48.4385611Z     %quantize_per_tensor_1510 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_46, 0.0004134253249503672, 31723, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4386399Z     %dequantize_per_tensor_2063 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1510, 0.0004134253249503672, 31723, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4386922Z     %stack_18 : [num_users=1] = call_function[target=torch.ops.aten.stack.default](args = ([%dequantize_per_tensor_2054, %dequantize_per_tensor_2057], -1), kwargs = {})
2025-03-21T20:30:48.4387630Z     %quantize_per_tensor_1511 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%stack_18, 0.00035090342862531543, 32108, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4388411Z     %dequantize_per_tensor_2064 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1511, 0.00035090342862531543, 32108, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4388872Z     %view_115 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_2064, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.4389567Z     %quantize_per_tensor_1512 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_115, 0.00035090342862531543, 32108, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4390355Z     %dequantize_per_tensor_2065 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1512, 0.00035090342862531543, 32108, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4390904Z     %stack_19 : [num_users=1] = call_function[target=torch.ops.aten.stack.default](args = ([%dequantize_per_tensor_2060, %dequantize_per_tensor_2063], -1), kwargs = {})
2025-03-21T20:30:48.4391634Z     %quantize_per_tensor_1513 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%stack_19, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4392415Z     %dequantize_per_tensor_2066 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1513, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4392895Z     %view_116 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_2066, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.4393592Z     %quantize_per_tensor_1514 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_116, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4394382Z     %dequantize_per_tensor_2067 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1514, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4394909Z     %type_as_18 : [num_users=1] = call_function[target=torch.ops.aten.type_as.default](args = (%dequantize_per_tensor_2065, %dequantize_per_tensor_2029), kwargs = {})
2025-03-21T20:30:48.4395620Z     %quantize_per_tensor_1515 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%type_as_18, 0.00035090342862531543, 32108, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4396399Z     %dequantize_per_tensor_2068 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1515, 0.00035090342862531543, 32108, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4396912Z     %type_as_19 : [num_users=1] = call_function[target=torch.ops.aten.type_as.default](args = (%dequantize_per_tensor_2067, %dequantize_per_tensor_2030), kwargs = {})
2025-03-21T20:30:48.4397609Z     %quantize_per_tensor_1516 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%type_as_19, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4398401Z     %dequantize_per_tensor_2069 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1516, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4398844Z     %transpose_375 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2068, 1, 2), kwargs = {})
2025-03-21T20:30:48.4399581Z     %quantize_per_tensor_1517 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_375, 0.00035090342862531543, 32108, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4400356Z     %dequantize_per_tensor_2070 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1517, 0.00035090342862531543, 32108, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4400997Z     %index_put_18 : [num_users=1] = call_function[target=torch.ops.aten.index_put.default](args = (%dequantize_per_tensor_140, [None, %attn_options_input_pos], %dequantize_per_tensor_2069), kwargs = {})
2025-03-21T20:30:48.4401706Z     %quantize_per_tensor_1518 : [num_users=13] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_put_18, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4402544Z     %dequantize_per_tensor_2071 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1518, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4403347Z     %dequantize_per_tensor_2072 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1518, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4404132Z     %dequantize_per_tensor_2073 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1518, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4404928Z     %dequantize_per_tensor_2074 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1518, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4405713Z     %dequantize_per_tensor_2075 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1518, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4406489Z     %dequantize_per_tensor_2076 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1518, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4407300Z     %dequantize_per_tensor_2077 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1518, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4408073Z     %dequantize_per_tensor_2078 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1518, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4408857Z     %dequantize_per_tensor_2079 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1518, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4409682Z     %dequantize_per_tensor_2080 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1518, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4410475Z     %dequantize_per_tensor_2081 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1518, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4411249Z     %dequantize_per_tensor_2082 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1518, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4412036Z     %dequantize_per_tensor_2083 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1518, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4412665Z     %index_put_19 : [num_users=1] = call_function[target=torch.ops.aten.index_put.default](args = (%dequantize_per_tensor_141, [None, %attn_options_input_pos], %dequantize_per_tensor_2031), kwargs = {})
2025-03-21T20:30:48.4413387Z     %quantize_per_tensor_1519 : [num_users=13] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_put_19, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4414161Z     %dequantize_per_tensor_2084 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1519, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4414972Z     %dequantize_per_tensor_2085 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1519, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4415769Z     %dequantize_per_tensor_2086 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1519, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4416575Z     %dequantize_per_tensor_2087 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1519, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4417345Z     %dequantize_per_tensor_2088 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1519, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4418129Z     %dequantize_per_tensor_2089 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1519, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4418934Z     %dequantize_per_tensor_2090 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1519, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4419715Z     %dequantize_per_tensor_2091 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1519, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4420497Z     %dequantize_per_tensor_2092 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1519, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4421267Z     %dequantize_per_tensor_2093 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1519, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4422048Z     %dequantize_per_tensor_2094 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1519, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4422822Z     %dequantize_per_tensor_2095 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1519, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4423602Z     %dequantize_per_tensor_2096 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1519, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4424049Z     %transpose_376 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2083, 1, 2), kwargs = {})
2025-03-21T20:30:48.4424779Z     %quantize_per_tensor_1520 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_376, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4425556Z     %dequantize_per_tensor_2097 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1520, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4425982Z     %select_432 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2097, 0, 0), kwargs = {})
2025-03-21T20:30:48.4426712Z     %quantize_per_tensor_1521 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_432, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4427526Z     %dequantize_per_tensor_2098 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1521, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4427936Z     %select_433 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2098, 0, 0), kwargs = {})
2025-03-21T20:30:48.4428664Z     %quantize_per_tensor_1522 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_433, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4429454Z     %dequantize_per_tensor_2099 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1522, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4429899Z     %transpose_377 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2082, 1, 2), kwargs = {})
2025-03-21T20:30:48.4430631Z     %quantize_per_tensor_1523 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_377, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4431429Z     %dequantize_per_tensor_2100 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1523, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4431850Z     %select_434 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2100, 0, 0), kwargs = {})
2025-03-21T20:30:48.4432681Z     %quantize_per_tensor_1524 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_434, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4433476Z     %dequantize_per_tensor_2101 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1524, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4433890Z     %select_435 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2101, 0, 1), kwargs = {})
2025-03-21T20:30:48.4434611Z     %quantize_per_tensor_1525 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_435, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4435385Z     %dequantize_per_tensor_2102 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1525, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4435849Z     %transpose_378 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2081, 1, 2), kwargs = {})
2025-03-21T20:30:48.4436573Z     %quantize_per_tensor_1526 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_378, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4437367Z     %dequantize_per_tensor_2103 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1526, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4437781Z     %select_436 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2103, 0, 0), kwargs = {})
2025-03-21T20:30:48.4438560Z     %quantize_per_tensor_1527 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_436, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4439368Z     %dequantize_per_tensor_2104 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1527, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4439791Z     %select_437 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2104, 0, 2), kwargs = {})
2025-03-21T20:30:48.4440533Z     %quantize_per_tensor_1528 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_437, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4441324Z     %dequantize_per_tensor_2105 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1528, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4441769Z     %transpose_379 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2080, 1, 2), kwargs = {})
2025-03-21T20:30:48.4442499Z     %quantize_per_tensor_1529 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_379, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4443314Z     %dequantize_per_tensor_2106 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1529, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4443739Z     %select_438 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2106, 0, 0), kwargs = {})
2025-03-21T20:30:48.4444448Z     %quantize_per_tensor_1530 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_438, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4445235Z     %dequantize_per_tensor_2107 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1530, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4445647Z     %select_439 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2107, 0, 3), kwargs = {})
2025-03-21T20:30:48.4446365Z     %quantize_per_tensor_1531 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_439, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4447142Z     %dequantize_per_tensor_2108 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1531, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4447596Z     %transpose_380 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2079, 1, 2), kwargs = {})
2025-03-21T20:30:48.4448315Z     %quantize_per_tensor_1532 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_380, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4449104Z     %dequantize_per_tensor_2109 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1532, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4449575Z     %select_440 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2109, 0, 0), kwargs = {})
2025-03-21T20:30:48.4450324Z     %quantize_per_tensor_1533 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_440, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4451125Z     %dequantize_per_tensor_2110 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1533, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4451554Z     %select_441 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2110, 0, 4), kwargs = {})
2025-03-21T20:30:48.4452288Z     %quantize_per_tensor_1534 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_441, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4453083Z     %dequantize_per_tensor_2111 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1534, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4453528Z     %transpose_381 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2078, 1, 2), kwargs = {})
2025-03-21T20:30:48.4454267Z     %quantize_per_tensor_1535 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_381, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4455073Z     %dequantize_per_tensor_2112 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1535, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4455499Z     %select_442 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2112, 0, 0), kwargs = {})
2025-03-21T20:30:48.4456209Z     %quantize_per_tensor_1536 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_442, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4457001Z     %dequantize_per_tensor_2113 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1536, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4457418Z     %select_443 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2113, 0, 5), kwargs = {})
2025-03-21T20:30:48.4458139Z     %quantize_per_tensor_1537 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_443, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4458919Z     %dequantize_per_tensor_2114 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1537, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4459379Z     %transpose_382 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2077, 1, 2), kwargs = {})
2025-03-21T20:30:48.4460099Z     %quantize_per_tensor_1538 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_382, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4460895Z     %dequantize_per_tensor_2115 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1538, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4461308Z     %select_444 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2115, 0, 0), kwargs = {})
2025-03-21T20:30:48.4462054Z     %quantize_per_tensor_1539 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_444, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4462858Z     %dequantize_per_tensor_2116 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1539, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4463286Z     %select_445 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2116, 0, 6), kwargs = {})
2025-03-21T20:30:48.4464025Z     %quantize_per_tensor_1540 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_445, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4464819Z     %dequantize_per_tensor_2117 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1540, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4465264Z     %transpose_383 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2076, 1, 2), kwargs = {})
2025-03-21T20:30:48.4465997Z     %quantize_per_tensor_1541 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_383, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4466803Z     %dequantize_per_tensor_2118 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1541, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4467226Z     %select_446 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2118, 0, 0), kwargs = {})
2025-03-21T20:30:48.4467934Z     %quantize_per_tensor_1542 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_446, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4468728Z     %dequantize_per_tensor_2119 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1542, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4469140Z     %select_447 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2119, 0, 7), kwargs = {})
2025-03-21T20:30:48.4469862Z     %quantize_per_tensor_1543 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_447, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4470636Z     %dequantize_per_tensor_2120 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1543, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4471093Z     %transpose_384 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2075, 1, 2), kwargs = {})
2025-03-21T20:30:48.4471811Z     %quantize_per_tensor_1544 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_384, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4472604Z     %dequantize_per_tensor_2121 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1544, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4473012Z     %select_448 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2121, 0, 0), kwargs = {})
2025-03-21T20:30:48.4473756Z     %quantize_per_tensor_1545 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_448, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4474558Z     %dequantize_per_tensor_2122 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1545, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4474985Z     %select_449 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2122, 0, 8), kwargs = {})
2025-03-21T20:30:48.4475712Z     %quantize_per_tensor_1546 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_449, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4476502Z     %dequantize_per_tensor_2123 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1546, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4476943Z     %transpose_385 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2074, 1, 2), kwargs = {})
2025-03-21T20:30:48.4477660Z     %quantize_per_tensor_1547 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_385, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4478475Z     %dequantize_per_tensor_2124 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1547, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4478883Z     %select_450 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2124, 0, 0), kwargs = {})
2025-03-21T20:30:48.4479602Z     %quantize_per_tensor_1548 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_450, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4480383Z     %dequantize_per_tensor_2125 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1548, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4480810Z     %select_451 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2125, 0, 9), kwargs = {})
2025-03-21T20:30:48.4481521Z     %quantize_per_tensor_1549 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_451, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4482313Z     %dequantize_per_tensor_2126 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1549, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4482759Z     %transpose_386 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2073, 1, 2), kwargs = {})
2025-03-21T20:30:48.4483494Z     %quantize_per_tensor_1550 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_386, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4484277Z     %dequantize_per_tensor_2127 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1550, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4484700Z     %select_452 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2127, 0, 0), kwargs = {})
2025-03-21T20:30:48.4485437Z     %quantize_per_tensor_1551 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_452, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4486255Z     %dequantize_per_tensor_2128 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1551, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4486674Z     %select_453 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2128, 0, 10), kwargs = {})
2025-03-21T20:30:48.4487418Z     %quantize_per_tensor_1552 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_453, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4488195Z     %dequantize_per_tensor_2129 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1552, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4488655Z     %transpose_387 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2072, 1, 2), kwargs = {})
2025-03-21T20:30:48.4489455Z     %quantize_per_tensor_1553 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_387, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4490252Z     %dequantize_per_tensor_2130 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1553, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4490662Z     %select_454 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2130, 0, 0), kwargs = {})
2025-03-21T20:30:48.4491380Z     %quantize_per_tensor_1554 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_454, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4492155Z     %dequantize_per_tensor_2131 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1554, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4492584Z     %select_455 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2131, 0, 11), kwargs = {})
2025-03-21T20:30:48.4493294Z     %quantize_per_tensor_1555 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_455, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4494084Z     %dequantize_per_tensor_2132 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1555, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4495582Z     %cat_18 : [num_users=1] = call_function[target=torch.ops.aten.cat.default](args = ([%dequantize_per_tensor_2099, %dequantize_per_tensor_2102, %dequantize_per_tensor_2105, %dequantize_per_tensor_2108, %dequantize_per_tensor_2111, %dequantize_per_tensor_2114, %dequantize_per_tensor_2117, %dequantize_per_tensor_2120, %dequantize_per_tensor_2123, %dequantize_per_tensor_2126, %dequantize_per_tensor_2129, %dequantize_per_tensor_2132],), kwargs = {})
2025-03-21T20:30:48.4496288Z     %quantize_per_tensor_1556 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%cat_18, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4497073Z     %dequantize_per_tensor_2133 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1556, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4497591Z     %view_117 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_2133, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:30:48.4498289Z     %quantize_per_tensor_1557 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_117, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4499101Z     %dequantize_per_tensor_2134 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1557, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4499547Z     %transpose_388 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2096, 1, 2), kwargs = {})
2025-03-21T20:30:48.4500277Z     %quantize_per_tensor_1558 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_388, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4501049Z     %dequantize_per_tensor_2135 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1558, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4501497Z     %select_456 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2135, 0, 0), kwargs = {})
2025-03-21T20:30:48.4502203Z     %quantize_per_tensor_1559 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_456, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4502983Z     %dequantize_per_tensor_2136 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1559, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4503398Z     %select_457 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2136, 0, 0), kwargs = {})
2025-03-21T20:30:48.4504110Z     %quantize_per_tensor_1560 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_457, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4504884Z     %dequantize_per_tensor_2137 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1560, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4505339Z     %transpose_389 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2095, 1, 2), kwargs = {})
2025-03-21T20:30:48.4506055Z     %quantize_per_tensor_1561 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_389, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4506839Z     %dequantize_per_tensor_2138 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1561, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4507255Z     %select_458 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2138, 0, 0), kwargs = {})
2025-03-21T20:30:48.4507969Z     %quantize_per_tensor_1562 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_458, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4508745Z     %dequantize_per_tensor_2139 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1562, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4509226Z     %select_459 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2139, 0, 1), kwargs = {})
2025-03-21T20:30:48.4509929Z     %quantize_per_tensor_1563 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_459, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4510740Z     %dequantize_per_tensor_2140 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1563, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4511184Z     %transpose_390 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2094, 1, 2), kwargs = {})
2025-03-21T20:30:48.4511915Z     %quantize_per_tensor_1564 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_390, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4512686Z     %dequantize_per_tensor_2141 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1564, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4513132Z     %select_460 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2141, 0, 0), kwargs = {})
2025-03-21T20:30:48.4513833Z     %quantize_per_tensor_1565 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_460, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4514616Z     %dequantize_per_tensor_2142 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1565, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4515029Z     %select_461 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2142, 0, 2), kwargs = {})
2025-03-21T20:30:48.4515740Z     %quantize_per_tensor_1566 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_461, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4516513Z     %dequantize_per_tensor_2143 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1566, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4516967Z     %transpose_391 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2093, 1, 2), kwargs = {})
2025-03-21T20:30:48.4517687Z     %quantize_per_tensor_1567 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_391, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4518473Z     %dequantize_per_tensor_2144 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1567, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4518887Z     %select_462 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2144, 0, 0), kwargs = {})
2025-03-21T20:30:48.4519600Z     %quantize_per_tensor_1568 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_462, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4520372Z     %dequantize_per_tensor_2145 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1568, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4520852Z     %select_463 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2145, 0, 3), kwargs = {})
2025-03-21T20:30:48.4521554Z     %quantize_per_tensor_1569 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_463, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4522364Z     %dequantize_per_tensor_2146 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1569, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4522808Z     %transpose_392 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2092, 1, 2), kwargs = {})
2025-03-21T20:30:48.4523537Z     %quantize_per_tensor_1570 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_392, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4524312Z     %dequantize_per_tensor_2147 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1570, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4524762Z     %select_464 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2147, 0, 0), kwargs = {})
2025-03-21T20:30:48.4525462Z     %quantize_per_tensor_1571 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_464, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4526247Z     %dequantize_per_tensor_2148 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1571, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4526659Z     %select_465 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2148, 0, 4), kwargs = {})
2025-03-21T20:30:48.4527372Z     %quantize_per_tensor_1572 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_465, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4528147Z     %dequantize_per_tensor_2149 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1572, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4528601Z     %transpose_393 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2091, 1, 2), kwargs = {})
2025-03-21T20:30:48.4529377Z     %quantize_per_tensor_1573 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_393, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4530164Z     %dequantize_per_tensor_2150 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1573, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4530576Z     %select_466 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2150, 0, 0), kwargs = {})
2025-03-21T20:30:48.4531296Z     %quantize_per_tensor_1574 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_466, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4532066Z     %dequantize_per_tensor_2151 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1574, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4532720Z     %select_467 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2151, 0, 5), kwargs = {})
2025-03-21T20:30:48.4533422Z     %quantize_per_tensor_1575 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_467, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4534236Z     %dequantize_per_tensor_2152 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1575, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4534679Z     %transpose_394 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2090, 1, 2), kwargs = {})
2025-03-21T20:30:48.4535408Z     %quantize_per_tensor_1576 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_394, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4536181Z     %dequantize_per_tensor_2153 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1576, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4536633Z     %select_468 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2153, 0, 0), kwargs = {})
2025-03-21T20:30:48.4537335Z     %quantize_per_tensor_1577 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_468, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4538104Z     %dequantize_per_tensor_2154 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1577, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4538531Z     %select_469 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2154, 0, 6), kwargs = {})
2025-03-21T20:30:48.4539233Z     %quantize_per_tensor_1578 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_469, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4540019Z     %dequantize_per_tensor_2155 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1578, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4540463Z     %transpose_395 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2089, 1, 2), kwargs = {})
2025-03-21T20:30:48.4541193Z     %quantize_per_tensor_1579 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_395, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4541966Z     %dequantize_per_tensor_2156 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1579, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4542388Z     %select_470 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2156, 0, 0), kwargs = {})
2025-03-21T20:30:48.4543091Z     %quantize_per_tensor_1580 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_470, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4543874Z     %dequantize_per_tensor_2157 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1580, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4544339Z     %select_471 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2157, 0, 7), kwargs = {})
2025-03-21T20:30:48.4545052Z     %quantize_per_tensor_1581 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_471, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4545823Z     %dequantize_per_tensor_2158 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1581, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4546300Z     %transpose_396 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2088, 1, 2), kwargs = {})
2025-03-21T20:30:48.4547019Z     %quantize_per_tensor_1582 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_396, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4547806Z     %dequantize_per_tensor_2159 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1582, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4548244Z     %select_472 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2159, 0, 0), kwargs = {})
2025-03-21T20:30:48.4548966Z     %quantize_per_tensor_1583 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_472, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4549738Z     %dequantize_per_tensor_2160 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1583, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4550165Z     %select_473 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2160, 0, 8), kwargs = {})
2025-03-21T20:30:48.4550866Z     %quantize_per_tensor_1584 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_473, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4551648Z     %dequantize_per_tensor_2161 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1584, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4552091Z     %transpose_397 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2087, 1, 2), kwargs = {})
2025-03-21T20:30:48.4552817Z     %quantize_per_tensor_1585 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_397, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4553591Z     %dequantize_per_tensor_2162 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1585, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4554016Z     %select_474 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2162, 0, 0), kwargs = {})
2025-03-21T20:30:48.4554718Z     %quantize_per_tensor_1586 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_474, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4555500Z     %dequantize_per_tensor_2163 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1586, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4555968Z     %select_475 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2163, 0, 9), kwargs = {})
2025-03-21T20:30:48.4556681Z     %quantize_per_tensor_1587 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_475, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4557452Z     %dequantize_per_tensor_2164 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1587, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4557927Z     %transpose_398 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2086, 1, 2), kwargs = {})
2025-03-21T20:30:48.4558646Z     %quantize_per_tensor_1588 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_398, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4559437Z     %dequantize_per_tensor_2165 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1588, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4559872Z     %select_476 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2165, 0, 0), kwargs = {})
2025-03-21T20:30:48.4560591Z     %quantize_per_tensor_1589 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_476, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4561364Z     %dequantize_per_tensor_2166 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1589, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4561794Z     %select_477 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2166, 0, 10), kwargs = {})
2025-03-21T20:30:48.4562495Z     %quantize_per_tensor_1590 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_477, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4563281Z     %dequantize_per_tensor_2167 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1590, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4563727Z     %transpose_399 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2085, 1, 2), kwargs = {})
2025-03-21T20:30:48.4564456Z     %quantize_per_tensor_1591 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_399, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4565233Z     %dequantize_per_tensor_2168 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1591, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4565663Z     %select_478 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2168, 0, 0), kwargs = {})
2025-03-21T20:30:48.4566365Z     %quantize_per_tensor_1592 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_478, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4567150Z     %dequantize_per_tensor_2169 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1592, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4567587Z     %select_479 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2169, 0, 11), kwargs = {})
2025-03-21T20:30:48.4568323Z     %quantize_per_tensor_1593 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_479, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4569096Z     %dequantize_per_tensor_2170 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1593, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4570694Z     %cat_19 : [num_users=1] = call_function[target=torch.ops.aten.cat.default](args = ([%dequantize_per_tensor_2137, %dequantize_per_tensor_2140, %dequantize_per_tensor_2143, %dequantize_per_tensor_2146, %dequantize_per_tensor_2149, %dequantize_per_tensor_2152, %dequantize_per_tensor_2155, %dequantize_per_tensor_2158, %dequantize_per_tensor_2161, %dequantize_per_tensor_2164, %dequantize_per_tensor_2167, %dequantize_per_tensor_2170],), kwargs = {})
2025-03-21T20:30:48.4571388Z     %quantize_per_tensor_1594 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%cat_19, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4572205Z     %dequantize_per_tensor_2171 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1594, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4572655Z     %view_118 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_2171, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:30:48.4573360Z     %quantize_per_tensor_1595 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_118, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4574136Z     %dequantize_per_tensor_2172 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1595, 0.0001724863686831668, 32338, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4574921Z     %quantize_per_tensor_1596 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%dequantize_per_tensor_2172, 0.0001747508649714291, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.4575701Z     %dequantize_per_tensor_2173 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1596, 0.0001747508649714291, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.4576203Z     %index_11 : [num_users=1] = call_function[target=torch.ops.aten.index.Tensor](args = (%dequantize_per_tensor_142, [%attn_options_input_pos]), kwargs = {})
2025-03-21T20:30:48.4576896Z     %quantize_per_tensor_1597 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_11, 0.0038910505827516317, 65535, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4577686Z     %dequantize_per_tensor_2174 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1597, 0.0038910505827516317, 65535, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4578139Z     %transpose_400 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2134, -2, -1), kwargs = {})
2025-03-21T20:30:48.4578882Z     %quantize_per_tensor_1598 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_400, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4579678Z     %dequantize_per_tensor_2175 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1598, 0.00041487260023131967, 31841, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4580484Z     %quantize_per_tensor_1599 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%dequantize_per_tensor_2175, 0.0004266138712409884, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.4581260Z     %dequantize_per_tensor_2176 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1599, 0.0004266138712409884, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.4581802Z     %matmul_18 : [num_users=1] = call_function[target=torch.ops.aten.matmul.default](args = (%dequantize_per_tensor_2070, %dequantize_per_tensor_2176), kwargs = {})
2025-03-21T20:30:48.4582506Z     %quantize_per_tensor_1600 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%matmul_18, 0.0032424358651041985, 35894, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4583292Z     %dequantize_per_tensor_2177 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1600, 0.0032424358651041985, 35894, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4584085Z     %dequantize_per_tensor_2178 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param158, 1.9073777366429567e-06, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4584582Z     %mul_107 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_2177, %dequantize_per_tensor_2178), kwargs = {})
2025-03-21T20:30:48.4585274Z     %quantize_per_tensor_1601 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_107, 0.0004053044831380248, 35894, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4586068Z     %dequantize_per_tensor_2179 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1601, 0.0004053044831380248, 35894, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4586542Z     %add_47 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_2179, %dequantize_per_tensor_2174), kwargs = {})
2025-03-21T20:30:48.4587242Z     %quantize_per_tensor_1602 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_47, 0.004210181534290314, 63056, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4588013Z     %dequantize_per_tensor_2180 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1602, 0.004210181534290314, 63056, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4588446Z     %softmax_9 : [num_users=1] = call_function[target=torch.ops.aten.softmax.int](args = (%dequantize_per_tensor_2180, -1), kwargs = {})
2025-03-21T20:30:48.4589137Z     %quantize_per_tensor_1603 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%softmax_9, 1.5259021893143654e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4589914Z     %dequantize_per_tensor_2181 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1603, 1.5259021893143654e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4590425Z     %matmul_19 : [num_users=1] = call_function[target=torch.ops.aten.matmul.default](args = (%dequantize_per_tensor_2181, %dequantize_per_tensor_2173), kwargs = {})
2025-03-21T20:30:48.4591133Z     %quantize_per_tensor_1604 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%matmul_19, 0.00012377489474602044, 34871, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4591958Z     %dequantize_per_tensor_2182 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1604, 0.00012377489474602044, 34871, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4592415Z     %transpose_401 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2182, 1, 2), kwargs = {})
2025-03-21T20:30:48.4593156Z     %quantize_per_tensor_1605 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_401, 0.00012377489474602044, 34871, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4593948Z     %dequantize_per_tensor_2183 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1605, 0.00012377489474602044, 34871, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4594378Z     %view_119 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_2183, [1, 1, 768]), kwargs = {})
2025-03-21T20:30:48.4595085Z     %quantize_per_tensor_1606 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_119, 0.00012377489474602044, 34871, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4595894Z     %dequantize_per_tensor_2184 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1606, 0.00012377489474602044, 34871, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4596367Z     %unsqueeze_66 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_2184, -1), kwargs = {})
2025-03-21T20:30:48.4597086Z     %quantize_per_tensor_1607 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_66, 0.00012377489474602044, 34871, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4597877Z     %dequantize_per_tensor_2185 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1607, 0.00012377489474602044, 34871, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4598320Z     %transpose_402 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2185, 1, 2), kwargs = {})
2025-03-21T20:30:48.4599055Z     %quantize_per_tensor_1608 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_402, 0.00012377489474602044, 34871, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4599830Z     %dequantize_per_tensor_2186 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1608, 0.00012377489474602044, 34871, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4600347Z     %conv2d_66 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_2186, %dequantize_per_tensor_86), kwargs = {})
2025-03-21T20:30:48.4601048Z     %quantize_per_tensor_1609 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_66, 0.00013408258382696658, 24208, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4601843Z     %dequantize_per_tensor_2187 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1609, 0.00013408258382696658, 24208, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4602287Z     %transpose_403 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2187, 1, 2), kwargs = {})
2025-03-21T20:30:48.4603041Z     %quantize_per_tensor_1610 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_403, 0.00013408258382696658, 24208, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4603840Z     %dequantize_per_tensor_2188 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1610, 0.00013408258382696658, 24208, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4604271Z     %squeeze_66 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_2188, -1), kwargs = {})
2025-03-21T20:30:48.4604994Z     %quantize_per_tensor_1611 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_66, 0.00013408258382696658, 24208, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4605784Z     %dequantize_per_tensor_2189 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1611, 0.00013408258382696658, 24208, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4606264Z     %add_48 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_2009, %dequantize_per_tensor_2189), kwargs = {})
2025-03-21T20:30:48.4606953Z     %quantize_per_tensor_1612 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_48, 0.002711330307647586, 7452, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4607746Z     %dequantize_per_tensor_2190 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1612, 0.002711330307647586, 7452, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4608526Z     %dequantize_per_tensor_2191 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1612, 0.002711330307647586, 7452, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4609070Z     %rms_norm_19 : [num_users=1] = call_function[target=torch.ops.aten.rms_norm.default](args = (%dequantize_per_tensor_2191, [768], %dequantize_per_tensor_87, 1e-05), kwargs = {})
2025-03-21T20:30:48.4609843Z     %quantize_per_tensor_1613 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%rms_norm_19, 0.00043149059638381004, 21157, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4610625Z     %dequantize_per_tensor_2192 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1613, 0.00043149059638381004, 21157, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4611412Z     %dequantize_per_tensor_2193 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1613, 0.00043149059638381004, 21157, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4611868Z     %unsqueeze_67 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_2193, -1), kwargs = {})
2025-03-21T20:30:48.4612599Z     %quantize_per_tensor_1614 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_67, 0.00043149059638381004, 21157, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4613378Z     %dequantize_per_tensor_2194 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1614, 0.00043149059638381004, 21157, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4613836Z     %transpose_404 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2194, 1, 2), kwargs = {})
2025-03-21T20:30:48.4614557Z     %quantize_per_tensor_1615 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_404, 0.00043149059638381004, 21157, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4615373Z     %dequantize_per_tensor_2195 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1615, 0.00043149059638381004, 21157, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4615904Z     %conv2d_67 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_2195, %dequantize_per_tensor_88), kwargs = {})
2025-03-21T20:30:48.4616634Z     %quantize_per_tensor_1616 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_67, 0.0001975321938516572, 32198, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4617412Z     %dequantize_per_tensor_2196 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1616, 0.0001975321938516572, 32198, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4617871Z     %transpose_405 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2196, 1, 2), kwargs = {})
2025-03-21T20:30:48.4618589Z     %quantize_per_tensor_1617 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_405, 0.0001975321938516572, 32198, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4619395Z     %dequantize_per_tensor_2197 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1617, 0.0001975321938516572, 32198, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4619811Z     %squeeze_67 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_2197, -1), kwargs = {})
2025-03-21T20:30:48.4620515Z     %quantize_per_tensor_1618 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_67, 0.0001975321938516572, 32198, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4621305Z     %dequantize_per_tensor_2198 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1618, 0.0001975321938516572, 32198, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4622093Z     %dequantize_per_tensor_2199 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1618, 0.0001975321938516572, 32198, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4622520Z     %sigmoid_9 : [num_users=1] = call_function[target=torch.ops.aten.sigmoid.default](args = (%dequantize_per_tensor_2199,), kwargs = {})
2025-03-21T20:30:48.4623192Z     %quantize_per_tensor_1619 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%sigmoid_9, 1.52587890625e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4623955Z     %dequantize_per_tensor_2200 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1619, 1.52587890625e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4624439Z     %mul_108 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_2198, %dequantize_per_tensor_2200), kwargs = {})
2025-03-21T20:30:48.4625141Z     %quantize_per_tensor_1620 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_108, 0.0001045933531713672, 2662, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4625911Z     %dequantize_per_tensor_2201 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1620, 0.0001045933531713672, 2662, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4626379Z     %unsqueeze_68 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_2192, -1), kwargs = {})
2025-03-21T20:30:48.4627140Z     %quantize_per_tensor_1621 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_68, 0.00043149059638381004, 21157, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4627937Z     %dequantize_per_tensor_2202 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1621, 0.00043149059638381004, 21157, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4628402Z     %transpose_406 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2202, 1, 2), kwargs = {})
2025-03-21T20:30:48.4629136Z     %quantize_per_tensor_1622 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_406, 0.00043149059638381004, 21157, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4629912Z     %dequantize_per_tensor_2203 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1622, 0.00043149059638381004, 21157, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4630426Z     %conv2d_68 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_2203, %dequantize_per_tensor_89), kwargs = {})
2025-03-21T20:30:48.4631151Z     %quantize_per_tensor_1623 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_68, 0.00024529712391085923, 28114, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4631938Z     %dequantize_per_tensor_2204 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1623, 0.00024529712391085923, 28114, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4632513Z     %transpose_407 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2204, 1, 2), kwargs = {})
2025-03-21T20:30:48.4633248Z     %quantize_per_tensor_1624 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_407, 0.00024529712391085923, 28114, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4634024Z     %dequantize_per_tensor_2205 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1624, 0.00024529712391085923, 28114, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4634452Z     %squeeze_68 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_2205, -1), kwargs = {})
2025-03-21T20:30:48.4635153Z     %quantize_per_tensor_1625 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_68, 0.00024529712391085923, 28114, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4635947Z     %dequantize_per_tensor_2206 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1625, 0.00024529712391085923, 28114, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4636424Z     %mul_109 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_2201, %dequantize_per_tensor_2206), kwargs = {})
2025-03-21T20:30:48.4637128Z     %quantize_per_tensor_1626 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_109, 0.0006203429074957967, 26598, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4637903Z     %dequantize_per_tensor_2207 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1626, 0.0006203429074957967, 26598, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4638373Z     %unsqueeze_69 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_2207, -1), kwargs = {})
2025-03-21T20:30:48.4639165Z     %quantize_per_tensor_1627 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_69, 0.0006203429074957967, 26598, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4639960Z     %dequantize_per_tensor_2208 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1627, 0.0006203429074957967, 26598, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4640443Z     %transpose_408 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2208, 1, 2), kwargs = {})
2025-03-21T20:30:48.4641175Z     %quantize_per_tensor_1628 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_408, 0.0006203429074957967, 26598, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4641949Z     %dequantize_per_tensor_2209 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1628, 0.0006203429074957967, 26598, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4642499Z     %conv2d_69 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_2209, %dequantize_per_tensor_90), kwargs = {})
2025-03-21T20:30:48.4643196Z     %quantize_per_tensor_1629 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_69, 0.0003197697224095464, 32722, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4643977Z     %dequantize_per_tensor_2210 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1629, 0.0003197697224095464, 32722, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4644421Z     %transpose_409 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2210, 1, 2), kwargs = {})
2025-03-21T20:30:48.4645150Z     %quantize_per_tensor_1630 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_409, 0.0003197697224095464, 32722, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4645919Z     %dequantize_per_tensor_2211 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1630, 0.0003197697224095464, 32722, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4646344Z     %squeeze_69 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_2211, -1), kwargs = {})
2025-03-21T20:30:48.4647042Z     %quantize_per_tensor_1631 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_69, 0.0003197697224095464, 32722, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4647825Z     %dequantize_per_tensor_2212 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1631, 0.0003197697224095464, 32722, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4648297Z     %add_49 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_2190, %dequantize_per_tensor_2212), kwargs = {})
2025-03-21T20:30:48.4648983Z     %quantize_per_tensor_1632 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_49, 0.002727663842961192, 9020, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4649806Z     %dequantize_per_tensor_2213 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1632, 0.002727663842961192, 9020, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4650611Z     %dequantize_per_tensor_2214 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1632, 0.002727663842961192, 9020, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4651178Z     %rms_norm_20 : [num_users=1] = call_function[target=torch.ops.aten.rms_norm.default](args = (%dequantize_per_tensor_2214, [768], %dequantize_per_tensor_91, 1e-05), kwargs = {})
2025-03-21T20:30:48.4651885Z     %quantize_per_tensor_1633 : [num_users=3] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%rms_norm_20, 0.000514648447278887, 33371, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4652674Z     %dequantize_per_tensor_2215 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1633, 0.000514648447278887, 33371, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4653455Z     %dequantize_per_tensor_2216 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1633, 0.000514648447278887, 33371, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4654219Z     %dequantize_per_tensor_2217 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1633, 0.000514648447278887, 33371, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4654715Z     %unsqueeze_70 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_2217, -1), kwargs = {})
2025-03-21T20:30:48.4655424Z     %quantize_per_tensor_1634 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_70, 0.000514648447278887, 33371, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4656204Z     %dequantize_per_tensor_2218 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1634, 0.000514648447278887, 33371, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4656650Z     %transpose_410 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2218, 1, 2), kwargs = {})
2025-03-21T20:30:48.4657375Z     %quantize_per_tensor_1635 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_410, 0.000514648447278887, 33371, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4658140Z     %dequantize_per_tensor_2219 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1635, 0.000514648447278887, 33371, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4658655Z     %conv2d_70 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_2219, %dequantize_per_tensor_92), kwargs = {})
2025-03-21T20:30:48.4659348Z     %quantize_per_tensor_1636 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_70, 0.000400586926843971, 33468, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4660131Z     %dequantize_per_tensor_2220 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1636, 0.000400586926843971, 33468, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4660575Z     %transpose_411 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2220, 1, 2), kwargs = {})
2025-03-21T20:30:48.4661301Z     %quantize_per_tensor_1637 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_411, 0.000400586926843971, 33468, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4662092Z     %dequantize_per_tensor_2221 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1637, 0.000400586926843971, 33468, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4662541Z     %squeeze_70 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_2221, -1), kwargs = {})
2025-03-21T20:30:48.4663240Z     %quantize_per_tensor_1638 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_70, 0.000400586926843971, 33468, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4664043Z     %dequantize_per_tensor_2222 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1638, 0.000400586926843971, 33468, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4664501Z     %unsqueeze_71 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_2216, -1), kwargs = {})
2025-03-21T20:30:48.4665220Z     %quantize_per_tensor_1639 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_71, 0.000514648447278887, 33371, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4665989Z     %dequantize_per_tensor_2223 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1639, 0.000514648447278887, 33371, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4666474Z     %transpose_412 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2223, 1, 2), kwargs = {})
2025-03-21T20:30:48.4667184Z     %quantize_per_tensor_1640 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_412, 0.000514648447278887, 33371, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4667965Z     %dequantize_per_tensor_2224 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1640, 0.000514648447278887, 33371, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4668469Z     %conv2d_71 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_2224, %dequantize_per_tensor_93), kwargs = {})
2025-03-21T20:30:48.4669178Z     %quantize_per_tensor_1641 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_71, 0.0004142843827139586, 29754, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4669948Z     %dequantize_per_tensor_2225 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1641, 0.0004142843827139586, 29754, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4670404Z     %transpose_413 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2225, 1, 2), kwargs = {})
2025-03-21T20:30:48.4671120Z     %quantize_per_tensor_1642 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_413, 0.0004142843827139586, 29754, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4671902Z     %dequantize_per_tensor_2226 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1642, 0.0004142843827139586, 29754, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4672315Z     %squeeze_71 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_2226, -1), kwargs = {})
2025-03-21T20:30:48.4673028Z     %quantize_per_tensor_1643 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_71, 0.0004142843827139586, 29754, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4673826Z     %dequantize_per_tensor_2227 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1643, 0.0004142843827139586, 29754, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4674316Z     %unsqueeze_72 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_2215, -1), kwargs = {})
2025-03-21T20:30:48.4675029Z     %quantize_per_tensor_1644 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_72, 0.000514648447278887, 33371, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4675829Z     %dequantize_per_tensor_2228 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1644, 0.000514648447278887, 33371, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4676272Z     %transpose_414 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2228, 1, 2), kwargs = {})
2025-03-21T20:30:48.4676997Z     %quantize_per_tensor_1645 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_414, 0.000514648447278887, 33371, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4677768Z     %dequantize_per_tensor_2229 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1645, 0.000514648447278887, 33371, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4678310Z     %conv2d_72 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_2229, %dequantize_per_tensor_94), kwargs = {})
2025-03-21T20:30:48.4679011Z     %quantize_per_tensor_1646 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_72, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4679804Z     %dequantize_per_tensor_2230 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1646, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4680248Z     %transpose_415 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2230, 1, 2), kwargs = {})
2025-03-21T20:30:48.4680987Z     %quantize_per_tensor_1647 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_415, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4681765Z     %dequantize_per_tensor_2231 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1647, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4682189Z     %squeeze_72 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_2231, -1), kwargs = {})
2025-03-21T20:30:48.4682895Z     %quantize_per_tensor_1648 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_72, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4683691Z     %dequantize_per_tensor_2232 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1648, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4684138Z     %view_120 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_2222, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.4684831Z     %quantize_per_tensor_1649 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_120, 0.000400586926843971, 33468, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4685643Z     %dequantize_per_tensor_2233 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1649, 0.000400586926843971, 33468, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4686147Z     %view_121 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_2227, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.4686860Z     %quantize_per_tensor_1650 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_121, 0.0004142843827139586, 29754, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4687659Z     %dequantize_per_tensor_2234 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1650, 0.0004142843827139586, 29754, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4688121Z     %view_122 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_2232, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.4688825Z     %quantize_per_tensor_1651 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_122, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4689675Z     %dequantize_per_tensor_2235 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1651, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4690187Z     %_to_copy_20 : [num_users=1] = call_function[target=torch.ops.aten._to_copy.default](args = (%dequantize_per_tensor_2233,), kwargs = {dtype: torch.float32})
2025-03-21T20:30:48.4690897Z     %quantize_per_tensor_1652 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%_to_copy_20, 0.000400586926843971, 33468, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4691670Z     %dequantize_per_tensor_2236 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1652, 0.000400586926843971, 33468, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4692142Z     %view_123 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_2236, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:30:48.4692835Z     %quantize_per_tensor_1653 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_123, 0.000400586926843971, 33468, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4693620Z     %dequantize_per_tensor_2237 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1653, 0.000400586926843971, 33468, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4694024Z     %unbind_20 : [num_users=2] = call_function[target=torch.ops.aten.unbind.int](args = (%dequantize_per_tensor_2237, -1), kwargs = {})
2025-03-21T20:30:48.4694356Z     %getitem_40 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_20, 0), kwargs = {})
2025-03-21T20:30:48.4694668Z     %getitem_41 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_20, 1), kwargs = {})
2025-03-21T20:30:48.4695383Z     %quantize_per_tensor_1654 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_40, 0.0003711249737534672, 36125, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4696155Z     %dequantize_per_tensor_2238 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1654, 0.0003711249737534672, 36125, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4696937Z     %dequantize_per_tensor_2239 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1654, 0.0003711249737534672, 36125, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4697686Z     %quantize_per_tensor_1655 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_41, 0.0003442920569796115, 28225, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4698473Z     %dequantize_per_tensor_2240 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1655, 0.0003442920569796115, 28225, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4699263Z     %dequantize_per_tensor_2241 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1655, 0.0003442920569796115, 28225, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4699756Z     %_to_copy_21 : [num_users=1] = call_function[target=torch.ops.aten._to_copy.default](args = (%dequantize_per_tensor_2234,), kwargs = {dtype: torch.float32})
2025-03-21T20:30:48.4700454Z     %quantize_per_tensor_1656 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%_to_copy_21, 0.0004142843827139586, 29754, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4701240Z     %dequantize_per_tensor_2242 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1656, 0.0004142843827139586, 29754, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4701720Z     %view_124 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_2242, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:30:48.4702420Z     %quantize_per_tensor_1657 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_124, 0.0004142843827139586, 29754, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4703195Z     %dequantize_per_tensor_2243 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1657, 0.0004142843827139586, 29754, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4703608Z     %unbind_21 : [num_users=2] = call_function[target=torch.ops.aten.unbind.int](args = (%dequantize_per_tensor_2243, -1), kwargs = {})
2025-03-21T20:30:48.4703924Z     %getitem_42 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_21, 0), kwargs = {})
2025-03-21T20:30:48.4704245Z     %getitem_43 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_21, 1), kwargs = {})
2025-03-21T20:30:48.4704950Z     %quantize_per_tensor_1658 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_42, 0.00039733032463118434, 28227, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4705742Z     %dequantize_per_tensor_2244 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1658, 0.00039733032463118434, 28227, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4706515Z     %dequantize_per_tensor_2245 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1658, 0.00039733032463118434, 28227, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4707231Z     %quantize_per_tensor_1659 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_43, 0.00039120655856095254, 31509, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4708007Z     %dequantize_per_tensor_2246 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1659, 0.00039120655856095254, 31509, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4708818Z     %dequantize_per_tensor_2247 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1659, 0.00039120655856095254, 31509, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4709279Z     %view_125 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_152, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:30:48.4709982Z     %quantize_per_tensor_1660 : [num_users=4] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_125, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4710779Z     %dequantize_per_tensor_2248 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1660, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4711560Z     %dequantize_per_tensor_2249 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1660, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4712340Z     %dequantize_per_tensor_2250 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1660, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4713146Z     %dequantize_per_tensor_2251 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1660, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4713583Z     %view_126 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_164, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:30:48.4714285Z     %quantize_per_tensor_1661 : [num_users=4] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_126, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4715057Z     %dequantize_per_tensor_2252 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1661, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4715843Z     %dequantize_per_tensor_2253 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1661, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4716615Z     %dequantize_per_tensor_2254 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1661, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4717397Z     %dequantize_per_tensor_2255 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1661, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4717878Z     %mul_110 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_2239, %dequantize_per_tensor_2251), kwargs = {})
2025-03-21T20:30:48.4718583Z     %quantize_per_tensor_1662 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_110, 0.0003691529855132103, 36256, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4719359Z     %dequantize_per_tensor_2256 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1662, 0.0003691529855132103, 36256, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4719852Z     %mul_111 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_2240, %dequantize_per_tensor_2254), kwargs = {})
2025-03-21T20:30:48.4720546Z     %quantize_per_tensor_1663 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_111, 0.00017168192425742745, 31044, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4721384Z     %dequantize_per_tensor_2257 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1663, 0.00017168192425742745, 31044, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4721862Z     %sub_20 : [num_users=1] = call_function[target=torch.ops.aten.sub.Tensor](args = (%dequantize_per_tensor_2256, %dequantize_per_tensor_2257), kwargs = {})
2025-03-21T20:30:48.4722588Z     %quantize_per_tensor_1664 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%sub_20, 0.00036686332896351814, 36433, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4723372Z     %dequantize_per_tensor_2258 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1664, 0.00036686332896351814, 36433, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4723866Z     %mul_112 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_2238, %dequantize_per_tensor_2255), kwargs = {})
2025-03-21T20:30:48.4724559Z     %quantize_per_tensor_1665 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_112, 0.00014334538718685508, 33099, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4725386Z     %dequantize_per_tensor_2259 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1665, 0.00014334538718685508, 33099, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4725864Z     %mul_113 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_2241, %dequantize_per_tensor_2250), kwargs = {})
2025-03-21T20:30:48.4726569Z     %quantize_per_tensor_1666 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_113, 0.00034285150468349457, 28223, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4727347Z     %dequantize_per_tensor_2260 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1666, 0.00034285150468349457, 28223, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4727834Z     %add_50 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_2259, %dequantize_per_tensor_2260), kwargs = {})
2025-03-21T20:30:48.4728515Z     %quantize_per_tensor_1667 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_50, 0.0003369115001987666, 28096, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4729355Z     %dequantize_per_tensor_2261 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1667, 0.0003369115001987666, 28096, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4729839Z     %mul_114 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_2245, %dequantize_per_tensor_2249), kwargs = {})
2025-03-21T20:30:48.4730538Z     %quantize_per_tensor_1668 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_114, 0.0003857550327666104, 28901, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4731314Z     %dequantize_per_tensor_2262 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1668, 0.0003857550327666104, 28901, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4731805Z     %mul_115 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_2246, %dequantize_per_tensor_2252), kwargs = {})
2025-03-21T20:30:48.4732692Z     %quantize_per_tensor_1669 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_115, 0.00017581522115506232, 32153, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4733517Z     %dequantize_per_tensor_2263 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1669, 0.00017581522115506232, 32153, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4733993Z     %sub_21 : [num_users=1] = call_function[target=torch.ops.aten.sub.Tensor](args = (%dequantize_per_tensor_2262, %dequantize_per_tensor_2263), kwargs = {})
2025-03-21T20:30:48.4734724Z     %quantize_per_tensor_1670 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%sub_21, 0.00037492933915928006, 29584, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4735507Z     %dequantize_per_tensor_2264 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1670, 0.00037492933915928006, 29584, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4736001Z     %mul_116 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_2244, %dequantize_per_tensor_2253), kwargs = {})
2025-03-21T20:30:48.4736723Z     %quantize_per_tensor_1671 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_116, 0.00016251628403551877, 33632, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4737517Z     %dequantize_per_tensor_2265 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1671, 0.00016251628403551877, 33632, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4737990Z     %mul_117 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_2247, %dequantize_per_tensor_2248), kwargs = {})
2025-03-21T20:30:48.4738692Z     %quantize_per_tensor_1672 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_117, 0.0003872132219839841, 31182, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4739464Z     %dequantize_per_tensor_2266 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1672, 0.0003872132219839841, 31182, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4739949Z     %add_51 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_2265, %dequantize_per_tensor_2266), kwargs = {})
2025-03-21T20:30:48.4740631Z     %quantize_per_tensor_1673 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_51, 0.0003922595642507076, 31433, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4741413Z     %dequantize_per_tensor_2267 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1673, 0.0003922595642507076, 31433, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4741937Z     %stack_20 : [num_users=1] = call_function[target=torch.ops.aten.stack.default](args = ([%dequantize_per_tensor_2258, %dequantize_per_tensor_2261], -1), kwargs = {})
2025-03-21T20:30:48.4742646Z     %quantize_per_tensor_1674 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%stack_20, 0.00039642397314310074, 33716, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4743423Z     %dequantize_per_tensor_2268 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1674, 0.00039642397314310074, 33716, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4743879Z     %view_127 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_2268, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.4744598Z     %quantize_per_tensor_1675 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_127, 0.00039642397314310074, 33716, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4745409Z     %dequantize_per_tensor_2269 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1675, 0.00039642397314310074, 33716, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4745930Z     %stack_21 : [num_users=1] = call_function[target=torch.ops.aten.stack.default](args = ([%dequantize_per_tensor_2264, %dequantize_per_tensor_2267], -1), kwargs = {})
2025-03-21T20:30:48.4746662Z     %quantize_per_tensor_1676 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%stack_21, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4747440Z     %dequantize_per_tensor_2270 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1676, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4747896Z     %view_128 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_2270, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.4748616Z     %quantize_per_tensor_1677 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_128, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4749404Z     %dequantize_per_tensor_2271 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1677, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4749903Z     %type_as_20 : [num_users=1] = call_function[target=torch.ops.aten.type_as.default](args = (%dequantize_per_tensor_2269, %dequantize_per_tensor_2233), kwargs = {})
2025-03-21T20:30:48.4750615Z     %quantize_per_tensor_1678 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%type_as_20, 0.00039642397314310074, 33716, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4751394Z     %dequantize_per_tensor_2272 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1678, 0.00039642397314310074, 33716, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4751904Z     %type_as_21 : [num_users=1] = call_function[target=torch.ops.aten.type_as.default](args = (%dequantize_per_tensor_2271, %dequantize_per_tensor_2234), kwargs = {})
2025-03-21T20:30:48.4752605Z     %quantize_per_tensor_1679 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%type_as_21, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4753394Z     %dequantize_per_tensor_2273 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1679, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4753840Z     %transpose_416 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2272, 1, 2), kwargs = {})
2025-03-21T20:30:48.4754558Z     %quantize_per_tensor_1680 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_416, 0.00039642397314310074, 33716, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4755349Z     %dequantize_per_tensor_2274 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1680, 0.00039642397314310074, 33716, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4756010Z     %index_put_20 : [num_users=1] = call_function[target=torch.ops.aten.index_put.default](args = (%dequantize_per_tensor_143, [None, %attn_options_input_pos], %dequantize_per_tensor_2273), kwargs = {})
2025-03-21T20:30:48.4756744Z     %quantize_per_tensor_1681 : [num_users=13] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_put_20, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4757535Z     %dequantize_per_tensor_2275 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1681, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4758332Z     %dequantize_per_tensor_2276 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1681, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4759120Z     %dequantize_per_tensor_2277 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1681, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4759894Z     %dequantize_per_tensor_2278 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1681, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4760702Z     %dequantize_per_tensor_2279 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1681, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4761475Z     %dequantize_per_tensor_2280 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1681, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4762261Z     %dequantize_per_tensor_2281 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1681, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4763034Z     %dequantize_per_tensor_2282 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1681, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4763820Z     %dequantize_per_tensor_2283 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1681, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4764593Z     %dequantize_per_tensor_2284 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1681, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4765378Z     %dequantize_per_tensor_2285 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1681, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4766151Z     %dequantize_per_tensor_2286 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1681, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4766937Z     %dequantize_per_tensor_2287 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1681, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4767562Z     %index_put_21 : [num_users=1] = call_function[target=torch.ops.aten.index_put.default](args = (%dequantize_per_tensor_144, [None, %attn_options_input_pos], %dequantize_per_tensor_2235), kwargs = {})
2025-03-21T20:30:48.4768305Z     %quantize_per_tensor_1682 : [num_users=13] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_put_21, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4769105Z     %dequantize_per_tensor_2288 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1682, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4770004Z     %dequantize_per_tensor_2289 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1682, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4770779Z     %dequantize_per_tensor_2290 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1682, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4771571Z     %dequantize_per_tensor_2291 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1682, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4772344Z     %dequantize_per_tensor_2292 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1682, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4773170Z     %dequantize_per_tensor_2293 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1682, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4773943Z     %dequantize_per_tensor_2294 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1682, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4774734Z     %dequantize_per_tensor_2295 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1682, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4775509Z     %dequantize_per_tensor_2296 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1682, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4776297Z     %dequantize_per_tensor_2297 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1682, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4777074Z     %dequantize_per_tensor_2298 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1682, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4777867Z     %dequantize_per_tensor_2299 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1682, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4778642Z     %dequantize_per_tensor_2300 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1682, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4779103Z     %transpose_417 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2287, 1, 2), kwargs = {})
2025-03-21T20:30:48.4779823Z     %quantize_per_tensor_1683 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_417, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4780632Z     %dequantize_per_tensor_2301 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1683, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4781065Z     %select_480 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2301, 0, 0), kwargs = {})
2025-03-21T20:30:48.4781783Z     %quantize_per_tensor_1684 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_480, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4782581Z     %dequantize_per_tensor_2302 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1684, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4783010Z     %select_481 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2302, 0, 0), kwargs = {})
2025-03-21T20:30:48.4783719Z     %quantize_per_tensor_1685 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_481, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4784529Z     %dequantize_per_tensor_2303 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1685, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4784972Z     %transpose_418 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2286, 1, 2), kwargs = {})
2025-03-21T20:30:48.4785707Z     %quantize_per_tensor_1686 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_418, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4786486Z     %dequantize_per_tensor_2304 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1686, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4786917Z     %select_482 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2304, 0, 0), kwargs = {})
2025-03-21T20:30:48.4787627Z     %quantize_per_tensor_1687 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_482, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4788419Z     %dequantize_per_tensor_2305 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1687, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4788832Z     %select_483 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2305, 0, 1), kwargs = {})
2025-03-21T20:30:48.4789551Z     %quantize_per_tensor_1688 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_483, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4790333Z     %dequantize_per_tensor_2306 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1688, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4790789Z     %transpose_419 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2285, 1, 2), kwargs = {})
2025-03-21T20:30:48.4791517Z     %quantize_per_tensor_1689 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_419, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4792327Z     %dequantize_per_tensor_2307 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1689, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4792764Z     %select_484 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2307, 0, 0), kwargs = {})
2025-03-21T20:30:48.4793483Z     %quantize_per_tensor_1690 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_484, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4794284Z     %dequantize_per_tensor_2308 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1690, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4794710Z     %select_485 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2308, 0, 2), kwargs = {})
2025-03-21T20:30:48.4795416Z     %quantize_per_tensor_1691 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_485, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4796227Z     %dequantize_per_tensor_2309 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1691, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4796671Z     %transpose_420 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2284, 1, 2), kwargs = {})
2025-03-21T20:30:48.4797403Z     %quantize_per_tensor_1692 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_420, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4798185Z     %dequantize_per_tensor_2310 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1692, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4798615Z     %select_486 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2310, 0, 0), kwargs = {})
2025-03-21T20:30:48.4799321Z     %quantize_per_tensor_1693 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_486, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4800113Z     %dequantize_per_tensor_2311 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1693, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4800523Z     %select_487 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2311, 0, 3), kwargs = {})
2025-03-21T20:30:48.4801244Z     %quantize_per_tensor_1694 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_487, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4802023Z     %dequantize_per_tensor_2312 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1694, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4802481Z     %transpose_421 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2283, 1, 2), kwargs = {})
2025-03-21T20:30:48.4803201Z     %quantize_per_tensor_1695 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_421, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4804018Z     %dequantize_per_tensor_2313 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1695, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4804455Z     %select_488 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2313, 0, 0), kwargs = {})
2025-03-21T20:30:48.4805176Z     %quantize_per_tensor_1696 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_488, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4805973Z     %dequantize_per_tensor_2314 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1696, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4806397Z     %select_489 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2314, 0, 4), kwargs = {})
2025-03-21T20:30:48.4807107Z     %quantize_per_tensor_1697 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_489, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4807909Z     %dequantize_per_tensor_2315 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1697, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4808366Z     %transpose_422 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2282, 1, 2), kwargs = {})
2025-03-21T20:30:48.4809087Z     %quantize_per_tensor_1698 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_422, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4809933Z     %dequantize_per_tensor_2316 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1698, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4810351Z     %select_490 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2316, 0, 0), kwargs = {})
2025-03-21T20:30:48.4811070Z     %quantize_per_tensor_1699 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_490, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4811852Z     %dequantize_per_tensor_2317 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1699, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4812276Z     %select_491 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2317, 0, 5), kwargs = {})
2025-03-21T20:30:48.4812984Z     %quantize_per_tensor_1700 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_491, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4813775Z     %dequantize_per_tensor_2318 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1700, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4814220Z     %transpose_423 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2281, 1, 2), kwargs = {})
2025-03-21T20:30:48.4814951Z     %quantize_per_tensor_1701 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_423, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4815757Z     %dequantize_per_tensor_2319 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1701, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4816201Z     %select_492 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2319, 0, 0), kwargs = {})
2025-03-21T20:30:48.4816904Z     %quantize_per_tensor_1702 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_492, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4817729Z     %dequantize_per_tensor_2320 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1702, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4818138Z     %select_493 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2320, 0, 6), kwargs = {})
2025-03-21T20:30:48.4818857Z     %quantize_per_tensor_1703 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_493, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4819659Z     %dequantize_per_tensor_2321 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1703, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4820111Z     %transpose_424 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2280, 1, 2), kwargs = {})
2025-03-21T20:30:48.4820826Z     %quantize_per_tensor_1704 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_424, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4821616Z     %dequantize_per_tensor_2322 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1704, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4822028Z     %select_494 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2322, 0, 0), kwargs = {})
2025-03-21T20:30:48.4822743Z     %quantize_per_tensor_1705 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_494, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4823520Z     %dequantize_per_tensor_2323 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1705, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4823942Z     %select_495 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2323, 0, 7), kwargs = {})
2025-03-21T20:30:48.4824651Z     %quantize_per_tensor_1706 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_495, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4825438Z     %dequantize_per_tensor_2324 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1706, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4825884Z     %transpose_425 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2279, 1, 2), kwargs = {})
2025-03-21T20:30:48.4826613Z     %quantize_per_tensor_1707 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_425, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4827414Z     %dequantize_per_tensor_2325 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1707, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4827865Z     %select_496 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2325, 0, 0), kwargs = {})
2025-03-21T20:30:48.4828572Z     %quantize_per_tensor_1708 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_496, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4829385Z     %dequantize_per_tensor_2326 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1708, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4829795Z     %select_497 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2326, 0, 8), kwargs = {})
2025-03-21T20:30:48.4830514Z     %quantize_per_tensor_1709 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_497, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4831319Z     %dequantize_per_tensor_2327 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1709, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4831777Z     %transpose_426 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2278, 1, 2), kwargs = {})
2025-03-21T20:30:48.4832640Z     %quantize_per_tensor_1710 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_426, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4833432Z     %dequantize_per_tensor_2328 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1710, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4833845Z     %select_498 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2328, 0, 0), kwargs = {})
2025-03-21T20:30:48.4834564Z     %quantize_per_tensor_1711 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_498, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4835343Z     %dequantize_per_tensor_2329 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1711, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4835767Z     %select_499 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2329, 0, 9), kwargs = {})
2025-03-21T20:30:48.4836475Z     %quantize_per_tensor_1712 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_499, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4837265Z     %dequantize_per_tensor_2330 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1712, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4837707Z     %transpose_427 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2277, 1, 2), kwargs = {})
2025-03-21T20:30:48.4838436Z     %quantize_per_tensor_1713 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_427, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4839258Z     %dequantize_per_tensor_2331 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1713, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4839712Z     %select_500 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2331, 0, 0), kwargs = {})
2025-03-21T20:30:48.4840415Z     %quantize_per_tensor_1714 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_500, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4841232Z     %dequantize_per_tensor_2332 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1714, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4841652Z     %select_501 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2332, 0, 10), kwargs = {})
2025-03-21T20:30:48.4842373Z     %quantize_per_tensor_1715 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_501, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4843183Z     %dequantize_per_tensor_2333 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1715, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4843639Z     %transpose_428 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2276, 1, 2), kwargs = {})
2025-03-21T20:30:48.4844353Z     %quantize_per_tensor_1716 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_428, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4845141Z     %dequantize_per_tensor_2334 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1716, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4845557Z     %select_502 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2334, 0, 0), kwargs = {})
2025-03-21T20:30:48.4846272Z     %quantize_per_tensor_1717 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_502, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4847051Z     %dequantize_per_tensor_2335 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1717, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4847479Z     %select_503 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2335, 0, 11), kwargs = {})
2025-03-21T20:30:48.4848183Z     %quantize_per_tensor_1718 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_503, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4848972Z     %dequantize_per_tensor_2336 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1718, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4850517Z     %cat_20 : [num_users=1] = call_function[target=torch.ops.aten.cat.default](args = ([%dequantize_per_tensor_2303, %dequantize_per_tensor_2306, %dequantize_per_tensor_2309, %dequantize_per_tensor_2312, %dequantize_per_tensor_2315, %dequantize_per_tensor_2318, %dequantize_per_tensor_2321, %dequantize_per_tensor_2324, %dequantize_per_tensor_2327, %dequantize_per_tensor_2330, %dequantize_per_tensor_2333, %dequantize_per_tensor_2336],), kwargs = {})
2025-03-21T20:30:48.4851279Z     %quantize_per_tensor_1719 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%cat_20, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4852058Z     %dequantize_per_tensor_2337 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1719, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4852544Z     %view_129 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_2337, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:30:48.4853242Z     %quantize_per_tensor_1720 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_129, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4854036Z     %dequantize_per_tensor_2338 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1720, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4854480Z     %transpose_429 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2300, 1, 2), kwargs = {})
2025-03-21T20:30:48.4855236Z     %quantize_per_tensor_1721 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_429, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4856011Z     %dequantize_per_tensor_2339 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1721, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4856437Z     %select_504 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2339, 0, 0), kwargs = {})
2025-03-21T20:30:48.4857145Z     %quantize_per_tensor_1722 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_504, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4857935Z     %dequantize_per_tensor_2340 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1722, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4858344Z     %select_505 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2340, 0, 0), kwargs = {})
2025-03-21T20:30:48.4859064Z     %quantize_per_tensor_1723 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_505, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4859839Z     %dequantize_per_tensor_2341 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1723, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4860295Z     %transpose_430 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2299, 1, 2), kwargs = {})
2025-03-21T20:30:48.4861011Z     %quantize_per_tensor_1724 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_430, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4861802Z     %dequantize_per_tensor_2342 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1724, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4862212Z     %select_506 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2342, 0, 0), kwargs = {})
2025-03-21T20:30:48.4862986Z     %quantize_per_tensor_1725 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_506, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4863765Z     %dequantize_per_tensor_2343 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1725, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4864210Z     %select_507 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2343, 0, 1), kwargs = {})
2025-03-21T20:30:48.4864917Z     %quantize_per_tensor_1726 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_507, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4865706Z     %dequantize_per_tensor_2344 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1726, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4866147Z     %transpose_431 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2298, 1, 2), kwargs = {})
2025-03-21T20:30:48.4866897Z     %quantize_per_tensor_1727 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_431, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4867675Z     %dequantize_per_tensor_2345 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1727, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4868096Z     %select_508 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2345, 0, 0), kwargs = {})
2025-03-21T20:30:48.4868804Z     %quantize_per_tensor_1728 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_508, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4869594Z     %dequantize_per_tensor_2346 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1728, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4870003Z     %select_509 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2346, 0, 2), kwargs = {})
2025-03-21T20:30:48.4870708Z     %quantize_per_tensor_1729 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_509, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4871492Z     %dequantize_per_tensor_2347 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1729, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4871936Z     %transpose_432 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2297, 1, 2), kwargs = {})
2025-03-21T20:30:48.4872665Z     %quantize_per_tensor_1730 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_432, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4873440Z     %dequantize_per_tensor_2348 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1730, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4873864Z     %select_510 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2348, 0, 0), kwargs = {})
2025-03-21T20:30:48.4874617Z     %quantize_per_tensor_1731 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_510, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4875408Z     %dequantize_per_tensor_2349 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1731, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4875842Z     %select_511 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2349, 0, 3), kwargs = {})
2025-03-21T20:30:48.4876559Z     %quantize_per_tensor_1732 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_511, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4877333Z     %dequantize_per_tensor_2350 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1732, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4877791Z     %transpose_433 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2296, 1, 2), kwargs = {})
2025-03-21T20:30:48.4878531Z     %quantize_per_tensor_1733 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_433, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4879318Z     %dequantize_per_tensor_2351 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1733, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4879727Z     %select_512 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2351, 0, 0), kwargs = {})
2025-03-21T20:30:48.4880443Z     %quantize_per_tensor_1734 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_512, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4881220Z     %dequantize_per_tensor_2352 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1734, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4881640Z     %select_513 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2352, 0, 4), kwargs = {})
2025-03-21T20:30:48.4882347Z     %quantize_per_tensor_1735 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_513, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4883133Z     %dequantize_per_tensor_2353 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1735, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4883577Z     %transpose_434 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2295, 1, 2), kwargs = {})
2025-03-21T20:30:48.4884308Z     %quantize_per_tensor_1736 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_434, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4885084Z     %dequantize_per_tensor_2354 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1736, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4885508Z     %select_514 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2354, 0, 0), kwargs = {})
2025-03-21T20:30:48.4886259Z     %quantize_per_tensor_1737 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_514, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4887056Z     %dequantize_per_tensor_2355 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1737, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4887494Z     %select_515 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2355, 0, 5), kwargs = {})
2025-03-21T20:30:48.4888215Z     %quantize_per_tensor_1738 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_515, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4888998Z     %dequantize_per_tensor_2356 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1738, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4889546Z     %transpose_435 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2294, 1, 2), kwargs = {})
2025-03-21T20:30:48.4890299Z     %quantize_per_tensor_1739 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_435, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4891094Z     %dequantize_per_tensor_2357 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1739, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4891511Z     %select_516 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2357, 0, 0), kwargs = {})
2025-03-21T20:30:48.4892234Z     %quantize_per_tensor_1740 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_516, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4893019Z     %dequantize_per_tensor_2358 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1740, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4893445Z     %select_517 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2358, 0, 6), kwargs = {})
2025-03-21T20:30:48.4894147Z     %quantize_per_tensor_1741 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_517, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4894938Z     %dequantize_per_tensor_2359 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1741, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4895383Z     %transpose_436 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2293, 1, 2), kwargs = {})
2025-03-21T20:30:48.4896111Z     %quantize_per_tensor_1742 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_436, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4896886Z     %dequantize_per_tensor_2360 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1742, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4901745Z     %select_518 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2360, 0, 0), kwargs = {})
2025-03-21T20:30:48.4902603Z     %quantize_per_tensor_1743 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_518, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4903410Z     %dequantize_per_tensor_2361 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1743, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4903858Z     %select_519 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2361, 0, 7), kwargs = {})
2025-03-21T20:30:48.4904583Z     %quantize_per_tensor_1744 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_519, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4905367Z     %dequantize_per_tensor_2362 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1744, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4905826Z     %transpose_437 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2292, 1, 2), kwargs = {})
2025-03-21T20:30:48.4906583Z     %quantize_per_tensor_1745 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_437, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4907379Z     %dequantize_per_tensor_2363 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1745, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4907791Z     %select_520 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2363, 0, 0), kwargs = {})
2025-03-21T20:30:48.4908505Z     %quantize_per_tensor_1746 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_520, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4909298Z     %dequantize_per_tensor_2364 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1746, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4909711Z     %select_521 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2364, 0, 8), kwargs = {})
2025-03-21T20:30:48.4910429Z     %quantize_per_tensor_1747 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_521, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4911207Z     %dequantize_per_tensor_2365 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1747, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4911657Z     %transpose_438 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2291, 1, 2), kwargs = {})
2025-03-21T20:30:48.4912392Z     %quantize_per_tensor_1748 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_438, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4913172Z     %dequantize_per_tensor_2366 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1748, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4913599Z     %select_522 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2366, 0, 0), kwargs = {})
2025-03-21T20:30:48.4914371Z     %quantize_per_tensor_1749 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_522, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4915166Z     %dequantize_per_tensor_2367 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1749, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4915600Z     %select_523 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2367, 0, 9), kwargs = {})
2025-03-21T20:30:48.4916325Z     %quantize_per_tensor_1750 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_523, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4917107Z     %dequantize_per_tensor_2368 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1750, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4917565Z     %transpose_439 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2290, 1, 2), kwargs = {})
2025-03-21T20:30:48.4918310Z     %quantize_per_tensor_1751 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_439, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4919089Z     %dequantize_per_tensor_2369 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1751, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4919515Z     %select_524 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2369, 0, 0), kwargs = {})
2025-03-21T20:30:48.4920225Z     %quantize_per_tensor_1752 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_524, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4921016Z     %dequantize_per_tensor_2370 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1752, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4921433Z     %select_525 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2370, 0, 10), kwargs = {})
2025-03-21T20:30:48.4922154Z     %quantize_per_tensor_1753 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_525, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4922931Z     %dequantize_per_tensor_2371 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1753, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4923388Z     %transpose_440 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2289, 1, 2), kwargs = {})
2025-03-21T20:30:48.4924112Z     %quantize_per_tensor_1754 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_440, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4924902Z     %dequantize_per_tensor_2372 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1754, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4925315Z     %select_526 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2372, 0, 0), kwargs = {})
2025-03-21T20:30:48.4926085Z     %quantize_per_tensor_1755 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_526, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4926866Z     %dequantize_per_tensor_2373 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1755, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4927318Z     %select_527 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2373, 0, 11), kwargs = {})
2025-03-21T20:30:48.4928025Z     %quantize_per_tensor_1756 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_527, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4928821Z     %dequantize_per_tensor_2374 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1756, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4930418Z     %cat_21 : [num_users=1] = call_function[target=torch.ops.aten.cat.default](args = ([%dequantize_per_tensor_2341, %dequantize_per_tensor_2344, %dequantize_per_tensor_2347, %dequantize_per_tensor_2350, %dequantize_per_tensor_2353, %dequantize_per_tensor_2356, %dequantize_per_tensor_2359, %dequantize_per_tensor_2362, %dequantize_per_tensor_2365, %dequantize_per_tensor_2368, %dequantize_per_tensor_2371, %dequantize_per_tensor_2374],), kwargs = {})
2025-03-21T20:30:48.4931154Z     %quantize_per_tensor_1757 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%cat_21, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4931951Z     %dequantize_per_tensor_2375 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1757, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4932551Z     %view_130 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_2375, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:30:48.4933357Z     %quantize_per_tensor_1758 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_130, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4934154Z     %dequantize_per_tensor_2376 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1758, 0.00021122458565514535, 31154, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4934946Z     %quantize_per_tensor_1759 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%dequantize_per_tensor_2376, 0.00022162823006510735, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.4935728Z     %dequantize_per_tensor_2377 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1759, 0.00022162823006510735, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.4936236Z     %index_12 : [num_users=1] = call_function[target=torch.ops.aten.index.Tensor](args = (%dequantize_per_tensor_145, [%attn_options_input_pos]), kwargs = {})
2025-03-21T20:30:48.4936929Z     %quantize_per_tensor_1760 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_12, 0.0038910505827516317, 65535, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4937719Z     %dequantize_per_tensor_2378 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1760, 0.0038910505827516317, 65535, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4938261Z     %transpose_441 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2338, -2, -1), kwargs = {})
2025-03-21T20:30:48.4938983Z     %quantize_per_tensor_1761 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_441, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4939805Z     %dequantize_per_tensor_2379 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1761, 0.00039381824899464846, 31308, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4940582Z     %quantize_per_tensor_1762 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%dequantize_per_tensor_2379, 0.000411360728321597, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.4941359Z     %dequantize_per_tensor_2380 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1762, 0.000411360728321597, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.4941915Z     %matmul_20 : [num_users=1] = call_function[target=torch.ops.aten.matmul.default](args = (%dequantize_per_tensor_2274, %dequantize_per_tensor_2380), kwargs = {})
2025-03-21T20:30:48.4942613Z     %quantize_per_tensor_1763 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%matmul_20, 0.0036731965374201536, 37823, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4943398Z     %dequantize_per_tensor_2381 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1763, 0.0036731965374201536, 37823, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4944143Z     %dequantize_per_tensor_2382 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param159, 1.9073777366429567e-06, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4944636Z     %mul_118 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_2381, %dequantize_per_tensor_2382), kwargs = {})
2025-03-21T20:30:48.4945327Z     %quantize_per_tensor_1764 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_118, 0.0004591495671775192, 37823, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4946099Z     %dequantize_per_tensor_2383 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1764, 0.0004591495671775192, 37823, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4946583Z     %add_52 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_2383, %dequantize_per_tensor_2378), kwargs = {})
2025-03-21T20:30:48.4947264Z     %quantize_per_tensor_1765 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_52, 0.004276345018297434, 62560, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4948046Z     %dequantize_per_tensor_2384 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1765, 0.004276345018297434, 62560, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4948464Z     %softmax_10 : [num_users=1] = call_function[target=torch.ops.aten.softmax.int](args = (%dequantize_per_tensor_2384, -1), kwargs = {})
2025-03-21T20:30:48.4949172Z     %quantize_per_tensor_1766 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%softmax_10, 1.5259021893143654e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4949961Z     %dequantize_per_tensor_2385 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1766, 1.5259021893143654e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4950511Z     %matmul_21 : [num_users=1] = call_function[target=torch.ops.aten.matmul.default](args = (%dequantize_per_tensor_2385, %dequantize_per_tensor_2377), kwargs = {})
2025-03-21T20:30:48.4951212Z     %quantize_per_tensor_1767 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%matmul_21, 0.00014636466221418232, 32803, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4952025Z     %dequantize_per_tensor_2386 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1767, 0.00014636466221418232, 32803, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4952473Z     %transpose_442 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2386, 1, 2), kwargs = {})
2025-03-21T20:30:48.4953207Z     %quantize_per_tensor_1768 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_442, 0.00014636466221418232, 32803, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4954025Z     %dequantize_per_tensor_2387 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1768, 0.00014636466221418232, 32803, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4954472Z     %view_131 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_2387, [1, 1, 768]), kwargs = {})
2025-03-21T20:30:48.4955167Z     %quantize_per_tensor_1769 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_131, 0.00014636466221418232, 32803, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4955961Z     %dequantize_per_tensor_2388 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1769, 0.00014636466221418232, 32803, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4956418Z     %unsqueeze_73 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_2388, -1), kwargs = {})
2025-03-21T20:30:48.4957146Z     %quantize_per_tensor_1770 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_73, 0.00014636466221418232, 32803, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4957923Z     %dequantize_per_tensor_2389 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1770, 0.00014636466221418232, 32803, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4958378Z     %transpose_443 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2389, 1, 2), kwargs = {})
2025-03-21T20:30:48.4959102Z     %quantize_per_tensor_1771 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_443, 0.00014636466221418232, 32803, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4959899Z     %dequantize_per_tensor_2390 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1771, 0.00014636466221418232, 32803, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4960403Z     %conv2d_73 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_2390, %dequantize_per_tensor_95), kwargs = {})
2025-03-21T20:30:48.4961111Z     %quantize_per_tensor_1772 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_73, 0.0002480327384546399, 28212, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4961951Z     %dequantize_per_tensor_2391 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1772, 0.0002480327384546399, 28212, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4962410Z     %transpose_444 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2391, 1, 2), kwargs = {})
2025-03-21T20:30:48.4963126Z     %quantize_per_tensor_1773 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_444, 0.0002480327384546399, 28212, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4963932Z     %dequantize_per_tensor_2392 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1773, 0.0002480327384546399, 28212, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4964350Z     %squeeze_73 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_2392, -1), kwargs = {})
2025-03-21T20:30:48.4965065Z     %quantize_per_tensor_1774 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_73, 0.0002480327384546399, 28212, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4965862Z     %dequantize_per_tensor_2393 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1774, 0.0002480327384546399, 28212, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4966348Z     %add_53 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_2213, %dequantize_per_tensor_2393), kwargs = {})
2025-03-21T20:30:48.4967028Z     %quantize_per_tensor_1775 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_53, 0.0027502242010086775, 9540, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4967814Z     %dequantize_per_tensor_2394 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1775, 0.0027502242010086775, 9540, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4968584Z     %dequantize_per_tensor_2395 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1775, 0.0027502242010086775, 9540, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4969139Z     %rms_norm_21 : [num_users=1] = call_function[target=torch.ops.aten.rms_norm.default](args = (%dequantize_per_tensor_2395, [768], %dequantize_per_tensor_96, 1e-05), kwargs = {})
2025-03-21T20:30:48.4969912Z     %quantize_per_tensor_1776 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%rms_norm_21, 0.0005783338565379381, 21200, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4970704Z     %dequantize_per_tensor_2396 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1776, 0.0005783338565379381, 21200, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4971476Z     %dequantize_per_tensor_2397 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1776, 0.0005783338565379381, 21200, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4971950Z     %unsqueeze_74 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_2397, -1), kwargs = {})
2025-03-21T20:30:48.4972662Z     %quantize_per_tensor_1777 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_74, 0.0005783338565379381, 21200, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4973477Z     %dequantize_per_tensor_2398 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1777, 0.0005783338565379381, 21200, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4973946Z     %transpose_445 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2398, 1, 2), kwargs = {})
2025-03-21T20:30:48.4974681Z     %quantize_per_tensor_1778 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_445, 0.0005783338565379381, 21200, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4975477Z     %dequantize_per_tensor_2399 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1778, 0.0005783338565379381, 21200, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4976001Z     %conv2d_74 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_2399, %dequantize_per_tensor_97), kwargs = {})
2025-03-21T20:30:48.4976702Z     %quantize_per_tensor_1779 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_74, 0.0002567260235082358, 25603, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4977512Z     %dequantize_per_tensor_2400 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1779, 0.0002567260235082358, 25603, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4977956Z     %transpose_446 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2400, 1, 2), kwargs = {})
2025-03-21T20:30:48.4978685Z     %quantize_per_tensor_1780 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_446, 0.0002567260235082358, 25603, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4979463Z     %dequantize_per_tensor_2401 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1780, 0.0002567260235082358, 25603, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4979890Z     %squeeze_74 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_2401, -1), kwargs = {})
2025-03-21T20:30:48.4980594Z     %quantize_per_tensor_1781 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_74, 0.0002567260235082358, 25603, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4981381Z     %dequantize_per_tensor_2402 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1781, 0.0002567260235082358, 25603, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4982153Z     %dequantize_per_tensor_2403 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1781, 0.0002567260235082358, 25603, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4982591Z     %sigmoid_10 : [num_users=1] = call_function[target=torch.ops.aten.sigmoid.default](args = (%dequantize_per_tensor_2403,), kwargs = {})
2025-03-21T20:30:48.4983269Z     %quantize_per_tensor_1782 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%sigmoid_10, 1.52587890625e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4984031Z     %dequantize_per_tensor_2404 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1782, 1.52587890625e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4984510Z     %mul_119 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_2402, %dequantize_per_tensor_2404), kwargs = {})
2025-03-21T20:30:48.4985233Z     %quantize_per_tensor_1783 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_119, 0.00016067380784079432, 1733, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4986033Z     %dequantize_per_tensor_2405 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1783, 0.00016067380784079432, 1733, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4986508Z     %unsqueeze_75 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_2396, -1), kwargs = {})
2025-03-21T20:30:48.4987243Z     %quantize_per_tensor_1784 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_75, 0.0005783338565379381, 21200, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4988034Z     %dequantize_per_tensor_2406 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1784, 0.0005783338565379381, 21200, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4988477Z     %transpose_447 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2406, 1, 2), kwargs = {})
2025-03-21T20:30:48.4989234Z     %quantize_per_tensor_1785 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_447, 0.0005783338565379381, 21200, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4990008Z     %dequantize_per_tensor_2407 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1785, 0.0005783338565379381, 21200, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4990523Z     %conv2d_75 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_2407, %dequantize_per_tensor_98), kwargs = {})
2025-03-21T20:30:48.4991222Z     %quantize_per_tensor_1786 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_75, 0.00028021426987834275, 27530, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4992015Z     %dequantize_per_tensor_2408 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1786, 0.00028021426987834275, 27530, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4992459Z     %transpose_448 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2408, 1, 2), kwargs = {})
2025-03-21T20:30:48.4993192Z     %quantize_per_tensor_1787 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_448, 0.00028021426987834275, 27530, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4993974Z     %dequantize_per_tensor_2409 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1787, 0.00028021426987834275, 27530, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4994406Z     %squeeze_75 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_2409, -1), kwargs = {})
2025-03-21T20:30:48.4995117Z     %quantize_per_tensor_1788 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_75, 0.00028021426987834275, 27530, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4995913Z     %dequantize_per_tensor_2410 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1788, 0.00028021426987834275, 27530, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4996393Z     %mul_120 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_2405, %dequantize_per_tensor_2410), kwargs = {})
2025-03-21T20:30:48.4997120Z     %quantize_per_tensor_1789 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_120, 0.0008850086014717817, 31787, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4997921Z     %dequantize_per_tensor_2411 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1789, 0.0008850086014717817, 31787, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4998395Z     %unsqueeze_76 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_2411, -1), kwargs = {})
2025-03-21T20:30:48.4999145Z     %quantize_per_tensor_1790 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_76, 0.0008850086014717817, 31787, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.4999940Z     %dequantize_per_tensor_2412 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1790, 0.0008850086014717817, 31787, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5000386Z     %transpose_449 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2412, 1, 2), kwargs = {})
2025-03-21T20:30:48.5001139Z     %quantize_per_tensor_1791 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_449, 0.0008850086014717817, 31787, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5001916Z     %dequantize_per_tensor_2413 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1791, 0.0008850086014717817, 31787, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5002430Z     %conv2d_76 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_2413, %dequantize_per_tensor_99), kwargs = {})
2025-03-21T20:30:48.5003128Z     %quantize_per_tensor_1792 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_76, 0.0007228487520478666, 44000, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5003915Z     %dequantize_per_tensor_2414 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1792, 0.0007228487520478666, 44000, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5004358Z     %transpose_450 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2414, 1, 2), kwargs = {})
2025-03-21T20:30:48.5005089Z     %quantize_per_tensor_1793 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_450, 0.0007228487520478666, 44000, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5005865Z     %dequantize_per_tensor_2415 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1793, 0.0007228487520478666, 44000, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5006294Z     %squeeze_76 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_2415, -1), kwargs = {})
2025-03-21T20:30:48.5006996Z     %quantize_per_tensor_1794 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_76, 0.0007228487520478666, 44000, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5007783Z     %dequantize_per_tensor_2416 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1794, 0.0007228487520478666, 44000, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5008254Z     %add_54 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_2394, %dequantize_per_tensor_2416), kwargs = {})
2025-03-21T20:30:48.5008989Z     %quantize_per_tensor_1795 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_54, 0.0024239460472017527, 13427, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5009837Z     %dequantize_per_tensor_2417 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1795, 0.0024239460472017527, 13427, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5010649Z     %dequantize_per_tensor_2418 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1795, 0.0024239460472017527, 13427, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5011201Z     %rms_norm_22 : [num_users=1] = call_function[target=torch.ops.aten.rms_norm.default](args = (%dequantize_per_tensor_2418, [768], %dequantize_per_tensor_100, 1e-05), kwargs = {})
2025-03-21T20:30:48.5011916Z     %quantize_per_tensor_1796 : [num_users=3] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%rms_norm_22, 0.0005588648491539061, 33862, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5012691Z     %dequantize_per_tensor_2419 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1796, 0.0005588648491539061, 33862, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5013512Z     %dequantize_per_tensor_2420 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1796, 0.0005588648491539061, 33862, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5014280Z     %dequantize_per_tensor_2421 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1796, 0.0005588648491539061, 33862, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5014754Z     %unsqueeze_77 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_2421, -1), kwargs = {})
2025-03-21T20:30:48.5015468Z     %quantize_per_tensor_1797 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_77, 0.0005588648491539061, 33862, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5016257Z     %dequantize_per_tensor_2422 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1797, 0.0005588648491539061, 33862, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5016700Z     %transpose_451 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2422, 1, 2), kwargs = {})
2025-03-21T20:30:48.5017416Z     %quantize_per_tensor_1798 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_451, 0.0005588648491539061, 33862, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5018206Z     %dequantize_per_tensor_2423 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1798, 0.0005588648491539061, 33862, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5018717Z     %conv2d_77 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_2423, %dequantize_per_tensor_101), kwargs = {})
2025-03-21T20:30:48.5019429Z     %quantize_per_tensor_1799 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_77, 0.00039327371632680297, 29965, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5020205Z     %dequantize_per_tensor_2424 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1799, 0.00039327371632680297, 29965, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5020709Z     %transpose_452 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2424, 1, 2), kwargs = {})
2025-03-21T20:30:48.5021430Z     %quantize_per_tensor_1800 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_452, 0.00039327371632680297, 29965, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5022244Z     %dequantize_per_tensor_2425 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1800, 0.00039327371632680297, 29965, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5022662Z     %squeeze_77 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_2425, -1), kwargs = {})
2025-03-21T20:30:48.5023386Z     %quantize_per_tensor_1801 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_77, 0.00039327371632680297, 29965, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5024164Z     %dequantize_per_tensor_2426 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1801, 0.00039327371632680297, 29965, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5024658Z     %unsqueeze_78 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_2420, -1), kwargs = {})
2025-03-21T20:30:48.5025372Z     %quantize_per_tensor_1802 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_78, 0.0005588648491539061, 33862, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5026157Z     %dequantize_per_tensor_2427 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1802, 0.0005588648491539061, 33862, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5026603Z     %transpose_453 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2427, 1, 2), kwargs = {})
2025-03-21T20:30:48.5027330Z     %quantize_per_tensor_1803 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_453, 0.0005588648491539061, 33862, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5028104Z     %dequantize_per_tensor_2428 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1803, 0.0005588648491539061, 33862, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5028625Z     %conv2d_78 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_2428, %dequantize_per_tensor_102), kwargs = {})
2025-03-21T20:30:48.5029322Z     %quantize_per_tensor_1804 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_78, 0.0004171783511992544, 32679, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5030104Z     %dequantize_per_tensor_2429 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1804, 0.0004171783511992544, 32679, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5030545Z     %transpose_454 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2429, 1, 2), kwargs = {})
2025-03-21T20:30:48.5031278Z     %quantize_per_tensor_1805 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_454, 0.0004171783511992544, 32679, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5032050Z     %dequantize_per_tensor_2430 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1805, 0.0004171783511992544, 32679, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5032755Z     %squeeze_78 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_2430, -1), kwargs = {})
2025-03-21T20:30:48.5033456Z     %quantize_per_tensor_1806 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_78, 0.0004171783511992544, 32679, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5034276Z     %dequantize_per_tensor_2431 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1806, 0.0004171783511992544, 32679, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5034736Z     %unsqueeze_79 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_2419, -1), kwargs = {})
2025-03-21T20:30:48.5035463Z     %quantize_per_tensor_1807 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_79, 0.0005588648491539061, 33862, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5036242Z     %dequantize_per_tensor_2432 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1807, 0.0005588648491539061, 33862, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5036737Z     %transpose_455 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2432, 1, 2), kwargs = {})
2025-03-21T20:30:48.5037458Z     %quantize_per_tensor_1808 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_455, 0.0005588648491539061, 33862, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5038251Z     %dequantize_per_tensor_2433 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1808, 0.0005588648491539061, 33862, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5038762Z     %conv2d_79 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_2433, %dequantize_per_tensor_103), kwargs = {})
2025-03-21T20:30:48.5039474Z     %quantize_per_tensor_1809 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_79, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5040246Z     %dequantize_per_tensor_2434 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1809, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5040704Z     %transpose_456 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2434, 1, 2), kwargs = {})
2025-03-21T20:30:48.5041422Z     %quantize_per_tensor_1810 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_456, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5042207Z     %dequantize_per_tensor_2435 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1810, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5042626Z     %squeeze_79 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_2435, -1), kwargs = {})
2025-03-21T20:30:48.5043343Z     %quantize_per_tensor_1811 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_79, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5044115Z     %dequantize_per_tensor_2436 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1811, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5044641Z     %view_132 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_2426, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.5045343Z     %quantize_per_tensor_1812 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_132, 0.00039327371632680297, 29965, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5046159Z     %dequantize_per_tensor_2437 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1812, 0.00039327371632680297, 29965, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5046604Z     %view_133 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_2431, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.5047312Z     %quantize_per_tensor_1813 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_133, 0.0004171783511992544, 32679, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5048087Z     %dequantize_per_tensor_2438 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1813, 0.0004171783511992544, 32679, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5048566Z     %view_134 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_2436, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.5049255Z     %quantize_per_tensor_1814 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_134, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5050104Z     %dequantize_per_tensor_2439 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1814, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5050585Z     %_to_copy_22 : [num_users=1] = call_function[target=torch.ops.aten._to_copy.default](args = (%dequantize_per_tensor_2437,), kwargs = {dtype: torch.float32})
2025-03-21T20:30:48.5051304Z     %quantize_per_tensor_1815 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%_to_copy_22, 0.00039327371632680297, 29965, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5052082Z     %dequantize_per_tensor_2440 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1815, 0.00039327371632680297, 29965, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5052549Z     %view_135 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_2440, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:30:48.5053245Z     %quantize_per_tensor_1816 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_135, 0.00039327371632680297, 29965, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5054037Z     %dequantize_per_tensor_2441 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1816, 0.00039327371632680297, 29965, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5054440Z     %unbind_22 : [num_users=2] = call_function[target=torch.ops.aten.unbind.int](args = (%dequantize_per_tensor_2441, -1), kwargs = {})
2025-03-21T20:30:48.5054771Z     %getitem_44 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_22, 0), kwargs = {})
2025-03-21T20:30:48.5055084Z     %getitem_45 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_22, 1), kwargs = {})
2025-03-21T20:30:48.5055826Z     %quantize_per_tensor_1817 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_44, 0.00039327371632680297, 29965, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5056627Z     %dequantize_per_tensor_2442 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1817, 0.00039327371632680297, 29965, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5057416Z     %dequantize_per_tensor_2443 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1817, 0.00039327371632680297, 29965, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5058135Z     %quantize_per_tensor_1818 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_45, 0.000342332263244316, 30696, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5058920Z     %dequantize_per_tensor_2444 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1818, 0.000342332263244316, 30696, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5059686Z     %dequantize_per_tensor_2445 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1818, 0.000342332263244316, 30696, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5060201Z     %_to_copy_23 : [num_users=1] = call_function[target=torch.ops.aten._to_copy.default](args = (%dequantize_per_tensor_2438,), kwargs = {dtype: torch.float32})
2025-03-21T20:30:48.5060899Z     %quantize_per_tensor_1819 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%_to_copy_23, 0.0004171783511992544, 32679, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5061685Z     %dequantize_per_tensor_2446 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1819, 0.0004171783511992544, 32679, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5062141Z     %view_136 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_2446, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:30:48.5062843Z     %quantize_per_tensor_1820 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_136, 0.0004171783511992544, 32679, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5063616Z     %dequantize_per_tensor_2447 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1820, 0.0004171783511992544, 32679, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5064035Z     %unbind_23 : [num_users=2] = call_function[target=torch.ops.aten.unbind.int](args = (%dequantize_per_tensor_2447, -1), kwargs = {})
2025-03-21T20:30:48.5064351Z     %getitem_46 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_23, 0), kwargs = {})
2025-03-21T20:30:48.5064671Z     %getitem_47 : [num_users=1] = call_function[target=operator.getitem](args = (%unbind_23, 1), kwargs = {})
2025-03-21T20:30:48.5065390Z     %quantize_per_tensor_1821 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_46, 0.00038696694537065923, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5066166Z     %dequantize_per_tensor_2448 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1821, 0.00038696694537065923, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5066955Z     %dequantize_per_tensor_2449 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1821, 0.00038696694537065923, 32773, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5067677Z     %quantize_per_tensor_1822 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%getitem_47, 0.0004171783511992544, 32679, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5068488Z     %dequantize_per_tensor_2450 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1822, 0.0004171783511992544, 32679, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5069291Z     %dequantize_per_tensor_2451 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1822, 0.0004171783511992544, 32679, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5069743Z     %view_137 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_151, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:30:48.5070440Z     %quantize_per_tensor_1823 : [num_users=4] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_137, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5071230Z     %dequantize_per_tensor_2452 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1823, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5072023Z     %dequantize_per_tensor_2453 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1823, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5072810Z     %dequantize_per_tensor_2454 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1823, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5073578Z     %dequantize_per_tensor_2455 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1823, 3.051804378628731e-05, 32768, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5074029Z     %view_138 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_163, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:30:48.5074727Z     %quantize_per_tensor_1824 : [num_users=4] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_138, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5075510Z     %dequantize_per_tensor_2456 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1824, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5076281Z     %dequantize_per_tensor_2457 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1824, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5077064Z     %dequantize_per_tensor_2458 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1824, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5077847Z     %dequantize_per_tensor_2459 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1824, 3.051786916330457e-05, 32767, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5078330Z     %mul_121 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_2443, %dequantize_per_tensor_2455), kwargs = {})
2025-03-21T20:30:48.5079019Z     %quantize_per_tensor_1825 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_121, 0.0003908620565198362, 30132, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5079830Z     %dequantize_per_tensor_2460 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1825, 0.0003908620565198362, 30132, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5080333Z     %mul_122 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_2444, %dequantize_per_tensor_2458), kwargs = {})
2025-03-21T20:30:48.5081035Z     %quantize_per_tensor_1826 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_122, 0.00015990187239367515, 32711, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5081835Z     %dequantize_per_tensor_2461 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1826, 0.00015990187239367515, 32711, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5082324Z     %sub_22 : [num_users=1] = call_function[target=torch.ops.aten.sub.Tensor](args = (%dequantize_per_tensor_2460, %dequantize_per_tensor_2461), kwargs = {})
2025-03-21T20:30:48.5083008Z     %quantize_per_tensor_1827 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%sub_22, 0.0003872470697388053, 30395, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5083817Z     %dequantize_per_tensor_2462 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1827, 0.0003872470697388053, 30395, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5084295Z     %mul_123 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_2442, %dequantize_per_tensor_2459), kwargs = {})
2025-03-21T20:30:48.5084999Z     %quantize_per_tensor_1828 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_123, 0.00018527904467191547, 30845, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5085781Z     %dequantize_per_tensor_2463 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1828, 0.00018527904467191547, 30845, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5086270Z     %mul_124 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_2445, %dequantize_per_tensor_2454), kwargs = {})
2025-03-21T20:30:48.5086962Z     %quantize_per_tensor_1829 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_124, 0.00033935264218598604, 30930, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5087751Z     %dequantize_per_tensor_2464 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1829, 0.00033935264218598604, 30930, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5088225Z     %add_55 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_2463, %dequantize_per_tensor_2464), kwargs = {})
2025-03-21T20:30:48.5088924Z     %quantize_per_tensor_1830 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_55, 0.0003357737441547215, 31113, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5089767Z     %dequantize_per_tensor_2465 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1830, 0.0003357737441547215, 31113, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5090266Z     %mul_125 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_2449, %dequantize_per_tensor_2453), kwargs = {})
2025-03-21T20:30:48.5090953Z     %quantize_per_tensor_1831 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_125, 0.0003779088146984577, 32871, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5091806Z     %dequantize_per_tensor_2466 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1831, 0.0003779088146984577, 32871, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5092286Z     %mul_126 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_2450, %dequantize_per_tensor_2456), kwargs = {})
2025-03-21T20:30:48.5093013Z     %quantize_per_tensor_1832 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_126, 0.00018996265134774148, 34253, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5093794Z     %dequantize_per_tensor_2467 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1832, 0.00018996265134774148, 34253, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5094289Z     %sub_23 : [num_users=1] = call_function[target=torch.ops.aten.sub.Tensor](args = (%dequantize_per_tensor_2466, %dequantize_per_tensor_2467), kwargs = {})
2025-03-21T20:30:48.5094981Z     %quantize_per_tensor_1833 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%sub_23, 0.00038636886165477335, 32957, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5095800Z     %dequantize_per_tensor_2468 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1833, 0.00038636886165477335, 32957, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5096282Z     %mul_127 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_2448, %dequantize_per_tensor_2457), kwargs = {})
2025-03-21T20:30:48.5096993Z     %quantize_per_tensor_1834 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_127, 0.00015066901687532663, 31607, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5097776Z     %dequantize_per_tensor_2469 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1834, 0.00015066901687532663, 31607, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5098272Z     %mul_128 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_2451, %dequantize_per_tensor_2452), kwargs = {})
2025-03-21T20:30:48.5098970Z     %quantize_per_tensor_1835 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_128, 0.00040073951822705567, 32950, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5099762Z     %dequantize_per_tensor_2470 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1835, 0.00040073951822705567, 32950, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5100241Z     %add_56 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_2469, %dequantize_per_tensor_2470), kwargs = {})
2025-03-21T20:30:48.5100944Z     %quantize_per_tensor_1836 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_56, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5101720Z     %dequantize_per_tensor_2471 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1836, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5102254Z     %stack_22 : [num_users=1] = call_function[target=torch.ops.aten.stack.default](args = ([%dequantize_per_tensor_2462, %dequantize_per_tensor_2465], -1), kwargs = {})
2025-03-21T20:30:48.5102970Z     %quantize_per_tensor_1837 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%stack_22, 0.0003872470697388053, 30395, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5103782Z     %dequantize_per_tensor_2472 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1837, 0.0003872470697388053, 30395, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5104231Z     %view_139 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_2472, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.5104958Z     %quantize_per_tensor_1838 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_139, 0.0003872470697388053, 30395, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5105736Z     %dequantize_per_tensor_2473 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1838, 0.0003872470697388053, 30395, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5106267Z     %stack_23 : [num_users=1] = call_function[target=torch.ops.aten.stack.default](args = ([%dequantize_per_tensor_2468, %dequantize_per_tensor_2471], -1), kwargs = {})
2025-03-21T20:30:48.5106983Z     %quantize_per_tensor_1839 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%stack_23, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5107765Z     %dequantize_per_tensor_2474 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1839, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5108208Z     %view_140 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_2474, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:30:48.5108908Z     %quantize_per_tensor_1840 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_140, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5109680Z     %dequantize_per_tensor_2475 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1840, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5110196Z     %type_as_22 : [num_users=1] = call_function[target=torch.ops.aten.type_as.default](args = (%dequantize_per_tensor_2473, %dequantize_per_tensor_2437), kwargs = {})
2025-03-21T20:30:48.5110892Z     %quantize_per_tensor_1841 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%type_as_22, 0.0003872470697388053, 30395, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5111679Z     %dequantize_per_tensor_2476 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1841, 0.0003872470697388053, 30395, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5112178Z     %type_as_23 : [num_users=1] = call_function[target=torch.ops.aten.type_as.default](args = (%dequantize_per_tensor_2475, %dequantize_per_tensor_2438), kwargs = {})
2025-03-21T20:30:48.5112886Z     %quantize_per_tensor_1842 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%type_as_23, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5113661Z     %dequantize_per_tensor_2477 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1842, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5114122Z     %transpose_457 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2476, 1, 2), kwargs = {})
2025-03-21T20:30:48.5114865Z     %quantize_per_tensor_1843 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_457, 0.0003872470697388053, 30395, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5115675Z     %dequantize_per_tensor_2478 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1843, 0.0003872470697388053, 30395, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5116328Z     %index_put_22 : [num_users=1] = call_function[target=torch.ops.aten.index_put.default](args = (%dequantize_per_tensor_146, [None, %attn_options_input_pos], %dequantize_per_tensor_2477), kwargs = {})
2025-03-21T20:30:48.5117050Z     %quantize_per_tensor_1844 : [num_users=13] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_put_22, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5117829Z     %dequantize_per_tensor_2479 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1844, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5118612Z     %dequantize_per_tensor_2480 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1844, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5119409Z     %dequantize_per_tensor_2481 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1844, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5120188Z     %dequantize_per_tensor_2482 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1844, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5120959Z     %dequantize_per_tensor_2483 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1844, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5121745Z     %dequantize_per_tensor_2484 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1844, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5122516Z     %dequantize_per_tensor_2485 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1844, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5123298Z     %dequantize_per_tensor_2486 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1844, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5124068Z     %dequantize_per_tensor_2487 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1844, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5124854Z     %dequantize_per_tensor_2488 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1844, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5125636Z     %dequantize_per_tensor_2489 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1844, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5126402Z     %dequantize_per_tensor_2490 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1844, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5127239Z     %dequantize_per_tensor_2491 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1844, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5127871Z     %index_put_23 : [num_users=1] = call_function[target=torch.ops.aten.index_put.default](args = (%dequantize_per_tensor_147, [None, %attn_options_input_pos], %dequantize_per_tensor_2439), kwargs = {})
2025-03-21T20:30:48.5128614Z     %quantize_per_tensor_1845 : [num_users=13] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_put_23, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5129447Z     %dequantize_per_tensor_2492 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1845, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5130236Z     %dequantize_per_tensor_2493 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1845, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5131042Z     %dequantize_per_tensor_2494 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1845, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5131818Z     %dequantize_per_tensor_2495 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1845, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5132729Z     %dequantize_per_tensor_2496 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1845, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5133500Z     %dequantize_per_tensor_2497 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1845, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5134282Z     %dequantize_per_tensor_2498 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1845, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5135057Z     %dequantize_per_tensor_2499 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1845, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5135841Z     %dequantize_per_tensor_2500 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1845, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5136609Z     %dequantize_per_tensor_2501 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1845, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5137399Z     %dequantize_per_tensor_2502 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1845, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5138183Z     %dequantize_per_tensor_2503 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1845, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5139002Z     %dequantize_per_tensor_2504 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1845, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5139488Z     %transpose_458 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2491, 1, 2), kwargs = {})
2025-03-21T20:30:48.5140207Z     %quantize_per_tensor_1846 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_458, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5141001Z     %dequantize_per_tensor_2505 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1846, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5141429Z     %select_528 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2505, 0, 0), kwargs = {})
2025-03-21T20:30:48.5142128Z     %quantize_per_tensor_1847 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_528, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5142909Z     %dequantize_per_tensor_2506 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1847, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5143349Z     %select_529 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2506, 0, 0), kwargs = {})
2025-03-21T20:30:48.5144062Z     %quantize_per_tensor_1848 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_529, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5144834Z     %dequantize_per_tensor_2507 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1848, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5145288Z     %transpose_459 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2490, 1, 2), kwargs = {})
2025-03-21T20:30:48.5146004Z     %quantize_per_tensor_1849 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_459, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5146790Z     %dequantize_per_tensor_2508 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1849, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5147197Z     %select_530 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2508, 0, 0), kwargs = {})
2025-03-21T20:30:48.5147911Z     %quantize_per_tensor_1850 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_530, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5148680Z     %dequantize_per_tensor_2509 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1850, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5149104Z     %select_531 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2509, 0, 1), kwargs = {})
2025-03-21T20:30:48.5149802Z     %quantize_per_tensor_1851 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_531, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5150627Z     %dequantize_per_tensor_2510 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1851, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5151085Z     %transpose_460 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2489, 1, 2), kwargs = {})
2025-03-21T20:30:48.5151810Z     %quantize_per_tensor_1852 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_460, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5152596Z     %dequantize_per_tensor_2511 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1852, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5153019Z     %select_532 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2511, 0, 0), kwargs = {})
2025-03-21T20:30:48.5153716Z     %quantize_per_tensor_1853 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_532, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5154499Z     %dequantize_per_tensor_2512 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1853, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5154932Z     %select_533 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2512, 0, 2), kwargs = {})
2025-03-21T20:30:48.5155644Z     %quantize_per_tensor_1854 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_533, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5156413Z     %dequantize_per_tensor_2513 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1854, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5156866Z     %transpose_461 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2488, 1, 2), kwargs = {})
2025-03-21T20:30:48.5157575Z     %quantize_per_tensor_1855 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_461, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5158354Z     %dequantize_per_tensor_2514 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1855, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5158762Z     %select_534 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2514, 0, 0), kwargs = {})
2025-03-21T20:30:48.5159475Z     %quantize_per_tensor_1856 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_534, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5160243Z     %dequantize_per_tensor_2515 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1856, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5160664Z     %select_535 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2515, 0, 3), kwargs = {})
2025-03-21T20:30:48.5161356Z     %quantize_per_tensor_1857 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_535, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5162162Z     %dequantize_per_tensor_2516 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1857, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5162621Z     %transpose_462 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2487, 1, 2), kwargs = {})
2025-03-21T20:30:48.5163345Z     %quantize_per_tensor_1858 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_462, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5164134Z     %dequantize_per_tensor_2517 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1858, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5164553Z     %select_536 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2517, 0, 0), kwargs = {})
2025-03-21T20:30:48.5165248Z     %quantize_per_tensor_1859 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_536, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5166029Z     %dequantize_per_tensor_2518 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1859, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5166459Z     %select_537 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2518, 0, 4), kwargs = {})
2025-03-21T20:30:48.5167175Z     %quantize_per_tensor_1860 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_537, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5167942Z     %dequantize_per_tensor_2519 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1860, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5168399Z     %transpose_463 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2486, 1, 2), kwargs = {})
2025-03-21T20:30:48.5169112Z     %quantize_per_tensor_1861 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_463, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5169947Z     %dequantize_per_tensor_2520 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1861, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5170354Z     %select_538 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2520, 0, 0), kwargs = {})
2025-03-21T20:30:48.5171066Z     %quantize_per_tensor_1862 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_538, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5171834Z     %dequantize_per_tensor_2521 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1862, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5172257Z     %select_539 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2521, 0, 5), kwargs = {})
2025-03-21T20:30:48.5172952Z     %quantize_per_tensor_1863 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_539, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5173759Z     %dequantize_per_tensor_2522 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1863, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5174220Z     %transpose_464 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2485, 1, 2), kwargs = {})
2025-03-21T20:30:48.5174945Z     %quantize_per_tensor_1864 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_464, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5175747Z     %dequantize_per_tensor_2523 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1864, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5176168Z     %select_540 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2523, 0, 0), kwargs = {})
2025-03-21T20:30:48.5176863Z     %quantize_per_tensor_1865 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_540, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5177647Z     %dequantize_per_tensor_2524 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1865, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5178077Z     %select_541 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2524, 0, 6), kwargs = {})
2025-03-21T20:30:48.5178785Z     %quantize_per_tensor_1866 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_541, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5179553Z     %dequantize_per_tensor_2525 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1866, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5180004Z     %transpose_465 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2484, 1, 2), kwargs = {})
2025-03-21T20:30:48.5180715Z     %quantize_per_tensor_1867 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_465, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5181495Z     %dequantize_per_tensor_2526 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1867, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5181898Z     %select_542 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2526, 0, 0), kwargs = {})
2025-03-21T20:30:48.5182606Z     %quantize_per_tensor_1868 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_542, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5183373Z     %dequantize_per_tensor_2527 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1868, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5183798Z     %select_543 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2527, 0, 7), kwargs = {})
2025-03-21T20:30:48.5184496Z     %quantize_per_tensor_1869 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_543, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5185287Z     %dequantize_per_tensor_2528 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1869, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5185762Z     %transpose_466 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2483, 1, 2), kwargs = {})
2025-03-21T20:30:48.5186475Z     %quantize_per_tensor_1870 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_466, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5187272Z     %dequantize_per_tensor_2529 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1870, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5187682Z     %select_544 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2529, 0, 0), kwargs = {})
2025-03-21T20:30:48.5188386Z     %quantize_per_tensor_1871 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_544, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5189155Z     %dequantize_per_tensor_2530 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1871, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5189598Z     %select_545 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2530, 0, 8), kwargs = {})
2025-03-21T20:30:48.5190295Z     %quantize_per_tensor_1872 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_545, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5191077Z     %dequantize_per_tensor_2531 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1872, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5191521Z     %transpose_467 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2482, 1, 2), kwargs = {})
2025-03-21T20:30:48.5192244Z     %quantize_per_tensor_1873 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_467, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5193015Z     %dequantize_per_tensor_2532 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1873, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5193431Z     %select_546 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2532, 0, 0), kwargs = {})
2025-03-21T20:30:48.5194128Z     %quantize_per_tensor_1874 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_546, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5194906Z     %dequantize_per_tensor_2533 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1874, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5195317Z     %select_547 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2533, 0, 9), kwargs = {})
2025-03-21T20:30:48.5196028Z     %quantize_per_tensor_1875 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_547, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5196824Z     %dequantize_per_tensor_2534 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1875, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5197299Z     %transpose_468 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2481, 1, 2), kwargs = {})
2025-03-21T20:30:48.5198018Z     %quantize_per_tensor_1876 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_468, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5198820Z     %dequantize_per_tensor_2535 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1876, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5199235Z     %select_548 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2535, 0, 0), kwargs = {})
2025-03-21T20:30:48.5199946Z     %quantize_per_tensor_1877 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_548, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5200721Z     %dequantize_per_tensor_2536 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1877, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5201173Z     %select_549 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2536, 0, 10), kwargs = {})
2025-03-21T20:30:48.5201878Z     %quantize_per_tensor_1878 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_549, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5202657Z     %dequantize_per_tensor_2537 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1878, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5203100Z     %transpose_469 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2480, 1, 2), kwargs = {})
2025-03-21T20:30:48.5203823Z     %quantize_per_tensor_1879 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_469, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5204594Z     %dequantize_per_tensor_2538 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1879, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5205013Z     %select_550 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2538, 0, 0), kwargs = {})
2025-03-21T20:30:48.5205708Z     %quantize_per_tensor_1880 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_550, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5206494Z     %dequantize_per_tensor_2539 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1880, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5206905Z     %select_551 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2539, 0, 11), kwargs = {})
2025-03-21T20:30:48.5207610Z     %quantize_per_tensor_1881 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_551, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5208399Z     %dequantize_per_tensor_2540 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1881, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5209982Z     %cat_22 : [num_users=1] = call_function[target=torch.ops.aten.cat.default](args = ([%dequantize_per_tensor_2507, %dequantize_per_tensor_2510, %dequantize_per_tensor_2513, %dequantize_per_tensor_2516, %dequantize_per_tensor_2519, %dequantize_per_tensor_2522, %dequantize_per_tensor_2525, %dequantize_per_tensor_2528, %dequantize_per_tensor_2531, %dequantize_per_tensor_2534, %dequantize_per_tensor_2537, %dequantize_per_tensor_2540],), kwargs = {})
2025-03-21T20:30:48.5210693Z     %quantize_per_tensor_1882 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%cat_22, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5211479Z     %dequantize_per_tensor_2541 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1882, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5211926Z     %view_141 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_2541, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:30:48.5212626Z     %quantize_per_tensor_1883 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_141, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5213423Z     %dequantize_per_tensor_2542 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1883, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5213873Z     %transpose_470 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2504, 1, 2), kwargs = {})
2025-03-21T20:30:48.5214588Z     %quantize_per_tensor_1884 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_470, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5215368Z     %dequantize_per_tensor_2543 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1884, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5215777Z     %select_552 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2543, 0, 0), kwargs = {})
2025-03-21T20:30:48.5216485Z     %quantize_per_tensor_1885 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_552, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5217254Z     %dequantize_per_tensor_2544 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1885, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5217676Z     %select_553 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2544, 0, 0), kwargs = {})
2025-03-21T20:30:48.5218373Z     %quantize_per_tensor_1886 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_553, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5219155Z     %dequantize_per_tensor_2545 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1886, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5219590Z     %transpose_471 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2503, 1, 2), kwargs = {})
2025-03-21T20:30:48.5220338Z     %quantize_per_tensor_1887 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_471, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5221141Z     %dequantize_per_tensor_2546 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1887, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5221567Z     %select_554 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2546, 0, 0), kwargs = {})
2025-03-21T20:30:48.5222286Z     %quantize_per_tensor_1888 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_554, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5223065Z     %dequantize_per_tensor_2547 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1888, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5223475Z     %select_555 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2547, 0, 1), kwargs = {})
2025-03-21T20:30:48.5224184Z     %quantize_per_tensor_1889 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_555, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5224978Z     %dequantize_per_tensor_2548 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1889, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5225429Z     %transpose_472 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2502, 1, 2), kwargs = {})
2025-03-21T20:30:48.5226143Z     %quantize_per_tensor_1890 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_472, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5226924Z     %dequantize_per_tensor_2549 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1890, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5227335Z     %select_556 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2549, 0, 0), kwargs = {})
2025-03-21T20:30:48.5228049Z     %quantize_per_tensor_1891 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_556, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5228815Z     %dequantize_per_tensor_2550 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1891, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5229239Z     %select_557 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2550, 0, 2), kwargs = {})
2025-03-21T20:30:48.5229936Z     %quantize_per_tensor_1892 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_557, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5230720Z     %dequantize_per_tensor_2551 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1892, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5231159Z     %transpose_473 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2501, 1, 2), kwargs = {})
2025-03-21T20:30:48.5231911Z     %quantize_per_tensor_1893 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_473, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5232824Z     %dequantize_per_tensor_2552 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1893, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5233248Z     %select_558 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2552, 0, 0), kwargs = {})
2025-03-21T20:30:48.5233990Z     %quantize_per_tensor_1894 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_558, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5234775Z     %dequantize_per_tensor_2553 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1894, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5235189Z     %select_559 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2553, 0, 3), kwargs = {})
2025-03-21T20:30:48.5235895Z     %quantize_per_tensor_1895 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_559, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5236697Z     %dequantize_per_tensor_2554 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1895, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5237153Z     %transpose_474 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2500, 1, 2), kwargs = {})
2025-03-21T20:30:48.5237867Z     %quantize_per_tensor_1896 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_474, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5238652Z     %dequantize_per_tensor_2555 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1896, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5239061Z     %select_560 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2555, 0, 0), kwargs = {})
2025-03-21T20:30:48.5239776Z     %quantize_per_tensor_1897 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_560, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5240543Z     %dequantize_per_tensor_2556 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1897, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5240968Z     %select_561 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2556, 0, 4), kwargs = {})
2025-03-21T20:30:48.5241661Z     %quantize_per_tensor_1898 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_561, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5242447Z     %dequantize_per_tensor_2557 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1898, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5242884Z     %transpose_475 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2499, 1, 2), kwargs = {})
2025-03-21T20:30:48.5243631Z     %quantize_per_tensor_1899 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_475, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5244433Z     %dequantize_per_tensor_2558 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1899, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5244843Z     %select_562 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2558, 0, 0), kwargs = {})
2025-03-21T20:30:48.5245572Z     %quantize_per_tensor_1900 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_562, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5246345Z     %dequantize_per_tensor_2559 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1900, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5246766Z     %select_563 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2559, 0, 5), kwargs = {})
2025-03-21T20:30:48.5247461Z     %quantize_per_tensor_1901 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_563, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5248269Z     %dequantize_per_tensor_2560 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1901, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5248709Z     %transpose_476 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2498, 1, 2), kwargs = {})
2025-03-21T20:30:48.5249487Z     %quantize_per_tensor_1902 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_476, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5250260Z     %dequantize_per_tensor_2561 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1902, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5250680Z     %select_564 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2561, 0, 0), kwargs = {})
2025-03-21T20:30:48.5251375Z     %quantize_per_tensor_1903 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_564, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5252151Z     %dequantize_per_tensor_2562 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1903, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5252566Z     %select_565 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2562, 0, 6), kwargs = {})
2025-03-21T20:30:48.5253272Z     %quantize_per_tensor_1904 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_565, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5254048Z     %dequantize_per_tensor_2563 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1904, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5254497Z     %transpose_477 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2497, 1, 2), kwargs = {})
2025-03-21T20:30:48.5255239Z     %quantize_per_tensor_1905 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_477, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5256041Z     %dequantize_per_tensor_2564 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1905, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5256449Z     %select_566 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2564, 0, 0), kwargs = {})
2025-03-21T20:30:48.5257178Z     %quantize_per_tensor_1906 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_566, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5257947Z     %dequantize_per_tensor_2565 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1906, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5258368Z     %select_567 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2565, 0, 7), kwargs = {})
2025-03-21T20:30:48.5259065Z     %quantize_per_tensor_1907 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_567, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5259861Z     %dequantize_per_tensor_2566 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1907, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5260301Z     %transpose_478 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2496, 1, 2), kwargs = {})
2025-03-21T20:30:48.5261021Z     %quantize_per_tensor_1908 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_478, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5261787Z     %dequantize_per_tensor_2567 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1908, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5262207Z     %select_568 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2567, 0, 0), kwargs = {})
2025-03-21T20:30:48.5262908Z     %quantize_per_tensor_1909 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_568, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5263687Z     %dequantize_per_tensor_2568 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1909, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5264101Z     %select_569 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2568, 0, 8), kwargs = {})
2025-03-21T20:30:48.5264812Z     %quantize_per_tensor_1910 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_569, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5265582Z     %dequantize_per_tensor_2569 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1910, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5266036Z     %transpose_479 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2495, 1, 2), kwargs = {})
2025-03-21T20:30:48.5266779Z     %quantize_per_tensor_1911 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_479, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5267581Z     %dequantize_per_tensor_2570 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1911, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5267991Z     %select_570 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2570, 0, 0), kwargs = {})
2025-03-21T20:30:48.5268719Z     %quantize_per_tensor_1912 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_570, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5269486Z     %dequantize_per_tensor_2571 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1912, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5269906Z     %select_571 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2571, 0, 9), kwargs = {})
2025-03-21T20:30:48.5270599Z     %quantize_per_tensor_1913 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_571, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5271402Z     %dequantize_per_tensor_2572 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1913, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5271840Z     %transpose_480 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2494, 1, 2), kwargs = {})
2025-03-21T20:30:48.5272567Z     %quantize_per_tensor_1914 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_480, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5273337Z     %dequantize_per_tensor_2573 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1914, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5273759Z     %select_572 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2573, 0, 0), kwargs = {})
2025-03-21T20:30:48.5274452Z     %quantize_per_tensor_1915 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_572, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5275233Z     %dequantize_per_tensor_2574 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1915, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5275647Z     %select_573 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2574, 0, 10), kwargs = {})
2025-03-21T20:30:48.5276359Z     %quantize_per_tensor_1916 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_573, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5277123Z     %dequantize_per_tensor_2575 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1916, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5277580Z     %transpose_481 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2493, 1, 2), kwargs = {})
2025-03-21T20:30:48.5278312Z     %quantize_per_tensor_1917 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_481, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5279117Z     %dequantize_per_tensor_2576 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1917, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5279526Z     %select_574 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2576, 0, 0), kwargs = {})
2025-03-21T20:30:48.5280262Z     %quantize_per_tensor_1918 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_574, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5281033Z     %dequantize_per_tensor_2577 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1918, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5281455Z     %select_575 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2577, 0, 11), kwargs = {})
2025-03-21T20:30:48.5282151Z     %quantize_per_tensor_1919 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_575, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5282955Z     %dequantize_per_tensor_2578 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1919, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5284452Z     %cat_23 : [num_users=1] = call_function[target=torch.ops.aten.cat.default](args = ([%dequantize_per_tensor_2545, %dequantize_per_tensor_2548, %dequantize_per_tensor_2551, %dequantize_per_tensor_2554, %dequantize_per_tensor_2557, %dequantize_per_tensor_2560, %dequantize_per_tensor_2563, %dequantize_per_tensor_2566, %dequantize_per_tensor_2569, %dequantize_per_tensor_2572, %dequantize_per_tensor_2575, %dequantize_per_tensor_2578],), kwargs = {})
2025-03-21T20:30:48.5285145Z     %quantize_per_tensor_1920 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%cat_23, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5285915Z     %dequantize_per_tensor_2579 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1920, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5286374Z     %view_142 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_2579, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:30:48.5287056Z     %quantize_per_tensor_1921 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_142, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5287837Z     %dequantize_per_tensor_2580 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1921, 0.0001868398830993101, 34146, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5288602Z     %quantize_per_tensor_1922 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%dequantize_per_tensor_2580, 0.00019470337429083884, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.5289448Z     %dequantize_per_tensor_2581 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1922, 0.00019470337429083884, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.5289928Z     %index_13 : [num_users=1] = call_function[target=torch.ops.aten.index.Tensor](args = (%dequantize_per_tensor_148, [%attn_options_input_pos]), kwargs = {})
2025-03-21T20:30:48.5290655Z     %quantize_per_tensor_1923 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%index_13, 0.0038910505827516317, 65535, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5291450Z     %dequantize_per_tensor_2582 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1923, 0.0038910505827516317, 65535, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5291910Z     %transpose_482 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2542, -2, -1), kwargs = {})
2025-03-21T20:30:48.5292647Z     %quantize_per_tensor_1924 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_482, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5293427Z     %dequantize_per_tensor_2583 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1924, 0.0004016910679638386, 33587, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5294194Z     %quantize_per_tensor_1925 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%dequantize_per_tensor_2583, 0.00041174760553985834, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.5295004Z     %dequantize_per_tensor_2584 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1925, 0.00041174760553985834, 0, -32767, 32767, torch.int16), kwargs = {})
2025-03-21T20:30:48.5295512Z     %matmul_22 : [num_users=1] = call_function[target=torch.ops.aten.matmul.default](args = (%dequantize_per_tensor_2478, %dequantize_per_tensor_2584), kwargs = {})
2025-03-21T20:30:48.5296222Z     %quantize_per_tensor_1926 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%matmul_22, 0.0039060052949935198, 34370, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5296997Z     %dequantize_per_tensor_2585 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1926, 0.0039060052949935198, 34370, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5297749Z     %dequantize_per_tensor_2586 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%b__frozen_param160, 1.9073777366429567e-06, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5298226Z     %mul_129 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_2585, %dequantize_per_tensor_2586), kwargs = {})
2025-03-21T20:30:48.5298925Z     %quantize_per_tensor_1927 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_129, 0.00048825066187418997, 34370, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5299702Z     %dequantize_per_tensor_2587 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1927, 0.00048825066187418997, 34370, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5300186Z     %add_57 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_2587, %dequantize_per_tensor_2582), kwargs = {})
2025-03-21T20:30:48.5300871Z     %quantize_per_tensor_1928 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_57, 0.0042822156101465225, 61982, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5301652Z     %dequantize_per_tensor_2588 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1928, 0.0042822156101465225, 61982, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5302091Z     %softmax_11 : [num_users=1] = call_function[target=torch.ops.aten.softmax.int](args = (%dequantize_per_tensor_2588, -1), kwargs = {})
2025-03-21T20:30:48.5302816Z     %quantize_per_tensor_1929 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%softmax_11, 1.5259021893143654e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5303579Z     %dequantize_per_tensor_2589 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1929, 1.5259021893143654e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5304119Z     %matmul_23 : [num_users=1] = call_function[target=torch.ops.aten.matmul.default](args = (%dequantize_per_tensor_2589, %dequantize_per_tensor_2581), kwargs = {})
2025-03-21T20:30:48.5304811Z     %quantize_per_tensor_1930 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%matmul_23, 0.00014522179844789207, 27770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5305603Z     %dequantize_per_tensor_2590 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1930, 0.00014522179844789207, 27770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5306079Z     %transpose_483 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2590, 1, 2), kwargs = {})
2025-03-21T20:30:48.5306808Z     %quantize_per_tensor_1931 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_483, 0.00014522179844789207, 27770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5307578Z     %dequantize_per_tensor_2591 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1931, 0.00014522179844789207, 27770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5308016Z     %view_143 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_2591, [1, 1, 768]), kwargs = {})
2025-03-21T20:30:48.5308708Z     %quantize_per_tensor_1932 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_143, 0.00014522179844789207, 27770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5309490Z     %dequantize_per_tensor_2592 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1932, 0.00014522179844789207, 27770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5309940Z     %unsqueeze_80 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_2592, -1), kwargs = {})
2025-03-21T20:30:48.5310665Z     %quantize_per_tensor_1933 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_80, 0.00014522179844789207, 27770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5311439Z     %dequantize_per_tensor_2593 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1933, 0.00014522179844789207, 27770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5311892Z     %transpose_484 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2593, 1, 2), kwargs = {})
2025-03-21T20:30:48.5312607Z     %quantize_per_tensor_1934 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_484, 0.00014522179844789207, 27770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5313389Z     %dequantize_per_tensor_2594 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1934, 0.00014522179844789207, 27770, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5313945Z     %conv2d_80 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_2594, %dequantize_per_tensor_104), kwargs = {})
2025-03-21T20:30:48.5314650Z     %quantize_per_tensor_1935 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_80, 0.0005083726719021797, 47465, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5315439Z     %dequantize_per_tensor_2595 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1935, 0.0005083726719021797, 47465, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5315889Z     %transpose_485 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2595, 1, 2), kwargs = {})
2025-03-21T20:30:48.5316602Z     %quantize_per_tensor_1936 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_485, 0.0005083726719021797, 47465, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5317386Z     %dequantize_per_tensor_2596 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1936, 0.0005083726719021797, 47465, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5317817Z     %squeeze_80 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_2596, -1), kwargs = {})
2025-03-21T20:30:48.5318513Z     %quantize_per_tensor_1937 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_80, 0.0005083726719021797, 47465, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5319287Z     %dequantize_per_tensor_2597 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1937, 0.0005083726719021797, 47465, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5319761Z     %add_58 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_2417, %dequantize_per_tensor_2597), kwargs = {})
2025-03-21T20:30:48.5320444Z     %quantize_per_tensor_1938 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_58, 0.0023697831202298403, 14969, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5321214Z     %dequantize_per_tensor_2598 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1938, 0.0023697831202298403, 14969, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5321986Z     %dequantize_per_tensor_2599 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1938, 0.0023697831202298403, 14969, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5322530Z     %rms_norm_23 : [num_users=1] = call_function[target=torch.ops.aten.rms_norm.default](args = (%dequantize_per_tensor_2599, [768], %dequantize_per_tensor_105, 1e-05), kwargs = {})
2025-03-21T20:30:48.5323233Z     %quantize_per_tensor_1939 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%rms_norm_23, 0.0006559237372130156, 27360, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5324001Z     %dequantize_per_tensor_2600 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1939, 0.0006559237372130156, 27360, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5324776Z     %dequantize_per_tensor_2601 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1939, 0.0006559237372130156, 27360, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5325259Z     %unsqueeze_81 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_2601, -1), kwargs = {})
2025-03-21T20:30:48.5325995Z     %quantize_per_tensor_1940 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_81, 0.0006559237372130156, 27360, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5326763Z     %dequantize_per_tensor_2602 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1940, 0.0006559237372130156, 27360, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5327235Z     %transpose_486 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2602, 1, 2), kwargs = {})
2025-03-21T20:30:48.5327954Z     %quantize_per_tensor_1941 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_486, 0.0006559237372130156, 27360, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5328730Z     %dequantize_per_tensor_2603 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1941, 0.0006559237372130156, 27360, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5329344Z     %conv2d_81 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_2603, %dequantize_per_tensor_106), kwargs = {})
2025-03-21T20:30:48.5330047Z     %quantize_per_tensor_1942 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_81, 0.0002535042294766754, 28878, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5330814Z     %dequantize_per_tensor_2604 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1942, 0.0002535042294766754, 28878, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5331265Z     %transpose_487 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2604, 1, 2), kwargs = {})
2025-03-21T20:30:48.5331981Z     %quantize_per_tensor_1943 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_487, 0.0002535042294766754, 28878, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5332883Z     %dequantize_per_tensor_2605 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1943, 0.0002535042294766754, 28878, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5333293Z     %squeeze_81 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_2605, -1), kwargs = {})
2025-03-21T20:30:48.5334011Z     %quantize_per_tensor_1944 : [num_users=2] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_81, 0.0002535042294766754, 28878, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5334787Z     %dequantize_per_tensor_2606 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1944, 0.0002535042294766754, 28878, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5335565Z     %dequantize_per_tensor_2607 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1944, 0.0002535042294766754, 28878, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5335988Z     %sigmoid_11 : [num_users=1] = call_function[target=torch.ops.aten.sigmoid.default](args = (%dequantize_per_tensor_2607,), kwargs = {})
2025-03-21T20:30:48.5336664Z     %quantize_per_tensor_1945 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%sigmoid_11, 1.52587890625e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5337454Z     %dequantize_per_tensor_2608 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1945, 1.52587890625e-05, 0, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5337969Z     %mul_130 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_2606, %dequantize_per_tensor_2608), kwargs = {})
2025-03-21T20:30:48.5338659Z     %quantize_per_tensor_1946 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_130, 0.00014603332965634763, 1907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5339468Z     %dequantize_per_tensor_2609 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1946, 0.00014603332965634763, 1907, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5339925Z     %unsqueeze_82 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_2600, -1), kwargs = {})
2025-03-21T20:30:48.5340644Z     %quantize_per_tensor_1947 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_82, 0.0006559237372130156, 27360, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5341449Z     %dequantize_per_tensor_2610 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1947, 0.0006559237372130156, 27360, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5341903Z     %transpose_488 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2610, 1, 2), kwargs = {})
2025-03-21T20:30:48.5342618Z     %quantize_per_tensor_1948 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_488, 0.0006559237372130156, 27360, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5343400Z     %dequantize_per_tensor_2611 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1948, 0.0006559237372130156, 27360, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5343903Z     %conv2d_82 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_2611, %dequantize_per_tensor_107), kwargs = {})
2025-03-21T20:30:48.5344609Z     %quantize_per_tensor_1949 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_82, 0.00044822643394581974, 39750, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5345385Z     %dequantize_per_tensor_2612 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1949, 0.00044822643394581974, 39750, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5345834Z     %transpose_489 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2612, 1, 2), kwargs = {})
2025-03-21T20:30:48.5346553Z     %quantize_per_tensor_1950 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_489, 0.00044822643394581974, 39750, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5347338Z     %dequantize_per_tensor_2613 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1950, 0.00044822643394581974, 39750, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5347750Z     %squeeze_82 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_2613, -1), kwargs = {})
2025-03-21T20:30:48.5348463Z     %quantize_per_tensor_1951 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_82, 0.00044822643394581974, 39750, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5349257Z     %dequantize_per_tensor_2614 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1951, 0.00044822643394581974, 39750, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5349764Z     %mul_131 : [num_users=1] = call_function[target=torch.ops.aten.mul.Tensor](args = (%dequantize_per_tensor_2609, %dequantize_per_tensor_2614), kwargs = {})
2025-03-21T20:30:48.5350444Z     %quantize_per_tensor_1952 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%mul_131, 0.002697124844416976, 47690, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5351248Z     %dequantize_per_tensor_2615 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1952, 0.002697124844416976, 47690, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5351702Z     %unsqueeze_83 : [num_users=1] = call_function[target=torch.ops.aten.unsqueeze.default](args = (%dequantize_per_tensor_2615, -1), kwargs = {})
2025-03-21T20:30:48.5352416Z     %quantize_per_tensor_1953 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%unsqueeze_83, 0.002697124844416976, 47690, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5353210Z     %dequantize_per_tensor_2616 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1953, 0.002697124844416976, 47690, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5353657Z     %transpose_490 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2616, 1, 2), kwargs = {})
2025-03-21T20:30:48.5354368Z     %quantize_per_tensor_1954 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_490, 0.002697124844416976, 47690, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5355142Z     %dequantize_per_tensor_2617 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1954, 0.002697124844416976, 47690, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5355647Z     %conv2d_83 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_2617, %dequantize_per_tensor_108), kwargs = {})
2025-03-21T20:30:48.5356340Z     %quantize_per_tensor_1955 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_83, 0.002150162821635604, 55113, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5357113Z     %dequantize_per_tensor_2618 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1955, 0.002150162821635604, 55113, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5357571Z     %transpose_491 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2618, 1, 2), kwargs = {})
2025-03-21T20:30:48.5358284Z     %quantize_per_tensor_1956 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_491, 0.002150162821635604, 55113, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5359069Z     %dequantize_per_tensor_2619 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1956, 0.002150162821635604, 55113, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5359483Z     %squeeze_83 : [num_users=1] = call_function[target=torch.ops.aten.squeeze.dim](args = (%dequantize_per_tensor_2619, -1), kwargs = {})
2025-03-21T20:30:48.5360191Z     %quantize_per_tensor_1957 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%squeeze_83, 0.002150162821635604, 55113, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5361006Z     %dequantize_per_tensor_2620 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1957, 0.002150162821635604, 55113, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5361493Z     %add_59 : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%dequantize_per_tensor_2598, %dequantize_per_tensor_2620), kwargs = {})
2025-03-21T20:30:48.5362171Z     %quantize_per_tensor_1958 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%add_59, 0.003176590660586953, 40851, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5362979Z     %dequantize_per_tensor_2621 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1958, 0.003176590660586953, 40851, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5363458Z     %slice_1 : [num_users=1] = call_function[target=torch.ops.aten.slice.Tensor](args = (%dequantize_per_tensor_2621, 0, 0, 9223372036854775807), kwargs = {})
2025-03-21T20:30:48.5364159Z     %quantize_per_tensor_1959 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%slice_1, 0.003176590660586953, 40851, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5364951Z     %dequantize_per_tensor_2622 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1959, 0.003176590660586953, 40851, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5365386Z     %select_576 : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%dequantize_per_tensor_2622, 1, -1), kwargs = {})
2025-03-21T20:30:48.5366085Z     %quantize_per_tensor_1960 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%select_576, 0.003176590660586953, 40851, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5366873Z     %dequantize_per_tensor_2623 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1960, 0.003176590660586953, 40851, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5367347Z     %slice_2 : [num_users=1] = call_function[target=torch.ops.aten.slice.Tensor](args = (%dequantize_per_tensor_2623, 1, 0, 9223372036854775807), kwargs = {})
2025-03-21T20:30:48.5368048Z     %quantize_per_tensor_1961 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%slice_2, 0.003176590660586953, 40851, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5368816Z     %dequantize_per_tensor_2624 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1961, 0.003176590660586953, 40851, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5369439Z     %rms_norm_24 : [num_users=1] = call_function[target=torch.ops.aten.rms_norm.default](args = (%dequantize_per_tensor_2624, [768], %dequantize_per_tensor_109, 1e-05), kwargs = {})
2025-03-21T20:30:48.5370145Z     %quantize_per_tensor_1962 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%rms_norm_24, 0.0029369546100497246, 33824, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5370932Z     %dequantize_per_tensor_2625 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1962, 0.0029369546100497246, 33824, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:30:48.5371377Z     %view_144 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_2625, [1, 1, 768, 1]), kwargs = {})
2025-03-21T20:31:03.1527458Z     %quantize_per_tensor_1963 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_144, 0.0029369546100497246, 33824, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:31:03.1529505Z     %dequantize_per_tensor_2626 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1963, 0.0029369546100497246, 33824, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:31:03.1530897Z     %transpose_492 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2626, 1, 2), kwargs = {})
2025-03-21T20:31:03.1532376Z     %quantize_per_tensor_1964 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_492, 0.0029369546100497246, 33824, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:31:03.1534051Z     %dequantize_per_tensor_2627 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1964, 0.0029369546100497246, 33824, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:31:03.1535459Z     %conv2d_84 : [num_users=1] = call_function[target=torch.ops.aten.conv2d.default](args = (%dequantize_per_tensor_2627, %dequantize_per_tensor_110), kwargs = {})
2025-03-21T20:31:03.1536790Z     %quantize_per_tensor_1965 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%conv2d_84, 0.0006781866541132331, 24939, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:31:03.1538429Z     %dequantize_per_tensor_2628 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1965, 0.0006781866541132331, 24939, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:31:03.1539764Z     %transpose_493 : [num_users=1] = call_function[target=torch.ops.aten.transpose.int](args = (%dequantize_per_tensor_2628, 1, 2), kwargs = {})
2025-03-21T20:31:03.1541046Z     %quantize_per_tensor_1966 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%transpose_493, 0.0006781866541132331, 24939, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:31:03.1542649Z     %dequantize_per_tensor_2629 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1966, 0.0006781866541132331, 24939, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:31:03.1543971Z     %view_145 : [num_users=1] = call_function[target=torch.ops.aten.view.default](args = (%dequantize_per_tensor_2629, [1, 32000]), kwargs = {})
2025-03-21T20:31:03.1545212Z     %quantize_per_tensor_1967 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.quantize_per_tensor.default](args = (%view_145, 0.0006781866541132331, 24939, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:31:03.1546789Z     %dequantize_per_tensor_2630 : [num_users=1] = call_function[target=torch.ops.quantized_decomposed.dequantize_per_tensor.default](args = (%quantize_per_tensor_1967, 0.0006781866541132331, 24939, 0, 65535, torch.int32), kwargs = {})
2025-03-21T20:31:03.1548288Z     %copy : [num_users=1] = call_function[target=torch.ops.aten.copy.default](args = (%b_getattr_l__self___layers___0___attention_kv_cache_past_k_caches, %dequantize_per_tensor_235), kwargs = {})
2025-03-21T20:31:03.1549593Z     %copy_1 : [num_users=1] = call_function[target=torch.ops.aten.copy.default](args = (%b_getattr_l__self___layers___0___attention_kv_cache_past_v_caches, %dequantize_per_tensor_248), kwargs = {})
2025-03-21T20:31:03.1550915Z     %copy_2 : [num_users=1] = call_function[target=torch.ops.aten.copy.default](args = (%b_getattr_l__self___layers___1___attention_kv_cache_past_k_caches, %dequantize_per_tensor_439), kwargs = {})
2025-03-21T20:31:03.1552231Z     %copy_3 : [num_users=1] = call_function[target=torch.ops.aten.copy.default](args = (%b_getattr_l__self___layers___1___attention_kv_cache_past_v_caches, %dequantize_per_tensor_452), kwargs = {})
2025-03-21T20:31:03.1553599Z     %copy_4 : [num_users=1] = call_function[target=torch.ops.aten.copy.default](args = (%b_getattr_l__self___layers___2___attention_kv_cache_past_k_caches, %dequantize_per_tensor_643), kwargs = {})
2025-03-21T20:31:03.1554952Z     %copy_5 : [num_users=1] = call_function[target=torch.ops.aten.copy.default](args = (%b_getattr_l__self___layers___2___attention_kv_cache_past_v_caches, %dequantize_per_tensor_656), kwargs = {})
2025-03-21T20:31:03.1556291Z     %copy_6 : [num_users=1] = call_function[target=torch.ops.aten.copy.default](args = (%b_getattr_l__self___layers___3___attention_kv_cache_past_k_caches, %dequantize_per_tensor_847), kwargs = {})
2025-03-21T20:31:03.1557643Z     %copy_7 : [num_users=1] = call_function[target=torch.ops.aten.copy.default](args = (%b_getattr_l__self___layers___3___attention_kv_cache_past_v_caches, %dequantize_per_tensor_860), kwargs = {})
2025-03-21T20:31:03.1558960Z     %copy_8 : [num_users=1] = call_function[target=torch.ops.aten.copy.default](args = (%b_getattr_l__self___layers___4___attention_kv_cache_past_k_caches, %dequantize_per_tensor_1051), kwargs = {})
2025-03-21T20:31:03.1560283Z     %copy_9 : [num_users=1] = call_function[target=torch.ops.aten.copy.default](args = (%b_getattr_l__self___layers___4___attention_kv_cache_past_v_caches, %dequantize_per_tensor_1064), kwargs = {})
2025-03-21T20:31:03.1561603Z     %copy_10 : [num_users=1] = call_function[target=torch.ops.aten.copy.default](args = (%b_getattr_l__self___layers___5___attention_kv_cache_past_k_caches, %dequantize_per_tensor_1255), kwargs = {})
2025-03-21T20:31:03.1562956Z     %copy_11 : [num_users=1] = call_function[target=torch.ops.aten.copy.default](args = (%b_getattr_l__self___layers___5___attention_kv_cache_past_v_caches, %dequantize_per_tensor_1268), kwargs = {})
2025-03-21T20:31:03.1564300Z     %copy_12 : [num_users=1] = call_function[target=torch.ops.aten.copy.default](args = (%b_getattr_l__self___layers___6___attention_kv_cache_past_k_caches, %dequantize_per_tensor_1459), kwargs = {})
2025-03-21T20:31:03.1565628Z     %copy_13 : [num_users=1] = call_function[target=torch.ops.aten.copy.default](args = (%b_getattr_l__self___layers___6___attention_kv_cache_past_v_caches, %dequantize_per_tensor_1472), kwargs = {})
2025-03-21T20:31:03.1566957Z     %copy_14 : [num_users=1] = call_function[target=torch.ops.aten.copy.default](args = (%b_getattr_l__self___layers___7___attention_kv_cache_past_k_caches, %dequantize_per_tensor_1663), kwargs = {})
2025-03-21T20:31:03.1568286Z     %copy_15 : [num_users=1] = call_function[target=torch.ops.aten.copy.default](args = (%b_getattr_l__self___layers___7___attention_kv_cache_past_v_caches, %dequantize_per_tensor_1676), kwargs = {})
2025-03-21T20:31:03.1569685Z     %copy_16 : [num_users=1] = call_function[target=torch.ops.aten.copy.default](args = (%b_getattr_l__self___layers___8___attention_kv_cache_past_k_caches, %dequantize_per_tensor_1867), kwargs = {})
2025-03-21T20:31:03.1571018Z     %copy_17 : [num_users=1] = call_function[target=torch.ops.aten.copy.default](args = (%b_getattr_l__self___layers___8___attention_kv_cache_past_v_caches, %dequantize_per_tensor_1880), kwargs = {})
2025-03-21T20:31:03.1572348Z     %copy_18 : [num_users=1] = call_function[target=torch.ops.aten.copy.default](args = (%b_getattr_l__self___layers___9___attention_kv_cache_past_k_caches, %dequantize_per_tensor_2071), kwargs = {})
2025-03-21T20:31:03.1573668Z     %copy_19 : [num_users=1] = call_function[target=torch.ops.aten.copy.default](args = (%b_getattr_l__self___layers___9___attention_kv_cache_past_v_caches, %dequantize_per_tensor_2084), kwargs = {})
2025-03-21T20:31:03.1574998Z     %copy_20 : [num_users=1] = call_function[target=torch.ops.aten.copy.default](args = (%b_getattr_l__self___layers___10___attention_kv_cache_past_k_caches, %dequantize_per_tensor_2275), kwargs = {})
2025-03-21T20:31:03.1576328Z     %copy_21 : [num_users=1] = call_function[target=torch.ops.aten.copy.default](args = (%b_getattr_l__self___layers___10___attention_kv_cache_past_v_caches, %dequantize_per_tensor_2288), kwargs = {})
2025-03-21T20:31:03.1577696Z     %copy_22 : [num_users=1] = call_function[target=torch.ops.aten.copy.default](args = (%b_getattr_l__self___layers___11___attention_kv_cache_past_k_caches, %dequantize_per_tensor_2479), kwargs = {})
2025-03-21T20:31:03.1579056Z     %copy_23 : [num_users=1] = call_function[target=torch.ops.aten.copy.default](args = (%b_getattr_l__self___layers___11___attention_kv_cache_past_v_caches, %dequantize_per_tensor_2492), kwargs = {})
2025-03-21T20:31:03.1580416Z     return (copy, copy_1, copy_2, copy_3, copy_4, copy_5, copy_6, copy_7, copy_8, copy_9, copy_10, copy_11, copy_12, copy_13, copy_14, copy_15, copy_16, copy_17, copy_18, copy_19, copy_20, copy_21, copy_22, copy_23, dequantize_per_tensor_2630)
2025-03-21T20:31:03.1582274Z /opt/conda/envs/py_3.10/lib/python3.10/site-packages/torch/backends/mkldnn/__init__.py:78: UserWarning: TF32 acceleration on top of oneDNN is available for Intel GPUs. The current Torch version does not have Intel GPU Support. (Triggered internally at /pytorch/aten/src/ATen/Context.cpp:148.)
2025-03-21T20:31:43.1299567Z   torch._C._set_onednn_allow_tf32(_allow_tf32)
2025-03-21T20:31:43.1300327Z [INFO 2025-03-21 20:31:43,128 utils.py:70] Exported graph:
2025-03-21T20:31:43.1300889Z ExportedProgram:
2025-03-21T20:31:43.1301314Z     class GraphModule(torch.nn.Module):
2025-03-21T20:31:43.1345263Z         def forward(self, b__frozen_param0: "i32[32000, 768]", b__frozen_param1: "i32[768]", b__frozen_param2: "i16[768, 768, 1, 1]", b__frozen_param3: "i16[768, 768, 1, 1]", b__frozen_param4: "i16[768, 768, 1, 1]", b__frozen_param5: "i16[768, 768, 1, 1]", b__frozen_param6: "i32[768]", b__frozen_param7: "i16[2048, 768, 1, 1]", b__frozen_param8: "i16[2048, 768, 1, 1]", b__frozen_param9: "i16[768, 2048, 1, 1]", b__frozen_param10: "i32[768]", b__frozen_param11: "i16[768, 768, 1, 1]", b__frozen_param12: "i16[768, 768, 1, 1]", b__frozen_param13: "i16[768, 768, 1, 1]", b__frozen_param14: "i16[768, 768, 1, 1]", b__frozen_param15: "i32[768]", b__frozen_param16: "i16[2048, 768, 1, 1]", b__frozen_param17: "i16[2048, 768, 1, 1]", b__frozen_param18: "i16[768, 2048, 1, 1]", b__frozen_param19: "i32[768]", b__frozen_param20: "i16[768, 768, 1, 1]", b__frozen_param21: "i16[768, 768, 1, 1]", b__frozen_param22: "i16[768, 768, 1, 1]", b__frozen_param23: "i16[768, 768, 1, 1]", b__frozen_param24: "i32[768]", b__frozen_param25: "i16[2048, 768, 1, 1]", b__frozen_param26: "i16[2048, 768, 1, 1]", b__frozen_param27: "i16[768, 2048, 1, 1]", b__frozen_param28: "i32[768]", b__frozen_param29: "i16[768, 768, 1, 1]", b__frozen_param30: "i16[768, 768, 1, 1]", b__frozen_param31: "i16[768, 768, 1, 1]", b__frozen_param32: "i16[768, 768, 1, 1]", b__frozen_param33: "i32[768]", b__frozen_param34: "i16[2048, 768, 1, 1]", b__frozen_param35: "i16[2048, 768, 1, 1]", b__frozen_param36: "i16[768, 2048, 1, 1]", b__frozen_param37: "i32[768]", b__frozen_param38: "i16[768, 768, 1, 1]", b__frozen_param39: "i16[768, 768, 1, 1]", b__frozen_param40: "i16[768, 768, 1, 1]", b__frozen_param41: "i16[768, 768, 1, 1]", b__frozen_param42: "i32[768]", b__frozen_param43: "i16[2048, 768, 1, 1]", b__frozen_param44: "i16[2048, 768, 1, 1]", b__frozen_param45: "i16[768, 2048, 1, 1]", b__frozen_param46: "i32[768]", b__frozen_param47: "i16[768, 768, 1, 1]", b__frozen_param48: "i16[768, 768, 1, 1]", b__frozen_param49: "i16[768, 768, 1, 1]", b__frozen_param50: "i16[768, 768, 1, 1]", b__frozen_param51: "i32[768]", b__frozen_param52: "i16[2048, 768, 1, 1]", b__frozen_param53: "i16[2048, 768, 1, 1]", b__frozen_param54: "i16[768, 2048, 1, 1]", b__frozen_param55: "i32[768]", b__frozen_param56: "i16[768, 768, 1, 1]", b__frozen_param57: "i16[768, 768, 1, 1]", b__frozen_param58: "i16[768, 768, 1, 1]", b__frozen_param59: "i16[768, 768, 1, 1]", b__frozen_param60: "i32[768]", b__frozen_param61: "i16[2048, 768, 1, 1]", b__frozen_param62: "i16[2048, 768, 1, 1]", b__frozen_param63: "i16[768, 2048, 1, 1]", b__frozen_param64: "i32[768]", b__frozen_param65: "i16[768, 768, 1, 1]", b__frozen_param66: "i16[768, 768, 1, 1]", b__frozen_param67: "i16[768, 768, 1, 1]", b__frozen_param68: "i16[768, 768, 1, 1]", b__frozen_param69: "i32[768]", b__frozen_param70: "i16[2048, 768, 1, 1]", b__frozen_param71: "i16[2048, 768, 1, 1]", b__frozen_param72: "i16[768, 2048, 1, 1]", b__frozen_param73: "i32[768]", b__frozen_param74: "i16[768, 768, 1, 1]", b__frozen_param75: "i16[768, 768, 1, 1]", b__frozen_param76: "i16[768, 768, 1, 1]", b__frozen_param77: "i16[768, 768, 1, 1]", b__frozen_param78: "i32[768]", b__frozen_param79: "i16[2048, 768, 1, 1]", b__frozen_param80: "i16[2048, 768, 1, 1]", b__frozen_param81: "i16[768, 2048, 1, 1]", b__frozen_param82: "i32[768]", b__frozen_param83: "i16[768, 768, 1, 1]", b__frozen_param84: "i16[768, 768, 1, 1]", b__frozen_param85: "i16[768, 768, 1, 1]", b__frozen_param86: "i16[768, 768, 1, 1]", b__frozen_param87: "i32[768]", b__frozen_param88: "i16[2048, 768, 1, 1]", b__frozen_param89: "i16[2048, 768, 1, 1]", b__frozen_param90: "i16[768, 2048, 1, 1]", b__frozen_param91: "i32[768]", b__frozen_param92: "i16[768, 768, 1, 1]", b__frozen_param93: "i16[768, 768, 1, 1]", b__frozen_param94: "i16[768, 768, 1, 1]", b__frozen_param95: "i16[768, 768, 1, 1]", b__frozen_param96: "i32[768]", b__frozen_param97: "i16[2048, 768, 1, 1]", b__frozen_param98: "i16[2048, 768, 1, 1]", b__frozen_param99: "i16[768, 2048, 1, 1]", b__frozen_param100: "i32[768]", b__frozen_param101: "i16[768, 768, 1, 1]", b__frozen_param102: "i16[768, 768, 1, 1]", b__frozen_param103: "i16[768, 768, 1, 1]", b__frozen_param104: "i16[768, 768, 1, 1]", b__frozen_param105: "i32[768]", b__frozen_param106: "i16[2048, 768, 1, 1]", b__frozen_param107: "i16[2048, 768, 1, 1]", b__frozen_param108: "i16[768, 2048, 1, 1]", b__frozen_param109: "i32[768]", b__frozen_param110: "i16[32000, 768, 1, 1]", b__frozen_param111: "i32[128, 32]", b__frozen_param112: "i32[128, 32]", b__frozen_param113: "i32[1, 128, 12, 64]", b__frozen_param114: "i32[1, 128, 12, 64]", b__frozen_param115: "i32[128, 128]", b__frozen_param116: "i32[1, 128, 12, 64]", b__frozen_param117: "i32[1, 128, 12, 64]", b__frozen_param118: "i32[128, 128]", b__frozen_param119: "i32[1, 128, 12, 64]", b__frozen_param120: "i32[1, 128, 12, 64]", b__frozen_param121: "i32[128, 128]", b__frozen_param122: "i32[1, 128, 12, 64]", b__frozen_param123: "i32[1, 128, 12, 64]", b__frozen_param124: "i32[128, 128]", b__frozen_param125: "i32[1, 128, 12, 64]", b__frozen_param126: "i32[1, 128, 12, 64]", b__frozen_param127: "i32[128, 128]", b__frozen_param128: "i32[1, 128, 12, 64]", b__frozen_param129: "i32[1, 128, 12, 64]", b__frozen_param130: "i32[128, 128]", b__frozen_param131: "i32[1, 128, 12, 64]", b__frozen_param132: "i32[1, 128, 12, 64]", b__frozen_param133: "i32[128, 128]", b__frozen_param134: "i32[1, 128, 12, 64]", b__frozen_param135: "i32[1, 128, 12, 64]", b__frozen_param136: "i32[128, 128]", b__frozen_param137: "i32[1, 128, 12, 64]", b__frozen_param138: "i32[1, 128, 12, 64]", b__frozen_param139: "i32[128, 128]", b__frozen_param140: "i32[1, 128, 12, 64]", b__frozen_param141: "i32[1, 128, 12, 64]", b__frozen_param142: "i32[128, 128]", b__frozen_param143: "i32[1, 128, 12, 64]", b__frozen_param144: "i32[1, 128, 12, 64]", b__frozen_param145: "i32[128, 128]", b__frozen_param146: "i32[1, 128, 12, 64]", b__frozen_param147: "i32[1, 128, 12, 64]", b__frozen_param148: "i32[128, 128]", b__frozen_param149: "i32[1]", b__frozen_param150: "i32[1]", b__frozen_param151: "i32[1]", b__frozen_param152: "i32[1]", b__frozen_param153: "i32[1]", b__frozen_param154: "i32[1]", b__frozen_param155: "i32[1]", b__frozen_param156: "i32[1]", b__frozen_param157: "i32[1]", b__frozen_param158: "i32[1]", b__frozen_param159: "i32[1]", b__frozen_param160: "i32[1]", b_layers_0_attention_kv_cache_past_k_caches: "f32[1, 128, 12, 64]", b_layers_0_attention_kv_cache_past_v_caches: "f32[1, 128, 12, 64]", b_layers_1_attention_kv_cache_past_k_caches: "f32[1, 128, 12, 64]", b_layers_1_attention_kv_cache_past_v_caches: "f32[1, 128, 12, 64]", b_layers_2_attention_kv_cache_past_k_caches: "f32[1, 128, 12, 64]", b_layers_2_attention_kv_cache_past_v_caches: "f32[1, 128, 12, 64]", b_layers_3_attention_kv_cache_past_k_caches: "f32[1, 128, 12, 64]", b_layers_3_attention_kv_cache_past_v_caches: "f32[1, 128, 12, 64]", b_layers_4_attention_kv_cache_past_k_caches: "f32[1, 128, 12, 64]", b_layers_4_attention_kv_cache_past_v_caches: "f32[1, 128, 12, 64]", b_layers_5_attention_kv_cache_past_k_caches: "f32[1, 128, 12, 64]", b_layers_5_attention_kv_cache_past_v_caches: "f32[1, 128, 12, 64]", b_layers_6_attention_kv_cache_past_k_caches: "f32[1, 128, 12, 64]", b_layers_6_attention_kv_cache_past_v_caches: "f32[1, 128, 12, 64]", b_layers_7_attention_kv_cache_past_k_caches: "f32[1, 128, 12, 64]", b_layers_7_attention_kv_cache_past_v_caches: "f32[1, 128, 12, 64]", b_layers_8_attention_kv_cache_past_k_caches: "f32[1, 128, 12, 64]", b_layers_8_attention_kv_cache_past_v_caches: "f32[1, 128, 12, 64]", b_layers_9_attention_kv_cache_past_k_caches: "f32[1, 128, 12, 64]", b_layers_9_attention_kv_cache_past_v_caches: "f32[1, 128, 12, 64]", b_layers_10_attention_kv_cache_past_k_caches: "f32[1, 128, 12, 64]", b_layers_10_attention_kv_cache_past_v_caches: "f32[1, 128, 12, 64]", b_layers_11_attention_kv_cache_past_k_caches: "f32[1, 128, 12, 64]", b_layers_11_attention_kv_cache_past_v_caches: "f32[1, 128, 12, 64]", tokens: "i64[1, 1]", attn_options_input_pos: "i64[1]"):
2025-03-21T20:31:43.1386441Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:161 in forward, code: h = self.tok_embeddings(tokens)
2025-03-21T20:31:43.1388980Z             quantized_decomposed_dequantize_per_tensor_default: "f32[32000, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param0, 1.9342933228472248e-05, 48293, 0, 65535, torch.int32);  b__frozen_param0 = None
2025-03-21T20:31:43.1390800Z             
2025-03-21T20:31:43.1391919Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:108 in forward, code: self.attention_norm(x), freqs_cos, freqs_sin, **attn_options
2025-03-21T20:31:43.1394296Z             quantized_decomposed_dequantize_per_tensor_default_1: "f32[768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param1, 1.2487619642342906e-05, 11698, 0, 65535, torch.int32);  b__frozen_param1 = None
2025-03-21T20:31:43.1395986Z             
2025-03-21T20:31:43.1396791Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1398884Z             quantized_decomposed_dequantize_per_tensor_default_2: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param2, 3.4356886317254975e-05, 0, -32767, 32767, torch.int16);  b__frozen_param2 = None
2025-03-21T20:31:43.1401770Z             quantized_decomposed_dequantize_per_tensor_default_3: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param3, 3.6641056794906035e-05, 0, -32767, 32767, torch.int16);  b__frozen_param3 = None
2025-03-21T20:31:43.1404634Z             quantized_decomposed_dequantize_per_tensor_default_4: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param4, 2.7063433662988245e-06, 0, -32767, 32767, torch.int16);  b__frozen_param4 = None
2025-03-21T20:31:43.1406404Z             
2025-03-21T20:31:43.1407190Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1409385Z             quantized_decomposed_dequantize_per_tensor_default_5: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param5, 2.292680619575549e-05, 0, -32767, 32767, torch.int16);  b__frozen_param5 = None
2025-03-21T20:31:43.1411209Z             
2025-03-21T20:31:43.1412242Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:115 in forward, code: out = h + self.feed_forward(self.ffn_norm(h))
2025-03-21T20:31:43.1414920Z             quantized_decomposed_dequantize_per_tensor_default_6: "f32[768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param6, 7.301607183762826e-06, 0, 0, 65535, torch.int32);  b__frozen_param6 = None
2025-03-21T20:31:43.1416731Z             
2025-03-21T20:31:43.1417537Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1419843Z             quantized_decomposed_dequantize_per_tensor_default_7: "f32[2048, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param7, 1.1212039680685848e-05, 0, -32767, 32767, torch.int16);  b__frozen_param7 = None
2025-03-21T20:31:43.1423160Z             quantized_decomposed_dequantize_per_tensor_default_8: "f32[2048, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param8, 8.377747690246906e-06, 0, -32767, 32767, torch.int16);  b__frozen_param8 = None
2025-03-21T20:31:43.1426144Z             quantized_decomposed_dequantize_per_tensor_default_9: "f32[768, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param9, 1.5975101632648148e-05, 0, -32767, 32767, torch.int16);  b__frozen_param9 = None
2025-03-21T20:31:43.1427847Z             
2025-03-21T20:31:43.1428977Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:108 in forward, code: self.attention_norm(x), freqs_cos, freqs_sin, **attn_options
2025-03-21T20:31:43.1432081Z             quantized_decomposed_dequantize_per_tensor_default_10: "f32[768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param10, 1.629848702577874e-05, 0, 0, 65535, torch.int32);  b__frozen_param10 = None
2025-03-21T20:31:43.1433916Z             
2025-03-21T20:31:43.1434685Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1436825Z             quantized_decomposed_dequantize_per_tensor_default_11: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param11, 2.386650157859549e-05, 0, -32767, 32767, torch.int16);  b__frozen_param11 = None
2025-03-21T20:31:43.1440067Z             quantized_decomposed_dequantize_per_tensor_default_12: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param12, 2.1627405658364296e-05, 0, -32767, 32767, torch.int16);  b__frozen_param12 = None
2025-03-21T20:31:43.1443096Z             quantized_decomposed_dequantize_per_tensor_default_13: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param13, 3.6092917525820667e-06, 0, -32767, 32767, torch.int16);  b__frozen_param13 = None
2025-03-21T20:31:43.1444931Z             
2025-03-21T20:31:43.1445697Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1447858Z             quantized_decomposed_dequantize_per_tensor_default_14: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param14, 2.6657653506845236e-05, 0, -32767, 32767, torch.int16);  b__frozen_param14 = None
2025-03-21T20:31:43.1449644Z             
2025-03-21T20:31:43.1450698Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:115 in forward, code: out = h + self.feed_forward(self.ffn_norm(h))
2025-03-21T20:31:43.1453010Z             quantized_decomposed_dequantize_per_tensor_default_15: "f32[768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param15, 1.0056614883069415e-05, 0, 0, 65535, torch.int32);  b__frozen_param15 = None
2025-03-21T20:31:43.1454689Z             
2025-03-21T20:31:43.1455483Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1457765Z             quantized_decomposed_dequantize_per_tensor_default_16: "f32[2048, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param16, 1.3041529200563673e-05, 0, -32767, 32767, torch.int16);  b__frozen_param16 = None
2025-03-21T20:31:43.1460992Z             quantized_decomposed_dequantize_per_tensor_default_17: "f32[2048, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param17, 1.2415116543706972e-05, 0, -32767, 32767, torch.int16);  b__frozen_param17 = None
2025-03-21T20:31:43.1464033Z             quantized_decomposed_dequantize_per_tensor_default_18: "f32[768, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param18, 4.851280027651228e-05, 0, -32767, 32767, torch.int16);  b__frozen_param18 = None
2025-03-21T20:31:43.1465867Z             
2025-03-21T20:31:43.1467032Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:108 in forward, code: self.attention_norm(x), freqs_cos, freqs_sin, **attn_options
2025-03-21T20:31:43.1469467Z             quantized_decomposed_dequantize_per_tensor_default_19: "f32[768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param19, 1.34903066282277e-05, 0, 0, 65535, torch.int32);  b__frozen_param19 = None
2025-03-21T20:31:43.1471167Z             
2025-03-21T20:31:43.1471828Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1474178Z             quantized_decomposed_dequantize_per_tensor_default_20: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param20, 1.2616974345291965e-05, 0, -32767, 32767, torch.int16);  b__frozen_param20 = None
2025-03-21T20:31:43.1477226Z             quantized_decomposed_dequantize_per_tensor_default_21: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param21, 1.8000935597228818e-05, 0, -32767, 32767, torch.int16);  b__frozen_param21 = None
2025-03-21T20:31:43.1480143Z             quantized_decomposed_dequantize_per_tensor_default_22: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param22, 3.838254997390322e-06, 0, -32767, 32767, torch.int16);  b__frozen_param22 = None
2025-03-21T20:31:43.1481857Z             
2025-03-21T20:31:43.1482671Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1485066Z             quantized_decomposed_dequantize_per_tensor_default_23: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param23, 1.5086939129105303e-05, 0, -32767, 32767, torch.int16);  b__frozen_param23 = None
2025-03-21T20:31:43.1486791Z             
2025-03-21T20:31:43.1487784Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:115 in forward, code: out = h + self.feed_forward(self.ffn_norm(h))
2025-03-21T20:31:43.1490377Z             quantized_decomposed_dequantize_per_tensor_default_24: "f32[768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param24, 1.2551431609608699e-05, 0, 0, 65535, torch.int32);  b__frozen_param24 = None
2025-03-21T20:31:43.1492075Z             
2025-03-21T20:31:43.1492910Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1495014Z             quantized_decomposed_dequantize_per_tensor_default_25: "f32[2048, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param25, 7.637921953573823e-06, 0, -32767, 32767, torch.int16);  b__frozen_param25 = None
2025-03-21T20:31:43.1498347Z             quantized_decomposed_dequantize_per_tensor_default_26: "f32[2048, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param26, 8.152154805429745e-06, 0, -32767, 32767, torch.int16);  b__frozen_param26 = None
2025-03-21T20:31:43.1501541Z             quantized_decomposed_dequantize_per_tensor_default_27: "f32[768, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param27, 5.8997531596105546e-05, 0, -32767, 32767, torch.int16);  b__frozen_param27 = None
2025-03-21T20:31:43.1503258Z             
2025-03-21T20:31:43.1504948Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:108 in forward, code: self.attention_norm(x), freqs_cos, freqs_sin, **attn_options
2025-03-21T20:31:43.1507394Z             quantized_decomposed_dequantize_per_tensor_default_28: "f32[768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param28, 1.4751847629668191e-05, 0, 0, 65535, torch.int32);  b__frozen_param28 = None
2025-03-21T20:31:43.1509018Z             
2025-03-21T20:31:43.1509825Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1512125Z             quantized_decomposed_dequantize_per_tensor_default_29: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param29, 1.285897542402381e-05, 0, -32767, 32767, torch.int16);  b__frozen_param29 = None
2025-03-21T20:31:43.1515561Z             quantized_decomposed_dequantize_per_tensor_default_30: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param30, 1.776821409293916e-05, 0, -32767, 32767, torch.int16);  b__frozen_param30 = None
2025-03-21T20:31:43.1518740Z             quantized_decomposed_dequantize_per_tensor_default_31: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param31, 3.8338889680744614e-06, 0, -32767, 32767, torch.int16);  b__frozen_param31 = None
2025-03-21T20:31:43.1520463Z             
2025-03-21T20:31:43.1521232Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1523297Z             quantized_decomposed_dequantize_per_tensor_default_32: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param32, 1.043909833242651e-05, 0, -32767, 32767, torch.int16);  b__frozen_param32 = None
2025-03-21T20:31:43.1525060Z             
2025-03-21T20:31:43.1526104Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:115 in forward, code: out = h + self.feed_forward(self.ffn_norm(h))
2025-03-21T20:31:43.1528476Z             quantized_decomposed_dequantize_per_tensor_default_33: "f32[768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param33, 1.2991034964215942e-05, 0, 0, 65535, torch.int32);  b__frozen_param33 = None
2025-03-21T20:31:43.1530252Z             
2025-03-21T20:31:43.1531020Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1533236Z             quantized_decomposed_dequantize_per_tensor_default_34: "f32[2048, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param34, 9.01338535186369e-06, 0, -32767, 32767, torch.int16);  b__frozen_param34 = None
2025-03-21T20:31:43.1536336Z             quantized_decomposed_dequantize_per_tensor_default_35: "f32[2048, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param35, 8.421571692451835e-06, 0, -32767, 32767, torch.int16);  b__frozen_param35 = None
2025-03-21T20:31:43.1539387Z             quantized_decomposed_dequantize_per_tensor_default_36: "f32[768, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param36, 5.0727699999697506e-05, 0, -32767, 32767, torch.int16);  b__frozen_param36 = None
2025-03-21T20:31:43.1541160Z             
2025-03-21T20:31:43.1542319Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:108 in forward, code: self.attention_norm(x), freqs_cos, freqs_sin, **attn_options
2025-03-21T20:31:43.1544929Z             quantized_decomposed_dequantize_per_tensor_default_37: "f32[768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param37, 1.6460680853924714e-05, 0, 0, 65535, torch.int32);  b__frozen_param37 = None
2025-03-21T20:31:43.1546549Z             
2025-03-21T20:31:43.1547327Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1549512Z             quantized_decomposed_dequantize_per_tensor_default_38: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param38, 1.0061074135592207e-05, 0, -32767, 32767, torch.int16);  b__frozen_param38 = None
2025-03-21T20:31:43.1552655Z             quantized_decomposed_dequantize_per_tensor_default_39: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param39, 1.3427632438833825e-05, 0, -32767, 32767, torch.int16);  b__frozen_param39 = None
2025-03-21T20:31:43.1555669Z             quantized_decomposed_dequantize_per_tensor_default_40: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param40, 3.969049885199638e-06, 0, -32767, 32767, torch.int16);  b__frozen_param40 = None
2025-03-21T20:31:43.1557486Z             
2025-03-21T20:31:43.1588039Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1590286Z             quantized_decomposed_dequantize_per_tensor_default_41: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param41, 4.623624136002036e-06, 0, -32767, 32767, torch.int16);  b__frozen_param41 = None
2025-03-21T20:31:43.1592065Z             
2025-03-21T20:31:43.1593101Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:115 in forward, code: out = h + self.feed_forward(self.ffn_norm(h))
2025-03-21T20:31:43.1595385Z             quantized_decomposed_dequantize_per_tensor_default_42: "f32[768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param42, 1.4132921023701783e-05, 0, 0, 65535, torch.int32);  b__frozen_param42 = None
2025-03-21T20:31:43.1597688Z             
2025-03-21T20:31:43.1598518Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1600704Z             quantized_decomposed_dequantize_per_tensor_default_43: "f32[2048, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param43, 9.02163446880877e-06, 0, -32767, 32767, torch.int16);  b__frozen_param43 = None
2025-03-21T20:31:43.1603871Z             quantized_decomposed_dequantize_per_tensor_default_44: "f32[2048, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param44, 6.684962045255816e-06, 0, -32767, 32767, torch.int16);  b__frozen_param44 = None
2025-03-21T20:31:43.1606956Z             quantized_decomposed_dequantize_per_tensor_default_45: "f32[768, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param45, 4.520918082562275e-05, 0, -32767, 32767, torch.int16);  b__frozen_param45 = None
2025-03-21T20:31:43.1608729Z             
2025-03-21T20:31:43.1609967Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:108 in forward, code: self.attention_norm(x), freqs_cos, freqs_sin, **attn_options
2025-03-21T20:31:43.1612665Z             quantized_decomposed_dequantize_per_tensor_default_46: "f32[768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param46, 1.633507781662047e-05, 0, 0, 65535, torch.int32);  b__frozen_param46 = None
2025-03-21T20:31:43.1614380Z             
2025-03-21T20:31:43.1615335Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1622560Z             quantized_decomposed_dequantize_per_tensor_default_47: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param47, 1.2622019312402699e-05, 0, -32767, 32767, torch.int16);  b__frozen_param47 = None
2025-03-21T20:31:43.1626128Z             quantized_decomposed_dequantize_per_tensor_default_48: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param48, 1.2933628568134736e-05, 0, -32767, 32767, torch.int16);  b__frozen_param48 = None
2025-03-21T20:31:43.1629830Z             quantized_decomposed_dequantize_per_tensor_default_49: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param49, 3.8965881685726345e-06, 0, -32767, 32767, torch.int16);  b__frozen_param49 = None
2025-03-21T20:31:43.1632060Z             
2025-03-21T20:31:43.1633226Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1635893Z             quantized_decomposed_dequantize_per_tensor_default_50: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param50, 7.438241027557524e-06, 0, -32767, 32767, torch.int16);  b__frozen_param50 = None
2025-03-21T20:31:43.1638093Z             
2025-03-21T20:31:43.1639358Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:115 in forward, code: out = h + self.feed_forward(self.ffn_norm(h))
2025-03-21T20:31:43.1642379Z             quantized_decomposed_dequantize_per_tensor_default_51: "f32[768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param51, 1.4315685803012457e-05, 0, 0, 65535, torch.int32);  b__frozen_param51 = None
2025-03-21T20:31:43.1644251Z             
2025-03-21T20:31:43.1645054Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1647353Z             quantized_decomposed_dequantize_per_tensor_default_52: "f32[2048, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param52, 6.619334271817934e-06, 0, -32767, 32767, torch.int16);  b__frozen_param52 = None
2025-03-21T20:31:43.1649552Z             quantized_decomposed_dequantize_per_tensor_default_53: "f32[2048, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param53, 1.2854585293098353e-05, 0, -32767, 32767, torch.int16);  b__frozen_param53 = None
2025-03-21T20:31:43.1651427Z             quantized_decomposed_dequantize_per_tensor_default_54: "f32[768, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param54, 4.18269082729239e-05, 0, -32767, 32767, torch.int16);  b__frozen_param54 = None
2025-03-21T20:31:43.1652513Z             
2025-03-21T20:31:43.1653318Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:108 in forward, code: self.attention_norm(x), freqs_cos, freqs_sin, **attn_options
2025-03-21T20:31:43.1654915Z             quantized_decomposed_dequantize_per_tensor_default_55: "f32[768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param55, 1.734791112539824e-05, 0, 0, 65535, torch.int32);  b__frozen_param55 = None
2025-03-21T20:31:43.1656090Z             
2025-03-21T20:31:43.1656625Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1657989Z             quantized_decomposed_dequantize_per_tensor_default_56: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param56, 1.3876242519472726e-05, 0, -32767, 32767, torch.int16);  b__frozen_param56 = None
2025-03-21T20:31:43.1659963Z             quantized_decomposed_dequantize_per_tensor_default_57: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param57, 1.4166372238832992e-05, 0, -32767, 32767, torch.int16);  b__frozen_param57 = None
2025-03-21T20:31:43.1662768Z             quantized_decomposed_dequantize_per_tensor_default_58: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param58, 4.262657057552133e-06, 0, -32767, 32767, torch.int16);  b__frozen_param58 = None
2025-03-21T20:31:43.1664242Z             
2025-03-21T20:31:43.1664757Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1666431Z             quantized_decomposed_dequantize_per_tensor_default_59: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param59, 4.859185082750628e-06, 0, -32767, 32767, torch.int16);  b__frozen_param59 = None
2025-03-21T20:31:43.1667897Z             
2025-03-21T20:31:43.1668693Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:115 in forward, code: out = h + self.feed_forward(self.ffn_norm(h))
2025-03-21T20:31:43.1670233Z             quantized_decomposed_dequantize_per_tensor_default_60: "f32[768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param60, 1.4755311894987244e-05, 0, 0, 65535, torch.int32);  b__frozen_param60 = None
2025-03-21T20:31:43.1671820Z             
2025-03-21T20:31:43.1672689Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1674539Z             quantized_decomposed_dequantize_per_tensor_default_61: "f32[2048, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param61, 7.526988156314474e-06, 0, -32767, 32767, torch.int16);  b__frozen_param61 = None
2025-03-21T20:31:43.1676856Z             quantized_decomposed_dequantize_per_tensor_default_62: "f32[2048, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param62, 5.435513230622746e-06, 0, -32767, 32767, torch.int16);  b__frozen_param62 = None
2025-03-21T20:31:43.1679146Z             quantized_decomposed_dequantize_per_tensor_default_63: "f32[768, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param63, 2.4650629711686634e-05, 0, -32767, 32767, torch.int16);  b__frozen_param63 = None
2025-03-21T20:31:43.1680626Z             
2025-03-21T20:31:43.1681407Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:108 in forward, code: self.attention_norm(x), freqs_cos, freqs_sin, **attn_options
2025-03-21T20:31:43.1683313Z             quantized_decomposed_dequantize_per_tensor_default_64: "f32[768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param64, 1.9291985154268332e-05, 0, 0, 65535, torch.int32);  b__frozen_param64 = None
2025-03-21T20:31:43.1684384Z             
2025-03-21T20:31:43.1684919Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1686347Z             quantized_decomposed_dequantize_per_tensor_default_65: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param65, 1.2612830687430687e-05, 0, -32767, 32767, torch.int16);  b__frozen_param65 = None
2025-03-21T20:31:43.1688238Z             quantized_decomposed_dequantize_per_tensor_default_66: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param66, 1.120004162658006e-05, 0, -32767, 32767, torch.int16);  b__frozen_param66 = None
2025-03-21T20:31:43.1690285Z             quantized_decomposed_dequantize_per_tensor_default_67: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param67, 4.108746452402556e-06, 0, -32767, 32767, torch.int16);  b__frozen_param67 = None
2025-03-21T20:31:43.1691438Z             
2025-03-21T20:31:43.1691947Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1693374Z             quantized_decomposed_dequantize_per_tensor_default_68: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param68, 4.289444405003451e-06, 0, -32767, 32767, torch.int16);  b__frozen_param68 = None
2025-03-21T20:31:43.1694454Z             
2025-03-21T20:31:43.1695140Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:115 in forward, code: out = h + self.feed_forward(self.ffn_norm(h))
2025-03-21T20:31:43.1696610Z             quantized_decomposed_dequantize_per_tensor_default_69: "f32[768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param69, 1.58265156642301e-05, 0, 0, 65535, torch.int32);  b__frozen_param69 = None
2025-03-21T20:31:43.1697903Z             
2025-03-21T20:31:43.1698675Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1700109Z             quantized_decomposed_dequantize_per_tensor_default_70: "f32[2048, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param70, 8.079993676801678e-06, 0, -32767, 32767, torch.int16);  b__frozen_param70 = None
2025-03-21T20:31:43.1702035Z             quantized_decomposed_dequantize_per_tensor_default_71: "f32[2048, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param71, 5.950272225163644e-06, 0, -32767, 32767, torch.int16);  b__frozen_param71 = None
2025-03-21T20:31:43.1703896Z             quantized_decomposed_dequantize_per_tensor_default_72: "f32[768, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param72, 8.790708307060413e-06, 0, -32767, 32767, torch.int16);  b__frozen_param72 = None
2025-03-21T20:31:43.1705024Z             
2025-03-21T20:31:43.1705839Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:108 in forward, code: self.attention_norm(x), freqs_cos, freqs_sin, **attn_options
2025-03-21T20:31:43.1707380Z             quantized_decomposed_dequantize_per_tensor_default_73: "f32[768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param73, 2.0017856513732113e-05, 0, 0, 65535, torch.int32);  b__frozen_param73 = None
2025-03-21T20:31:43.1708436Z             
2025-03-21T20:31:43.1708938Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1710363Z             quantized_decomposed_dequantize_per_tensor_default_74: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param74, 1.0534595276112668e-05, 0, -32767, 32767, torch.int16);  b__frozen_param74 = None
2025-03-21T20:31:43.1712248Z             quantized_decomposed_dequantize_per_tensor_default_75: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param75, 9.947799298970494e-06, 0, -32767, 32767, torch.int16);  b__frozen_param75 = None
2025-03-21T20:31:43.1714232Z             quantized_decomposed_dequantize_per_tensor_default_76: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param76, 4.18247509514913e-06, 0, -32767, 32767, torch.int16);  b__frozen_param76 = None
2025-03-21T20:31:43.1715321Z             
2025-03-21T20:31:43.1715824Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1717217Z             quantized_decomposed_dequantize_per_tensor_default_77: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param77, 5.61682645638939e-06, 0, -32767, 32767, torch.int16);  b__frozen_param77 = None
2025-03-21T20:31:43.1718362Z             
2025-03-21T20:31:43.1719079Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:115 in forward, code: out = h + self.feed_forward(self.ffn_norm(h))
2025-03-21T20:31:43.1720610Z             quantized_decomposed_dequantize_per_tensor_default_78: "f32[768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param78, 1.605357465450652e-05, 0, 0, 65535, torch.int32);  b__frozen_param78 = None
2025-03-21T20:31:43.1721696Z             
2025-03-21T20:31:43.1722188Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1723546Z             quantized_decomposed_dequantize_per_tensor_default_79: "f32[2048, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param79, 5.956742825219408e-06, 0, -32767, 32767, torch.int16);  b__frozen_param79 = None
2025-03-21T20:31:43.1725404Z             quantized_decomposed_dequantize_per_tensor_default_80: "f32[2048, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param80, 5.543797669815831e-06, 0, -32767, 32767, torch.int16);  b__frozen_param80 = None
2025-03-21T20:31:43.1727283Z             quantized_decomposed_dequantize_per_tensor_default_81: "f32[768, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param81, 1.7314116121269763e-05, 0, -32767, 32767, torch.int16);  b__frozen_param81 = None
2025-03-21T20:31:43.1728363Z             
2025-03-21T20:31:43.1729138Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:108 in forward, code: self.attention_norm(x), freqs_cos, freqs_sin, **attn_options
2025-03-21T20:31:43.1730743Z             quantized_decomposed_dequantize_per_tensor_default_82: "f32[768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param82, 2.1098459910717793e-05, 0, 0, 65535, torch.int32);  b__frozen_param82 = None
2025-03-21T20:31:43.1731797Z             
2025-03-21T20:31:43.1732461Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1733828Z             quantized_decomposed_dequantize_per_tensor_default_83: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param83, 9.977230547519866e-06, 0, -32767, 32767, torch.int16);  b__frozen_param83 = None
2025-03-21T20:31:43.1735960Z             quantized_decomposed_dequantize_per_tensor_default_84: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param84, 1.0152723916689865e-05, 0, -32767, 32767, torch.int16);  b__frozen_param84 = None
2025-03-21T20:31:43.1737825Z             quantized_decomposed_dequantize_per_tensor_default_85: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param85, 4.536270353128202e-06, 0, -32767, 32767, torch.int16);  b__frozen_param85 = None
2025-03-21T20:31:43.1739007Z             
2025-03-21T20:31:43.1739511Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1740874Z             quantized_decomposed_dequantize_per_tensor_default_86: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param86, 5.920260718994541e-06, 0, -32767, 32767, torch.int16);  b__frozen_param86 = None
2025-03-21T20:31:43.1742268Z             
2025-03-21T20:31:43.1743031Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:115 in forward, code: out = h + self.feed_forward(self.ffn_norm(h))
2025-03-21T20:31:43.1744516Z             quantized_decomposed_dequantize_per_tensor_default_87: "f32[768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param87, 1.749423063301947e-05, 0, 0, 65535, torch.int32);  b__frozen_param87 = None
2025-03-21T20:31:43.1745571Z             
2025-03-21T20:31:43.1746101Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1747503Z             quantized_decomposed_dequantize_per_tensor_default_88: "f32[2048, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param88, 6.546213626279496e-06, 0, -32767, 32767, torch.int16);  b__frozen_param88 = None
2025-03-21T20:31:43.1749410Z             quantized_decomposed_dequantize_per_tensor_default_89: "f32[2048, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param89, 8.761990102357231e-06, 0, -32767, 32767, torch.int16);  b__frozen_param89 = None
2025-03-21T20:31:43.1751268Z             quantized_decomposed_dequantize_per_tensor_default_90: "f32[768, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param90, 1.633228748687543e-05, 0, -32767, 32767, torch.int16);  b__frozen_param90 = None
2025-03-21T20:31:43.1752345Z             
2025-03-21T20:31:43.1753054Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:108 in forward, code: self.attention_norm(x), freqs_cos, freqs_sin, **attn_options
2025-03-21T20:31:43.1754575Z             quantized_decomposed_dequantize_per_tensor_default_91: "f32[768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param91, 2.414468144706916e-05, 0, 0, 65535, torch.int32);  b__frozen_param91 = None
2025-03-21T20:31:43.1755624Z             
2025-03-21T20:31:43.1756121Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1757474Z             quantized_decomposed_dequantize_per_tensor_default_92: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param92, 1.072352006303845e-05, 0, -32767, 32767, torch.int16);  b__frozen_param92 = None
2025-03-21T20:31:43.1759322Z             quantized_decomposed_dequantize_per_tensor_default_93: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param93, 1.0837483387149405e-05, 0, -32767, 32767, torch.int16);  b__frozen_param93 = None
2025-03-21T20:31:43.1761166Z             quantized_decomposed_dequantize_per_tensor_default_94: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param94, 4.776206424139673e-06, 0, -32767, 32767, torch.int16);  b__frozen_param94 = None
2025-03-21T20:31:43.1762233Z             
2025-03-21T20:31:43.1762716Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1764080Z             quantized_decomposed_dequantize_per_tensor_default_95: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param95, 7.434290637320373e-06, 0, -32767, 32767, torch.int16);  b__frozen_param95 = None
2025-03-21T20:31:43.1765154Z             
2025-03-21T20:31:43.1765777Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:115 in forward, code: out = h + self.feed_forward(self.ffn_norm(h))
2025-03-21T20:31:43.1767257Z             quantized_decomposed_dequantize_per_tensor_default_96: "f32[768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param96, 1.9142669771099463e-05, 0, 0, 65535, torch.int32);  b__frozen_param96 = None
2025-03-21T20:31:43.1768294Z             
2025-03-21T20:31:43.1768773Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1770188Z             quantized_decomposed_dequantize_per_tensor_default_97: "f32[2048, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param97, 9.545610737404786e-06, 0, -32767, 32767, torch.int16);  b__frozen_param97 = None
2025-03-21T20:31:43.1772050Z             quantized_decomposed_dequantize_per_tensor_default_98: "f32[2048, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param98, 1.0316829502698965e-05, 0, -32767, 32767, torch.int16);  b__frozen_param98 = None
2025-03-21T20:31:43.1774020Z             quantized_decomposed_dequantize_per_tensor_default_99: "f32[768, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param99, 2.7532219974091277e-05, 0, -32767, 32767, torch.int16);  b__frozen_param99 = None
2025-03-21T20:31:43.1775193Z             
2025-03-21T20:31:43.1775893Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:108 in forward, code: self.attention_norm(x), freqs_cos, freqs_sin, **attn_options
2025-03-21T20:31:43.1777419Z             quantized_decomposed_dequantize_per_tensor_default_100: "f32[768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param100, 2.333568590984214e-05, 0, 0, 65535, torch.int32);  b__frozen_param100 = None
2025-03-21T20:31:43.1778470Z             
2025-03-21T20:31:43.1778957Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1780318Z             quantized_decomposed_dequantize_per_tensor_default_101: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param101, 1.1849775546579622e-05, 0, -32767, 32767, torch.int16);  b__frozen_param101 = None
2025-03-21T20:31:43.1782193Z             quantized_decomposed_dequantize_per_tensor_default_102: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param102, 9.849293746810872e-06, 0, -32767, 32767, torch.int16);  b__frozen_param102 = None
2025-03-21T20:31:43.1784053Z             quantized_decomposed_dequantize_per_tensor_default_103: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param103, 5.271489044389455e-06, 0, -32767, 32767, torch.int16);  b__frozen_param103 = None
2025-03-21T20:31:43.1785118Z             
2025-03-21T20:31:43.1785593Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1786937Z             quantized_decomposed_dequantize_per_tensor_default_104: "f32[768, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param104, 1.626361336093396e-05, 0, -32767, 32767, torch.int16);  b__frozen_param104 = None
2025-03-21T20:31:43.1788014Z             
2025-03-21T20:31:43.1788682Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:115 in forward, code: out = h + self.feed_forward(self.ffn_norm(h))
2025-03-21T20:31:43.1790176Z             quantized_decomposed_dequantize_per_tensor_default_105: "f32[768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param105, 2.1847066818736494e-05, 0, 0, 65535, torch.int32);  b__frozen_param105 = None
2025-03-21T20:31:43.1791222Z             
2025-03-21T20:31:43.1791705Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1793085Z             quantized_decomposed_dequantize_per_tensor_default_106: "f32[2048, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param106, 1.223628714797087e-05, 0, -32767, 32767, torch.int16);  b__frozen_param106 = None
2025-03-21T20:31:43.1794963Z             quantized_decomposed_dequantize_per_tensor_default_107: "f32[2048, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param107, 1.3578906873590313e-05, 0, -32767, 32767, torch.int16);  b__frozen_param107 = None
2025-03-21T20:31:43.1796832Z             quantized_decomposed_dequantize_per_tensor_default_108: "f32[768, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param108, 3.873001696774736e-05, 0, -32767, 32767, torch.int16);  b__frozen_param108 = None
2025-03-21T20:31:43.1797928Z             
2025-03-21T20:31:43.1798455Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:182 in forward, code: h = self.norm(h)
2025-03-21T20:31:43.1799822Z             quantized_decomposed_dequantize_per_tensor_default_109: "f32[768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param109, 0.0001457274629501626, 0, 0, 65535, torch.int32);  b__frozen_param109 = None
2025-03-21T20:31:43.1800880Z             
2025-03-21T20:31:43.1801366Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.1802742Z             quantized_decomposed_dequantize_per_tensor_default_110: "f32[32000, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param110, 2.8508189643616788e-05, 0, -32767, 32767, torch.int16);  b__frozen_param110 = None
2025-03-21T20:31:43.1803832Z             
2025-03-21T20:31:43.1804375Z              # File: /pytorch/executorch/examples/models/llama/rope.py:300 in get_freqs, code: freqs_cos = self.freqs_cos[input_pos]
2025-03-21T20:31:43.1805783Z             quantized_decomposed_dequantize_per_tensor_default_111: "f32[128, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param111, 3.051804378628731e-05, 32768, 0, 65535, torch.int32);  b__frozen_param111 = None
2025-03-21T20:31:43.1806852Z             
2025-03-21T20:31:43.1807407Z              # File: /pytorch/executorch/examples/models/llama/rope.py:301 in get_freqs, code: freqs_sin = self.freqs_sin[input_pos]
2025-03-21T20:31:43.1808812Z             quantized_decomposed_dequantize_per_tensor_default_112: "f32[128, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param112, 3.051786916330457e-05, 32767, 0, 65535, torch.int32);  b__frozen_param112 = None
2025-03-21T20:31:43.1809974Z             
2025-03-21T20:31:43.1810779Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:345 in update, code: k_out = torch.ops.aten.index_put_(self.past_k_caches, [None, input_pos], k_val)
2025-03-21T20:31:43.1812438Z             quantized_decomposed_dequantize_per_tensor_default_113: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param113, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  b__frozen_param113 = None
2025-03-21T20:31:43.1813515Z             
2025-03-21T20:31:43.1814375Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:346 in update, code: v_out = torch.ops.aten.index_put_(self.past_v_caches, [None, input_pos], v_val)
2025-03-21T20:31:43.1816025Z             quantized_decomposed_dequantize_per_tensor_default_114: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param114, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  b__frozen_param114 = None
2025-03-21T20:31:43.1817103Z             
2025-03-21T20:31:43.1817746Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:157 in forward, code: attn_mask = mask[input_pos]
2025-03-21T20:31:43.1819218Z             quantized_decomposed_dequantize_per_tensor_default_115: "f32[128, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param115, 0.0038910505827516317, 65535, 0, 65535, torch.int32);  b__frozen_param115 = None
2025-03-21T20:31:43.1820290Z             
2025-03-21T20:31:43.1821080Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:345 in update, code: k_out = torch.ops.aten.index_put_(self.past_k_caches, [None, input_pos], k_val)
2025-03-21T20:31:43.1822755Z             quantized_decomposed_dequantize_per_tensor_default_116: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param116, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  b__frozen_param116 = None
2025-03-21T20:31:43.1823835Z             
2025-03-21T20:31:43.1824616Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:346 in update, code: v_out = torch.ops.aten.index_put_(self.past_v_caches, [None, input_pos], v_val)
2025-03-21T20:31:43.1826271Z             quantized_decomposed_dequantize_per_tensor_default_117: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param117, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  b__frozen_param117 = None
2025-03-21T20:31:43.1827340Z             
2025-03-21T20:31:43.1827960Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:157 in forward, code: attn_mask = mask[input_pos]
2025-03-21T20:31:43.1829427Z             quantized_decomposed_dequantize_per_tensor_default_118: "f32[128, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param118, 0.0038910505827516317, 65535, 0, 65535, torch.int32);  b__frozen_param118 = None
2025-03-21T20:31:43.1830494Z             
2025-03-21T20:31:43.1831280Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:345 in update, code: k_out = torch.ops.aten.index_put_(self.past_k_caches, [None, input_pos], k_val)
2025-03-21T20:31:43.1833118Z             quantized_decomposed_dequantize_per_tensor_default_119: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param119, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  b__frozen_param119 = None
2025-03-21T20:31:43.1834200Z             
2025-03-21T20:31:43.1834980Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:346 in update, code: v_out = torch.ops.aten.index_put_(self.past_v_caches, [None, input_pos], v_val)
2025-03-21T20:31:43.1836628Z             quantized_decomposed_dequantize_per_tensor_default_120: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param120, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  b__frozen_param120 = None
2025-03-21T20:31:43.1837702Z             
2025-03-21T20:31:43.1838318Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:157 in forward, code: attn_mask = mask[input_pos]
2025-03-21T20:31:43.1839904Z             quantized_decomposed_dequantize_per_tensor_default_121: "f32[128, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param121, 0.0038910505827516317, 65535, 0, 65535, torch.int32);  b__frozen_param121 = None
2025-03-21T20:31:43.1840992Z             
2025-03-21T20:31:43.1841791Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:345 in update, code: k_out = torch.ops.aten.index_put_(self.past_k_caches, [None, input_pos], k_val)
2025-03-21T20:31:43.1843477Z             quantized_decomposed_dequantize_per_tensor_default_122: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param122, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  b__frozen_param122 = None
2025-03-21T20:31:43.1844626Z             
2025-03-21T20:31:43.1845402Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:346 in update, code: v_out = torch.ops.aten.index_put_(self.past_v_caches, [None, input_pos], v_val)
2025-03-21T20:31:43.1847058Z             quantized_decomposed_dequantize_per_tensor_default_123: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param123, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  b__frozen_param123 = None
2025-03-21T20:31:43.1848180Z             
2025-03-21T20:31:43.1848797Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:157 in forward, code: attn_mask = mask[input_pos]
2025-03-21T20:31:43.1850339Z             quantized_decomposed_dequantize_per_tensor_default_124: "f32[128, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param124, 0.0038910505827516317, 65535, 0, 65535, torch.int32);  b__frozen_param124 = None
2025-03-21T20:31:43.1851416Z             
2025-03-21T20:31:43.1852210Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:345 in update, code: k_out = torch.ops.aten.index_put_(self.past_k_caches, [None, input_pos], k_val)
2025-03-21T20:31:43.1853864Z             quantized_decomposed_dequantize_per_tensor_default_125: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param125, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  b__frozen_param125 = None
2025-03-21T20:31:43.1854940Z             
2025-03-21T20:31:43.1855736Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:346 in update, code: v_out = torch.ops.aten.index_put_(self.past_v_caches, [None, input_pos], v_val)
2025-03-21T20:31:43.1857385Z             quantized_decomposed_dequantize_per_tensor_default_126: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param126, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  b__frozen_param126 = None
2025-03-21T20:31:43.1858462Z             
2025-03-21T20:31:43.1859081Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:157 in forward, code: attn_mask = mask[input_pos]
2025-03-21T20:31:43.1860549Z             quantized_decomposed_dequantize_per_tensor_default_127: "f32[128, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param127, 0.0038910505827516317, 65535, 0, 65535, torch.int32);  b__frozen_param127 = None
2025-03-21T20:31:43.1861616Z             
2025-03-21T20:31:43.1862409Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:345 in update, code: k_out = torch.ops.aten.index_put_(self.past_k_caches, [None, input_pos], k_val)
2025-03-21T20:31:43.1864084Z             quantized_decomposed_dequantize_per_tensor_default_128: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param128, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  b__frozen_param128 = None
2025-03-21T20:31:43.1865172Z             
2025-03-21T20:31:43.1865962Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:346 in update, code: v_out = torch.ops.aten.index_put_(self.past_v_caches, [None, input_pos], v_val)
2025-03-21T20:31:43.1867606Z             quantized_decomposed_dequantize_per_tensor_default_129: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param129, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  b__frozen_param129 = None
2025-03-21T20:31:43.1868702Z             
2025-03-21T20:31:43.1869316Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:157 in forward, code: attn_mask = mask[input_pos]
2025-03-21T20:31:43.1870788Z             quantized_decomposed_dequantize_per_tensor_default_130: "f32[128, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param130, 0.0038910505827516317, 65535, 0, 65535, torch.int32);  b__frozen_param130 = None
2025-03-21T20:31:43.1871861Z             
2025-03-21T20:31:43.1872664Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:345 in update, code: k_out = torch.ops.aten.index_put_(self.past_k_caches, [None, input_pos], k_val)
2025-03-21T20:31:43.1874331Z             quantized_decomposed_dequantize_per_tensor_default_131: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param131, 0.000468338665086776, 33988, 0, 65535, torch.int32);  b__frozen_param131 = None
2025-03-21T20:31:43.1875470Z             
2025-03-21T20:31:43.1876334Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:346 in update, code: v_out = torch.ops.aten.index_put_(self.past_v_caches, [None, input_pos], v_val)
2025-03-21T20:31:43.1877986Z             quantized_decomposed_dequantize_per_tensor_default_132: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param132, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  b__frozen_param132 = None
2025-03-21T20:31:43.1879081Z             
2025-03-21T20:31:43.1879705Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:157 in forward, code: attn_mask = mask[input_pos]
2025-03-21T20:31:43.1881180Z             quantized_decomposed_dequantize_per_tensor_default_133: "f32[128, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param133, 0.0038910505827516317, 65535, 0, 65535, torch.int32);  b__frozen_param133 = None
2025-03-21T20:31:43.1882250Z             
2025-03-21T20:31:43.1883042Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:345 in update, code: k_out = torch.ops.aten.index_put_(self.past_k_caches, [None, input_pos], k_val)
2025-03-21T20:31:43.1884688Z             quantized_decomposed_dequantize_per_tensor_default_134: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param134, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  b__frozen_param134 = None
2025-03-21T20:31:43.1885769Z             
2025-03-21T20:31:43.1886562Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:346 in update, code: v_out = torch.ops.aten.index_put_(self.past_v_caches, [None, input_pos], v_val)
2025-03-21T20:31:43.1888217Z             quantized_decomposed_dequantize_per_tensor_default_135: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param135, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  b__frozen_param135 = None
2025-03-21T20:31:43.1889355Z             
2025-03-21T20:31:43.1890025Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:157 in forward, code: attn_mask = mask[input_pos]
2025-03-21T20:31:43.1891538Z             quantized_decomposed_dequantize_per_tensor_default_136: "f32[128, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param136, 0.0038910505827516317, 65535, 0, 65535, torch.int32);  b__frozen_param136 = None
2025-03-21T20:31:43.1892610Z             
2025-03-21T20:31:43.1893397Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:345 in update, code: k_out = torch.ops.aten.index_put_(self.past_k_caches, [None, input_pos], k_val)
2025-03-21T20:31:43.1895061Z             quantized_decomposed_dequantize_per_tensor_default_137: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param137, 0.000408027321100235, 35365, 0, 65535, torch.int32);  b__frozen_param137 = None
2025-03-21T20:31:43.1896141Z             
2025-03-21T20:31:43.1896943Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:346 in update, code: v_out = torch.ops.aten.index_put_(self.past_v_caches, [None, input_pos], v_val)
2025-03-21T20:31:43.1898599Z             quantized_decomposed_dequantize_per_tensor_default_138: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param138, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  b__frozen_param138 = None
2025-03-21T20:31:43.1899710Z             
2025-03-21T20:31:43.1900338Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:157 in forward, code: attn_mask = mask[input_pos]
2025-03-21T20:31:43.1901818Z             quantized_decomposed_dequantize_per_tensor_default_139: "f32[128, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param139, 0.0038910505827516317, 65535, 0, 65535, torch.int32);  b__frozen_param139 = None
2025-03-21T20:31:43.1902904Z             
2025-03-21T20:31:43.1903706Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:345 in update, code: k_out = torch.ops.aten.index_put_(self.past_k_caches, [None, input_pos], k_val)
2025-03-21T20:31:43.1905357Z             quantized_decomposed_dequantize_per_tensor_default_140: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param140, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  b__frozen_param140 = None
2025-03-21T20:31:43.1906443Z             
2025-03-21T20:31:43.1907243Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:346 in update, code: v_out = torch.ops.aten.index_put_(self.past_v_caches, [None, input_pos], v_val)
2025-03-21T20:31:43.1908902Z             quantized_decomposed_dequantize_per_tensor_default_141: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param141, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  b__frozen_param141 = None
2025-03-21T20:31:43.1909989Z             
2025-03-21T20:31:43.1910616Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:157 in forward, code: attn_mask = mask[input_pos]
2025-03-21T20:31:43.1912097Z             quantized_decomposed_dequantize_per_tensor_default_142: "f32[128, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param142, 0.0038910505827516317, 65535, 0, 65535, torch.int32);  b__frozen_param142 = None
2025-03-21T20:31:43.1913179Z             
2025-03-21T20:31:43.1913961Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:345 in update, code: k_out = torch.ops.aten.index_put_(self.past_k_caches, [None, input_pos], k_val)
2025-03-21T20:31:43.1915662Z             quantized_decomposed_dequantize_per_tensor_default_143: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param143, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  b__frozen_param143 = None
2025-03-21T20:31:43.1916773Z             
2025-03-21T20:31:43.1917567Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:346 in update, code: v_out = torch.ops.aten.index_put_(self.past_v_caches, [None, input_pos], v_val)
2025-03-21T20:31:43.1919248Z             quantized_decomposed_dequantize_per_tensor_default_144: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param144, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  b__frozen_param144 = None
2025-03-21T20:31:43.1920340Z             
2025-03-21T20:31:43.1920960Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:157 in forward, code: attn_mask = mask[input_pos]
2025-03-21T20:31:43.1922437Z             quantized_decomposed_dequantize_per_tensor_default_145: "f32[128, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param145, 0.0038910505827516317, 65535, 0, 65535, torch.int32);  b__frozen_param145 = None
2025-03-21T20:31:43.1923538Z             
2025-03-21T20:31:43.1924319Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:345 in update, code: k_out = torch.ops.aten.index_put_(self.past_k_caches, [None, input_pos], k_val)
2025-03-21T20:31:43.1925969Z             quantized_decomposed_dequantize_per_tensor_default_146: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param146, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  b__frozen_param146 = None
2025-03-21T20:31:43.1927041Z             
2025-03-21T20:31:43.1927835Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:346 in update, code: v_out = torch.ops.aten.index_put_(self.past_v_caches, [None, input_pos], v_val)
2025-03-21T20:31:43.1929556Z             quantized_decomposed_dequantize_per_tensor_default_147: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param147, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  b__frozen_param147 = None
2025-03-21T20:31:43.1930643Z             
2025-03-21T20:31:43.1931265Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:157 in forward, code: attn_mask = mask[input_pos]
2025-03-21T20:31:43.1932934Z             quantized_decomposed_dequantize_per_tensor_default_148: "f32[128, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param148, 0.0038910505827516317, 65535, 0, 65535, torch.int32);  b__frozen_param148 = None
2025-03-21T20:31:43.1934015Z             
2025-03-21T20:31:43.1934601Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:161 in forward, code: h = self.tok_embeddings(tokens)
2025-03-21T20:31:43.1935973Z             aten_embedding_default: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_embedding_default(quantized_decomposed_dequantize_per_tensor_default, tokens);  quantized_decomposed_dequantize_per_tensor_default = tokens = None
2025-03-21T20:31:43.1937760Z             quantized_decomposed_quantize_per_tensor_default: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_embedding_default, 1.9342933228472248e-05, 48293, 0, 65535, torch.int32);  aten_embedding_default = None
2025-03-21T20:31:43.1938845Z             
2025-03-21T20:31:43.1939345Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:111 in forward, code: h = x + h
2025-03-21T20:31:43.1940799Z             quantized_decomposed_dequantize_per_tensor_default_149: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default, 1.9342933228472248e-05, 48293, 0, 65535, torch.int32)
2025-03-21T20:31:43.1941934Z             
2025-03-21T20:31:43.1942631Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:108 in forward, code: self.attention_norm(x), freqs_cos, freqs_sin, **attn_options
2025-03-21T20:31:43.1944457Z             quantized_decomposed_dequantize_per_tensor_default_150: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default, 1.9342933228472248e-05, 48293, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default = None
2025-03-21T20:31:43.1945761Z             
2025-03-21T20:31:43.1946322Z              # File: /pytorch/executorch/examples/models/llama/rope.py:300 in get_freqs, code: freqs_cos = self.freqs_cos[input_pos]
2025-03-21T20:31:43.1947642Z             aten_index_tensor: "f32[1, 32]" = executorch_exir_dialects_edge__ops_aten_index_Tensor(quantized_decomposed_dequantize_per_tensor_default_111, [attn_options_input_pos]);  quantized_decomposed_dequantize_per_tensor_default_111 = None
2025-03-21T20:31:43.1949369Z             quantized_decomposed_quantize_per_tensor_default_1: "i32[1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_tensor, 3.051804378628731e-05, 32768, 0, 65535, torch.int32);  aten_index_tensor = None
2025-03-21T20:31:43.1950443Z             
2025-03-21T20:31:43.1951024Z              # File: /pytorch/executorch/examples/models/llama/rope.py:78 in reshape_for_broadcast, code: return freqs_cis.view(shape)
2025-03-21T20:31:43.1952473Z             quantized_decomposed_dequantize_per_tensor_default_151: "f32[1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.1954371Z             quantized_decomposed_dequantize_per_tensor_default_152: "f32[1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.1956273Z             quantized_decomposed_dequantize_per_tensor_default_153: "f32[1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.1958169Z             quantized_decomposed_dequantize_per_tensor_default_154: "f32[1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.1960062Z             quantized_decomposed_dequantize_per_tensor_default_155: "f32[1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.1961956Z             quantized_decomposed_dequantize_per_tensor_default_156: "f32[1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.1963839Z             quantized_decomposed_dequantize_per_tensor_default_157: "f32[1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.1965729Z             quantized_decomposed_dequantize_per_tensor_default_158: "f32[1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.1967786Z             quantized_decomposed_dequantize_per_tensor_default_159: "f32[1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.1969751Z             quantized_decomposed_dequantize_per_tensor_default_160: "f32[1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.1971662Z             quantized_decomposed_dequantize_per_tensor_default_161: "f32[1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.1973775Z             quantized_decomposed_dequantize_per_tensor_default_162: "f32[1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1, 3.051804378628731e-05, 32768, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1 = None
2025-03-21T20:31:43.1975113Z             
2025-03-21T20:31:43.1975678Z              # File: /pytorch/executorch/examples/models/llama/rope.py:301 in get_freqs, code: freqs_sin = self.freqs_sin[input_pos]
2025-03-21T20:31:43.1977155Z             aten_index_tensor_1: "f32[1, 32]" = executorch_exir_dialects_edge__ops_aten_index_Tensor(quantized_decomposed_dequantize_per_tensor_default_112, [attn_options_input_pos]);  quantized_decomposed_dequantize_per_tensor_default_112 = None
2025-03-21T20:31:43.1979020Z             quantized_decomposed_quantize_per_tensor_default_2: "i32[1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_tensor_1, 3.051786916330457e-05, 32767, 0, 65535, torch.int32);  aten_index_tensor_1 = None
2025-03-21T20:31:43.1980071Z             
2025-03-21T20:31:43.1980643Z              # File: /pytorch/executorch/examples/models/llama/rope.py:78 in reshape_for_broadcast, code: return freqs_cis.view(shape)
2025-03-21T20:31:43.1982098Z             quantized_decomposed_dequantize_per_tensor_default_163: "f32[1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_2, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.1983998Z             quantized_decomposed_dequantize_per_tensor_default_164: "f32[1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_2, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.1985889Z             quantized_decomposed_dequantize_per_tensor_default_165: "f32[1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_2, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.1987779Z             quantized_decomposed_dequantize_per_tensor_default_166: "f32[1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_2, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.1989676Z             quantized_decomposed_dequantize_per_tensor_default_167: "f32[1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_2, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.1991569Z             quantized_decomposed_dequantize_per_tensor_default_168: "f32[1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_2, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.1993537Z             quantized_decomposed_dequantize_per_tensor_default_169: "f32[1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_2, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.1995433Z             quantized_decomposed_dequantize_per_tensor_default_170: "f32[1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_2, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.1997349Z             quantized_decomposed_dequantize_per_tensor_default_171: "f32[1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_2, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.1999248Z             quantized_decomposed_dequantize_per_tensor_default_172: "f32[1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_2, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.2001139Z             quantized_decomposed_dequantize_per_tensor_default_173: "f32[1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_2, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.2003297Z             quantized_decomposed_dequantize_per_tensor_default_174: "f32[1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_2, 3.051786916330457e-05, 32767, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_2 = None
2025-03-21T20:31:43.2004604Z             
2025-03-21T20:31:43.2005311Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:108 in forward, code: self.attention_norm(x), freqs_cos, freqs_sin, **attn_options
2025-03-21T20:31:43.2006507Z             aten_pow_tensor_scalar: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_pow_Tensor_Scalar(quantized_decomposed_dequantize_per_tensor_default_150, 2)
2025-03-21T20:31:43.2007572Z             aten_mean_dim: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_mean_dim(aten_pow_tensor_scalar, [2], True);  aten_pow_tensor_scalar = None
2025-03-21T20:31:43.2008554Z             aten_add_scalar: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_add_Scalar(aten_mean_dim, 9.999999747378752e-06);  aten_mean_dim = None
2025-03-21T20:31:43.2009578Z             aten_rsqrt_default: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_rsqrt_default(aten_add_scalar);  aten_add_scalar = None
2025-03-21T20:31:43.2010938Z             aten_mul_tensor: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_150, aten_rsqrt_default);  quantized_decomposed_dequantize_per_tensor_default_150 = aten_rsqrt_default = None
2025-03-21T20:31:43.2012664Z             aten_mul_tensor_1: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(aten_mul_tensor, quantized_decomposed_dequantize_per_tensor_default_1);  aten_mul_tensor = quantized_decomposed_dequantize_per_tensor_default_1 = None
2025-03-21T20:31:43.2014408Z             quantized_decomposed_quantize_per_tensor_default_3: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_1, 0.00010396946890978143, 52957, 0, 65535, torch.int32);  aten_mul_tensor_1 = None
2025-03-21T20:31:43.2015441Z             
2025-03-21T20:31:43.2016114Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.2017685Z             quantized_decomposed_dequantize_per_tensor_default_175: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_3, 0.00010396946890978143, 52957, 0, 65535, torch.int32)
2025-03-21T20:31:43.2019631Z             quantized_decomposed_dequantize_per_tensor_default_176: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_3, 0.00010396946890978143, 52957, 0, 65535, torch.int32)
2025-03-21T20:31:43.2021804Z             quantized_decomposed_dequantize_per_tensor_default_177: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_3, 0.00010396946890978143, 52957, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_3 = None
2025-03-21T20:31:43.2023838Z             aten_unsqueeze_copy_default: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_177, -1);  quantized_decomposed_dequantize_per_tensor_default_177 = None
2025-03-21T20:31:43.2025673Z             quantized_decomposed_quantize_per_tensor_default_4: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default, 0.00010396946890978143, 52957, 0, 65535, torch.int32);  aten_unsqueeze_copy_default = None
2025-03-21T20:31:43.2026830Z             
2025-03-21T20:31:43.2027379Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.2029038Z             quantized_decomposed_dequantize_per_tensor_default_178: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_4, 0.00010396946890978143, 52957, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_4 = None
2025-03-21T20:31:43.2031067Z             aten_permute_copy_default: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_178, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_178 = None
2025-03-21T20:31:43.2033039Z             quantized_decomposed_quantize_per_tensor_default_5: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default, 0.00010396946890978143, 52957, 0, 65535, torch.int32);  aten_permute_copy_default = None
2025-03-21T20:31:43.2034166Z             
2025-03-21T20:31:43.2034660Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.2036282Z             quantized_decomposed_dequantize_per_tensor_default_179: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_5, 0.00010396946890978143, 52957, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_5 = None
2025-03-21T20:31:43.2038779Z             aten_convolution_default: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_179, quantized_decomposed_dequantize_per_tensor_default_2, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_179 = quantized_decomposed_dequantize_per_tensor_default_2 = None
2025-03-21T20:31:43.2041057Z             quantized_decomposed_quantize_per_tensor_default_6: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default, 0.0004140927630942315, 29454, 0, 65535, torch.int32);  aten_convolution_default = None
2025-03-21T20:31:43.2042176Z             
2025-03-21T20:31:43.2042733Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.2044494Z             quantized_decomposed_dequantize_per_tensor_default_180: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_6, 0.0004140927630942315, 29454, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_6 = None
2025-03-21T20:31:43.2046551Z             aten_permute_copy_default_1: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_180, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_180 = None
2025-03-21T20:31:43.2048358Z             quantized_decomposed_quantize_per_tensor_default_7: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_1, 0.0004140927630942315, 29454, 0, 65535, torch.int32);  aten_permute_copy_default_1 = None
2025-03-21T20:31:43.2049546Z             
2025-03-21T20:31:43.2050225Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.2052048Z             quantized_decomposed_dequantize_per_tensor_default_181: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_7, 0.0004140927630942315, 29454, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_7 = None
2025-03-21T20:31:43.2054023Z             aten_squeeze_copy_dims: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_181, [-1]);  quantized_decomposed_dequantize_per_tensor_default_181 = None
2025-03-21T20:31:43.2055757Z             quantized_decomposed_quantize_per_tensor_default_8: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims, 0.0004140927630942315, 29454, 0, 65535, torch.int32);  aten_squeeze_copy_dims = None
2025-03-21T20:31:43.2056835Z             
2025-03-21T20:31:43.2057477Z              # File: /pytorch/executorch/examples/models/llama/attention.py:242 in forward, code: q = q.view(bsz, seqlen, self.n_local_heads, self.head_dim)
2025-03-21T20:31:43.2059231Z             quantized_decomposed_dequantize_per_tensor_default_182: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_8, 0.0004140927630942315, 29454, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_8 = None
2025-03-21T20:31:43.2060553Z             
2025-03-21T20:31:43.2061207Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.2062638Z             aten_unsqueeze_copy_default_1: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_176, -1);  quantized_decomposed_dequantize_per_tensor_default_176 = None
2025-03-21T20:31:43.2064478Z             quantized_decomposed_quantize_per_tensor_default_9: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_1, 0.00010396946890978143, 52957, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_1 = None
2025-03-21T20:31:43.2065618Z             
2025-03-21T20:31:43.2066161Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.2067838Z             quantized_decomposed_dequantize_per_tensor_default_183: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_9, 0.00010396946890978143, 52957, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_9 = None
2025-03-21T20:31:43.2069880Z             aten_permute_copy_default_2: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_183, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_183 = None
2025-03-21T20:31:43.2071719Z             quantized_decomposed_quantize_per_tensor_default_10: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_2, 0.00010396946890978143, 52957, 0, 65535, torch.int32);  aten_permute_copy_default_2 = None
2025-03-21T20:31:43.2072830Z             
2025-03-21T20:31:43.2073328Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.2074945Z             quantized_decomposed_dequantize_per_tensor_default_184: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_10, 0.00010396946890978143, 52957, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_10 = None
2025-03-21T20:31:43.2077470Z             aten_convolution_default_1: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_184, quantized_decomposed_dequantize_per_tensor_default_3, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_184 = quantized_decomposed_dequantize_per_tensor_default_3 = None
2025-03-21T20:31:43.2079900Z             quantized_decomposed_quantize_per_tensor_default_11: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_1, 0.0002585018228273839, 30370, 0, 65535, torch.int32);  aten_convolution_default_1 = None
2025-03-21T20:31:43.2081024Z             
2025-03-21T20:31:43.2081586Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.2083363Z             quantized_decomposed_dequantize_per_tensor_default_185: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_11, 0.0002585018228273839, 30370, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_11 = None
2025-03-21T20:31:43.2085397Z             aten_permute_copy_default_3: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_185, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_185 = None
2025-03-21T20:31:43.2087206Z             quantized_decomposed_quantize_per_tensor_default_12: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_3, 0.0002585018228273839, 30370, 0, 65535, torch.int32);  aten_permute_copy_default_3 = None
2025-03-21T20:31:43.2088328Z             
2025-03-21T20:31:43.2089006Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.2090878Z             quantized_decomposed_dequantize_per_tensor_default_186: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_12, 0.0002585018228273839, 30370, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_12 = None
2025-03-21T20:31:43.2092873Z             aten_squeeze_copy_dims_1: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_186, [-1]);  quantized_decomposed_dequantize_per_tensor_default_186 = None
2025-03-21T20:31:43.2094666Z             quantized_decomposed_quantize_per_tensor_default_13: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_1, 0.0002585018228273839, 30370, 0, 65535, torch.int32);  aten_squeeze_copy_dims_1 = None
2025-03-21T20:31:43.2095783Z             
2025-03-21T20:31:43.2096451Z              # File: /pytorch/executorch/examples/models/llama/attention.py:243 in forward, code: k = k.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.2098262Z             quantized_decomposed_dequantize_per_tensor_default_187: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_13, 0.0002585018228273839, 30370, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_13 = None
2025-03-21T20:31:43.2099591Z             
2025-03-21T20:31:43.2100250Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.2101677Z             aten_unsqueeze_copy_default_2: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_175, -1);  quantized_decomposed_dequantize_per_tensor_default_175 = None
2025-03-21T20:31:43.2103549Z             quantized_decomposed_quantize_per_tensor_default_14: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_2, 0.00010396946890978143, 52957, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_2 = None
2025-03-21T20:31:43.2104691Z             
2025-03-21T20:31:43.2105234Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.2106883Z             quantized_decomposed_dequantize_per_tensor_default_188: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_14, 0.00010396946890978143, 52957, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_14 = None
2025-03-21T20:31:43.2108916Z             aten_permute_copy_default_4: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_188, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_188 = None
2025-03-21T20:31:43.2110724Z             quantized_decomposed_quantize_per_tensor_default_15: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_4, 0.00010396946890978143, 52957, 0, 65535, torch.int32);  aten_permute_copy_default_4 = None
2025-03-21T20:31:43.2111840Z             
2025-03-21T20:31:43.2112341Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.2113960Z             quantized_decomposed_dequantize_per_tensor_default_189: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_15, 0.00010396946890978143, 52957, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_15 = None
2025-03-21T20:31:43.2116461Z             aten_convolution_default_2: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_189, quantized_decomposed_dequantize_per_tensor_default_4, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_189 = quantized_decomposed_dequantize_per_tensor_default_4 = None
2025-03-21T20:31:43.2118769Z             quantized_decomposed_quantize_per_tensor_default_16: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_2, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_convolution_default_2 = None
2025-03-21T20:31:43.2119909Z             
2025-03-21T20:31:43.2120465Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.2122135Z             quantized_decomposed_dequantize_per_tensor_default_190: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_16, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_16 = None
2025-03-21T20:31:43.2124186Z             aten_permute_copy_default_5: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_190, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_190 = None
2025-03-21T20:31:43.2125997Z             quantized_decomposed_quantize_per_tensor_default_17: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_5, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_permute_copy_default_5 = None
2025-03-21T20:31:43.2127141Z             
2025-03-21T20:31:43.2127802Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.2129651Z             quantized_decomposed_dequantize_per_tensor_default_191: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_17, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_17 = None
2025-03-21T20:31:43.2131642Z             aten_squeeze_copy_dims_2: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_191, [-1]);  quantized_decomposed_dequantize_per_tensor_default_191 = None
2025-03-21T20:31:43.2133740Z             quantized_decomposed_quantize_per_tensor_default_18: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_2, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_squeeze_copy_dims_2 = None
2025-03-21T20:31:43.2134842Z             
2025-03-21T20:31:43.2135505Z              # File: /pytorch/executorch/examples/models/llama/attention.py:244 in forward, code: v = v.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.2137282Z             quantized_decomposed_dequantize_per_tensor_default_192: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_18, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_18 = None
2025-03-21T20:31:43.2138610Z             
2025-03-21T20:31:43.2139261Z              # File: /pytorch/executorch/examples/models/llama/attention.py:242 in forward, code: q = q.view(bsz, seqlen, self.n_local_heads, self.head_dim)
2025-03-21T20:31:43.2140643Z             aten_view_copy_default: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_182, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_182 = None
2025-03-21T20:31:43.2142406Z             quantized_decomposed_quantize_per_tensor_default_19: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default, 0.0004140927630942315, 29454, 0, 65535, torch.int32);  aten_view_copy_default = None
2025-03-21T20:31:43.2143494Z             
2025-03-21T20:31:43.2144618Z              # File: <eval_with_key>.50:412 in forward, code: dequantize_per_tensor_default_168 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_168, 0.0004140927630942315, 29454, 0, 65535, torch.int32);  quantize_per_tensor_default_168 = None
2025-03-21T20:31:43.2146830Z             quantized_decomposed_dequantize_per_tensor_default_193: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_19, 0.0004140927630942315, 29454, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_19 = None
2025-03-21T20:31:43.2148164Z             
2025-03-21T20:31:43.2148864Z              # File: /pytorch/executorch/examples/models/llama/attention.py:243 in forward, code: k = k.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.2150261Z             aten_view_copy_default_1: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_187, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_187 = None
2025-03-21T20:31:43.2152028Z             quantized_decomposed_quantize_per_tensor_default_20: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_1, 0.0002585018228273839, 30370, 0, 65535, torch.int32);  aten_view_copy_default_1 = None
2025-03-21T20:31:43.2153161Z             
2025-03-21T20:31:43.2154224Z              # File: <eval_with_key>.50:415 in forward, code: dequantize_per_tensor_default_169 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_169, 0.0002585018228273839, 30370, 0, 65535, torch.int32);  quantize_per_tensor_default_169 = None
2025-03-21T20:31:43.2156393Z             quantized_decomposed_dequantize_per_tensor_default_194: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_20, 0.0002585018228273839, 30370, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_20 = None
2025-03-21T20:31:43.2157727Z             
2025-03-21T20:31:43.2158395Z              # File: /pytorch/executorch/examples/models/llama/attention.py:244 in forward, code: v = v.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.2159778Z             aten_view_copy_default_2: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_192, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_192 = None
2025-03-21T20:31:43.2161536Z             quantized_decomposed_quantize_per_tensor_default_21: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_2, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_view_copy_default_2 = None
2025-03-21T20:31:43.2162626Z             
2025-03-21T20:31:43.2163433Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:346 in update, code: v_out = torch.ops.aten.index_put_(self.past_v_caches, [None, input_pos], v_val)
2025-03-21T20:31:43.2165343Z             quantized_decomposed_dequantize_per_tensor_default_195: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_21, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_21 = None
2025-03-21T20:31:43.2166670Z             
2025-03-21T20:31:43.2167545Z              # File: <eval_with_key>.50:420 in forward, code: quantize_per_tensor_default_171 = torch.ops.quantized_decomposed.quantize_per_tensor.default(_to_copy, 0.0004140927630942315, 29454, 0, 65535, torch.int32);  _to_copy = None
2025-03-21T20:31:43.2169707Z             quantized_decomposed_quantize_per_tensor_default_22: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_193, 0.0004140927630942315, 29454, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_193 = None
2025-03-21T20:31:43.2171088Z             
2025-03-21T20:31:43.2171756Z              # File: /pytorch/executorch/examples/models/llama/rope.py:84 in apply_rotary_emb, code: xq_r, xq_i = xq.float().reshape(xq.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.2173558Z             quantized_decomposed_dequantize_per_tensor_default_196: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_22, 0.0004140927630942315, 29454, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_22 = None
2025-03-21T20:31:43.2175566Z             aten_view_copy_default_3: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_196, [1, 1, 12, -1, 2]);  quantized_decomposed_dequantize_per_tensor_default_196 = None
2025-03-21T20:31:43.2177327Z             quantized_decomposed_quantize_per_tensor_default_23: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_3, 0.0004140927630942315, 29454, 0, 65535, torch.int32);  aten_view_copy_default_3 = None
2025-03-21T20:31:43.2179484Z             quantized_decomposed_dequantize_per_tensor_default_197: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_23, 0.0004140927630942315, 29454, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_23 = None
2025-03-21T20:31:43.2181518Z             aten_slice_copy_tensor: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_197, 4, 0, 1)
2025-03-21T20:31:43.2182902Z             aten_slice_copy_tensor_1: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_197, 4, 1, 2);  quantized_decomposed_dequantize_per_tensor_default_197 = None
2025-03-21T20:31:43.2184265Z             aten_squeeze_copy_dims_3: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor, [4]);  aten_slice_copy_tensor = None
2025-03-21T20:31:43.2185391Z             aten_squeeze_copy_dims_4: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_1, [4]);  aten_slice_copy_tensor_1 = None
2025-03-21T20:31:43.2186916Z             quantized_decomposed_quantize_per_tensor_default_24: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_3, 0.00039459901745431125, 27671, 0, 65535, torch.int32);  aten_squeeze_copy_dims_3 = None
2025-03-21T20:31:43.2188011Z             
2025-03-21T20:31:43.2188626Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.2190128Z             quantized_decomposed_dequantize_per_tensor_default_198: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_24, 0.00039459901745431125, 27671, 0, 65535, torch.int32)
2025-03-21T20:31:43.2191243Z             
2025-03-21T20:31:43.2191855Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.2193580Z             quantized_decomposed_dequantize_per_tensor_default_199: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_24, 0.00039459901745431125, 27671, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_24 = None
2025-03-21T20:31:43.2194895Z             
2025-03-21T20:31:43.2195637Z              # File: /pytorch/executorch/examples/models/llama/rope.py:84 in apply_rotary_emb, code: xq_r, xq_i = xq.float().reshape(xq.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.2197162Z             quantized_decomposed_quantize_per_tensor_default_25: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_4, 0.0003584773512557149, 34023, 0, 65535, torch.int32);  aten_squeeze_copy_dims_4 = None
2025-03-21T20:31:43.2198254Z             
2025-03-21T20:31:43.2198888Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.2200384Z             quantized_decomposed_dequantize_per_tensor_default_200: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_25, 0.0003584773512557149, 34023, 0, 65535, torch.int32)
2025-03-21T20:31:43.2201554Z             
2025-03-21T20:31:43.2202164Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.2203909Z             quantized_decomposed_dequantize_per_tensor_default_201: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_25, 0.0003584773512557149, 34023, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_25 = None
2025-03-21T20:31:43.2205221Z             
2025-03-21T20:31:43.2206109Z              # File: <eval_with_key>.50:435 in forward, code: quantize_per_tensor_default_175 = torch.ops.quantized_decomposed.quantize_per_tensor.default(_to_copy_1, 0.0002585018228273839, 30370, 0, 65535, torch.int32);  _to_copy_1 = None
2025-03-21T20:31:43.2208103Z             quantized_decomposed_quantize_per_tensor_default_26: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_194, 0.0002585018228273839, 30370, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_194 = None
2025-03-21T20:31:43.2209530Z             
2025-03-21T20:31:43.2210194Z              # File: /pytorch/executorch/examples/models/llama/rope.py:85 in apply_rotary_emb, code: xk_r, xk_i = xk.float().reshape(xk.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.2211953Z             quantized_decomposed_dequantize_per_tensor_default_202: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_26, 0.0002585018228273839, 30370, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_26 = None
2025-03-21T20:31:43.2213961Z             aten_view_copy_default_4: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_202, [1, 1, 12, -1, 2]);  quantized_decomposed_dequantize_per_tensor_default_202 = None
2025-03-21T20:31:43.2215721Z             quantized_decomposed_quantize_per_tensor_default_27: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_4, 0.0002585018228273839, 30370, 0, 65535, torch.int32);  aten_view_copy_default_4 = None
2025-03-21T20:31:43.2217849Z             quantized_decomposed_dequantize_per_tensor_default_203: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_27, 0.0002585018228273839, 30370, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_27 = None
2025-03-21T20:31:43.2219614Z             aten_slice_copy_tensor_2: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_203, 4, 0, 1)
2025-03-21T20:31:43.2221065Z             aten_slice_copy_tensor_3: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_203, 4, 1, 2);  quantized_decomposed_dequantize_per_tensor_default_203 = None
2025-03-21T20:31:43.2222439Z             aten_squeeze_copy_dims_5: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_2, [4]);  aten_slice_copy_tensor_2 = None
2025-03-21T20:31:43.2223595Z             aten_squeeze_copy_dims_6: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_3, [4]);  aten_slice_copy_tensor_3 = None
2025-03-21T20:31:43.2225109Z             quantized_decomposed_quantize_per_tensor_default_28: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_5, 0.0002567824558354914, 30134, 0, 65535, torch.int32);  aten_squeeze_copy_dims_5 = None
2025-03-21T20:31:43.2226206Z             
2025-03-21T20:31:43.2226805Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.2228320Z             quantized_decomposed_dequantize_per_tensor_default_204: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_28, 0.0002567824558354914, 30134, 0, 65535, torch.int32)
2025-03-21T20:31:43.2229426Z             
2025-03-21T20:31:43.2230031Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.2231746Z             quantized_decomposed_dequantize_per_tensor_default_205: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_28, 0.0002567824558354914, 30134, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_28 = None
2025-03-21T20:31:43.2233228Z             
2025-03-21T20:31:43.2233885Z              # File: /pytorch/executorch/examples/models/llama/rope.py:85 in apply_rotary_emb, code: xk_r, xk_i = xk.float().reshape(xk.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.2235415Z             quantized_decomposed_quantize_per_tensor_default_29: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_6, 0.0002435054339002818, 32240, 0, 65535, torch.int32);  aten_squeeze_copy_dims_6 = None
2025-03-21T20:31:43.2236511Z             
2025-03-21T20:31:43.2237106Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.2238600Z             quantized_decomposed_dequantize_per_tensor_default_206: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_29, 0.0002435054339002818, 32240, 0, 65535, torch.int32)
2025-03-21T20:31:43.2239707Z             
2025-03-21T20:31:43.2240315Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.2242038Z             quantized_decomposed_dequantize_per_tensor_default_207: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_29, 0.0002435054339002818, 32240, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_29 = None
2025-03-21T20:31:43.2243359Z             
2025-03-21T20:31:43.2243933Z              # File: /pytorch/executorch/examples/models/llama/rope.py:78 in reshape_for_broadcast, code: return freqs_cis.view(shape)
2025-03-21T20:31:43.2245307Z             aten_view_copy_default_5: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_162, [1, 1, 1, 32]);  quantized_decomposed_dequantize_per_tensor_default_162 = None
2025-03-21T20:31:43.2247094Z             quantized_decomposed_quantize_per_tensor_default_30: "i32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_5, 3.051804378628731e-05, 32768, 0, 65535, torch.int32);  aten_view_copy_default_5 = None
2025-03-21T20:31:43.2248176Z             
2025-03-21T20:31:43.2248822Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.2250382Z             quantized_decomposed_dequantize_per_tensor_default_208: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_30, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.2251495Z             
2025-03-21T20:31:43.2252103Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.2253632Z             quantized_decomposed_dequantize_per_tensor_default_209: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_30, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.2254738Z             
2025-03-21T20:31:43.2255344Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.2256815Z             quantized_decomposed_dequantize_per_tensor_default_210: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_30, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.2257924Z             
2025-03-21T20:31:43.2258533Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.2260246Z             quantized_decomposed_dequantize_per_tensor_default_211: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_30, 3.051804378628731e-05, 32768, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_30 = None
2025-03-21T20:31:43.2261570Z             
2025-03-21T20:31:43.2262143Z              # File: /pytorch/executorch/examples/models/llama/rope.py:78 in reshape_for_broadcast, code: return freqs_cis.view(shape)
2025-03-21T20:31:43.2263456Z             aten_view_copy_default_6: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_174, [1, 1, 1, 32]);  quantized_decomposed_dequantize_per_tensor_default_174 = None
2025-03-21T20:31:43.2265212Z             quantized_decomposed_quantize_per_tensor_default_31: "i32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_6, 3.051786916330457e-05, 32767, 0, 65535, torch.int32);  aten_view_copy_default_6 = None
2025-03-21T20:31:43.2266304Z             
2025-03-21T20:31:43.2266910Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.2268410Z             quantized_decomposed_dequantize_per_tensor_default_212: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_31, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.2269519Z             
2025-03-21T20:31:43.2270178Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.2271667Z             quantized_decomposed_dequantize_per_tensor_default_213: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_31, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.2272775Z             
2025-03-21T20:31:43.2273414Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.2274904Z             quantized_decomposed_dequantize_per_tensor_default_214: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_31, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.2276007Z             
2025-03-21T20:31:43.2276602Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.2278303Z             quantized_decomposed_dequantize_per_tensor_default_215: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_31, 3.051786916330457e-05, 32767, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_31 = None
2025-03-21T20:31:43.2279646Z             
2025-03-21T20:31:43.2280253Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.2281952Z             aten_mul_tensor_2: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_199, quantized_decomposed_dequantize_per_tensor_default_211);  quantized_decomposed_dequantize_per_tensor_default_199 = quantized_decomposed_dequantize_per_tensor_default_211 = None
2025-03-21T20:31:43.2284153Z             quantized_decomposed_quantize_per_tensor_default_32: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_2, 0.0003940780588891357, 27683, 0, 65535, torch.int32);  aten_mul_tensor_2 = None
2025-03-21T20:31:43.2286232Z             quantized_decomposed_dequantize_per_tensor_default_216: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_32, 0.0003940780588891357, 27683, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_32 = None
2025-03-21T20:31:43.2288571Z             aten_mul_tensor_3: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_200, quantized_decomposed_dequantize_per_tensor_default_214);  quantized_decomposed_dequantize_per_tensor_default_200 = quantized_decomposed_dequantize_per_tensor_default_214 = None
2025-03-21T20:31:43.2290725Z             quantized_decomposed_quantize_per_tensor_default_33: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_3, 0.00031320139532908797, 30302, 0, 65535, torch.int32);  aten_mul_tensor_3 = None
2025-03-21T20:31:43.2292810Z             quantized_decomposed_dequantize_per_tensor_default_217: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_33, 0.00031320139532908797, 30302, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_33 = None
2025-03-21T20:31:43.2295219Z             aten_sub_tensor: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_sub_Tensor(quantized_decomposed_dequantize_per_tensor_default_216, quantized_decomposed_dequantize_per_tensor_default_217);  quantized_decomposed_dequantize_per_tensor_default_216 = quantized_decomposed_dequantize_per_tensor_default_217 = None
2025-03-21T20:31:43.2297287Z             quantized_decomposed_quantize_per_tensor_default_34: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_sub_tensor, 0.000392118061427027, 27719, 0, 65535, torch.int32);  aten_sub_tensor = None
2025-03-21T20:31:43.2298312Z             
2025-03-21T20:31:43.2299397Z              # File: <eval_with_key>.50:469 in forward, code: dequantize_per_tensor_default_183 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_183, 0.000392118061427027, 27719, 0, 65535, torch.int32);  quantize_per_tensor_default_183 = None
2025-03-21T20:31:43.2301559Z             quantized_decomposed_dequantize_per_tensor_default_218: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_34, 0.000392118061427027, 27719, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_34 = None
2025-03-21T20:31:43.2302888Z             
2025-03-21T20:31:43.2303495Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.2305229Z             aten_mul_tensor_4: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_198, quantized_decomposed_dequantize_per_tensor_default_215);  quantized_decomposed_dequantize_per_tensor_default_198 = quantized_decomposed_dequantize_per_tensor_default_215 = None
2025-03-21T20:31:43.2307283Z             quantized_decomposed_quantize_per_tensor_default_35: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_4, 0.00019886602240148932, 32650, 0, 65535, torch.int32);  aten_mul_tensor_4 = None
2025-03-21T20:31:43.2309368Z             quantized_decomposed_dequantize_per_tensor_default_219: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_35, 0.00019886602240148932, 32650, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_35 = None
2025-03-21T20:31:43.2311716Z             aten_mul_tensor_5: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_201, quantized_decomposed_dequantize_per_tensor_default_210);  quantized_decomposed_dequantize_per_tensor_default_201 = quantized_decomposed_dequantize_per_tensor_default_210 = None
2025-03-21T20:31:43.2313765Z             quantized_decomposed_quantize_per_tensor_default_36: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_5, 0.000358294986654073, 34007, 0, 65535, torch.int32);  aten_mul_tensor_5 = None
2025-03-21T20:31:43.2315828Z             quantized_decomposed_dequantize_per_tensor_default_220: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_36, 0.000358294986654073, 34007, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_36 = None
2025-03-21T20:31:43.2318161Z             aten_add_tensor: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_219, quantized_decomposed_dequantize_per_tensor_default_220);  quantized_decomposed_dequantize_per_tensor_default_219 = quantized_decomposed_dequantize_per_tensor_default_220 = None
2025-03-21T20:31:43.2320216Z             quantized_decomposed_quantize_per_tensor_default_37: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor, 0.0003606027748901397, 33984, 0, 65535, torch.int32);  aten_add_tensor = None
2025-03-21T20:31:43.2321296Z             
2025-03-21T20:31:43.2322356Z              # File: <eval_with_key>.50:478 in forward, code: dequantize_per_tensor_default_186 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_186, 0.0003606027748901397, 33984, 0, 65535, torch.int32);  quantize_per_tensor_default_186 = None
2025-03-21T20:31:43.2324549Z             quantized_decomposed_dequantize_per_tensor_default_221: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_37, 0.0003606027748901397, 33984, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_37 = None
2025-03-21T20:31:43.2325872Z             
2025-03-21T20:31:43.2326488Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.2328183Z             aten_mul_tensor_6: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_205, quantized_decomposed_dequantize_per_tensor_default_209);  quantized_decomposed_dequantize_per_tensor_default_205 = quantized_decomposed_dequantize_per_tensor_default_209 = None
2025-03-21T20:31:43.2330338Z             quantized_decomposed_quantize_per_tensor_default_38: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_6, 0.0002772818843368441, 32772, 0, 65535, torch.int32);  aten_mul_tensor_6 = None
2025-03-21T20:31:43.2332567Z             quantized_decomposed_dequantize_per_tensor_default_222: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_38, 0.0002772818843368441, 32772, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_38 = None
2025-03-21T20:31:43.2334923Z             aten_mul_tensor_7: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_206, quantized_decomposed_dequantize_per_tensor_default_212);  quantized_decomposed_dequantize_per_tensor_default_206 = quantized_decomposed_dequantize_per_tensor_default_212 = None
2025-03-21T20:31:43.2336984Z             quantized_decomposed_quantize_per_tensor_default_39: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_7, 0.00019303792214486748, 32722, 0, 65535, torch.int32);  aten_mul_tensor_7 = None
2025-03-21T20:31:43.2339069Z             quantized_decomposed_dequantize_per_tensor_default_223: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_39, 0.00019303792214486748, 32722, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_39 = None
2025-03-21T20:31:43.2341412Z             aten_sub_tensor_1: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_sub_Tensor(quantized_decomposed_dequantize_per_tensor_default_222, quantized_decomposed_dequantize_per_tensor_default_223);  quantized_decomposed_dequantize_per_tensor_default_222 = quantized_decomposed_dequantize_per_tensor_default_223 = None
2025-03-21T20:31:43.2343469Z             quantized_decomposed_quantize_per_tensor_default_40: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_sub_tensor_1, 0.00027735860203392804, 32706, 0, 65535, torch.int32);  aten_sub_tensor_1 = None
2025-03-21T20:31:43.2344512Z             
2025-03-21T20:31:43.2345570Z              # File: <eval_with_key>.50:487 in forward, code: dequantize_per_tensor_default_189 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_189, 0.00027735860203392804, 32706, 0, 65535, torch.int32);  quantize_per_tensor_default_189 = None
2025-03-21T20:31:43.2347846Z             quantized_decomposed_dequantize_per_tensor_default_224: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_40, 0.00027735860203392804, 32706, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_40 = None
2025-03-21T20:31:43.2349179Z             
2025-03-21T20:31:43.2349777Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.2351517Z             aten_mul_tensor_8: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_204, quantized_decomposed_dequantize_per_tensor_default_213);  quantized_decomposed_dequantize_per_tensor_default_204 = quantized_decomposed_dequantize_per_tensor_default_213 = None
2025-03-21T20:31:43.2353572Z             quantized_decomposed_quantize_per_tensor_default_41: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_8, 0.0002768072590697557, 32698, 0, 65535, torch.int32);  aten_mul_tensor_8 = None
2025-03-21T20:31:43.2355681Z             quantized_decomposed_dequantize_per_tensor_default_225: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_41, 0.0002768072590697557, 32698, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_41 = None
2025-03-21T20:31:43.2358017Z             aten_mul_tensor_9: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_207, quantized_decomposed_dequantize_per_tensor_default_208);  quantized_decomposed_dequantize_per_tensor_default_207 = quantized_decomposed_dequantize_per_tensor_default_208 = None
2025-03-21T20:31:43.2360072Z             quantized_decomposed_quantize_per_tensor_default_42: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_9, 0.0002400432713329792, 32705, 0, 65535, torch.int32);  aten_mul_tensor_9 = None
2025-03-21T20:31:43.2362145Z             quantized_decomposed_dequantize_per_tensor_default_226: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_42, 0.0002400432713329792, 32705, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_42 = None
2025-03-21T20:31:43.2364484Z             aten_add_tensor_1: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_225, quantized_decomposed_dequantize_per_tensor_default_226);  quantized_decomposed_dequantize_per_tensor_default_225 = quantized_decomposed_dequantize_per_tensor_default_226 = None
2025-03-21T20:31:43.2366535Z             quantized_decomposed_quantize_per_tensor_default_43: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_1, 0.0002778804919216782, 32772, 0, 65535, torch.int32);  aten_add_tensor_1 = None
2025-03-21T20:31:43.2367579Z             
2025-03-21T20:31:43.2368640Z              # File: <eval_with_key>.50:496 in forward, code: dequantize_per_tensor_default_192 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_192, 0.0002778804919216782, 32772, 0, 65535, torch.int32);  quantize_per_tensor_default_192 = None
2025-03-21T20:31:43.2370882Z             quantized_decomposed_dequantize_per_tensor_default_227: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_43, 0.0002778804919216782, 32772, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_43 = None
2025-03-21T20:31:43.2372204Z             
2025-03-21T20:31:43.2372922Z              # File: /pytorch/executorch/examples/models/llama/rope.py:95 in apply_rotary_emb, code: xq_out = torch.stack([xq_out_r, xq_out_i], dim=-1).flatten(3)
2025-03-21T20:31:43.2374454Z             aten_unsqueeze_copy_default_3: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_218, 4);  quantized_decomposed_dequantize_per_tensor_default_218 = None
2025-03-21T20:31:43.2376183Z             aten_unsqueeze_copy_default_4: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_221, 4);  quantized_decomposed_dequantize_per_tensor_default_221 = None
2025-03-21T20:31:43.2377809Z             aten_cat_default: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_cat_default([aten_unsqueeze_copy_default_3, aten_unsqueeze_copy_default_4], -1);  aten_unsqueeze_copy_default_3 = aten_unsqueeze_copy_default_4 = None
2025-03-21T20:31:43.2379492Z             quantized_decomposed_quantize_per_tensor_default_44: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default, 0.0004132623434998095, 29653, 0, 65535, torch.int32);  aten_cat_default = None
2025-03-21T20:31:43.2381611Z             quantized_decomposed_dequantize_per_tensor_default_228: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_44, 0.0004132623434998095, 29653, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_44 = None
2025-03-21T20:31:43.2383601Z             aten_view_copy_default_7: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_228, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_228 = None
2025-03-21T20:31:43.2385625Z             quantized_decomposed_quantize_per_tensor_default_45: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_7, 0.0004132623434998095, 29653, 0, 65535, torch.int32);  aten_view_copy_default_7 = None
2025-03-21T20:31:43.2386707Z             
2025-03-21T20:31:43.2387765Z              # File: <eval_with_key>.50:502 in forward, code: dequantize_per_tensor_default_194 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_194, 0.0004132623434998095, 29653, 0, 65535, torch.int32);  quantize_per_tensor_default_194 = None
2025-03-21T20:31:43.2389934Z             quantized_decomposed_dequantize_per_tensor_default_229: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_45, 0.0004132623434998095, 29653, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_45 = None
2025-03-21T20:31:43.2391255Z             
2025-03-21T20:31:43.2391917Z              # File: /pytorch/executorch/examples/models/llama/rope.py:96 in apply_rotary_emb, code: xk_out = torch.stack([xk_out_r, xk_out_i], dim=-1).flatten(3)
2025-03-21T20:31:43.2393354Z             aten_unsqueeze_copy_default_5: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_224, 4);  quantized_decomposed_dequantize_per_tensor_default_224 = None
2025-03-21T20:31:43.2395036Z             aten_unsqueeze_copy_default_6: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_227, 4);  quantized_decomposed_dequantize_per_tensor_default_227 = None
2025-03-21T20:31:43.2396663Z             aten_cat_default_1: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_cat_default([aten_unsqueeze_copy_default_5, aten_unsqueeze_copy_default_6], -1);  aten_unsqueeze_copy_default_5 = aten_unsqueeze_copy_default_6 = None
2025-03-21T20:31:43.2398431Z             quantized_decomposed_quantize_per_tensor_default_46: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_1, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_cat_default_1 = None
2025-03-21T20:31:43.2400552Z             quantized_decomposed_dequantize_per_tensor_default_230: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_46, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_46 = None
2025-03-21T20:31:43.2402544Z             aten_view_copy_default_8: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_230, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_230 = None
2025-03-21T20:31:43.2404301Z             quantized_decomposed_quantize_per_tensor_default_47: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_8, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_view_copy_default_8 = None
2025-03-21T20:31:43.2405423Z             
2025-03-21T20:31:43.2406483Z              # File: <eval_with_key>.50:508 in forward, code: dequantize_per_tensor_default_196 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_196, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantize_per_tensor_default_196 = None
2025-03-21T20:31:43.2408655Z             quantized_decomposed_dequantize_per_tensor_default_231: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_47, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_47 = None
2025-03-21T20:31:43.2410101Z             
2025-03-21T20:31:43.2410957Z              # File: <eval_with_key>.50:510 in forward, code: quantize_per_tensor_default_197 = torch.ops.quantized_decomposed.quantize_per_tensor.default(type_as, 0.0004132623434998095, 29653, 0, 65535, torch.int32);  type_as = None
2025-03-21T20:31:43.2412940Z             quantized_decomposed_quantize_per_tensor_default_48: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_229, 0.0004132623434998095, 29653, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_229 = None
2025-03-21T20:31:43.2414266Z             
2025-03-21T20:31:43.2414929Z              # File: /pytorch/executorch/examples/models/llama/attention.py:249 in forward, code: q = q.transpose(1, 2)  # (bs, n_local_heads, seqlen, head_dim)
2025-03-21T20:31:43.2416690Z             quantized_decomposed_dequantize_per_tensor_default_232: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_48, 0.0004132623434998095, 29653, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_48 = None
2025-03-21T20:31:43.2418013Z             
2025-03-21T20:31:43.2418890Z              # File: <eval_with_key>.50:513 in forward, code: quantize_per_tensor_default_198 = torch.ops.quantized_decomposed.quantize_per_tensor.default(type_as_1, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  type_as_1 = None
2025-03-21T20:31:43.2420879Z             quantized_decomposed_quantize_per_tensor_default_49: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_231, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_231 = None
2025-03-21T20:31:43.2422200Z             
2025-03-21T20:31:43.2423035Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:345 in update, code: k_out = torch.ops.aten.index_put_(self.past_k_caches, [None, input_pos], k_val)
2025-03-21T20:31:43.2424967Z             quantized_decomposed_dequantize_per_tensor_default_233: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_49, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_49 = None
2025-03-21T20:31:43.2426275Z             
2025-03-21T20:31:43.2426954Z              # File: /pytorch/executorch/examples/models/llama/attention.py:249 in forward, code: q = q.transpose(1, 2)  # (bs, n_local_heads, seqlen, head_dim)
2025-03-21T20:31:43.2428369Z             aten_permute_copy_default_6: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_232, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_232 = None
2025-03-21T20:31:43.2430170Z             quantized_decomposed_quantize_per_tensor_default_50: "i32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_6, 0.0004132623434998095, 29653, 0, 65535, torch.int32);  aten_permute_copy_default_6 = None
2025-03-21T20:31:43.2431306Z             
2025-03-21T20:31:43.2432014Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.2434006Z             quantized_decomposed_dequantize_per_tensor_default_234: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_50, 0.0004132623434998095, 29653, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_50 = None
2025-03-21T20:31:43.2435327Z             
2025-03-21T20:31:43.2436128Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:345 in update, code: k_out = torch.ops.aten.index_put_(self.past_k_caches, [None, input_pos], k_val)
2025-03-21T20:31:43.2438186Z             aten_index_put_default: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_index_put_default(quantized_decomposed_dequantize_per_tensor_default_113, [None, attn_options_input_pos], quantized_decomposed_dequantize_per_tensor_default_233);  quantized_decomposed_dequantize_per_tensor_default_113 = quantized_decomposed_dequantize_per_tensor_default_233 = None
2025-03-21T20:31:43.2440464Z             quantized_decomposed_quantize_per_tensor_default_51: "i32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_put_default, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_index_put_default = None
2025-03-21T20:31:43.2441539Z             
2025-03-21T20:31:43.2442454Z              # File: <eval_with_key>.50:520 in forward, code: dequantize_per_tensor_default_200 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_200, 0.0002779011847451329, 32770, 0, 65535, torch.int32)
2025-03-21T20:31:43.2444267Z             quantized_decomposed_dequantize_per_tensor_default_235: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_51, 0.0002779011847451329, 32770, 0, 65535, torch.int32)
2025-03-21T20:31:43.2445379Z             
2025-03-21T20:31:43.2446155Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.2447880Z             quantized_decomposed_dequantize_per_tensor_default_236: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_51, 0.0002779011847451329, 32770, 0, 65535, torch.int32)
2025-03-21T20:31:43.2449912Z             quantized_decomposed_dequantize_per_tensor_default_237: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_51, 0.0002779011847451329, 32770, 0, 65535, torch.int32)
2025-03-21T20:31:43.2451892Z             quantized_decomposed_dequantize_per_tensor_default_238: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_51, 0.0002779011847451329, 32770, 0, 65535, torch.int32)
2025-03-21T20:31:43.2453823Z             quantized_decomposed_dequantize_per_tensor_default_239: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_51, 0.0002779011847451329, 32770, 0, 65535, torch.int32)
2025-03-21T20:31:43.2455760Z             quantized_decomposed_dequantize_per_tensor_default_240: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_51, 0.0002779011847451329, 32770, 0, 65535, torch.int32)
2025-03-21T20:31:43.2457725Z             quantized_decomposed_dequantize_per_tensor_default_241: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_51, 0.0002779011847451329, 32770, 0, 65535, torch.int32)
2025-03-21T20:31:43.2459649Z             quantized_decomposed_dequantize_per_tensor_default_242: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_51, 0.0002779011847451329, 32770, 0, 65535, torch.int32)
2025-03-21T20:31:43.2461577Z             quantized_decomposed_dequantize_per_tensor_default_243: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_51, 0.0002779011847451329, 32770, 0, 65535, torch.int32)
2025-03-21T20:31:43.2463502Z             quantized_decomposed_dequantize_per_tensor_default_244: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_51, 0.0002779011847451329, 32770, 0, 65535, torch.int32)
2025-03-21T20:31:43.2465437Z             quantized_decomposed_dequantize_per_tensor_default_245: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_51, 0.0002779011847451329, 32770, 0, 65535, torch.int32)
2025-03-21T20:31:43.2467365Z             quantized_decomposed_dequantize_per_tensor_default_246: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_51, 0.0002779011847451329, 32770, 0, 65535, torch.int32)
2025-03-21T20:31:43.2469515Z             quantized_decomposed_dequantize_per_tensor_default_247: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_51, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_51 = None
2025-03-21T20:31:43.2470843Z             
2025-03-21T20:31:43.2471647Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:346 in update, code: v_out = torch.ops.aten.index_put_(self.past_v_caches, [None, input_pos], v_val)
2025-03-21T20:31:43.2473715Z             aten_index_put_default_1: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_index_put_default(quantized_decomposed_dequantize_per_tensor_default_114, [None, attn_options_input_pos], quantized_decomposed_dequantize_per_tensor_default_195);  quantized_decomposed_dequantize_per_tensor_default_114 = quantized_decomposed_dequantize_per_tensor_default_195 = None
2025-03-21T20:31:43.2476025Z             quantized_decomposed_quantize_per_tensor_default_52: "i32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_put_default_1, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_index_put_default_1 = None
2025-03-21T20:31:43.2477117Z             
2025-03-21T20:31:43.2478075Z              # File: <eval_with_key>.50:535 in forward, code: dequantize_per_tensor_default_201 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_201, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32)
2025-03-21T20:31:43.2479899Z             quantized_decomposed_dequantize_per_tensor_default_248: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_52, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32)
2025-03-21T20:31:43.2481015Z             
2025-03-21T20:31:43.2481782Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.2483472Z             quantized_decomposed_dequantize_per_tensor_default_249: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_52, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32)
2025-03-21T20:31:43.2485407Z             quantized_decomposed_dequantize_per_tensor_default_250: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_52, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32)
2025-03-21T20:31:43.2487478Z             quantized_decomposed_dequantize_per_tensor_default_251: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_52, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32)
2025-03-21T20:31:43.2489475Z             quantized_decomposed_dequantize_per_tensor_default_252: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_52, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32)
2025-03-21T20:31:43.2491416Z             quantized_decomposed_dequantize_per_tensor_default_253: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_52, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32)
2025-03-21T20:31:43.2526138Z             quantized_decomposed_dequantize_per_tensor_default_254: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_52, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32)
2025-03-21T20:31:43.2528264Z             quantized_decomposed_dequantize_per_tensor_default_255: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_52, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32)
2025-03-21T20:31:43.2530279Z             quantized_decomposed_dequantize_per_tensor_default_256: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_52, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32)
2025-03-21T20:31:43.2532481Z             quantized_decomposed_dequantize_per_tensor_default_257: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_52, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32)
2025-03-21T20:31:43.2534463Z             quantized_decomposed_dequantize_per_tensor_default_258: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_52, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32)
2025-03-21T20:31:43.2536432Z             quantized_decomposed_dequantize_per_tensor_default_259: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_52, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32)
2025-03-21T20:31:43.2538585Z             quantized_decomposed_dequantize_per_tensor_default_260: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_52, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_52 = None
2025-03-21T20:31:43.2539916Z             
2025-03-21T20:31:43.2540683Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.2542264Z             aten_permute_copy_default_7: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_247, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_247 = None
2025-03-21T20:31:43.2544075Z             quantized_decomposed_quantize_per_tensor_default_53: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_7, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_permute_copy_default_7 = None
2025-03-21T20:31:43.2546234Z             quantized_decomposed_dequantize_per_tensor_default_261: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_53, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_53 = None
2025-03-21T20:31:43.2548198Z             aten_select_copy_int: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_261, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_261 = None
2025-03-21T20:31:43.2549898Z             quantized_decomposed_quantize_per_tensor_default_54: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_select_copy_int = None
2025-03-21T20:31:43.2551997Z             quantized_decomposed_dequantize_per_tensor_default_262: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_54, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_54 = None
2025-03-21T20:31:43.2553968Z             aten_select_copy_int_1: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_262, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_262 = None
2025-03-21T20:31:43.2555674Z             quantized_decomposed_quantize_per_tensor_default_55: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_1, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_select_copy_int_1 = None
2025-03-21T20:31:43.2556742Z             
2025-03-21T20:31:43.2557830Z              # File: <eval_with_key>.50:556 in forward, code: dequantize_per_tensor_default_204 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_204, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantize_per_tensor_default_204 = None
2025-03-21T20:31:43.2560029Z             quantized_decomposed_dequantize_per_tensor_default_263: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_55, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_55 = None
2025-03-21T20:31:43.2561353Z             
2025-03-21T20:31:43.2562150Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.2563685Z             aten_permute_copy_default_8: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_246, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_246 = None
2025-03-21T20:31:43.2565495Z             quantized_decomposed_quantize_per_tensor_default_56: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_8, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_permute_copy_default_8 = None
2025-03-21T20:31:43.2567659Z             quantized_decomposed_dequantize_per_tensor_default_264: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_56, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_56 = None
2025-03-21T20:31:43.2569680Z             aten_select_copy_int_2: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_264, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_264 = None
2025-03-21T20:31:43.2571393Z             quantized_decomposed_quantize_per_tensor_default_57: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_2, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_select_copy_int_2 = None
2025-03-21T20:31:43.2573491Z             quantized_decomposed_dequantize_per_tensor_default_265: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_57, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_57 = None
2025-03-21T20:31:43.2575435Z             aten_select_copy_int_3: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_265, 0, 1);  quantized_decomposed_dequantize_per_tensor_default_265 = None
2025-03-21T20:31:43.2577248Z             quantized_decomposed_quantize_per_tensor_default_58: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_3, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_select_copy_int_3 = None
2025-03-21T20:31:43.2578311Z             
2025-03-21T20:31:43.2579358Z              # File: <eval_with_key>.50:565 in forward, code: dequantize_per_tensor_default_207 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_207, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantize_per_tensor_default_207 = None
2025-03-21T20:31:43.2581519Z             quantized_decomposed_dequantize_per_tensor_default_266: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_58, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_58 = None
2025-03-21T20:31:43.2582833Z             
2025-03-21T20:31:43.2583632Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.2585185Z             aten_permute_copy_default_9: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_245, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_245 = None
2025-03-21T20:31:43.2587068Z             quantized_decomposed_quantize_per_tensor_default_59: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_9, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_permute_copy_default_9 = None
2025-03-21T20:31:43.2589444Z             quantized_decomposed_dequantize_per_tensor_default_267: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_59, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_59 = None
2025-03-21T20:31:43.2591405Z             aten_select_copy_int_4: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_267, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_267 = None
2025-03-21T20:31:43.2593138Z             quantized_decomposed_quantize_per_tensor_default_60: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_4, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_select_copy_int_4 = None
2025-03-21T20:31:43.2595239Z             quantized_decomposed_dequantize_per_tensor_default_268: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_60, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_60 = None
2025-03-21T20:31:43.2597191Z             aten_select_copy_int_5: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_268, 0, 2);  quantized_decomposed_dequantize_per_tensor_default_268 = None
2025-03-21T20:31:43.2598882Z             quantized_decomposed_quantize_per_tensor_default_61: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_5, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_select_copy_int_5 = None
2025-03-21T20:31:43.2599943Z             
2025-03-21T20:31:43.2600997Z              # File: <eval_with_key>.50:574 in forward, code: dequantize_per_tensor_default_210 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_210, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantize_per_tensor_default_210 = None
2025-03-21T20:31:43.2603153Z             quantized_decomposed_dequantize_per_tensor_default_269: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_61, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_61 = None
2025-03-21T20:31:43.2604461Z             
2025-03-21T20:31:43.2605231Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.2606763Z             aten_permute_copy_default_10: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_244, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_244 = None
2025-03-21T20:31:43.2608601Z             quantized_decomposed_quantize_per_tensor_default_62: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_10, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_permute_copy_default_10 = None
2025-03-21T20:31:43.2610895Z             quantized_decomposed_dequantize_per_tensor_default_270: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_62, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_62 = None
2025-03-21T20:31:43.2612886Z             aten_select_copy_int_6: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_270, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_270 = None
2025-03-21T20:31:43.2614588Z             quantized_decomposed_quantize_per_tensor_default_63: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_6, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_select_copy_int_6 = None
2025-03-21T20:31:43.2616698Z             quantized_decomposed_dequantize_per_tensor_default_271: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_63, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_63 = None
2025-03-21T20:31:43.2618672Z             aten_select_copy_int_7: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_271, 0, 3);  quantized_decomposed_dequantize_per_tensor_default_271 = None
2025-03-21T20:31:43.2620359Z             quantized_decomposed_quantize_per_tensor_default_64: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_7, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_select_copy_int_7 = None
2025-03-21T20:31:43.2621419Z             
2025-03-21T20:31:43.2622466Z              # File: <eval_with_key>.50:583 in forward, code: dequantize_per_tensor_default_213 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_213, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantize_per_tensor_default_213 = None
2025-03-21T20:31:43.2624624Z             quantized_decomposed_dequantize_per_tensor_default_272: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_64, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_64 = None
2025-03-21T20:31:43.2625936Z             
2025-03-21T20:31:43.2626700Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.2628233Z             aten_permute_copy_default_11: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_243, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_243 = None
2025-03-21T20:31:43.2630030Z             quantized_decomposed_quantize_per_tensor_default_65: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_11, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_permute_copy_default_11 = None
2025-03-21T20:31:43.2632186Z             quantized_decomposed_dequantize_per_tensor_default_273: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_65, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_65 = None
2025-03-21T20:31:43.2634398Z             aten_select_copy_int_8: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_273, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_273 = None
2025-03-21T20:31:43.2636138Z             quantized_decomposed_quantize_per_tensor_default_66: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_8, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_select_copy_int_8 = None
2025-03-21T20:31:43.2638281Z             quantized_decomposed_dequantize_per_tensor_default_274: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_66, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_66 = None
2025-03-21T20:31:43.2640237Z             aten_select_copy_int_9: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_274, 0, 4);  quantized_decomposed_dequantize_per_tensor_default_274 = None
2025-03-21T20:31:43.2641926Z             quantized_decomposed_quantize_per_tensor_default_67: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_9, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_select_copy_int_9 = None
2025-03-21T20:31:43.2643020Z             
2025-03-21T20:31:43.2644069Z              # File: <eval_with_key>.50:592 in forward, code: dequantize_per_tensor_default_216 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_216, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantize_per_tensor_default_216 = None
2025-03-21T20:31:43.2646233Z             quantized_decomposed_dequantize_per_tensor_default_275: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_67, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_67 = None
2025-03-21T20:31:43.2647553Z             
2025-03-21T20:31:43.2648313Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.2649910Z             aten_permute_copy_default_12: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_242, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_242 = None
2025-03-21T20:31:43.2651726Z             quantized_decomposed_quantize_per_tensor_default_68: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_12, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_permute_copy_default_12 = None
2025-03-21T20:31:43.2653878Z             quantized_decomposed_dequantize_per_tensor_default_276: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_68, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_68 = None
2025-03-21T20:31:43.2655836Z             aten_select_copy_int_10: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_276, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_276 = None
2025-03-21T20:31:43.2657541Z             quantized_decomposed_quantize_per_tensor_default_69: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_10, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_select_copy_int_10 = None
2025-03-21T20:31:43.2659680Z             quantized_decomposed_dequantize_per_tensor_default_277: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_69, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_69 = None
2025-03-21T20:31:43.2661657Z             aten_select_copy_int_11: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_277, 0, 5);  quantized_decomposed_dequantize_per_tensor_default_277 = None
2025-03-21T20:31:43.2663377Z             quantized_decomposed_quantize_per_tensor_default_70: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_11, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_select_copy_int_11 = None
2025-03-21T20:31:43.2664445Z             
2025-03-21T20:31:43.2665483Z              # File: <eval_with_key>.50:601 in forward, code: dequantize_per_tensor_default_219 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_219, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantize_per_tensor_default_219 = None
2025-03-21T20:31:43.2667637Z             quantized_decomposed_dequantize_per_tensor_default_278: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_70, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_70 = None
2025-03-21T20:31:43.2668981Z             
2025-03-21T20:31:43.2669751Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.2671277Z             aten_permute_copy_default_13: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_241, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_241 = None
2025-03-21T20:31:43.2673096Z             quantized_decomposed_quantize_per_tensor_default_71: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_13, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_permute_copy_default_13 = None
2025-03-21T20:31:43.2675256Z             quantized_decomposed_dequantize_per_tensor_default_279: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_71, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_71 = None
2025-03-21T20:31:43.2677216Z             aten_select_copy_int_12: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_279, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_279 = None
2025-03-21T20:31:43.2678932Z             quantized_decomposed_quantize_per_tensor_default_72: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_12, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_select_copy_int_12 = None
2025-03-21T20:31:43.2681042Z             quantized_decomposed_dequantize_per_tensor_default_280: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_72, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_72 = None
2025-03-21T20:31:43.2682999Z             aten_select_copy_int_13: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_280, 0, 6);  quantized_decomposed_dequantize_per_tensor_default_280 = None
2025-03-21T20:31:43.2684731Z             quantized_decomposed_quantize_per_tensor_default_73: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_13, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_select_copy_int_13 = None
2025-03-21T20:31:43.2685828Z             
2025-03-21T20:31:43.2686882Z              # File: <eval_with_key>.50:610 in forward, code: dequantize_per_tensor_default_222 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_222, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantize_per_tensor_default_222 = None
2025-03-21T20:31:43.2689179Z             quantized_decomposed_dequantize_per_tensor_default_281: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_73, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_73 = None
2025-03-21T20:31:43.2690601Z             
2025-03-21T20:31:43.2691372Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.2692895Z             aten_permute_copy_default_14: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_240, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_240 = None
2025-03-21T20:31:43.2694751Z             quantized_decomposed_quantize_per_tensor_default_74: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_14, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_permute_copy_default_14 = None
2025-03-21T20:31:43.2696915Z             quantized_decomposed_dequantize_per_tensor_default_282: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_74, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_74 = None
2025-03-21T20:31:43.2698877Z             aten_select_copy_int_14: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_282, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_282 = None
2025-03-21T20:31:43.2700598Z             quantized_decomposed_quantize_per_tensor_default_75: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_14, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_select_copy_int_14 = None
2025-03-21T20:31:43.2702702Z             quantized_decomposed_dequantize_per_tensor_default_283: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_75, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_75 = None
2025-03-21T20:31:43.2704656Z             aten_select_copy_int_15: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_283, 0, 7);  quantized_decomposed_dequantize_per_tensor_default_283 = None
2025-03-21T20:31:43.2706357Z             quantized_decomposed_quantize_per_tensor_default_76: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_15, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_select_copy_int_15 = None
2025-03-21T20:31:43.2707423Z             
2025-03-21T20:31:43.2708480Z              # File: <eval_with_key>.50:619 in forward, code: dequantize_per_tensor_default_225 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_225, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantize_per_tensor_default_225 = None
2025-03-21T20:31:43.2710673Z             quantized_decomposed_dequantize_per_tensor_default_284: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_76, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_76 = None
2025-03-21T20:31:43.2712025Z             
2025-03-21T20:31:43.2712784Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.2714340Z             aten_permute_copy_default_15: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_239, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_239 = None
2025-03-21T20:31:43.2716159Z             quantized_decomposed_quantize_per_tensor_default_77: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_15, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_permute_copy_default_15 = None
2025-03-21T20:31:43.2718311Z             quantized_decomposed_dequantize_per_tensor_default_285: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_77, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_77 = None
2025-03-21T20:31:43.2720297Z             aten_select_copy_int_16: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_285, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_285 = None
2025-03-21T20:31:43.2721998Z             quantized_decomposed_quantize_per_tensor_default_78: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_16, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_select_copy_int_16 = None
2025-03-21T20:31:43.2724105Z             quantized_decomposed_dequantize_per_tensor_default_286: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_78, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_78 = None
2025-03-21T20:31:43.2726055Z             aten_select_copy_int_17: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_286, 0, 8);  quantized_decomposed_dequantize_per_tensor_default_286 = None
2025-03-21T20:31:43.2727758Z             quantized_decomposed_quantize_per_tensor_default_79: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_17, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_select_copy_int_17 = None
2025-03-21T20:31:43.2728820Z             
2025-03-21T20:31:43.2729928Z              # File: <eval_with_key>.50:628 in forward, code: dequantize_per_tensor_default_228 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_228, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantize_per_tensor_default_228 = None
2025-03-21T20:31:43.2732093Z             quantized_decomposed_dequantize_per_tensor_default_287: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_79, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_79 = None
2025-03-21T20:31:43.2733562Z             
2025-03-21T20:31:43.2734321Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.2735912Z             aten_permute_copy_default_16: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_238, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_238 = None
2025-03-21T20:31:43.2737759Z             quantized_decomposed_quantize_per_tensor_default_80: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_16, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_permute_copy_default_16 = None
2025-03-21T20:31:43.2739945Z             quantized_decomposed_dequantize_per_tensor_default_288: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_80, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_80 = None
2025-03-21T20:31:43.2741901Z             aten_select_copy_int_18: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_288, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_288 = None
2025-03-21T20:31:43.2743616Z             quantized_decomposed_quantize_per_tensor_default_81: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_18, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_select_copy_int_18 = None
2025-03-21T20:31:43.2745761Z             quantized_decomposed_dequantize_per_tensor_default_289: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_81, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_81 = None
2025-03-21T20:31:43.2747714Z             aten_select_copy_int_19: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_289, 0, 9);  quantized_decomposed_dequantize_per_tensor_default_289 = None
2025-03-21T20:31:43.2749427Z             quantized_decomposed_quantize_per_tensor_default_82: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_19, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_select_copy_int_19 = None
2025-03-21T20:31:43.2750497Z             
2025-03-21T20:31:43.2751543Z              # File: <eval_with_key>.50:637 in forward, code: dequantize_per_tensor_default_231 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_231, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantize_per_tensor_default_231 = None
2025-03-21T20:31:43.2753701Z             quantized_decomposed_dequantize_per_tensor_default_290: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_82, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_82 = None
2025-03-21T20:31:43.2755011Z             
2025-03-21T20:31:43.2755763Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.2757295Z             aten_permute_copy_default_17: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_237, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_237 = None
2025-03-21T20:31:43.2759116Z             quantized_decomposed_quantize_per_tensor_default_83: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_17, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_permute_copy_default_17 = None
2025-03-21T20:31:43.2761296Z             quantized_decomposed_dequantize_per_tensor_default_291: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_83, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_83 = None
2025-03-21T20:31:43.2763281Z             aten_select_copy_int_20: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_291, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_291 = None
2025-03-21T20:31:43.2765019Z             quantized_decomposed_quantize_per_tensor_default_84: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_20, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_select_copy_int_20 = None
2025-03-21T20:31:43.2767187Z             quantized_decomposed_dequantize_per_tensor_default_292: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_84, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_84 = None
2025-03-21T20:31:43.2769391Z             aten_select_copy_int_21: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_292, 0, 10);  quantized_decomposed_dequantize_per_tensor_default_292 = None
2025-03-21T20:31:43.2771115Z             quantized_decomposed_quantize_per_tensor_default_85: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_21, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_select_copy_int_21 = None
2025-03-21T20:31:43.2772187Z             
2025-03-21T20:31:43.2773245Z              # File: <eval_with_key>.50:646 in forward, code: dequantize_per_tensor_default_234 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_234, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantize_per_tensor_default_234 = None
2025-03-21T20:31:43.2775444Z             quantized_decomposed_dequantize_per_tensor_default_293: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_85, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_85 = None
2025-03-21T20:31:43.2776790Z             
2025-03-21T20:31:43.2777564Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.2780028Z             aten_permute_copy_default_18: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_236, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_236 = None
2025-03-21T20:31:43.2781862Z             quantized_decomposed_quantize_per_tensor_default_86: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_18, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_permute_copy_default_18 = None
2025-03-21T20:31:43.2784031Z             quantized_decomposed_dequantize_per_tensor_default_294: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_86, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_86 = None
2025-03-21T20:31:43.2785995Z             aten_select_copy_int_22: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_294, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_294 = None
2025-03-21T20:31:43.2787802Z             quantized_decomposed_quantize_per_tensor_default_87: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_22, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_select_copy_int_22 = None
2025-03-21T20:31:43.2790907Z             quantized_decomposed_dequantize_per_tensor_default_295: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_87, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_87 = None
2025-03-21T20:31:43.2792940Z             aten_select_copy_int_23: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_295, 0, 11);  quantized_decomposed_dequantize_per_tensor_default_295 = None
2025-03-21T20:31:43.2794660Z             quantized_decomposed_quantize_per_tensor_default_88: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_23, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_select_copy_int_23 = None
2025-03-21T20:31:43.2795728Z             
2025-03-21T20:31:43.2796839Z              # File: <eval_with_key>.50:655 in forward, code: dequantize_per_tensor_default_237 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_237, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantize_per_tensor_default_237 = None
2025-03-21T20:31:43.2799249Z             quantized_decomposed_dequantize_per_tensor_default_296: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_88, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_88 = None
2025-03-21T20:31:43.2800792Z             
2025-03-21T20:31:43.2801573Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.2807704Z             aten_cat_default_2: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_aten_cat_default([quantized_decomposed_dequantize_per_tensor_default_263, quantized_decomposed_dequantize_per_tensor_default_266, quantized_decomposed_dequantize_per_tensor_default_269, quantized_decomposed_dequantize_per_tensor_default_272, quantized_decomposed_dequantize_per_tensor_default_275, quantized_decomposed_dequantize_per_tensor_default_278, quantized_decomposed_dequantize_per_tensor_default_281, quantized_decomposed_dequantize_per_tensor_default_284, quantized_decomposed_dequantize_per_tensor_default_287, quantized_decomposed_dequantize_per_tensor_default_290, quantized_decomposed_dequantize_per_tensor_default_293, quantized_decomposed_dequantize_per_tensor_default_296]);  quantized_decomposed_dequantize_per_tensor_default_263 = quantized_decomposed_dequantize_per_tensor_default_266 = quantized_decomposed_dequantize_per_tensor_default_269 = quantized_decomposed_dequantize_per_tensor_default_272 = quantized_decomposed_dequantize_per_tensor_default_275 = quantized_decomposed_dequantize_per_tensor_default_278 = quantized_decomposed_dequantize_per_tensor_default_281 = quantized_decomposed_dequantize_per_tensor_default_284 = quantized_decomposed_dequantize_per_tensor_default_287 = quantized_decomposed_dequantize_per_tensor_default_290 = quantized_decomposed_dequantize_per_tensor_default_293 = quantized_decomposed_dequantize_per_tensor_default_296 = None
2025-03-21T20:31:43.2814348Z             quantized_decomposed_quantize_per_tensor_default_89: "i32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_2, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_cat_default_2 = None
2025-03-21T20:31:43.2816481Z             quantized_decomposed_dequantize_per_tensor_default_297: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_89, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_89 = None
2025-03-21T20:31:43.2818517Z             aten_view_copy_default_9: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_297, [1, 12, 128, 64]);  quantized_decomposed_dequantize_per_tensor_default_297 = None
2025-03-21T20:31:43.2820311Z             quantized_decomposed_quantize_per_tensor_default_90: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_9, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_view_copy_default_9 = None
2025-03-21T20:31:43.2821411Z             
2025-03-21T20:31:43.2822130Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.2823947Z             quantized_decomposed_dequantize_per_tensor_default_298: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_90, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_90 = None
2025-03-21T20:31:43.2825302Z             
2025-03-21T20:31:43.2826070Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.2827610Z             aten_permute_copy_default_19: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_260, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_260 = None
2025-03-21T20:31:43.2829436Z             quantized_decomposed_quantize_per_tensor_default_91: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_19, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_permute_copy_default_19 = None
2025-03-21T20:31:43.2831599Z             quantized_decomposed_dequantize_per_tensor_default_299: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_91, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_91 = None
2025-03-21T20:31:43.2833738Z             aten_select_copy_int_24: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_299, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_299 = None
2025-03-21T20:31:43.2835452Z             quantized_decomposed_quantize_per_tensor_default_92: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_24, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_select_copy_int_24 = None
2025-03-21T20:31:43.2837572Z             quantized_decomposed_dequantize_per_tensor_default_300: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_92, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_92 = None
2025-03-21T20:31:43.2839535Z             aten_select_copy_int_25: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_300, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_300 = None
2025-03-21T20:31:43.2841318Z             quantized_decomposed_quantize_per_tensor_default_93: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_25, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_select_copy_int_25 = None
2025-03-21T20:31:43.2842429Z             
2025-03-21T20:31:43.2843490Z              # File: <eval_with_key>.50:670 in forward, code: dequantize_per_tensor_default_242 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_242, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantize_per_tensor_default_242 = None
2025-03-21T20:31:43.2845687Z             quantized_decomposed_dequantize_per_tensor_default_301: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_93, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_93 = None
2025-03-21T20:31:43.2847010Z             
2025-03-21T20:31:43.2847783Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.2849391Z             aten_permute_copy_default_20: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_259, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_259 = None
2025-03-21T20:31:43.2851267Z             quantized_decomposed_quantize_per_tensor_default_94: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_20, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_permute_copy_default_20 = None
2025-03-21T20:31:43.2853425Z             quantized_decomposed_dequantize_per_tensor_default_302: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_94, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_94 = None
2025-03-21T20:31:43.2855391Z             aten_select_copy_int_26: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_302, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_302 = None
2025-03-21T20:31:43.2857114Z             quantized_decomposed_quantize_per_tensor_default_95: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_26, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_select_copy_int_26 = None
2025-03-21T20:31:43.2859228Z             quantized_decomposed_dequantize_per_tensor_default_303: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_95, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_95 = None
2025-03-21T20:31:43.2861189Z             aten_select_copy_int_27: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_303, 0, 1);  quantized_decomposed_dequantize_per_tensor_default_303 = None
2025-03-21T20:31:43.2862896Z             quantized_decomposed_quantize_per_tensor_default_96: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_27, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_select_copy_int_27 = None
2025-03-21T20:31:43.2863965Z             
2025-03-21T20:31:43.2865017Z              # File: <eval_with_key>.50:679 in forward, code: dequantize_per_tensor_default_245 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_245, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantize_per_tensor_default_245 = None
2025-03-21T20:31:43.2867202Z             quantized_decomposed_dequantize_per_tensor_default_304: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_96, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_96 = None
2025-03-21T20:31:43.2868549Z             
2025-03-21T20:31:43.2869319Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.2870876Z             aten_permute_copy_default_21: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_258, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_258 = None
2025-03-21T20:31:43.2872706Z             quantized_decomposed_quantize_per_tensor_default_97: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_21, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_permute_copy_default_21 = None
2025-03-21T20:31:43.2874871Z             quantized_decomposed_dequantize_per_tensor_default_305: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_97, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_97 = None
2025-03-21T20:31:43.2876863Z             aten_select_copy_int_28: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_305, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_305 = None
2025-03-21T20:31:43.2878579Z             quantized_decomposed_quantize_per_tensor_default_98: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_28, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_select_copy_int_28 = None
2025-03-21T20:31:43.2880689Z             quantized_decomposed_dequantize_per_tensor_default_306: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_98, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_98 = None
2025-03-21T20:31:43.2882646Z             aten_select_copy_int_29: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_306, 0, 2);  quantized_decomposed_dequantize_per_tensor_default_306 = None
2025-03-21T20:31:43.2884348Z             quantized_decomposed_quantize_per_tensor_default_99: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_29, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_select_copy_int_29 = None
2025-03-21T20:31:43.2885422Z             
2025-03-21T20:31:43.2886484Z              # File: <eval_with_key>.50:688 in forward, code: dequantize_per_tensor_default_248 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_248, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantize_per_tensor_default_248 = None
2025-03-21T20:31:43.2888652Z             quantized_decomposed_dequantize_per_tensor_default_307: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_99, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_99 = None
2025-03-21T20:31:43.2890046Z             
2025-03-21T20:31:43.2890815Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.2892508Z             aten_permute_copy_default_22: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_257, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_257 = None
2025-03-21T20:31:43.2894380Z             quantized_decomposed_quantize_per_tensor_default_100: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_22, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_permute_copy_default_22 = None
2025-03-21T20:31:43.2896599Z             quantized_decomposed_dequantize_per_tensor_default_308: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_100, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_100 = None
2025-03-21T20:31:43.2898572Z             aten_select_copy_int_30: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_308, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_308 = None
2025-03-21T20:31:43.2900288Z             quantized_decomposed_quantize_per_tensor_default_101: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_30, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_select_copy_int_30 = None
2025-03-21T20:31:43.2902441Z             quantized_decomposed_dequantize_per_tensor_default_309: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_101, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_101 = None
2025-03-21T20:31:43.2904411Z             aten_select_copy_int_31: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_309, 0, 3);  quantized_decomposed_dequantize_per_tensor_default_309 = None
2025-03-21T20:31:43.2906124Z             quantized_decomposed_quantize_per_tensor_default_102: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_31, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_select_copy_int_31 = None
2025-03-21T20:31:43.2907201Z             
2025-03-21T20:31:43.2908264Z              # File: <eval_with_key>.50:697 in forward, code: dequantize_per_tensor_default_251 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_251, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantize_per_tensor_default_251 = None
2025-03-21T20:31:43.2910436Z             quantized_decomposed_dequantize_per_tensor_default_310: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_102, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_102 = None
2025-03-21T20:31:43.2911770Z             
2025-03-21T20:31:43.2912538Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.2914073Z             aten_permute_copy_default_23: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_256, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_256 = None
2025-03-21T20:31:43.2915894Z             quantized_decomposed_quantize_per_tensor_default_103: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_23, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_permute_copy_default_23 = None
2025-03-21T20:31:43.2918124Z             quantized_decomposed_dequantize_per_tensor_default_311: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_103, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_103 = None
2025-03-21T20:31:43.2920096Z             aten_select_copy_int_32: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_311, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_311 = None
2025-03-21T20:31:43.2921855Z             quantized_decomposed_quantize_per_tensor_default_104: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_32, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_select_copy_int_32 = None
2025-03-21T20:31:43.2923992Z             quantized_decomposed_dequantize_per_tensor_default_312: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_104, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_104 = None
2025-03-21T20:31:43.2925988Z             aten_select_copy_int_33: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_312, 0, 4);  quantized_decomposed_dequantize_per_tensor_default_312 = None
2025-03-21T20:31:43.2927703Z             quantized_decomposed_quantize_per_tensor_default_105: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_33, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_select_copy_int_33 = None
2025-03-21T20:31:43.2928777Z             
2025-03-21T20:31:43.2929905Z              # File: <eval_with_key>.50:706 in forward, code: dequantize_per_tensor_default_254 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_254, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantize_per_tensor_default_254 = None
2025-03-21T20:31:43.2932078Z             quantized_decomposed_dequantize_per_tensor_default_313: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_105, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_105 = None
2025-03-21T20:31:43.2933570Z             
2025-03-21T20:31:43.2934339Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.2935877Z             aten_permute_copy_default_24: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_255, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_255 = None
2025-03-21T20:31:43.2937705Z             quantized_decomposed_quantize_per_tensor_default_106: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_24, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_permute_copy_default_24 = None
2025-03-21T20:31:43.2939884Z             quantized_decomposed_dequantize_per_tensor_default_314: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_106, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_106 = None
2025-03-21T20:31:43.2941873Z             aten_select_copy_int_34: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_314, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_314 = None
2025-03-21T20:31:43.2943710Z             quantized_decomposed_quantize_per_tensor_default_107: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_34, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_select_copy_int_34 = None
2025-03-21T20:31:43.2945877Z             quantized_decomposed_dequantize_per_tensor_default_315: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_107, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_107 = None
2025-03-21T20:31:43.2947845Z             aten_select_copy_int_35: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_315, 0, 5);  quantized_decomposed_dequantize_per_tensor_default_315 = None
2025-03-21T20:31:43.2949566Z             quantized_decomposed_quantize_per_tensor_default_108: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_35, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_select_copy_int_35 = None
2025-03-21T20:31:43.2950683Z             
2025-03-21T20:31:43.2951739Z              # File: <eval_with_key>.50:715 in forward, code: dequantize_per_tensor_default_257 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_257, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantize_per_tensor_default_257 = None
2025-03-21T20:31:43.2953903Z             quantized_decomposed_dequantize_per_tensor_default_316: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_108, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_108 = None
2025-03-21T20:31:43.2955229Z             
2025-03-21T20:31:43.2956002Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.2957527Z             aten_permute_copy_default_25: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_254, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_254 = None
2025-03-21T20:31:43.2959349Z             quantized_decomposed_quantize_per_tensor_default_109: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_25, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_permute_copy_default_25 = None
2025-03-21T20:31:43.2961527Z             quantized_decomposed_dequantize_per_tensor_default_317: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_109, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_109 = None
2025-03-21T20:31:43.2963503Z             aten_select_copy_int_36: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_317, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_317 = None
2025-03-21T20:31:43.2965225Z             quantized_decomposed_quantize_per_tensor_default_110: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_36, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_select_copy_int_36 = None
2025-03-21T20:31:43.2967375Z             quantized_decomposed_dequantize_per_tensor_default_318: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_110, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_110 = None
2025-03-21T20:31:43.2969428Z             aten_select_copy_int_37: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_318, 0, 6);  quantized_decomposed_dequantize_per_tensor_default_318 = None
2025-03-21T20:31:43.2971183Z             quantized_decomposed_quantize_per_tensor_default_111: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_37, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_select_copy_int_37 = None
2025-03-21T20:31:43.2972267Z             
2025-03-21T20:31:43.2973335Z              # File: <eval_with_key>.50:724 in forward, code: dequantize_per_tensor_default_260 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_260, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantize_per_tensor_default_260 = None
2025-03-21T20:31:43.2975505Z             quantized_decomposed_dequantize_per_tensor_default_319: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_111, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_111 = None
2025-03-21T20:31:43.2976859Z             
2025-03-21T20:31:43.2977628Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.2979163Z             aten_permute_copy_default_26: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_253, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_253 = None
2025-03-21T20:31:43.2980990Z             quantized_decomposed_quantize_per_tensor_default_112: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_26, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_permute_copy_default_26 = None
2025-03-21T20:31:43.2983283Z             quantized_decomposed_dequantize_per_tensor_default_320: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_112, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_112 = None
2025-03-21T20:31:43.2985275Z             aten_select_copy_int_38: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_320, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_320 = None
2025-03-21T20:31:43.2987008Z             quantized_decomposed_quantize_per_tensor_default_113: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_38, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_select_copy_int_38 = None
2025-03-21T20:31:43.2989139Z             quantized_decomposed_dequantize_per_tensor_default_321: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_113, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_113 = None
2025-03-21T20:31:43.2991108Z             aten_select_copy_int_39: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_321, 0, 7);  quantized_decomposed_dequantize_per_tensor_default_321 = None
2025-03-21T20:31:43.2992861Z             quantized_decomposed_quantize_per_tensor_default_114: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_39, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_select_copy_int_39 = None
2025-03-21T20:31:43.2994224Z             
2025-03-21T20:31:43.2995285Z              # File: <eval_with_key>.50:733 in forward, code: dequantize_per_tensor_default_263 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_263, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantize_per_tensor_default_263 = None
2025-03-21T20:31:43.2997501Z             quantized_decomposed_dequantize_per_tensor_default_322: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_114, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_114 = None
2025-03-21T20:31:43.2998832Z             
2025-03-21T20:31:43.2999607Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.3001147Z             aten_permute_copy_default_27: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_252, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_252 = None
2025-03-21T20:31:43.3003014Z             quantized_decomposed_quantize_per_tensor_default_115: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_27, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_permute_copy_default_27 = None
2025-03-21T20:31:43.3005201Z             quantized_decomposed_dequantize_per_tensor_default_323: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_115, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_115 = None
2025-03-21T20:31:43.3007176Z             aten_select_copy_int_40: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_323, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_323 = None
2025-03-21T20:31:43.3008904Z             quantized_decomposed_quantize_per_tensor_default_116: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_40, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_select_copy_int_40 = None
2025-03-21T20:31:43.3011136Z             quantized_decomposed_dequantize_per_tensor_default_324: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_116, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_116 = None
2025-03-21T20:31:43.3013110Z             aten_select_copy_int_41: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_324, 0, 8);  quantized_decomposed_dequantize_per_tensor_default_324 = None
2025-03-21T20:31:43.3014836Z             quantized_decomposed_quantize_per_tensor_default_117: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_41, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_select_copy_int_41 = None
2025-03-21T20:31:43.3015912Z             
2025-03-21T20:31:43.3016970Z              # File: <eval_with_key>.50:742 in forward, code: dequantize_per_tensor_default_266 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_266, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantize_per_tensor_default_266 = None
2025-03-21T20:31:43.3019174Z             quantized_decomposed_dequantize_per_tensor_default_325: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_117, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_117 = None
2025-03-21T20:31:43.3020528Z             
2025-03-21T20:31:43.3021287Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.3022848Z             aten_permute_copy_default_28: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_251, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_251 = None
2025-03-21T20:31:43.3024678Z             quantized_decomposed_quantize_per_tensor_default_118: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_28, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_permute_copy_default_28 = None
2025-03-21T20:31:43.3026861Z             quantized_decomposed_dequantize_per_tensor_default_326: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_118, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_118 = None
2025-03-21T20:31:43.3028867Z             aten_select_copy_int_42: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_326, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_326 = None
2025-03-21T20:31:43.3030590Z             quantized_decomposed_quantize_per_tensor_default_119: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_42, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_select_copy_int_42 = None
2025-03-21T20:31:43.3032891Z             quantized_decomposed_dequantize_per_tensor_default_327: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_119, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_119 = None
2025-03-21T20:31:43.3034870Z             aten_select_copy_int_43: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_327, 0, 9);  quantized_decomposed_dequantize_per_tensor_default_327 = None
2025-03-21T20:31:43.3036587Z             quantized_decomposed_quantize_per_tensor_default_120: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_43, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_select_copy_int_43 = None
2025-03-21T20:31:43.3037667Z             
2025-03-21T20:31:43.3038732Z              # File: <eval_with_key>.50:751 in forward, code: dequantize_per_tensor_default_269 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_269, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantize_per_tensor_default_269 = None
2025-03-21T20:31:43.3040908Z             quantized_decomposed_dequantize_per_tensor_default_328: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_120, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_120 = None
2025-03-21T20:31:43.3042240Z             
2025-03-21T20:31:43.3043012Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.3044613Z             aten_permute_copy_default_29: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_250, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_250 = None
2025-03-21T20:31:43.3046480Z             quantized_decomposed_quantize_per_tensor_default_121: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_29, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_permute_copy_default_29 = None
2025-03-21T20:31:43.3048693Z             quantized_decomposed_dequantize_per_tensor_default_329: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_121, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_121 = None
2025-03-21T20:31:43.3050741Z             aten_select_copy_int_44: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_329, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_329 = None
2025-03-21T20:31:43.3052468Z             quantized_decomposed_quantize_per_tensor_default_122: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_44, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_select_copy_int_44 = None
2025-03-21T20:31:43.3054641Z             quantized_decomposed_dequantize_per_tensor_default_330: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_122, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_122 = None
2025-03-21T20:31:43.3056610Z             aten_select_copy_int_45: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_330, 0, 10);  quantized_decomposed_dequantize_per_tensor_default_330 = None
2025-03-21T20:31:43.3058325Z             quantized_decomposed_quantize_per_tensor_default_123: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_45, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_select_copy_int_45 = None
2025-03-21T20:31:43.3059409Z             
2025-03-21T20:31:43.3060453Z              # File: <eval_with_key>.50:760 in forward, code: dequantize_per_tensor_default_272 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_272, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantize_per_tensor_default_272 = None
2025-03-21T20:31:43.3062622Z             quantized_decomposed_dequantize_per_tensor_default_331: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_123, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_123 = None
2025-03-21T20:31:43.3063952Z             
2025-03-21T20:31:43.3064724Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.3066255Z             aten_permute_copy_default_30: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_249, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_249 = None
2025-03-21T20:31:43.3068078Z             quantized_decomposed_quantize_per_tensor_default_124: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_30, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_permute_copy_default_30 = None
2025-03-21T20:31:43.3070283Z             quantized_decomposed_dequantize_per_tensor_default_332: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_124, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_124 = None
2025-03-21T20:31:43.3072287Z             aten_select_copy_int_46: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_332, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_332 = None
2025-03-21T20:31:43.3074023Z             quantized_decomposed_quantize_per_tensor_default_125: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_46, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_select_copy_int_46 = None
2025-03-21T20:31:43.3076162Z             quantized_decomposed_dequantize_per_tensor_default_333: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_125, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_125 = None
2025-03-21T20:31:43.3078164Z             aten_select_copy_int_47: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_333, 0, 11);  quantized_decomposed_dequantize_per_tensor_default_333 = None
2025-03-21T20:31:43.3079881Z             quantized_decomposed_quantize_per_tensor_default_126: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_47, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_select_copy_int_47 = None
2025-03-21T20:31:43.3080961Z             
2025-03-21T20:31:43.3082008Z              # File: <eval_with_key>.50:769 in forward, code: dequantize_per_tensor_default_275 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_275, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantize_per_tensor_default_275 = None
2025-03-21T20:31:43.3084181Z             quantized_decomposed_dequantize_per_tensor_default_334: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_126, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_126 = None
2025-03-21T20:31:43.3085516Z             
2025-03-21T20:31:43.3086293Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.3092555Z             aten_cat_default_3: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_aten_cat_default([quantized_decomposed_dequantize_per_tensor_default_301, quantized_decomposed_dequantize_per_tensor_default_304, quantized_decomposed_dequantize_per_tensor_default_307, quantized_decomposed_dequantize_per_tensor_default_310, quantized_decomposed_dequantize_per_tensor_default_313, quantized_decomposed_dequantize_per_tensor_default_316, quantized_decomposed_dequantize_per_tensor_default_319, quantized_decomposed_dequantize_per_tensor_default_322, quantized_decomposed_dequantize_per_tensor_default_325, quantized_decomposed_dequantize_per_tensor_default_328, quantized_decomposed_dequantize_per_tensor_default_331, quantized_decomposed_dequantize_per_tensor_default_334]);  quantized_decomposed_dequantize_per_tensor_default_301 = quantized_decomposed_dequantize_per_tensor_default_304 = quantized_decomposed_dequantize_per_tensor_default_307 = quantized_decomposed_dequantize_per_tensor_default_310 = quantized_decomposed_dequantize_per_tensor_default_313 = quantized_decomposed_dequantize_per_tensor_default_316 = quantized_decomposed_dequantize_per_tensor_default_319 = quantized_decomposed_dequantize_per_tensor_default_322 = quantized_decomposed_dequantize_per_tensor_default_325 = quantized_decomposed_dequantize_per_tensor_default_328 = quantized_decomposed_dequantize_per_tensor_default_331 = quantized_decomposed_dequantize_per_tensor_default_334 = None
2025-03-21T20:31:43.3099265Z             quantized_decomposed_quantize_per_tensor_default_127: "i32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_3, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_cat_default_3 = None
2025-03-21T20:31:43.3101411Z             quantized_decomposed_dequantize_per_tensor_default_335: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_127, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_127 = None
2025-03-21T20:31:43.3103444Z             aten_view_copy_default_10: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_335, [1, 12, 128, 64]);  quantized_decomposed_dequantize_per_tensor_default_335 = None
2025-03-21T20:31:43.3105233Z             quantized_decomposed_quantize_per_tensor_default_128: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_10, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  aten_view_copy_default_10 = None
2025-03-21T20:31:43.3106362Z             
2025-03-21T20:31:43.3107416Z              # File: <eval_with_key>.50:775 in forward, code: dequantize_per_tensor_default_277 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_277, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantize_per_tensor_default_277 = None
2025-03-21T20:31:43.3109590Z             quantized_decomposed_dequantize_per_tensor_default_336: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_128, 2.5713339709909633e-05, 32398, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_128 = None
2025-03-21T20:31:43.3110927Z             
2025-03-21T20:31:43.3111967Z              # File: <eval_with_key>.50:776 in forward, code: quantize_per_tensor_default_278 = torch.ops.quantized_decomposed.quantize_per_tensor.default(dequantize_per_tensor_default_277, 2.6003737730206922e-05, 0, -32767, 32767, torch.int16);  dequantize_per_tensor_default_277 = None
2025-03-21T20:31:43.3114141Z             quantized_decomposed_quantize_per_tensor_default_129: "i16[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_336, 2.6003737730206922e-05, 0, -32767, 32767, torch.int16);  quantized_decomposed_dequantize_per_tensor_default_336 = None
2025-03-21T20:31:43.3115474Z             
2025-03-21T20:31:43.3116069Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:163 in forward, code: y = attn_weight @ v
2025-03-21T20:31:43.3117785Z             quantized_decomposed_dequantize_per_tensor_default_337: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_129, 2.6003737730206922e-05, 0, -32767, 32767, torch.int16);  quantized_decomposed_quantize_per_tensor_default_129 = None
2025-03-21T20:31:43.3119116Z             
2025-03-21T20:31:43.3119742Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:157 in forward, code: attn_mask = mask[input_pos]
2025-03-21T20:31:43.3121132Z             aten_index_tensor_2: "f32[1, 128]" = executorch_exir_dialects_edge__ops_aten_index_Tensor(quantized_decomposed_dequantize_per_tensor_default_115, [attn_options_input_pos]);  quantized_decomposed_dequantize_per_tensor_default_115 = None
2025-03-21T20:31:43.3122939Z             quantized_decomposed_quantize_per_tensor_default_130: "i32[1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_tensor_2, 0.0038910505827516317, 65535, 0, 65535, torch.int32);  aten_index_tensor_2 = None
2025-03-21T20:31:43.3123998Z             
2025-03-21T20:31:43.3124598Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:161 in forward, code: attn_weight += attn_mask
2025-03-21T20:31:43.3126344Z             quantized_decomposed_dequantize_per_tensor_default_338: "f32[1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_130, 0.0038910505827516317, 65535, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_130 = None
2025-03-21T20:31:43.3127672Z             
2025-03-21T20:31:43.3128376Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.3129911Z             aten_permute_copy_default_31: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_298, [0, 1, 3, 2]);  quantized_decomposed_dequantize_per_tensor_default_298 = None
2025-03-21T20:31:43.3131784Z             quantized_decomposed_quantize_per_tensor_default_131: "i32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_31, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  aten_permute_copy_default_31 = None
2025-03-21T20:31:43.3133055Z             
2025-03-21T20:31:43.3134109Z              # File: <eval_with_key>.50:783 in forward, code: dequantize_per_tensor_default_280 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_280, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantize_per_tensor_default_280 = None
2025-03-21T20:31:43.3136294Z             quantized_decomposed_dequantize_per_tensor_default_339: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_131, 0.0002779011847451329, 32770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_131 = None
2025-03-21T20:31:43.3137626Z             
2025-03-21T20:31:43.3138679Z              # File: <eval_with_key>.50:784 in forward, code: quantize_per_tensor_default_281 = torch.ops.quantized_decomposed.quantize_per_tensor.default(dequantize_per_tensor_default_280, 0.00027792342007160187, 0, -32767, 32767, torch.int16);  dequantize_per_tensor_default_280 = None
2025-03-21T20:31:43.3140868Z             quantized_decomposed_quantize_per_tensor_default_132: "i16[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_339, 0.00027792342007160187, 0, -32767, 32767, torch.int16);  quantized_decomposed_dequantize_per_tensor_default_339 = None
2025-03-21T20:31:43.3142197Z             
2025-03-21T20:31:43.3142903Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.3144735Z             quantized_decomposed_dequantize_per_tensor_default_340: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_132, 0.00027792342007160187, 0, -32767, 32767, torch.int16);  quantized_decomposed_quantize_per_tensor_default_132 = None
2025-03-21T20:31:43.3146760Z             aten_expand_copy_default: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_234, [1, 12, 1, 64]);  quantized_decomposed_dequantize_per_tensor_default_234 = None
2025-03-21T20:31:43.3148279Z             aten_view_copy_default_11: "f32[12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default, [12, 1, 64]);  aten_expand_copy_default = None
2025-03-21T20:31:43.3149725Z             aten_expand_copy_default_1: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_340, [1, 12, 64, 128]);  quantized_decomposed_dequantize_per_tensor_default_340 = None
2025-03-21T20:31:43.3151213Z             aten_view_copy_default_12: "f32[12, 64, 128]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_1, [12, 64, 128]);  aten_expand_copy_default_1 = None
2025-03-21T20:31:43.3152524Z             aten_bmm_default: "f32[12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_bmm_default(aten_view_copy_default_11, aten_view_copy_default_12);  aten_view_copy_default_11 = aten_view_copy_default_12 = None
2025-03-21T20:31:43.3153774Z             aten_view_copy_default_13: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_bmm_default, [1, 12, 1, 128]);  aten_bmm_default = None
2025-03-21T20:31:43.3155283Z             quantized_decomposed_quantize_per_tensor_default_133: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_13, 0.006018729880452156, 34998, 0, 65535, torch.int32);  aten_view_copy_default_13 = None
2025-03-21T20:31:43.3157472Z             quantized_decomposed_dequantize_per_tensor_default_341: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_133, 0.006018729880452156, 34998, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_133 = None
2025-03-21T20:31:43.3159555Z             quantized_decomposed_dequantize_per_tensor_default_342: "f32[1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param149, 1.9073777366429567e-06, 0, 0, 65535, torch.int32);  b__frozen_param149 = None
2025-03-21T20:31:43.3161618Z             aten_mul_tensor_10: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_341, quantized_decomposed_dequantize_per_tensor_default_342);  quantized_decomposed_dequantize_per_tensor_default_341 = quantized_decomposed_dequantize_per_tensor_default_342 = None
2025-03-21T20:31:43.3163693Z             quantized_decomposed_quantize_per_tensor_default_134: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_10, 0.0007523412350565195, 34998, 0, 65535, torch.int32);  aten_mul_tensor_10 = None
2025-03-21T20:31:43.3164732Z             
2025-03-21T20:31:43.3165333Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:161 in forward, code: attn_weight += attn_mask
2025-03-21T20:31:43.3167066Z             quantized_decomposed_dequantize_per_tensor_default_343: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_134, 0.0007523412350565195, 34998, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_134 = None
2025-03-21T20:31:43.3169496Z             aten_add_tensor_2: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_343, quantized_decomposed_dequantize_per_tensor_default_338);  quantized_decomposed_dequantize_per_tensor_default_343 = quantized_decomposed_dequantize_per_tensor_default_338 = None
2025-03-21T20:31:43.3171548Z             quantized_decomposed_quantize_per_tensor_default_135: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_2, 0.00445493683218956, 61746, 0, 65535, torch.int32);  aten_add_tensor_2 = None
2025-03-21T20:31:43.3172612Z             
2025-03-21T20:31:43.3173330Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:162 in forward, code: attn_weight = torch.softmax(attn_weight, dim=-1)
2025-03-21T20:31:43.3175142Z             quantized_decomposed_dequantize_per_tensor_default_344: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_135, 0.00445493683218956, 61746, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_135 = None
2025-03-21T20:31:43.3177171Z             aten__softmax_default: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten__softmax_default(quantized_decomposed_dequantize_per_tensor_default_344, -1, False);  quantized_decomposed_dequantize_per_tensor_default_344 = None
2025-03-21T20:31:43.3178907Z             quantized_decomposed_quantize_per_tensor_default_136: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten__softmax_default, 1.5259021893143654e-05, 0, 0, 65535, torch.int32);  aten__softmax_default = None
2025-03-21T20:31:43.3179979Z             
2025-03-21T20:31:43.3180568Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:163 in forward, code: y = attn_weight @ v
2025-03-21T20:31:43.3182318Z             quantized_decomposed_dequantize_per_tensor_default_345: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_136, 1.5259021893143654e-05, 0, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_136 = None
2025-03-21T20:31:43.3184317Z             aten_expand_copy_default_2: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_345, [1, 12, 1, 128]);  quantized_decomposed_dequantize_per_tensor_default_345 = None
2025-03-21T20:31:43.3185768Z             aten_view_copy_default_14: "f32[12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_2, [12, 1, 128]);  aten_expand_copy_default_2 = None
2025-03-21T20:31:43.3187325Z             aten_expand_copy_default_3: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_337, [1, 12, 128, 64]);  quantized_decomposed_dequantize_per_tensor_default_337 = None
2025-03-21T20:31:43.3188784Z             aten_view_copy_default_15: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_3, [12, 128, 64]);  aten_expand_copy_default_3 = None
2025-03-21T20:31:43.3190079Z             aten_bmm_default_1: "f32[12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_bmm_default(aten_view_copy_default_14, aten_view_copy_default_15);  aten_view_copy_default_14 = aten_view_copy_default_15 = None
2025-03-21T20:31:43.3191338Z             aten_view_copy_default_16: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_bmm_default_1, [1, 12, 1, 64]);  aten_bmm_default_1 = None
2025-03-21T20:31:43.3192843Z             quantized_decomposed_quantize_per_tensor_default_137: "i32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_16, 2.0544466678984463e-05, 35449, 0, 65535, torch.int32);  aten_view_copy_default_16 = None
2025-03-21T20:31:43.3193935Z             
2025-03-21T20:31:43.3194704Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:165 in forward, code: return y.transpose(1, 2).contiguous().view(bsz, seqlen, self.dim)
2025-03-21T20:31:43.3196621Z             quantized_decomposed_dequantize_per_tensor_default_346: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_137, 2.0544466678984463e-05, 35449, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_137 = None
2025-03-21T20:31:43.3198935Z             aten_permute_copy_default_32: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_346, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_346 = None
2025-03-21T20:31:43.3200800Z             quantized_decomposed_quantize_per_tensor_default_138: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_32, 2.0544466678984463e-05, 35449, 0, 65535, torch.int32);  aten_permute_copy_default_32 = None
2025-03-21T20:31:43.3202964Z             quantized_decomposed_dequantize_per_tensor_default_347: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_138, 2.0544466678984463e-05, 35449, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_138 = None
2025-03-21T20:31:43.3204963Z             aten_view_copy_default_17: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_347, [1, 1, 768]);  quantized_decomposed_dequantize_per_tensor_default_347 = None
2025-03-21T20:31:43.3206745Z             quantized_decomposed_quantize_per_tensor_default_139: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_17, 2.0544466678984463e-05, 35449, 0, 65535, torch.int32);  aten_view_copy_default_17 = None
2025-03-21T20:31:43.3207848Z             
2025-03-21T20:31:43.3208518Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.3210362Z             quantized_decomposed_dequantize_per_tensor_default_348: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_139, 2.0544466678984463e-05, 35449, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_139 = None
2025-03-21T20:31:43.3212422Z             aten_unsqueeze_copy_default_7: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_348, -1);  quantized_decomposed_dequantize_per_tensor_default_348 = None
2025-03-21T20:31:43.3214261Z             quantized_decomposed_quantize_per_tensor_default_140: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_7, 2.0544466678984463e-05, 35449, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_7 = None
2025-03-21T20:31:43.3215385Z             
2025-03-21T20:31:43.3215934Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.3217606Z             quantized_decomposed_dequantize_per_tensor_default_349: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_140, 2.0544466678984463e-05, 35449, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_140 = None
2025-03-21T20:31:43.3219647Z             aten_permute_copy_default_33: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_349, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_349 = None
2025-03-21T20:31:43.3221477Z             quantized_decomposed_quantize_per_tensor_default_141: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_33, 2.0544466678984463e-05, 35449, 0, 65535, torch.int32);  aten_permute_copy_default_33 = None
2025-03-21T20:31:43.3222607Z             
2025-03-21T20:31:43.3223187Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.3224806Z             quantized_decomposed_dequantize_per_tensor_default_350: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_141, 2.0544466678984463e-05, 35449, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_141 = None
2025-03-21T20:31:43.3227338Z             aten_convolution_default_3: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_350, quantized_decomposed_dequantize_per_tensor_default_5, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_350 = quantized_decomposed_dequantize_per_tensor_default_5 = None
2025-03-21T20:31:43.3229634Z             quantized_decomposed_quantize_per_tensor_default_142: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_3, 2.3234304535435513e-05, 31262, 0, 65535, torch.int32);  aten_convolution_default_3 = None
2025-03-21T20:31:43.3230788Z             
2025-03-21T20:31:43.3231345Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.3233181Z             quantized_decomposed_dequantize_per_tensor_default_351: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_142, 2.3234304535435513e-05, 31262, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_142 = None
2025-03-21T20:31:43.3235216Z             aten_permute_copy_default_34: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_351, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_351 = None
2025-03-21T20:31:43.3237038Z             quantized_decomposed_quantize_per_tensor_default_143: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_34, 2.3234304535435513e-05, 31262, 0, 65535, torch.int32);  aten_permute_copy_default_34 = None
2025-03-21T20:31:43.3238150Z             
2025-03-21T20:31:43.3238823Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.3240610Z             quantized_decomposed_dequantize_per_tensor_default_352: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_143, 2.3234304535435513e-05, 31262, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_143 = None
2025-03-21T20:31:43.3242602Z             aten_squeeze_copy_dims_7: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_352, [-1]);  quantized_decomposed_dequantize_per_tensor_default_352 = None
2025-03-21T20:31:43.3244345Z             quantized_decomposed_quantize_per_tensor_default_144: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_7, 2.3234304535435513e-05, 31262, 0, 65535, torch.int32);  aten_squeeze_copy_dims_7 = None
2025-03-21T20:31:43.3245439Z             
2025-03-21T20:31:43.3245946Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:111 in forward, code: h = x + h
2025-03-21T20:31:43.3247637Z             quantized_decomposed_dequantize_per_tensor_default_353: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_144, 2.3234304535435513e-05, 31262, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_144 = None
2025-03-21T20:31:43.3250103Z             aten_add_tensor_3: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_149, quantized_decomposed_dequantize_per_tensor_default_353);  quantized_decomposed_dequantize_per_tensor_default_149 = quantized_decomposed_dequantize_per_tensor_default_353 = None
2025-03-21T20:31:43.3252209Z             quantized_decomposed_quantize_per_tensor_default_145: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_3, 2.3993761715246364e-05, 31139, 0, 65535, torch.int32);  aten_add_tensor_3 = None
2025-03-21T20:31:43.3253255Z             
2025-03-21T20:31:43.3253896Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:115 in forward, code: out = h + self.feed_forward(self.ffn_norm(h))
2025-03-21T20:31:43.3255426Z             quantized_decomposed_dequantize_per_tensor_default_354: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_145, 2.3993761715246364e-05, 31139, 0, 65535, torch.int32)
2025-03-21T20:31:43.3257626Z             quantized_decomposed_dequantize_per_tensor_default_355: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_145, 2.3993761715246364e-05, 31139, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_145 = None
2025-03-21T20:31:43.3259380Z             aten_pow_tensor_scalar_1: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_pow_Tensor_Scalar(quantized_decomposed_dequantize_per_tensor_default_355, 2)
2025-03-21T20:31:43.3260459Z             aten_mean_dim_1: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_mean_dim(aten_pow_tensor_scalar_1, [2], True);  aten_pow_tensor_scalar_1 = None
2025-03-21T20:31:43.3261470Z             aten_add_scalar_1: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_add_Scalar(aten_mean_dim_1, 9.999999747378752e-06);  aten_mean_dim_1 = None
2025-03-21T20:31:43.3262443Z             aten_rsqrt_default_1: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_rsqrt_default(aten_add_scalar_1);  aten_add_scalar_1 = None
2025-03-21T20:31:43.3263824Z             aten_mul_tensor_11: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_355, aten_rsqrt_default_1);  quantized_decomposed_dequantize_per_tensor_default_355 = aten_rsqrt_default_1 = None
2025-03-21T20:31:43.3265573Z             aten_mul_tensor_12: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(aten_mul_tensor_11, quantized_decomposed_dequantize_per_tensor_default_6);  aten_mul_tensor_11 = quantized_decomposed_dequantize_per_tensor_default_6 = None
2025-03-21T20:31:43.3267327Z             quantized_decomposed_quantize_per_tensor_default_146: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_12, 6.304631824605167e-05, 32297, 0, 65535, torch.int32);  aten_mul_tensor_12 = None
2025-03-21T20:31:43.3268377Z             
2025-03-21T20:31:43.3269027Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.3270565Z             quantized_decomposed_dequantize_per_tensor_default_356: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_146, 6.304631824605167e-05, 32297, 0, 65535, torch.int32)
2025-03-21T20:31:43.3272747Z             quantized_decomposed_dequantize_per_tensor_default_357: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_146, 6.304631824605167e-05, 32297, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_146 = None
2025-03-21T20:31:43.3274805Z             aten_unsqueeze_copy_default_8: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_357, -1);  quantized_decomposed_dequantize_per_tensor_default_357 = None
2025-03-21T20:31:43.3276680Z             quantized_decomposed_quantize_per_tensor_default_147: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_8, 6.304631824605167e-05, 32297, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_8 = None
2025-03-21T20:31:43.3277806Z             
2025-03-21T20:31:43.3278354Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.3280009Z             quantized_decomposed_dequantize_per_tensor_default_358: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_147, 6.304631824605167e-05, 32297, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_147 = None
2025-03-21T20:31:43.3282071Z             aten_permute_copy_default_35: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_358, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_358 = None
2025-03-21T20:31:43.3283910Z             quantized_decomposed_quantize_per_tensor_default_148: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_35, 6.304631824605167e-05, 32297, 0, 65535, torch.int32);  aten_permute_copy_default_35 = None
2025-03-21T20:31:43.3285051Z             
2025-03-21T20:31:43.3285552Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.3287181Z             quantized_decomposed_dequantize_per_tensor_default_359: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_148, 6.304631824605167e-05, 32297, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_148 = None
2025-03-21T20:31:43.3289777Z             aten_convolution_default_4: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_359, quantized_decomposed_dequantize_per_tensor_default_7, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_359 = quantized_decomposed_dequantize_per_tensor_default_7 = None
2025-03-21T20:31:43.3292089Z             quantized_decomposed_quantize_per_tensor_default_149: "i32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_4, 0.00015858362894505262, 37454, 0, 65535, torch.int32);  aten_convolution_default_4 = None
2025-03-21T20:31:43.3293230Z             
2025-03-21T20:31:43.3293794Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.3295472Z             quantized_decomposed_dequantize_per_tensor_default_360: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_149, 0.00015858362894505262, 37454, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_149 = None
2025-03-21T20:31:43.3297536Z             aten_permute_copy_default_36: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_360, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_360 = None
2025-03-21T20:31:43.3299612Z             quantized_decomposed_quantize_per_tensor_default_150: "i32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_36, 0.00015858362894505262, 37454, 0, 65535, torch.int32);  aten_permute_copy_default_36 = None
2025-03-21T20:31:43.3300758Z             
2025-03-21T20:31:43.3301433Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.3303255Z             quantized_decomposed_dequantize_per_tensor_default_361: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_150, 0.00015858362894505262, 37454, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_150 = None
2025-03-21T20:31:43.3305260Z             aten_squeeze_copy_dims_8: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_361, [-1]);  quantized_decomposed_dequantize_per_tensor_default_361 = None
2025-03-21T20:31:43.3307025Z             quantized_decomposed_quantize_per_tensor_default_151: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_8, 0.00015858362894505262, 37454, 0, 65535, torch.int32);  aten_squeeze_copy_dims_8 = None
2025-03-21T20:31:43.3308163Z             
2025-03-21T20:31:43.3308814Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:36 in forward, code: return self.w2(F.silu(self.w1(x)) * self.w3(x))
2025-03-21T20:31:43.3310352Z             quantized_decomposed_dequantize_per_tensor_default_362: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_151, 0.00015858362894505262, 37454, 0, 65535, torch.int32)
2025-03-21T20:31:43.3312522Z             quantized_decomposed_dequantize_per_tensor_default_363: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_151, 0.00015858362894505262, 37454, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_151 = None
2025-03-21T20:31:43.3314508Z             aten_sigmoid_default: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_sigmoid_default(quantized_decomposed_dequantize_per_tensor_default_363);  quantized_decomposed_dequantize_per_tensor_default_363 = None
2025-03-21T20:31:43.3316199Z             quantized_decomposed_quantize_per_tensor_default_152: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_sigmoid_default, 1.52587890625e-05, 0, 0, 65535, torch.int32);  aten_sigmoid_default = None
2025-03-21T20:31:43.3318255Z             quantized_decomposed_dequantize_per_tensor_default_364: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_152, 1.52587890625e-05, 0, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_152 = None
2025-03-21T20:31:43.3320587Z             aten_mul_tensor_13: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_362, quantized_decomposed_dequantize_per_tensor_default_364);  quantized_decomposed_dequantize_per_tensor_default_362 = quantized_decomposed_dequantize_per_tensor_default_364 = None
2025-03-21T20:31:43.3322660Z             quantized_decomposed_quantize_per_tensor_default_153: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_13, 7.141960668377578e-05, 3899, 0, 65535, torch.int32);  aten_mul_tensor_13 = None
2025-03-21T20:31:43.3324779Z             quantized_decomposed_dequantize_per_tensor_default_365: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_153, 7.141960668377578e-05, 3899, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_153 = None
2025-03-21T20:31:43.3326136Z             
2025-03-21T20:31:43.3326782Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.3328237Z             aten_unsqueeze_copy_default_9: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_356, -1);  quantized_decomposed_dequantize_per_tensor_default_356 = None
2025-03-21T20:31:43.3330150Z             quantized_decomposed_quantize_per_tensor_default_154: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_9, 6.304631824605167e-05, 32297, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_9 = None
2025-03-21T20:31:43.3331287Z             
2025-03-21T20:31:43.3331830Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.3333681Z             quantized_decomposed_dequantize_per_tensor_default_366: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_154, 6.304631824605167e-05, 32297, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_154 = None
2025-03-21T20:31:43.3335715Z             aten_permute_copy_default_37: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_366, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_366 = None
2025-03-21T20:31:43.3337535Z             quantized_decomposed_quantize_per_tensor_default_155: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_37, 6.304631824605167e-05, 32297, 0, 65535, torch.int32);  aten_permute_copy_default_37 = None
2025-03-21T20:31:43.3338670Z             
2025-03-21T20:31:43.3339171Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.3340785Z             quantized_decomposed_dequantize_per_tensor_default_367: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_155, 6.304631824605167e-05, 32297, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_155 = None
2025-03-21T20:31:43.3343295Z             aten_convolution_default_5: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_367, quantized_decomposed_dequantize_per_tensor_default_8, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_367 = quantized_decomposed_dequantize_per_tensor_default_8 = None
2025-03-21T20:31:43.3345599Z             quantized_decomposed_quantize_per_tensor_default_156: "i32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_5, 0.00017520938126835972, 26511, 0, 65535, torch.int32);  aten_convolution_default_5 = None
2025-03-21T20:31:43.3346741Z             
2025-03-21T20:31:43.3347288Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.3349045Z             quantized_decomposed_dequantize_per_tensor_default_368: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_156, 0.00017520938126835972, 26511, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_156 = None
2025-03-21T20:31:43.3351135Z             aten_permute_copy_default_38: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_368, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_368 = None
2025-03-21T20:31:43.3353022Z             quantized_decomposed_quantize_per_tensor_default_157: "i32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_38, 0.00017520938126835972, 26511, 0, 65535, torch.int32);  aten_permute_copy_default_38 = None
2025-03-21T20:31:43.3354164Z             
2025-03-21T20:31:43.3354836Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.3356640Z             quantized_decomposed_dequantize_per_tensor_default_369: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_157, 0.00017520938126835972, 26511, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_157 = None
2025-03-21T20:31:43.3358691Z             aten_squeeze_copy_dims_9: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_369, [-1]);  quantized_decomposed_dequantize_per_tensor_default_369 = None
2025-03-21T20:31:43.3360464Z             quantized_decomposed_quantize_per_tensor_default_158: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_9, 0.00017520938126835972, 26511, 0, 65535, torch.int32);  aten_squeeze_copy_dims_9 = None
2025-03-21T20:31:43.3361574Z             
2025-03-21T20:31:43.3362222Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:36 in forward, code: return self.w2(F.silu(self.w1(x)) * self.w3(x))
2025-03-21T20:31:43.3364005Z             quantized_decomposed_dequantize_per_tensor_default_370: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_158, 0.00017520938126835972, 26511, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_158 = None
2025-03-21T20:31:43.3366388Z             aten_mul_tensor_14: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_365, quantized_decomposed_dequantize_per_tensor_default_370);  quantized_decomposed_dequantize_per_tensor_default_365 = quantized_decomposed_dequantize_per_tensor_default_370 = None
2025-03-21T20:31:43.3368482Z             quantized_decomposed_quantize_per_tensor_default_159: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_14, 0.00046910217497497797, 34492, 0, 65535, torch.int32);  aten_mul_tensor_14 = None
2025-03-21T20:31:43.3369598Z             
2025-03-21T20:31:43.3370261Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.3372043Z             quantized_decomposed_dequantize_per_tensor_default_371: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_159, 0.00046910217497497797, 34492, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_159 = None
2025-03-21T20:31:43.3374107Z             aten_unsqueeze_copy_default_10: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_371, -1);  quantized_decomposed_dequantize_per_tensor_default_371 = None
2025-03-21T20:31:43.3376025Z             quantized_decomposed_quantize_per_tensor_default_160: "i32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_10, 0.00046910217497497797, 34492, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_10 = None
2025-03-21T20:31:43.3377222Z             
2025-03-21T20:31:43.3377767Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.3379464Z             quantized_decomposed_dequantize_per_tensor_default_372: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_160, 0.00046910217497497797, 34492, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_160 = None
2025-03-21T20:31:43.3381522Z             aten_permute_copy_default_39: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_372, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_372 = None
2025-03-21T20:31:43.3383358Z             quantized_decomposed_quantize_per_tensor_default_161: "i32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_39, 0.00046910217497497797, 34492, 0, 65535, torch.int32);  aten_permute_copy_default_39 = None
2025-03-21T20:31:43.3384534Z             
2025-03-21T20:31:43.3385038Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.3386661Z             quantized_decomposed_dequantize_per_tensor_default_373: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_161, 0.00046910217497497797, 34492, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_161 = None
2025-03-21T20:31:43.3389190Z             aten_convolution_default_6: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_373, quantized_decomposed_dequantize_per_tensor_default_9, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_373 = quantized_decomposed_dequantize_per_tensor_default_9 = None
2025-03-21T20:31:43.3391615Z             quantized_decomposed_quantize_per_tensor_default_162: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_6, 0.00015648982662241906, 29373, 0, 65535, torch.int32);  aten_convolution_default_6 = None
2025-03-21T20:31:43.3392728Z             
2025-03-21T20:31:43.3393285Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.3394960Z             quantized_decomposed_dequantize_per_tensor_default_374: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_162, 0.00015648982662241906, 29373, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_162 = None
2025-03-21T20:31:43.3396994Z             aten_permute_copy_default_40: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_374, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_374 = None
2025-03-21T20:31:43.3398816Z             quantized_decomposed_quantize_per_tensor_default_163: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_40, 0.00015648982662241906, 29373, 0, 65535, torch.int32);  aten_permute_copy_default_40 = None
2025-03-21T20:31:43.3399940Z             
2025-03-21T20:31:43.3400933Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.3402766Z             quantized_decomposed_dequantize_per_tensor_default_375: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_163, 0.00015648982662241906, 29373, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_163 = None
2025-03-21T20:31:43.3404803Z             aten_squeeze_copy_dims_10: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_375, [-1]);  quantized_decomposed_dequantize_per_tensor_default_375 = None
2025-03-21T20:31:43.3406561Z             quantized_decomposed_quantize_per_tensor_default_164: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_10, 0.00015648982662241906, 29373, 0, 65535, torch.int32);  aten_squeeze_copy_dims_10 = None
2025-03-21T20:31:43.3407669Z             
2025-03-21T20:31:43.3408315Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:115 in forward, code: out = h + self.feed_forward(self.ffn_norm(h))
2025-03-21T20:31:43.3410175Z             quantized_decomposed_dequantize_per_tensor_default_376: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_164, 0.00015648982662241906, 29373, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_164 = None
2025-03-21T20:31:43.3412548Z             aten_add_tensor_4: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_354, quantized_decomposed_dequantize_per_tensor_default_376);  quantized_decomposed_dequantize_per_tensor_default_354 = quantized_decomposed_dequantize_per_tensor_default_376 = None
2025-03-21T20:31:43.3414614Z             quantized_decomposed_quantize_per_tensor_default_165: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_4, 0.0001625629374757409, 28917, 0, 65535, torch.int32);  aten_add_tensor_4 = None
2025-03-21T20:31:43.3415662Z             
2025-03-21T20:31:43.3416172Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:111 in forward, code: h = x + h
2025-03-21T20:31:43.3417575Z             quantized_decomposed_dequantize_per_tensor_default_377: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_165, 0.0001625629374757409, 28917, 0, 65535, torch.int32)
2025-03-21T20:31:43.3418690Z             
2025-03-21T20:31:43.3419385Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:108 in forward, code: self.attention_norm(x), freqs_cos, freqs_sin, **attn_options
2025-03-21T20:31:43.3421197Z             quantized_decomposed_dequantize_per_tensor_default_378: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_165, 0.0001625629374757409, 28917, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_165 = None
2025-03-21T20:31:43.3422948Z             aten_pow_tensor_scalar_2: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_pow_Tensor_Scalar(quantized_decomposed_dequantize_per_tensor_default_378, 2)
2025-03-21T20:31:43.3424027Z             aten_mean_dim_2: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_mean_dim(aten_pow_tensor_scalar_2, [2], True);  aten_pow_tensor_scalar_2 = None
2025-03-21T20:31:43.3425038Z             aten_add_scalar_2: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_add_Scalar(aten_mean_dim_2, 9.999999747378752e-06);  aten_mean_dim_2 = None
2025-03-21T20:31:43.3426034Z             aten_rsqrt_default_2: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_rsqrt_default(aten_add_scalar_2);  aten_add_scalar_2 = None
2025-03-21T20:31:43.3427435Z             aten_mul_tensor_15: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_378, aten_rsqrt_default_2);  quantized_decomposed_dequantize_per_tensor_default_378 = aten_rsqrt_default_2 = None
2025-03-21T20:31:43.3429217Z             aten_mul_tensor_16: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(aten_mul_tensor_15, quantized_decomposed_dequantize_per_tensor_default_10);  aten_mul_tensor_15 = quantized_decomposed_dequantize_per_tensor_default_10 = None
2025-03-21T20:31:43.3430979Z             quantized_decomposed_quantize_per_tensor_default_166: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_16, 0.0002292444696649909, 31927, 0, 65535, torch.int32);  aten_mul_tensor_16 = None
2025-03-21T20:31:43.3432024Z             
2025-03-21T20:31:43.3432839Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.3434386Z             quantized_decomposed_dequantize_per_tensor_default_379: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_166, 0.0002292444696649909, 31927, 0, 65535, torch.int32)
2025-03-21T20:31:43.3436380Z             quantized_decomposed_dequantize_per_tensor_default_380: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_166, 0.0002292444696649909, 31927, 0, 65535, torch.int32)
2025-03-21T20:31:43.3438536Z             quantized_decomposed_dequantize_per_tensor_default_381: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_166, 0.0002292444696649909, 31927, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_166 = None
2025-03-21T20:31:43.3440578Z             aten_unsqueeze_copy_default_11: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_381, -1);  quantized_decomposed_dequantize_per_tensor_default_381 = None
2025-03-21T20:31:43.3442430Z             quantized_decomposed_quantize_per_tensor_default_167: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_11, 0.0002292444696649909, 31927, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_11 = None
2025-03-21T20:31:43.3443566Z             
2025-03-21T20:31:43.3444109Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.3445755Z             quantized_decomposed_dequantize_per_tensor_default_382: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_167, 0.0002292444696649909, 31927, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_167 = None
2025-03-21T20:31:43.3447790Z             aten_permute_copy_default_41: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_382, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_382 = None
2025-03-21T20:31:43.3449676Z             quantized_decomposed_quantize_per_tensor_default_168: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_41, 0.0002292444696649909, 31927, 0, 65535, torch.int32);  aten_permute_copy_default_41 = None
2025-03-21T20:31:43.3450804Z             
2025-03-21T20:31:43.3451362Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.3453015Z             quantized_decomposed_dequantize_per_tensor_default_383: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_168, 0.0002292444696649909, 31927, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_168 = None
2025-03-21T20:31:43.3455563Z             aten_convolution_default_7: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_383, quantized_decomposed_dequantize_per_tensor_default_11, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_383 = quantized_decomposed_dequantize_per_tensor_default_11 = None
2025-03-21T20:31:43.3457860Z             quantized_decomposed_quantize_per_tensor_default_169: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_7, 0.0005588589119724929, 30540, 0, 65535, torch.int32);  aten_convolution_default_7 = None
2025-03-21T20:31:43.3458986Z             
2025-03-21T20:31:43.3459568Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.3461311Z             quantized_decomposed_dequantize_per_tensor_default_384: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_169, 0.0005588589119724929, 30540, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_169 = None
2025-03-21T20:31:43.3463451Z             aten_permute_copy_default_42: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_384, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_384 = None
2025-03-21T20:31:43.3465349Z             quantized_decomposed_quantize_per_tensor_default_170: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_42, 0.0005588589119724929, 30540, 0, 65535, torch.int32);  aten_permute_copy_default_42 = None
2025-03-21T20:31:43.3466750Z             
2025-03-21T20:31:43.3467528Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.3469446Z             quantized_decomposed_dequantize_per_tensor_default_385: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_170, 0.0005588589119724929, 30540, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_170 = None
2025-03-21T20:31:43.3471568Z             aten_squeeze_copy_dims_11: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_385, [-1]);  quantized_decomposed_dequantize_per_tensor_default_385 = None
2025-03-21T20:31:43.3473425Z             quantized_decomposed_quantize_per_tensor_default_171: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_11, 0.0005588589119724929, 30540, 0, 65535, torch.int32);  aten_squeeze_copy_dims_11 = None
2025-03-21T20:31:43.3474664Z             
2025-03-21T20:31:43.3475418Z              # File: /pytorch/executorch/examples/models/llama/attention.py:242 in forward, code: q = q.view(bsz, seqlen, self.n_local_heads, self.head_dim)
2025-03-21T20:31:43.3477306Z             quantized_decomposed_dequantize_per_tensor_default_386: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_171, 0.0005588589119724929, 30540, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_171 = None
2025-03-21T20:31:43.3478814Z             
2025-03-21T20:31:43.3479525Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.3481038Z             aten_unsqueeze_copy_default_12: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_380, -1);  quantized_decomposed_dequantize_per_tensor_default_380 = None
2025-03-21T20:31:43.3483053Z             quantized_decomposed_quantize_per_tensor_default_172: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_12, 0.0002292444696649909, 31927, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_12 = None
2025-03-21T20:31:43.3484302Z             
2025-03-21T20:31:43.3484951Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.3486727Z             quantized_decomposed_dequantize_per_tensor_default_387: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_172, 0.0002292444696649909, 31927, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_172 = None
2025-03-21T20:31:43.3488891Z             aten_permute_copy_default_43: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_387, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_387 = None
2025-03-21T20:31:43.3490935Z             quantized_decomposed_quantize_per_tensor_default_173: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_43, 0.0002292444696649909, 31927, 0, 65535, torch.int32);  aten_permute_copy_default_43 = None
2025-03-21T20:31:43.3492176Z             
2025-03-21T20:31:43.3492754Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.3494540Z             quantized_decomposed_dequantize_per_tensor_default_388: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_173, 0.0002292444696649909, 31927, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_173 = None
2025-03-21T20:31:43.3497164Z             aten_convolution_default_8: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_388, quantized_decomposed_dequantize_per_tensor_default_12, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_388 = quantized_decomposed_dequantize_per_tensor_default_12 = None
2025-03-21T20:31:43.3499564Z             quantized_decomposed_quantize_per_tensor_default_174: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_8, 0.00035107287112623453, 33587, 0, 65535, torch.int32);  aten_convolution_default_8 = None
2025-03-21T20:31:43.3500815Z             
2025-03-21T20:31:43.3501430Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.3503369Z             quantized_decomposed_dequantize_per_tensor_default_389: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_174, 0.00035107287112623453, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_174 = None
2025-03-21T20:31:43.3505588Z             aten_permute_copy_default_44: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_389, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_389 = None
2025-03-21T20:31:43.3507539Z             quantized_decomposed_quantize_per_tensor_default_175: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_44, 0.00035107287112623453, 33587, 0, 65535, torch.int32);  aten_permute_copy_default_44 = None
2025-03-21T20:31:43.3508809Z             
2025-03-21T20:31:43.3509615Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.3511480Z             quantized_decomposed_dequantize_per_tensor_default_390: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_175, 0.00035107287112623453, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_175 = None
2025-03-21T20:31:43.3513641Z             aten_squeeze_copy_dims_12: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_390, [-1]);  quantized_decomposed_dequantize_per_tensor_default_390 = None
2025-03-21T20:31:43.3515528Z             quantized_decomposed_quantize_per_tensor_default_176: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_12, 0.00035107287112623453, 33587, 0, 65535, torch.int32);  aten_squeeze_copy_dims_12 = None
2025-03-21T20:31:43.3516749Z             
2025-03-21T20:31:43.3517595Z              # File: /pytorch/executorch/examples/models/llama/attention.py:243 in forward, code: k = k.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.3519483Z             quantized_decomposed_dequantize_per_tensor_default_391: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_176, 0.00035107287112623453, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_176 = None
2025-03-21T20:31:43.3520949Z             
2025-03-21T20:31:43.3521700Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.3523184Z             aten_unsqueeze_copy_default_13: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_379, -1);  quantized_decomposed_dequantize_per_tensor_default_379 = None
2025-03-21T20:31:43.3525157Z             quantized_decomposed_quantize_per_tensor_default_177: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_13, 0.0002292444696649909, 31927, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_13 = None
2025-03-21T20:31:43.3526389Z             
2025-03-21T20:31:43.3527010Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.3528814Z             quantized_decomposed_dequantize_per_tensor_default_392: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_177, 0.0002292444696649909, 31927, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_177 = None
2025-03-21T20:31:43.3531053Z             aten_permute_copy_default_45: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_392, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_392 = None
2025-03-21T20:31:43.3533280Z             quantized_decomposed_quantize_per_tensor_default_178: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_45, 0.0002292444696649909, 31927, 0, 65535, torch.int32);  aten_permute_copy_default_45 = None
2025-03-21T20:31:43.3534629Z             
2025-03-21T20:31:43.3535225Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.3537023Z             quantized_decomposed_dequantize_per_tensor_default_393: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_178, 0.0002292444696649909, 31927, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_178 = None
2025-03-21T20:31:43.3539638Z             aten_convolution_default_9: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_393, quantized_decomposed_dequantize_per_tensor_default_13, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_393 = quantized_decomposed_dequantize_per_tensor_default_13 = None
2025-03-21T20:31:43.3541996Z             quantized_decomposed_quantize_per_tensor_default_179: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_9, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_convolution_default_9 = None
2025-03-21T20:31:43.3543297Z             
2025-03-21T20:31:43.3543951Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.3545718Z             quantized_decomposed_dequantize_per_tensor_default_394: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_179, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_179 = None
2025-03-21T20:31:43.3547863Z             aten_permute_copy_default_46: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_394, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_394 = None
2025-03-21T20:31:43.3549808Z             quantized_decomposed_quantize_per_tensor_default_180: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_46, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_permute_copy_default_46 = None
2025-03-21T20:31:43.3551050Z             
2025-03-21T20:31:43.3551775Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.3553648Z             quantized_decomposed_dequantize_per_tensor_default_395: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_180, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_180 = None
2025-03-21T20:31:43.3555768Z             aten_squeeze_copy_dims_13: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_395, [-1]);  quantized_decomposed_dequantize_per_tensor_default_395 = None
2025-03-21T20:31:43.3557623Z             quantized_decomposed_quantize_per_tensor_default_181: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_13, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_squeeze_copy_dims_13 = None
2025-03-21T20:31:43.3558795Z             
2025-03-21T20:31:43.3559606Z              # File: /pytorch/executorch/examples/models/llama/attention.py:244 in forward, code: v = v.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.3561529Z             quantized_decomposed_dequantize_per_tensor_default_396: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_181, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_181 = None
2025-03-21T20:31:43.3562968Z             
2025-03-21T20:31:43.3563728Z              # File: /pytorch/executorch/examples/models/llama/attention.py:242 in forward, code: q = q.view(bsz, seqlen, self.n_local_heads, self.head_dim)
2025-03-21T20:31:43.3565271Z             aten_view_copy_default_18: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_386, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_386 = None
2025-03-21T20:31:43.3567166Z             quantized_decomposed_quantize_per_tensor_default_182: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_18, 0.0005588589119724929, 30540, 0, 65535, torch.int32);  aten_view_copy_default_18 = None
2025-03-21T20:31:43.3568396Z             
2025-03-21T20:31:43.3569585Z              # File: <eval_with_key>.50:943 in forward, code: dequantize_per_tensor_default_332 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_332, 0.0005588589119724929, 30540, 0, 65535, torch.int32);  quantize_per_tensor_default_332 = None
2025-03-21T20:31:43.3571898Z             quantized_decomposed_dequantize_per_tensor_default_397: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_182, 0.0005588589119724929, 30540, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_182 = None
2025-03-21T20:31:43.3573331Z             
2025-03-21T20:31:43.3574071Z              # File: /pytorch/executorch/examples/models/llama/attention.py:243 in forward, code: k = k.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.3575623Z             aten_view_copy_default_19: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_391, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_391 = None
2025-03-21T20:31:43.3577485Z             quantized_decomposed_quantize_per_tensor_default_183: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_19, 0.00035107287112623453, 33587, 0, 65535, torch.int32);  aten_view_copy_default_19 = None
2025-03-21T20:31:43.3578691Z             
2025-03-21T20:31:43.3579901Z              # File: <eval_with_key>.50:946 in forward, code: dequantize_per_tensor_default_333 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_333, 0.00035107287112623453, 33587, 0, 65535, torch.int32);  quantize_per_tensor_default_333 = None
2025-03-21T20:31:43.3582189Z             quantized_decomposed_dequantize_per_tensor_default_398: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_183, 0.00035107287112623453, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_183 = None
2025-03-21T20:31:43.3583659Z             
2025-03-21T20:31:43.3584416Z              # File: /pytorch/executorch/examples/models/llama/attention.py:244 in forward, code: v = v.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.3585892Z             aten_view_copy_default_20: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_396, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_396 = None
2025-03-21T20:31:43.3587842Z             quantized_decomposed_quantize_per_tensor_default_184: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_20, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_view_copy_default_20 = None
2025-03-21T20:31:43.3589054Z             
2025-03-21T20:31:43.3589893Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:346 in update, code: v_out = torch.ops.aten.index_put_(self.past_v_caches, [None, input_pos], v_val)
2025-03-21T20:31:43.3591977Z             quantized_decomposed_dequantize_per_tensor_default_399: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_184, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_184 = None
2025-03-21T20:31:43.3593527Z             
2025-03-21T20:31:43.3594543Z              # File: <eval_with_key>.50:951 in forward, code: quantize_per_tensor_default_335 = torch.ops.quantized_decomposed.quantize_per_tensor.default(_to_copy_2, 0.0005588589119724929, 30540, 0, 65535, torch.int32);  _to_copy_2 = None
2025-03-21T20:31:43.3596687Z             quantized_decomposed_quantize_per_tensor_default_185: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_397, 0.0005588589119724929, 30540, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_397 = None
2025-03-21T20:31:43.3598154Z             
2025-03-21T20:31:43.3598952Z              # File: /pytorch/executorch/examples/models/llama/rope.py:84 in apply_rotary_emb, code: xq_r, xq_i = xq.float().reshape(xq.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.3600813Z             quantized_decomposed_dequantize_per_tensor_default_400: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_185, 0.0005588589119724929, 30540, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_185 = None
2025-03-21T20:31:43.3602878Z             aten_view_copy_default_21: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_400, [1, 1, 12, -1, 2]);  quantized_decomposed_dequantize_per_tensor_default_400 = None
2025-03-21T20:31:43.3605150Z             quantized_decomposed_quantize_per_tensor_default_186: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_21, 0.0005588589119724929, 30540, 0, 65535, torch.int32);  aten_view_copy_default_21 = None
2025-03-21T20:31:43.3607413Z             quantized_decomposed_dequantize_per_tensor_default_401: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_186, 0.0005588589119724929, 30540, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_186 = None
2025-03-21T20:31:43.3609447Z             aten_slice_copy_tensor_4: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_401, 4, 0, 1)
2025-03-21T20:31:43.3610965Z             aten_slice_copy_tensor_5: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_401, 4, 1, 2);  quantized_decomposed_dequantize_per_tensor_default_401 = None
2025-03-21T20:31:43.3612446Z             aten_squeeze_copy_dims_14: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_4, [4]);  aten_slice_copy_tensor_4 = None
2025-03-21T20:31:43.3613738Z             aten_squeeze_copy_dims_15: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_5, [4]);  aten_slice_copy_tensor_5 = None
2025-03-21T20:31:43.3615459Z             quantized_decomposed_quantize_per_tensor_default_187: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_14, 0.00031485746148973703, 24746, 0, 65535, torch.int32);  aten_squeeze_copy_dims_14 = None
2025-03-21T20:31:43.3616638Z             
2025-03-21T20:31:43.3617363Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.3619005Z             quantized_decomposed_dequantize_per_tensor_default_402: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_187, 0.00031485746148973703, 24746, 0, 65535, torch.int32)
2025-03-21T20:31:43.3620194Z             
2025-03-21T20:31:43.3620968Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.3622794Z             quantized_decomposed_dequantize_per_tensor_default_403: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_187, 0.00031485746148973703, 24746, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_187 = None
2025-03-21T20:31:43.3624291Z             
2025-03-21T20:31:43.3625061Z              # File: /pytorch/executorch/examples/models/llama/rope.py:84 in apply_rotary_emb, code: xq_r, xq_i = xq.float().reshape(xq.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.3626713Z             quantized_decomposed_quantize_per_tensor_default_188: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_15, 0.0005588589119724929, 30540, 0, 65535, torch.int32);  aten_squeeze_copy_dims_15 = None
2025-03-21T20:31:43.3627944Z             
2025-03-21T20:31:43.3628604Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.3630194Z             quantized_decomposed_dequantize_per_tensor_default_404: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_188, 0.0005588589119724929, 30540, 0, 65535, torch.int32)
2025-03-21T20:31:43.3631442Z             
2025-03-21T20:31:43.3632150Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.3634143Z             quantized_decomposed_dequantize_per_tensor_default_405: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_188, 0.0005588589119724929, 30540, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_188 = None
2025-03-21T20:31:43.3635648Z             
2025-03-21T20:31:43.3636631Z              # File: <eval_with_key>.50:966 in forward, code: quantize_per_tensor_default_339 = torch.ops.quantized_decomposed.quantize_per_tensor.default(_to_copy_3, 0.00035107287112623453, 33587, 0, 65535, torch.int32);  _to_copy_3 = None
2025-03-21T20:31:43.3638757Z             quantized_decomposed_quantize_per_tensor_default_189: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_398, 0.00035107287112623453, 33587, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_398 = None
2025-03-21T20:31:43.3640201Z             
2025-03-21T20:31:43.3640985Z              # File: /pytorch/executorch/examples/models/llama/rope.py:85 in apply_rotary_emb, code: xk_r, xk_i = xk.float().reshape(xk.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.3643004Z             quantized_decomposed_dequantize_per_tensor_default_406: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_189, 0.00035107287112623453, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_189 = None
2025-03-21T20:31:43.3645127Z             aten_view_copy_default_22: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_406, [1, 1, 12, -1, 2]);  quantized_decomposed_dequantize_per_tensor_default_406 = None
2025-03-21T20:31:43.3647014Z             quantized_decomposed_quantize_per_tensor_default_190: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_22, 0.00035107287112623453, 33587, 0, 65535, torch.int32);  aten_view_copy_default_22 = None
2025-03-21T20:31:43.3649384Z             quantized_decomposed_dequantize_per_tensor_default_407: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_190, 0.00035107287112623453, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_190 = None
2025-03-21T20:31:43.3651317Z             aten_slice_copy_tensor_6: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_407, 4, 0, 1)
2025-03-21T20:31:43.3652845Z             aten_slice_copy_tensor_7: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_407, 4, 1, 2);  quantized_decomposed_dequantize_per_tensor_default_407 = None
2025-03-21T20:31:43.3654331Z             aten_squeeze_copy_dims_16: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_6, [4]);  aten_slice_copy_tensor_6 = None
2025-03-21T20:31:43.3655530Z             aten_squeeze_copy_dims_17: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_7, [4]);  aten_slice_copy_tensor_7 = None
2025-03-21T20:31:43.3657160Z             quantized_decomposed_quantize_per_tensor_default_191: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_16, 0.00035107287112623453, 33587, 0, 65535, torch.int32);  aten_squeeze_copy_dims_16 = None
2025-03-21T20:31:43.3658414Z             
2025-03-21T20:31:43.3659123Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.3660751Z             quantized_decomposed_dequantize_per_tensor_default_408: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_191, 0.00035107287112623453, 33587, 0, 65535, torch.int32)
2025-03-21T20:31:43.3661964Z             
2025-03-21T20:31:43.3662647Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.3664518Z             quantized_decomposed_dequantize_per_tensor_default_409: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_191, 0.00035107287112623453, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_191 = None
2025-03-21T20:31:43.3665947Z             
2025-03-21T20:31:43.3666778Z              # File: /pytorch/executorch/examples/models/llama/rope.py:85 in apply_rotary_emb, code: xk_r, xk_i = xk.float().reshape(xk.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.3668404Z             quantized_decomposed_quantize_per_tensor_default_192: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_17, 0.0003347279562149197, 34945, 0, 65535, torch.int32);  aten_squeeze_copy_dims_17 = None
2025-03-21T20:31:43.3669621Z             
2025-03-21T20:31:43.3670346Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.3671979Z             quantized_decomposed_dequantize_per_tensor_default_410: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_192, 0.0003347279562149197, 34945, 0, 65535, torch.int32)
2025-03-21T20:31:43.3673192Z             
2025-03-21T20:31:43.3673916Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.3675735Z             quantized_decomposed_dequantize_per_tensor_default_411: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_192, 0.0003347279562149197, 34945, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_192 = None
2025-03-21T20:31:43.3677169Z             
2025-03-21T20:31:43.3677884Z              # File: /pytorch/executorch/examples/models/llama/rope.py:78 in reshape_for_broadcast, code: return freqs_cis.view(shape)
2025-03-21T20:31:43.3679268Z             aten_view_copy_default_23: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_161, [1, 1, 1, 32]);  quantized_decomposed_dequantize_per_tensor_default_161 = None
2025-03-21T20:31:43.3681094Z             quantized_decomposed_quantize_per_tensor_default_193: "i32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_23, 3.051804378628731e-05, 32768, 0, 65535, torch.int32);  aten_view_copy_default_23 = None
2025-03-21T20:31:43.3682331Z             
2025-03-21T20:31:43.3683042Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.3684639Z             quantized_decomposed_dequantize_per_tensor_default_412: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_193, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.3685872Z             
2025-03-21T20:31:43.3686576Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.3688187Z             quantized_decomposed_dequantize_per_tensor_default_413: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_193, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.3689469Z             
2025-03-21T20:31:43.3690157Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.3691820Z             quantized_decomposed_dequantize_per_tensor_default_414: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_193, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.3693000Z             
2025-03-21T20:31:43.3693683Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.3695599Z             quantized_decomposed_dequantize_per_tensor_default_415: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_193, 3.051804378628731e-05, 32768, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_193 = None
2025-03-21T20:31:43.3697044Z             
2025-03-21T20:31:43.3697740Z              # File: /pytorch/executorch/examples/models/llama/rope.py:78 in reshape_for_broadcast, code: return freqs_cis.view(shape)
2025-03-21T20:31:43.3699158Z             aten_view_copy_default_24: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_173, [1, 1, 1, 32]);  quantized_decomposed_dequantize_per_tensor_default_173 = None
2025-03-21T20:31:43.3701039Z             quantized_decomposed_quantize_per_tensor_default_194: "i32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_24, 3.051786916330457e-05, 32767, 0, 65535, torch.int32);  aten_view_copy_default_24 = None
2025-03-21T20:31:43.3702261Z             
2025-03-21T20:31:43.3702970Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.3704545Z             quantized_decomposed_dequantize_per_tensor_default_416: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_194, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.3705972Z             
2025-03-21T20:31:43.3706686Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.3708262Z             quantized_decomposed_dequantize_per_tensor_default_417: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_194, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.3709513Z             
2025-03-21T20:31:43.3710226Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.3711820Z             quantized_decomposed_dequantize_per_tensor_default_418: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_194, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.3713044Z             
2025-03-21T20:31:43.3713758Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.3715591Z             quantized_decomposed_dequantize_per_tensor_default_419: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_194, 3.051786916330457e-05, 32767, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_194 = None
2025-03-21T20:31:43.3725993Z             
2025-03-21T20:31:43.3726767Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.3728495Z             aten_mul_tensor_17: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_403, quantized_decomposed_dequantize_per_tensor_default_415);  quantized_decomposed_dequantize_per_tensor_default_403 = quantized_decomposed_dequantize_per_tensor_default_415 = None
2025-03-21T20:31:43.3730703Z             quantized_decomposed_quantize_per_tensor_default_195: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_17, 0.00031216273782774806, 24881, 0, 65535, torch.int32);  aten_mul_tensor_17 = None
2025-03-21T20:31:43.3733108Z             quantized_decomposed_dequantize_per_tensor_default_420: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_195, 0.00031216273782774806, 24881, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_195 = None
2025-03-21T20:31:43.3735575Z             aten_mul_tensor_18: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_404, quantized_decomposed_dequantize_per_tensor_default_418);  quantized_decomposed_dequantize_per_tensor_default_404 = quantized_decomposed_dequantize_per_tensor_default_418 = None
2025-03-21T20:31:43.3737643Z             quantized_decomposed_quantize_per_tensor_default_196: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_18, 0.00018542019824963063, 32753, 0, 65535, torch.int32);  aten_mul_tensor_18 = None
2025-03-21T20:31:43.3739750Z             quantized_decomposed_dequantize_per_tensor_default_421: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_196, 0.00018542019824963063, 32753, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_196 = None
2025-03-21T20:31:43.3742137Z             aten_sub_tensor_2: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_sub_Tensor(quantized_decomposed_dequantize_per_tensor_default_420, quantized_decomposed_dequantize_per_tensor_default_421);  quantized_decomposed_dequantize_per_tensor_default_420 = quantized_decomposed_dequantize_per_tensor_default_421 = None
2025-03-21T20:31:43.3744200Z             quantized_decomposed_quantize_per_tensor_default_197: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_sub_tensor_2, 0.0003158242325298488, 26127, 0, 65535, torch.int32);  aten_sub_tensor_2 = None
2025-03-21T20:31:43.3745245Z             
2025-03-21T20:31:43.3746317Z              # File: <eval_with_key>.50:1000 in forward, code: dequantize_per_tensor_default_347 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_347, 0.0003158242325298488, 26127, 0, 65535, torch.int32);  quantize_per_tensor_default_347 = None
2025-03-21T20:31:43.3748504Z             quantized_decomposed_dequantize_per_tensor_default_422: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_197, 0.0003158242325298488, 26127, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_197 = None
2025-03-21T20:31:43.3749838Z             
2025-03-21T20:31:43.3750441Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.3752149Z             aten_mul_tensor_19: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_402, quantized_decomposed_dequantize_per_tensor_default_419);  quantized_decomposed_dequantize_per_tensor_default_402 = quantized_decomposed_dequantize_per_tensor_default_419 = None
2025-03-21T20:31:43.3754220Z             quantized_decomposed_quantize_per_tensor_default_198: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_19, 0.00020952976774424314, 32714, 0, 65535, torch.int32);  aten_mul_tensor_19 = None
2025-03-21T20:31:43.3756316Z             quantized_decomposed_dequantize_per_tensor_default_423: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_198, 0.00020952976774424314, 32714, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_198 = None
2025-03-21T20:31:43.3758689Z             aten_mul_tensor_20: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_405, quantized_decomposed_dequantize_per_tensor_default_414);  quantized_decomposed_dequantize_per_tensor_default_405 = quantized_decomposed_dequantize_per_tensor_default_414 = None
2025-03-21T20:31:43.3760773Z             quantized_decomposed_quantize_per_tensor_default_199: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_20, 0.0005582913290709257, 30556, 0, 65535, torch.int32);  aten_mul_tensor_20 = None
2025-03-21T20:31:43.3762877Z             quantized_decomposed_dequantize_per_tensor_default_424: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_199, 0.0005582913290709257, 30556, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_199 = None
2025-03-21T20:31:43.3765227Z             aten_add_tensor_5: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_423, quantized_decomposed_dequantize_per_tensor_default_424);  quantized_decomposed_dequantize_per_tensor_default_423 = quantized_decomposed_dequantize_per_tensor_default_424 = None
2025-03-21T20:31:43.3767306Z             quantized_decomposed_quantize_per_tensor_default_200: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_5, 0.0005553436931222677, 30616, 0, 65535, torch.int32);  aten_add_tensor_5 = None
2025-03-21T20:31:43.3768344Z             
2025-03-21T20:31:43.3769476Z              # File: <eval_with_key>.50:1009 in forward, code: dequantize_per_tensor_default_350 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_350, 0.0005553436931222677, 30616, 0, 65535, torch.int32);  quantize_per_tensor_default_350 = None
2025-03-21T20:31:43.3771666Z             quantized_decomposed_dequantize_per_tensor_default_425: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_200, 0.0005553436931222677, 30616, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_200 = None
2025-03-21T20:31:43.3773004Z             
2025-03-21T20:31:43.3773621Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.3775322Z             aten_mul_tensor_21: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_409, quantized_decomposed_dequantize_per_tensor_default_413);  quantized_decomposed_dequantize_per_tensor_default_409 = quantized_decomposed_dequantize_per_tensor_default_413 = None
2025-03-21T20:31:43.3777391Z             quantized_decomposed_quantize_per_tensor_default_201: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_21, 0.00035014102468267083, 33669, 0, 65535, torch.int32);  aten_mul_tensor_21 = None
2025-03-21T20:31:43.3779486Z             quantized_decomposed_dequantize_per_tensor_default_426: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_201, 0.00035014102468267083, 33669, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_201 = None
2025-03-21T20:31:43.3781840Z             aten_mul_tensor_22: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_410, quantized_decomposed_dequantize_per_tensor_default_416);  quantized_decomposed_dequantize_per_tensor_default_410 = quantized_decomposed_dequantize_per_tensor_default_416 = None
2025-03-21T20:31:43.3783925Z             quantized_decomposed_quantize_per_tensor_default_202: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_22, 0.0002225427160738036, 32972, 0, 65535, torch.int32);  aten_mul_tensor_22 = None
2025-03-21T20:31:43.3786034Z             quantized_decomposed_dequantize_per_tensor_default_427: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_202, 0.0002225427160738036, 32972, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_202 = None
2025-03-21T20:31:43.3788399Z             aten_sub_tensor_3: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_sub_Tensor(quantized_decomposed_dequantize_per_tensor_default_426, quantized_decomposed_dequantize_per_tensor_default_427);  quantized_decomposed_dequantize_per_tensor_default_426 = quantized_decomposed_dequantize_per_tensor_default_427 = None
2025-03-21T20:31:43.3790456Z             quantized_decomposed_quantize_per_tensor_default_203: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_sub_tensor_3, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_sub_tensor_3 = None
2025-03-21T20:31:43.3791547Z             
2025-03-21T20:31:43.3792619Z              # File: <eval_with_key>.50:1018 in forward, code: dequantize_per_tensor_default_353 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_353, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantize_per_tensor_default_353 = None
2025-03-21T20:31:43.3794810Z             quantized_decomposed_dequantize_per_tensor_default_428: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_203, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_203 = None
2025-03-21T20:31:43.3796171Z             
2025-03-21T20:31:43.3796867Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.3798571Z             aten_mul_tensor_23: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_408, quantized_decomposed_dequantize_per_tensor_default_417);  quantized_decomposed_dequantize_per_tensor_default_408 = quantized_decomposed_dequantize_per_tensor_default_417 = None
2025-03-21T20:31:43.3800637Z             quantized_decomposed_quantize_per_tensor_default_204: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_23, 0.0002190972154494375, 28074, 0, 65535, torch.int32);  aten_mul_tensor_23 = None
2025-03-21T20:31:43.3801784Z             quantized_decomposed_dequantize_per_tensor_default_429: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_204, 0.0002190972154494375, 28074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_204 = None
2025-03-21T20:31:43.3802895Z             aten_mul_tensor_24: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_411, quantized_decomposed_dequantize_per_tensor_default_412);  quantized_decomposed_dequantize_per_tensor_default_411 = quantized_decomposed_dequantize_per_tensor_default_412 = None
2025-03-21T20:31:43.3803761Z             quantized_decomposed_quantize_per_tensor_default_205: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_24, 0.00033182575134560466, 34828, 0, 65535, torch.int32);  aten_mul_tensor_24 = None
2025-03-21T20:31:43.3804931Z             quantized_decomposed_dequantize_per_tensor_default_430: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_205, 0.00033182575134560466, 34828, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_205 = None
2025-03-21T20:31:43.3806075Z             aten_add_tensor_6: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_429, quantized_decomposed_dequantize_per_tensor_default_430);  quantized_decomposed_dequantize_per_tensor_default_429 = quantized_decomposed_dequantize_per_tensor_default_430 = None
2025-03-21T20:31:43.3807031Z             quantized_decomposed_quantize_per_tensor_default_206: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_6, 0.0003313907072879374, 34832, 0, 65535, torch.int32);  aten_add_tensor_6 = None
2025-03-21T20:31:43.3807160Z             
2025-03-21T20:31:43.3808287Z              # File: <eval_with_key>.50:1027 in forward, code: dequantize_per_tensor_default_356 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_356, 0.0003313907072879374, 34832, 0, 65535, torch.int32);  quantize_per_tensor_default_356 = None
2025-03-21T20:31:43.3809507Z             quantized_decomposed_dequantize_per_tensor_default_431: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_206, 0.0003313907072879374, 34832, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_206 = None
2025-03-21T20:31:43.3809659Z             
2025-03-21T20:31:43.3810192Z              # File: /pytorch/executorch/examples/models/llama/rope.py:95 in apply_rotary_emb, code: xq_out = torch.stack([xq_out_r, xq_out_i], dim=-1).flatten(3)
2025-03-21T20:31:43.3811004Z             aten_unsqueeze_copy_default_14: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_422, 4);  quantized_decomposed_dequantize_per_tensor_default_422 = None
2025-03-21T20:31:43.3811793Z             aten_unsqueeze_copy_default_15: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_425, 4);  quantized_decomposed_dequantize_per_tensor_default_425 = None
2025-03-21T20:31:43.3812545Z             aten_cat_default_4: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_cat_default([aten_unsqueeze_copy_default_14, aten_unsqueeze_copy_default_15], -1);  aten_unsqueeze_copy_default_14 = aten_unsqueeze_copy_default_15 = None
2025-03-21T20:31:43.3813399Z             quantized_decomposed_quantize_per_tensor_default_207: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_4, 0.0005553436931222677, 30616, 0, 65535, torch.int32);  aten_cat_default_4 = None
2025-03-21T20:31:43.3814551Z             quantized_decomposed_dequantize_per_tensor_default_432: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_207, 0.0005553436931222677, 30616, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_207 = None
2025-03-21T20:31:43.3815309Z             aten_view_copy_default_25: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_432, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_432 = None
2025-03-21T20:31:43.3816214Z             quantized_decomposed_quantize_per_tensor_default_208: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_25, 0.0005553436931222677, 30616, 0, 65535, torch.int32);  aten_view_copy_default_25 = None
2025-03-21T20:31:43.3816303Z             
2025-03-21T20:31:43.3817268Z              # File: <eval_with_key>.50:1033 in forward, code: dequantize_per_tensor_default_358 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_358, 0.0005553436931222677, 30616, 0, 65535, torch.int32);  quantize_per_tensor_default_358 = None
2025-03-21T20:31:43.3818427Z             quantized_decomposed_dequantize_per_tensor_default_433: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_208, 0.0005553436931222677, 30616, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_208 = None
2025-03-21T20:31:43.3818530Z             
2025-03-21T20:31:43.3819074Z              # File: /pytorch/executorch/examples/models/llama/rope.py:96 in apply_rotary_emb, code: xk_out = torch.stack([xk_out_r, xk_out_i], dim=-1).flatten(3)
2025-03-21T20:31:43.3819878Z             aten_unsqueeze_copy_default_16: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_428, 4);  quantized_decomposed_dequantize_per_tensor_default_428 = None
2025-03-21T20:31:43.3820666Z             aten_unsqueeze_copy_default_17: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_431, 4);  quantized_decomposed_dequantize_per_tensor_default_431 = None
2025-03-21T20:31:43.3821439Z             aten_cat_default_5: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_cat_default([aten_unsqueeze_copy_default_16, aten_unsqueeze_copy_default_17], -1);  aten_unsqueeze_copy_default_16 = aten_unsqueeze_copy_default_17 = None
2025-03-21T20:31:43.3822297Z             quantized_decomposed_quantize_per_tensor_default_209: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_5, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_cat_default_5 = None
2025-03-21T20:31:43.3823448Z             quantized_decomposed_dequantize_per_tensor_default_434: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_209, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_209 = None
2025-03-21T20:31:43.3824205Z             aten_view_copy_default_26: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_434, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_434 = None
2025-03-21T20:31:43.3825121Z             quantized_decomposed_quantize_per_tensor_default_210: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_26, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_view_copy_default_26 = None
2025-03-21T20:31:43.3825210Z             
2025-03-21T20:31:43.3826153Z              # File: <eval_with_key>.50:1039 in forward, code: dequantize_per_tensor_default_360 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_360, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantize_per_tensor_default_360 = None
2025-03-21T20:31:43.3827292Z             quantized_decomposed_dequantize_per_tensor_default_435: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_210, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_210 = None
2025-03-21T20:31:43.3827394Z             
2025-03-21T20:31:43.3828138Z              # File: <eval_with_key>.50:1041 in forward, code: quantize_per_tensor_default_361 = torch.ops.quantized_decomposed.quantize_per_tensor.default(type_as_2, 0.0005553436931222677, 30616, 0, 65535, torch.int32);  type_as_2 = None
2025-03-21T20:31:43.3829301Z             quantized_decomposed_quantize_per_tensor_default_211: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_433, 0.0005553436931222677, 30616, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_433 = None
2025-03-21T20:31:43.3829413Z             
2025-03-21T20:31:43.3829950Z              # File: /pytorch/executorch/examples/models/llama/attention.py:249 in forward, code: q = q.transpose(1, 2)  # (bs, n_local_heads, seqlen, head_dim)
2025-03-21T20:31:43.3831104Z             quantized_decomposed_dequantize_per_tensor_default_436: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_211, 0.0005553436931222677, 30616, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_211 = None
2025-03-21T20:31:43.3831205Z             
2025-03-21T20:31:43.3831959Z              # File: <eval_with_key>.50:1044 in forward, code: quantize_per_tensor_default_362 = torch.ops.quantized_decomposed.quantize_per_tensor.default(type_as_3, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  type_as_3 = None
2025-03-21T20:31:43.3833288Z             quantized_decomposed_quantize_per_tensor_default_212: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_435, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_435 = None
2025-03-21T20:31:43.3833444Z             
2025-03-21T20:31:43.3834134Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:345 in update, code: k_out = torch.ops.aten.index_put_(self.past_k_caches, [None, input_pos], k_val)
2025-03-21T20:31:43.3835269Z             quantized_decomposed_dequantize_per_tensor_default_437: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_212, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_212 = None
2025-03-21T20:31:43.3835377Z             
2025-03-21T20:31:43.3835900Z              # File: /pytorch/executorch/examples/models/llama/attention.py:249 in forward, code: q = q.transpose(1, 2)  # (bs, n_local_heads, seqlen, head_dim)
2025-03-21T20:31:43.3836700Z             aten_permute_copy_default_47: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_436, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_436 = None
2025-03-21T20:31:43.3837621Z             quantized_decomposed_quantize_per_tensor_default_213: "i32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_47, 0.0005553436931222677, 30616, 0, 65535, torch.int32);  aten_permute_copy_default_47 = None
2025-03-21T20:31:43.3837725Z             
2025-03-21T20:31:43.3838303Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.3839450Z             quantized_decomposed_dequantize_per_tensor_default_438: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_213, 0.0005553436931222677, 30616, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_213 = None
2025-03-21T20:31:43.3839539Z             
2025-03-21T20:31:43.3840205Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:345 in update, code: k_out = torch.ops.aten.index_put_(self.past_k_caches, [None, input_pos], k_val)
2025-03-21T20:31:43.3841532Z             aten_index_put_default_2: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_index_put_default(quantized_decomposed_dequantize_per_tensor_default_116, [None, attn_options_input_pos], quantized_decomposed_dequantize_per_tensor_default_437);  quantized_decomposed_dequantize_per_tensor_default_116 = quantized_decomposed_dequantize_per_tensor_default_437 = None
2025-03-21T20:31:43.3842486Z             quantized_decomposed_quantize_per_tensor_default_214: "i32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_put_default_2, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_index_put_default_2 = None
2025-03-21T20:31:43.3842577Z             
2025-03-21T20:31:43.3843405Z              # File: <eval_with_key>.50:1051 in forward, code: dequantize_per_tensor_default_364 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_364, 0.00035046463017351925, 33692, 0, 65535, torch.int32)
2025-03-21T20:31:43.3844338Z             quantized_decomposed_dequantize_per_tensor_default_439: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_214, 0.00035046463017351925, 33692, 0, 65535, torch.int32)
2025-03-21T20:31:43.3844427Z             
2025-03-21T20:31:43.3845100Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.3846021Z             quantized_decomposed_dequantize_per_tensor_default_440: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_214, 0.00035046463017351925, 33692, 0, 65535, torch.int32)
2025-03-21T20:31:43.3846948Z             quantized_decomposed_dequantize_per_tensor_default_441: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_214, 0.00035046463017351925, 33692, 0, 65535, torch.int32)
2025-03-21T20:31:43.3847874Z             quantized_decomposed_dequantize_per_tensor_default_442: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_214, 0.00035046463017351925, 33692, 0, 65535, torch.int32)
2025-03-21T20:31:43.3848786Z             quantized_decomposed_dequantize_per_tensor_default_443: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_214, 0.00035046463017351925, 33692, 0, 65535, torch.int32)
2025-03-21T20:31:43.3849771Z             quantized_decomposed_dequantize_per_tensor_default_444: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_214, 0.00035046463017351925, 33692, 0, 65535, torch.int32)
2025-03-21T20:31:43.3850690Z             quantized_decomposed_dequantize_per_tensor_default_445: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_214, 0.00035046463017351925, 33692, 0, 65535, torch.int32)
2025-03-21T20:31:43.3851611Z             quantized_decomposed_dequantize_per_tensor_default_446: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_214, 0.00035046463017351925, 33692, 0, 65535, torch.int32)
2025-03-21T20:31:43.3852525Z             quantized_decomposed_dequantize_per_tensor_default_447: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_214, 0.00035046463017351925, 33692, 0, 65535, torch.int32)
2025-03-21T20:31:43.3853479Z             quantized_decomposed_dequantize_per_tensor_default_448: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_214, 0.00035046463017351925, 33692, 0, 65535, torch.int32)
2025-03-21T20:31:43.3854428Z             quantized_decomposed_dequantize_per_tensor_default_449: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_214, 0.00035046463017351925, 33692, 0, 65535, torch.int32)
2025-03-21T20:31:43.3855378Z             quantized_decomposed_dequantize_per_tensor_default_450: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_214, 0.00035046463017351925, 33692, 0, 65535, torch.int32)
2025-03-21T20:31:43.3856523Z             quantized_decomposed_dequantize_per_tensor_default_451: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_214, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_214 = None
2025-03-21T20:31:43.3856624Z             
2025-03-21T20:31:43.3857315Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:346 in update, code: v_out = torch.ops.aten.index_put_(self.past_v_caches, [None, input_pos], v_val)
2025-03-21T20:31:43.3858599Z             aten_index_put_default_3: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_index_put_default(quantized_decomposed_dequantize_per_tensor_default_117, [None, attn_options_input_pos], quantized_decomposed_dequantize_per_tensor_default_399);  quantized_decomposed_dequantize_per_tensor_default_117 = quantized_decomposed_dequantize_per_tensor_default_399 = None
2025-03-21T20:31:43.3859491Z             quantized_decomposed_quantize_per_tensor_default_215: "i32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_put_default_3, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_index_put_default_3 = None
2025-03-21T20:31:43.3859595Z             
2025-03-21T20:31:43.3860380Z              # File: <eval_with_key>.50:1066 in forward, code: dequantize_per_tensor_default_365 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_365, 8.02720314823091e-05, 34074, 0, 65535, torch.int32)
2025-03-21T20:31:43.3861308Z             quantized_decomposed_dequantize_per_tensor_default_452: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_215, 8.02720314823091e-05, 34074, 0, 65535, torch.int32)
2025-03-21T20:31:43.3861395Z             
2025-03-21T20:31:43.3862040Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.3862957Z             quantized_decomposed_dequantize_per_tensor_default_453: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_215, 8.02720314823091e-05, 34074, 0, 65535, torch.int32)
2025-03-21T20:31:43.3863879Z             quantized_decomposed_dequantize_per_tensor_default_454: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_215, 8.02720314823091e-05, 34074, 0, 65535, torch.int32)
2025-03-21T20:31:43.3864788Z             quantized_decomposed_dequantize_per_tensor_default_455: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_215, 8.02720314823091e-05, 34074, 0, 65535, torch.int32)
2025-03-21T20:31:43.3865731Z             quantized_decomposed_dequantize_per_tensor_default_456: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_215, 8.02720314823091e-05, 34074, 0, 65535, torch.int32)
2025-03-21T20:31:43.3866664Z             quantized_decomposed_dequantize_per_tensor_default_457: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_215, 8.02720314823091e-05, 34074, 0, 65535, torch.int32)
2025-03-21T20:31:43.3867603Z             quantized_decomposed_dequantize_per_tensor_default_458: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_215, 8.02720314823091e-05, 34074, 0, 65535, torch.int32)
2025-03-21T20:31:43.3868512Z             quantized_decomposed_dequantize_per_tensor_default_459: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_215, 8.02720314823091e-05, 34074, 0, 65535, torch.int32)
2025-03-21T20:31:43.3869436Z             quantized_decomposed_dequantize_per_tensor_default_460: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_215, 8.02720314823091e-05, 34074, 0, 65535, torch.int32)
2025-03-21T20:31:43.3870379Z             quantized_decomposed_dequantize_per_tensor_default_461: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_215, 8.02720314823091e-05, 34074, 0, 65535, torch.int32)
2025-03-21T20:31:43.3871286Z             quantized_decomposed_dequantize_per_tensor_default_462: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_215, 8.02720314823091e-05, 34074, 0, 65535, torch.int32)
2025-03-21T20:31:43.3872207Z             quantized_decomposed_dequantize_per_tensor_default_463: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_215, 8.02720314823091e-05, 34074, 0, 65535, torch.int32)
2025-03-21T20:31:43.3873339Z             quantized_decomposed_dequantize_per_tensor_default_464: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_215, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_215 = None
2025-03-21T20:31:43.3873442Z             
2025-03-21T20:31:43.3874075Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.3874882Z             aten_permute_copy_default_48: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_451, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_451 = None
2025-03-21T20:31:43.3875815Z             quantized_decomposed_quantize_per_tensor_default_216: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_48, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_permute_copy_default_48 = None
2025-03-21T20:31:43.3876976Z             quantized_decomposed_dequantize_per_tensor_default_465: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_216, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_216 = None
2025-03-21T20:31:43.3877756Z             aten_select_copy_int_48: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_465, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_465 = None
2025-03-21T20:31:43.3878661Z             quantized_decomposed_quantize_per_tensor_default_217: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_48, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_select_copy_int_48 = None
2025-03-21T20:31:43.3879819Z             quantized_decomposed_dequantize_per_tensor_default_466: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_217, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_217 = None
2025-03-21T20:31:43.3880559Z             aten_select_copy_int_49: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_466, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_466 = None
2025-03-21T20:31:43.3881442Z             quantized_decomposed_quantize_per_tensor_default_218: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_49, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_select_copy_int_49 = None
2025-03-21T20:31:43.3881569Z             
2025-03-21T20:31:43.3882506Z              # File: <eval_with_key>.50:1087 in forward, code: dequantize_per_tensor_default_368 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_368, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantize_per_tensor_default_368 = None
2025-03-21T20:31:43.3883662Z             quantized_decomposed_dequantize_per_tensor_default_467: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_218, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_218 = None
2025-03-21T20:31:43.3883751Z             
2025-03-21T20:31:43.3884402Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.3885194Z             aten_permute_copy_default_49: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_450, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_450 = None
2025-03-21T20:31:43.3886140Z             quantized_decomposed_quantize_per_tensor_default_219: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_49, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_permute_copy_default_49 = None
2025-03-21T20:31:43.3887287Z             quantized_decomposed_dequantize_per_tensor_default_468: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_219, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_219 = None
2025-03-21T20:31:43.3888035Z             aten_select_copy_int_50: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_468, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_468 = None
2025-03-21T20:31:43.3888924Z             quantized_decomposed_quantize_per_tensor_default_220: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_50, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_select_copy_int_50 = None
2025-03-21T20:31:43.3890217Z             quantized_decomposed_dequantize_per_tensor_default_469: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_220, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_220 = None
2025-03-21T20:31:43.3890974Z             aten_select_copy_int_51: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_469, 0, 1);  quantized_decomposed_dequantize_per_tensor_default_469 = None
2025-03-21T20:31:43.3891893Z             quantized_decomposed_quantize_per_tensor_default_221: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_51, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_select_copy_int_51 = None
2025-03-21T20:31:43.3891983Z             
2025-03-21T20:31:43.3892931Z              # File: <eval_with_key>.50:1096 in forward, code: dequantize_per_tensor_default_371 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_371, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantize_per_tensor_default_371 = None
2025-03-21T20:31:43.3894110Z             quantized_decomposed_dequantize_per_tensor_default_470: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_221, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_221 = None
2025-03-21T20:31:43.3894199Z             
2025-03-21T20:31:43.3894834Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.3895643Z             aten_permute_copy_default_50: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_449, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_449 = None
2025-03-21T20:31:43.3896577Z             quantized_decomposed_quantize_per_tensor_default_222: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_50, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_permute_copy_default_50 = None
2025-03-21T20:31:43.3897735Z             quantized_decomposed_dequantize_per_tensor_default_471: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_222, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_222 = None
2025-03-21T20:31:43.3898480Z             aten_select_copy_int_52: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_471, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_471 = None
2025-03-21T20:31:43.3899362Z             quantized_decomposed_quantize_per_tensor_default_223: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_52, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_select_copy_int_52 = None
2025-03-21T20:31:43.3900512Z             quantized_decomposed_dequantize_per_tensor_default_472: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_223, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_223 = None
2025-03-21T20:31:43.3901235Z             aten_select_copy_int_53: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_472, 0, 2);  quantized_decomposed_dequantize_per_tensor_default_472 = None
2025-03-21T20:31:43.3902194Z             quantized_decomposed_quantize_per_tensor_default_224: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_53, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_select_copy_int_53 = None
2025-03-21T20:31:43.3902284Z             
2025-03-21T20:31:43.3903250Z              # File: <eval_with_key>.50:1105 in forward, code: dequantize_per_tensor_default_374 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_374, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantize_per_tensor_default_374 = None
2025-03-21T20:31:43.3904386Z             quantized_decomposed_dequantize_per_tensor_default_473: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_224, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_224 = None
2025-03-21T20:31:43.3904490Z             
2025-03-21T20:31:43.3905124Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.3905950Z             aten_permute_copy_default_51: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_448, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_448 = None
2025-03-21T20:31:43.3906886Z             quantized_decomposed_quantize_per_tensor_default_225: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_51, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_permute_copy_default_51 = None
2025-03-21T20:31:43.3908045Z             quantized_decomposed_dequantize_per_tensor_default_474: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_225, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_225 = None
2025-03-21T20:31:43.3908793Z             aten_select_copy_int_54: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_474, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_474 = None
2025-03-21T20:31:43.3909828Z             quantized_decomposed_quantize_per_tensor_default_226: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_54, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_select_copy_int_54 = None
2025-03-21T20:31:43.3910976Z             quantized_decomposed_dequantize_per_tensor_default_475: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_226, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_226 = None
2025-03-21T20:31:43.3911716Z             aten_select_copy_int_55: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_475, 0, 3);  quantized_decomposed_dequantize_per_tensor_default_475 = None
2025-03-21T20:31:43.3912603Z             quantized_decomposed_quantize_per_tensor_default_227: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_55, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_select_copy_int_55 = None
2025-03-21T20:31:43.3912707Z             
2025-03-21T20:31:43.3913670Z              # File: <eval_with_key>.50:1114 in forward, code: dequantize_per_tensor_default_377 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_377, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantize_per_tensor_default_377 = None
2025-03-21T20:31:43.3914842Z             quantized_decomposed_dequantize_per_tensor_default_476: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_227, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_227 = None
2025-03-21T20:31:43.3914933Z             
2025-03-21T20:31:43.3915603Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.3916396Z             aten_permute_copy_default_52: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_447, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_447 = None
2025-03-21T20:31:43.3917343Z             quantized_decomposed_quantize_per_tensor_default_228: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_52, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_permute_copy_default_52 = None
2025-03-21T20:31:43.3918511Z             quantized_decomposed_dequantize_per_tensor_default_477: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_228, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_228 = None
2025-03-21T20:31:43.3919249Z             aten_select_copy_int_56: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_477, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_477 = None
2025-03-21T20:31:43.3920137Z             quantized_decomposed_quantize_per_tensor_default_229: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_56, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_select_copy_int_56 = None
2025-03-21T20:31:43.3921285Z             quantized_decomposed_dequantize_per_tensor_default_478: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_229, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_229 = None
2025-03-21T20:31:43.3922024Z             aten_select_copy_int_57: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_478, 0, 4);  quantized_decomposed_dequantize_per_tensor_default_478 = None
2025-03-21T20:31:43.3922907Z             quantized_decomposed_quantize_per_tensor_default_230: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_57, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_select_copy_int_57 = None
2025-03-21T20:31:43.3923014Z             
2025-03-21T20:31:43.3923943Z              # File: <eval_with_key>.50:1123 in forward, code: dequantize_per_tensor_default_380 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_380, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantize_per_tensor_default_380 = None
2025-03-21T20:31:43.3925090Z             quantized_decomposed_dequantize_per_tensor_default_479: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_230, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_230 = None
2025-03-21T20:31:43.3925176Z             
2025-03-21T20:31:43.3925837Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.3926665Z             aten_permute_copy_default_53: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_446, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_446 = None
2025-03-21T20:31:43.3927636Z             quantized_decomposed_quantize_per_tensor_default_231: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_53, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_permute_copy_default_53 = None
2025-03-21T20:31:43.3928790Z             quantized_decomposed_dequantize_per_tensor_default_480: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_231, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_231 = None
2025-03-21T20:31:43.3929623Z             aten_select_copy_int_58: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_480, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_480 = None
2025-03-21T20:31:43.3930544Z             quantized_decomposed_quantize_per_tensor_default_232: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_58, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_select_copy_int_58 = None
2025-03-21T20:31:43.3931694Z             quantized_decomposed_dequantize_per_tensor_default_481: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_232, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_232 = None
2025-03-21T20:31:43.3932571Z             aten_select_copy_int_59: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_481, 0, 5);  quantized_decomposed_dequantize_per_tensor_default_481 = None
2025-03-21T20:31:43.3933474Z             quantized_decomposed_quantize_per_tensor_default_233: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_59, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_select_copy_int_59 = None
2025-03-21T20:31:43.3933563Z             
2025-03-21T20:31:43.3934511Z              # File: <eval_with_key>.50:1132 in forward, code: dequantize_per_tensor_default_383 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_383, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantize_per_tensor_default_383 = None
2025-03-21T20:31:43.3935653Z             quantized_decomposed_dequantize_per_tensor_default_482: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_233, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_233 = None
2025-03-21T20:31:43.3935761Z             
2025-03-21T20:31:43.3936394Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.3937196Z             aten_permute_copy_default_54: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_445, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_445 = None
2025-03-21T20:31:43.3938196Z             quantized_decomposed_quantize_per_tensor_default_234: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_54, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_permute_copy_default_54 = None
2025-03-21T20:31:43.3939381Z             quantized_decomposed_dequantize_per_tensor_default_483: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_234, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_234 = None
2025-03-21T20:31:43.3940150Z             aten_select_copy_int_60: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_483, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_483 = None
2025-03-21T20:31:43.3941051Z             quantized_decomposed_quantize_per_tensor_default_235: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_60, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_select_copy_int_60 = None
2025-03-21T20:31:43.3942191Z             quantized_decomposed_dequantize_per_tensor_default_484: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_235, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_235 = None
2025-03-21T20:31:43.3942973Z             aten_select_copy_int_61: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_484, 0, 6);  quantized_decomposed_dequantize_per_tensor_default_484 = None
2025-03-21T20:31:43.3943850Z             quantized_decomposed_quantize_per_tensor_default_236: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_61, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_select_copy_int_61 = None
2025-03-21T20:31:43.3943956Z             
2025-03-21T20:31:43.3944889Z              # File: <eval_with_key>.50:1141 in forward, code: dequantize_per_tensor_default_386 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_386, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantize_per_tensor_default_386 = None
2025-03-21T20:31:43.3946039Z             quantized_decomposed_dequantize_per_tensor_default_485: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_236, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_236 = None
2025-03-21T20:31:43.3946127Z             
2025-03-21T20:31:43.3946771Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.3947564Z             aten_permute_copy_default_55: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_444, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_444 = None
2025-03-21T20:31:43.3948508Z             quantized_decomposed_quantize_per_tensor_default_237: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_55, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_permute_copy_default_55 = None
2025-03-21T20:31:43.3949649Z             quantized_decomposed_dequantize_per_tensor_default_486: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_237, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_237 = None
2025-03-21T20:31:43.3950413Z             aten_select_copy_int_62: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_486, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_486 = None
2025-03-21T20:31:43.3951326Z             quantized_decomposed_quantize_per_tensor_default_238: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_62, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_select_copy_int_62 = None
2025-03-21T20:31:43.3952500Z             quantized_decomposed_dequantize_per_tensor_default_487: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_238, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_238 = None
2025-03-21T20:31:43.3953237Z             aten_select_copy_int_63: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_487, 0, 7);  quantized_decomposed_dequantize_per_tensor_default_487 = None
2025-03-21T20:31:43.3954121Z             quantized_decomposed_quantize_per_tensor_default_239: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_63, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_select_copy_int_63 = None
2025-03-21T20:31:43.3954247Z             
2025-03-21T20:31:43.3955177Z              # File: <eval_with_key>.50:1150 in forward, code: dequantize_per_tensor_default_389 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_389, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantize_per_tensor_default_389 = None
2025-03-21T20:31:43.3956326Z             quantized_decomposed_dequantize_per_tensor_default_488: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_239, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_239 = None
2025-03-21T20:31:43.3956419Z             
2025-03-21T20:31:43.3957051Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.3957855Z             aten_permute_copy_default_56: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_443, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_443 = None
2025-03-21T20:31:43.3958797Z             quantized_decomposed_quantize_per_tensor_default_240: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_56, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_permute_copy_default_56 = None
2025-03-21T20:31:43.3959939Z             quantized_decomposed_dequantize_per_tensor_default_489: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_240, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_240 = None
2025-03-21T20:31:43.3960682Z             aten_select_copy_int_64: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_489, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_489 = None
2025-03-21T20:31:43.3961566Z             quantized_decomposed_quantize_per_tensor_default_241: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_64, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_select_copy_int_64 = None
2025-03-21T20:31:43.3962738Z             quantized_decomposed_dequantize_per_tensor_default_490: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_241, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_241 = None
2025-03-21T20:31:43.3963481Z             aten_select_copy_int_65: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_490, 0, 8);  quantized_decomposed_dequantize_per_tensor_default_490 = None
2025-03-21T20:31:43.3964398Z             quantized_decomposed_quantize_per_tensor_default_242: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_65, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_select_copy_int_65 = None
2025-03-21T20:31:43.3964486Z             
2025-03-21T20:31:43.3965429Z              # File: <eval_with_key>.50:1159 in forward, code: dequantize_per_tensor_default_392 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_392, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantize_per_tensor_default_392 = None
2025-03-21T20:31:43.3966584Z             quantized_decomposed_dequantize_per_tensor_default_491: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_242, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_242 = None
2025-03-21T20:31:43.3966684Z             
2025-03-21T20:31:43.3967318Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.3968123Z             aten_permute_copy_default_57: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_442, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_442 = None
2025-03-21T20:31:43.3969057Z             quantized_decomposed_quantize_per_tensor_default_243: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_57, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_permute_copy_default_57 = None
2025-03-21T20:31:43.3970288Z             quantized_decomposed_dequantize_per_tensor_default_492: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_243, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_243 = None
2025-03-21T20:31:43.3971027Z             aten_select_copy_int_66: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_492, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_492 = None
2025-03-21T20:31:43.3971927Z             quantized_decomposed_quantize_per_tensor_default_244: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_66, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_select_copy_int_66 = None
2025-03-21T20:31:43.3973078Z             quantized_decomposed_dequantize_per_tensor_default_493: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_244, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_244 = None
2025-03-21T20:31:43.3973816Z             aten_select_copy_int_67: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_493, 0, 9);  quantized_decomposed_dequantize_per_tensor_default_493 = None
2025-03-21T20:31:43.3974748Z             quantized_decomposed_quantize_per_tensor_default_245: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_67, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_select_copy_int_67 = None
2025-03-21T20:31:43.3974853Z             
2025-03-21T20:31:43.3975781Z              # File: <eval_with_key>.50:1168 in forward, code: dequantize_per_tensor_default_395 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_395, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantize_per_tensor_default_395 = None
2025-03-21T20:31:43.3976951Z             quantized_decomposed_dequantize_per_tensor_default_494: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_245, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_245 = None
2025-03-21T20:31:43.3977042Z             
2025-03-21T20:31:43.3977689Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.3978510Z             aten_permute_copy_default_58: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_441, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_441 = None
2025-03-21T20:31:43.3979459Z             quantized_decomposed_quantize_per_tensor_default_246: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_58, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_permute_copy_default_58 = None
2025-03-21T20:31:43.3980600Z             quantized_decomposed_dequantize_per_tensor_default_495: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_246, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_246 = None
2025-03-21T20:31:43.3981348Z             aten_select_copy_int_68: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_495, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_495 = None
2025-03-21T20:31:43.3982231Z             quantized_decomposed_quantize_per_tensor_default_247: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_68, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_select_copy_int_68 = None
2025-03-21T20:31:43.3983378Z             quantized_decomposed_dequantize_per_tensor_default_496: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_247, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_247 = None
2025-03-21T20:31:43.3984115Z             aten_select_copy_int_69: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_496, 0, 10);  quantized_decomposed_dequantize_per_tensor_default_496 = None
2025-03-21T20:31:43.3984995Z             quantized_decomposed_quantize_per_tensor_default_248: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_69, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_select_copy_int_69 = None
2025-03-21T20:31:43.3985096Z             
2025-03-21T20:31:43.3986048Z              # File: <eval_with_key>.50:1177 in forward, code: dequantize_per_tensor_default_398 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_398, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantize_per_tensor_default_398 = None
2025-03-21T20:31:43.3987221Z             quantized_decomposed_dequantize_per_tensor_default_497: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_248, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_248 = None
2025-03-21T20:31:43.3987310Z             
2025-03-21T20:31:43.3988016Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.3988806Z             aten_permute_copy_default_59: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_440, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_440 = None
2025-03-21T20:31:43.3989753Z             quantized_decomposed_quantize_per_tensor_default_249: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_59, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_permute_copy_default_59 = None
2025-03-21T20:31:43.3990916Z             quantized_decomposed_dequantize_per_tensor_default_498: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_249, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_249 = None
2025-03-21T20:31:43.3991657Z             aten_select_copy_int_70: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_498, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_498 = None
2025-03-21T20:31:43.3992545Z             quantized_decomposed_quantize_per_tensor_default_250: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_70, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_select_copy_int_70 = None
2025-03-21T20:31:43.3993696Z             quantized_decomposed_dequantize_per_tensor_default_499: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_250, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_250 = None
2025-03-21T20:31:43.3994425Z             aten_select_copy_int_71: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_499, 0, 11);  quantized_decomposed_dequantize_per_tensor_default_499 = None
2025-03-21T20:31:43.3995319Z             quantized_decomposed_quantize_per_tensor_default_251: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_71, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_select_copy_int_71 = None
2025-03-21T20:31:43.3995411Z             
2025-03-21T20:31:43.3996363Z              # File: <eval_with_key>.50:1186 in forward, code: dequantize_per_tensor_default_401 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_401, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantize_per_tensor_default_401 = None
2025-03-21T20:31:43.3997504Z             quantized_decomposed_dequantize_per_tensor_default_500: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_251, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_251 = None
2025-03-21T20:31:43.3997608Z             
2025-03-21T20:31:43.3998267Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4003861Z             aten_cat_default_6: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_aten_cat_default([quantized_decomposed_dequantize_per_tensor_default_467, quantized_decomposed_dequantize_per_tensor_default_470, quantized_decomposed_dequantize_per_tensor_default_473, quantized_decomposed_dequantize_per_tensor_default_476, quantized_decomposed_dequantize_per_tensor_default_479, quantized_decomposed_dequantize_per_tensor_default_482, quantized_decomposed_dequantize_per_tensor_default_485, quantized_decomposed_dequantize_per_tensor_default_488, quantized_decomposed_dequantize_per_tensor_default_491, quantized_decomposed_dequantize_per_tensor_default_494, quantized_decomposed_dequantize_per_tensor_default_497, quantized_decomposed_dequantize_per_tensor_default_500]);  quantized_decomposed_dequantize_per_tensor_default_467 = quantized_decomposed_dequantize_per_tensor_default_470 = quantized_decomposed_dequantize_per_tensor_default_473 = quantized_decomposed_dequantize_per_tensor_default_476 = quantized_decomposed_dequantize_per_tensor_default_479 = quantized_decomposed_dequantize_per_tensor_default_482 = quantized_decomposed_dequantize_per_tensor_default_485 = quantized_decomposed_dequantize_per_tensor_default_488 = quantized_decomposed_dequantize_per_tensor_default_491 = quantized_decomposed_dequantize_per_tensor_default_494 = quantized_decomposed_dequantize_per_tensor_default_497 = quantized_decomposed_dequantize_per_tensor_default_500 = None
2025-03-21T20:31:43.4004773Z             quantized_decomposed_quantize_per_tensor_default_252: "i32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_6, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_cat_default_6 = None
2025-03-21T20:31:43.4005914Z             quantized_decomposed_dequantize_per_tensor_default_501: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_252, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_252 = None
2025-03-21T20:31:43.4006701Z             aten_view_copy_default_27: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_501, [1, 12, 128, 64]);  quantized_decomposed_dequantize_per_tensor_default_501 = None
2025-03-21T20:31:43.4007610Z             quantized_decomposed_quantize_per_tensor_default_253: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_27, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_view_copy_default_27 = None
2025-03-21T20:31:43.4007713Z             
2025-03-21T20:31:43.4008294Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.4009514Z             quantized_decomposed_dequantize_per_tensor_default_502: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_253, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_253 = None
2025-03-21T20:31:43.4009609Z             
2025-03-21T20:31:43.4010268Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4011326Z             aten_permute_copy_default_60: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_464, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_464 = None
2025-03-21T20:31:43.4012315Z             quantized_decomposed_quantize_per_tensor_default_254: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_60, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_permute_copy_default_60 = None
2025-03-21T20:31:43.4013475Z             quantized_decomposed_dequantize_per_tensor_default_503: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_254, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_254 = None
2025-03-21T20:31:43.4014249Z             aten_select_copy_int_72: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_503, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_503 = None
2025-03-21T20:31:43.4015140Z             quantized_decomposed_quantize_per_tensor_default_255: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_72, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_select_copy_int_72 = None
2025-03-21T20:31:43.4016287Z             quantized_decomposed_dequantize_per_tensor_default_504: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_255, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_255 = None
2025-03-21T20:31:43.4017041Z             aten_select_copy_int_73: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_504, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_504 = None
2025-03-21T20:31:43.4017927Z             quantized_decomposed_quantize_per_tensor_default_256: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_73, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_select_copy_int_73 = None
2025-03-21T20:31:43.4018020Z             
2025-03-21T20:31:43.4018956Z              # File: <eval_with_key>.50:1201 in forward, code: dequantize_per_tensor_default_406 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_406, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantize_per_tensor_default_406 = None
2025-03-21T20:31:43.4020083Z             quantized_decomposed_dequantize_per_tensor_default_505: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_256, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_256 = None
2025-03-21T20:31:43.4020186Z             
2025-03-21T20:31:43.4020826Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4021630Z             aten_permute_copy_default_61: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_463, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_463 = None
2025-03-21T20:31:43.4022555Z             quantized_decomposed_quantize_per_tensor_default_257: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_61, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_permute_copy_default_61 = None
2025-03-21T20:31:43.4023690Z             quantized_decomposed_dequantize_per_tensor_default_506: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_257, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_257 = None
2025-03-21T20:31:43.4024470Z             aten_select_copy_int_74: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_506, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_506 = None
2025-03-21T20:31:43.4025362Z             quantized_decomposed_quantize_per_tensor_default_258: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_74, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_select_copy_int_74 = None
2025-03-21T20:31:43.4026520Z             quantized_decomposed_dequantize_per_tensor_default_507: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_258, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_258 = None
2025-03-21T20:31:43.4027249Z             aten_select_copy_int_75: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_507, 0, 1);  quantized_decomposed_dequantize_per_tensor_default_507 = None
2025-03-21T20:31:43.4028158Z             quantized_decomposed_quantize_per_tensor_default_259: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_75, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_select_copy_int_75 = None
2025-03-21T20:31:43.4028245Z             
2025-03-21T20:31:43.4029178Z              # File: <eval_with_key>.50:1210 in forward, code: dequantize_per_tensor_default_409 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_409, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantize_per_tensor_default_409 = None
2025-03-21T20:31:43.4030304Z             quantized_decomposed_dequantize_per_tensor_default_508: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_259, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_259 = None
2025-03-21T20:31:43.4030407Z             
2025-03-21T20:31:43.4031045Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4031836Z             aten_permute_copy_default_62: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_462, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_462 = None
2025-03-21T20:31:43.4032940Z             quantized_decomposed_quantize_per_tensor_default_260: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_62, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_permute_copy_default_62 = None
2025-03-21T20:31:43.4034085Z             quantized_decomposed_dequantize_per_tensor_default_509: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_260, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_260 = None
2025-03-21T20:31:43.4034817Z             aten_select_copy_int_76: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_509, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_509 = None
2025-03-21T20:31:43.4035706Z             quantized_decomposed_quantize_per_tensor_default_261: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_76, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_select_copy_int_76 = None
2025-03-21T20:31:43.4036938Z             quantized_decomposed_dequantize_per_tensor_default_510: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_261, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_261 = None
2025-03-21T20:31:43.4037679Z             aten_select_copy_int_77: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_510, 0, 2);  quantized_decomposed_dequantize_per_tensor_default_510 = None
2025-03-21T20:31:43.4038583Z             quantized_decomposed_quantize_per_tensor_default_262: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_77, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_select_copy_int_77 = None
2025-03-21T20:31:43.4038685Z             
2025-03-21T20:31:43.4039611Z              # File: <eval_with_key>.50:1219 in forward, code: dequantize_per_tensor_default_412 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_412, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantize_per_tensor_default_412 = None
2025-03-21T20:31:43.4040782Z             quantized_decomposed_dequantize_per_tensor_default_511: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_262, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_262 = None
2025-03-21T20:31:43.4040871Z             
2025-03-21T20:31:43.4041520Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4042308Z             aten_permute_copy_default_63: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_461, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_461 = None
2025-03-21T20:31:43.4043239Z             quantized_decomposed_quantize_per_tensor_default_263: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_63, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_permute_copy_default_63 = None
2025-03-21T20:31:43.4044374Z             quantized_decomposed_dequantize_per_tensor_default_512: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_263, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_263 = None
2025-03-21T20:31:43.4045111Z             aten_select_copy_int_78: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_512, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_512 = None
2025-03-21T20:31:43.4045985Z             quantized_decomposed_quantize_per_tensor_default_264: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_78, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_select_copy_int_78 = None
2025-03-21T20:31:43.4047126Z             quantized_decomposed_dequantize_per_tensor_default_513: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_264, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_264 = None
2025-03-21T20:31:43.4047873Z             aten_select_copy_int_79: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_513, 0, 3);  quantized_decomposed_dequantize_per_tensor_default_513 = None
2025-03-21T20:31:43.4048785Z             quantized_decomposed_quantize_per_tensor_default_265: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_79, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_select_copy_int_79 = None
2025-03-21T20:31:43.4048873Z             
2025-03-21T20:31:43.4049902Z              # File: <eval_with_key>.50:1228 in forward, code: dequantize_per_tensor_default_415 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_415, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantize_per_tensor_default_415 = None
2025-03-21T20:31:43.4051030Z             quantized_decomposed_dequantize_per_tensor_default_514: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_265, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_265 = None
2025-03-21T20:31:43.4051132Z             
2025-03-21T20:31:43.4051767Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4052593Z             aten_permute_copy_default_64: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_460, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_460 = None
2025-03-21T20:31:43.4053513Z             quantized_decomposed_quantize_per_tensor_default_266: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_64, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_permute_copy_default_64 = None
2025-03-21T20:31:43.4054652Z             quantized_decomposed_dequantize_per_tensor_default_515: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_266, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_266 = None
2025-03-21T20:31:43.4055386Z             aten_select_copy_int_80: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_515, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_515 = None
2025-03-21T20:31:43.4056277Z             quantized_decomposed_quantize_per_tensor_default_267: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_80, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_select_copy_int_80 = None
2025-03-21T20:31:43.4057413Z             quantized_decomposed_dequantize_per_tensor_default_516: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_267, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_267 = None
2025-03-21T20:31:43.4058137Z             aten_select_copy_int_81: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_516, 0, 4);  quantized_decomposed_dequantize_per_tensor_default_516 = None
2025-03-21T20:31:43.4059016Z             quantized_decomposed_quantize_per_tensor_default_268: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_81, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_select_copy_int_81 = None
2025-03-21T20:31:43.4059103Z             
2025-03-21T20:31:43.4060058Z              # File: <eval_with_key>.50:1237 in forward, code: dequantize_per_tensor_default_418 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_418, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantize_per_tensor_default_418 = None
2025-03-21T20:31:43.4061205Z             quantized_decomposed_dequantize_per_tensor_default_517: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_268, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_268 = None
2025-03-21T20:31:43.4061305Z             
2025-03-21T20:31:43.4061963Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4062748Z             aten_permute_copy_default_65: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_459, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_459 = None
2025-03-21T20:31:43.4063682Z             quantized_decomposed_quantize_per_tensor_default_269: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_65, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_permute_copy_default_65 = None
2025-03-21T20:31:43.4064843Z             quantized_decomposed_dequantize_per_tensor_default_518: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_269, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_269 = None
2025-03-21T20:31:43.4065569Z             aten_select_copy_int_82: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_518, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_518 = None
2025-03-21T20:31:43.4066455Z             quantized_decomposed_quantize_per_tensor_default_270: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_82, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_select_copy_int_82 = None
2025-03-21T20:31:43.4067585Z             quantized_decomposed_dequantize_per_tensor_default_519: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_270, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_270 = None
2025-03-21T20:31:43.4068322Z             aten_select_copy_int_83: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_519, 0, 5);  quantized_decomposed_dequantize_per_tensor_default_519 = None
2025-03-21T20:31:43.4069195Z             quantized_decomposed_quantize_per_tensor_default_271: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_83, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_select_copy_int_83 = None
2025-03-21T20:31:43.4069297Z             
2025-03-21T20:31:43.4070215Z              # File: <eval_with_key>.50:1246 in forward, code: dequantize_per_tensor_default_421 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_421, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantize_per_tensor_default_421 = None
2025-03-21T20:31:43.4071354Z             quantized_decomposed_dequantize_per_tensor_default_520: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_271, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_271 = None
2025-03-21T20:31:43.4071445Z             
2025-03-21T20:31:43.4072117Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4072935Z             aten_permute_copy_default_66: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_458, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_458 = None
2025-03-21T20:31:43.4073890Z             quantized_decomposed_quantize_per_tensor_default_272: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_66, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_permute_copy_default_66 = None
2025-03-21T20:31:43.4075021Z             quantized_decomposed_dequantize_per_tensor_default_521: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_272, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_272 = None
2025-03-21T20:31:43.4075761Z             aten_select_copy_int_84: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_521, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_521 = None
2025-03-21T20:31:43.4076661Z             quantized_decomposed_quantize_per_tensor_default_273: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_84, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_select_copy_int_84 = None
2025-03-21T20:31:43.4077797Z             quantized_decomposed_dequantize_per_tensor_default_522: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_273, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_273 = None
2025-03-21T20:31:43.4078523Z             aten_select_copy_int_85: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_522, 0, 6);  quantized_decomposed_dequantize_per_tensor_default_522 = None
2025-03-21T20:31:43.4079407Z             quantized_decomposed_quantize_per_tensor_default_274: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_85, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_select_copy_int_85 = None
2025-03-21T20:31:43.4079500Z             
2025-03-21T20:31:43.4080429Z              # File: <eval_with_key>.50:1255 in forward, code: dequantize_per_tensor_default_424 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_424, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantize_per_tensor_default_424 = None
2025-03-21T20:31:43.4081550Z             quantized_decomposed_dequantize_per_tensor_default_523: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_274, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_274 = None
2025-03-21T20:31:43.4081656Z             
2025-03-21T20:31:43.4082291Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4083094Z             aten_permute_copy_default_67: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_457, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_457 = None
2025-03-21T20:31:43.4084045Z             quantized_decomposed_quantize_per_tensor_default_275: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_67, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_permute_copy_default_67 = None
2025-03-21T20:31:43.4085204Z             quantized_decomposed_dequantize_per_tensor_default_524: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_275, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_275 = None
2025-03-21T20:31:43.4085958Z             aten_select_copy_int_86: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_524, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_524 = None
2025-03-21T20:31:43.4086847Z             quantized_decomposed_quantize_per_tensor_default_276: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_86, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_select_copy_int_86 = None
2025-03-21T20:31:43.4087982Z             quantized_decomposed_dequantize_per_tensor_default_525: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_276, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_276 = None
2025-03-21T20:31:43.4088726Z             aten_select_copy_int_87: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_525, 0, 7);  quantized_decomposed_dequantize_per_tensor_default_525 = None
2025-03-21T20:31:43.4089673Z             quantized_decomposed_quantize_per_tensor_default_277: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_87, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_select_copy_int_87 = None
2025-03-21T20:31:43.4089776Z             
2025-03-21T20:31:43.4090711Z              # File: <eval_with_key>.50:1264 in forward, code: dequantize_per_tensor_default_427 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_427, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantize_per_tensor_default_427 = None
2025-03-21T20:31:43.4091836Z             quantized_decomposed_dequantize_per_tensor_default_526: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_277, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_277 = None
2025-03-21T20:31:43.4091938Z             
2025-03-21T20:31:43.4092575Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4093383Z             aten_permute_copy_default_68: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_456, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_456 = None
2025-03-21T20:31:43.4094300Z             quantized_decomposed_quantize_per_tensor_default_278: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_68, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_permute_copy_default_68 = None
2025-03-21T20:31:43.4095444Z             quantized_decomposed_dequantize_per_tensor_default_527: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_278, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_278 = None
2025-03-21T20:31:43.4096207Z             aten_select_copy_int_88: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_527, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_527 = None
2025-03-21T20:31:43.4097126Z             quantized_decomposed_quantize_per_tensor_default_279: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_88, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_select_copy_int_88 = None
2025-03-21T20:31:43.4098272Z             quantized_decomposed_dequantize_per_tensor_default_528: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_279, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_279 = None
2025-03-21T20:31:43.4099009Z             aten_select_copy_int_89: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_528, 0, 8);  quantized_decomposed_dequantize_per_tensor_default_528 = None
2025-03-21T20:31:43.4099880Z             quantized_decomposed_quantize_per_tensor_default_280: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_89, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_select_copy_int_89 = None
2025-03-21T20:31:43.4100001Z             
2025-03-21T20:31:43.4100914Z              # File: <eval_with_key>.50:1273 in forward, code: dequantize_per_tensor_default_430 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_430, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantize_per_tensor_default_430 = None
2025-03-21T20:31:43.4102049Z             quantized_decomposed_dequantize_per_tensor_default_529: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_280, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_280 = None
2025-03-21T20:31:43.4102137Z             
2025-03-21T20:31:43.4102781Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4103571Z             aten_permute_copy_default_69: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_455, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_455 = None
2025-03-21T20:31:43.4104500Z             quantized_decomposed_quantize_per_tensor_default_281: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_69, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_permute_copy_default_69 = None
2025-03-21T20:31:43.4105626Z             quantized_decomposed_dequantize_per_tensor_default_530: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_281, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_281 = None
2025-03-21T20:31:43.4106367Z             aten_select_copy_int_90: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_530, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_530 = None
2025-03-21T20:31:43.4107240Z             quantized_decomposed_quantize_per_tensor_default_282: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_90, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_select_copy_int_90 = None
2025-03-21T20:31:43.4108398Z             quantized_decomposed_dequantize_per_tensor_default_531: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_282, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_282 = None
2025-03-21T20:31:43.4109144Z             aten_select_copy_int_91: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_531, 0, 9);  quantized_decomposed_dequantize_per_tensor_default_531 = None
2025-03-21T20:31:43.4110054Z             quantized_decomposed_quantize_per_tensor_default_283: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_91, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_select_copy_int_91 = None
2025-03-21T20:31:43.4110146Z             
2025-03-21T20:31:43.4111077Z              # File: <eval_with_key>.50:1282 in forward, code: dequantize_per_tensor_default_433 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_433, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantize_per_tensor_default_433 = None
2025-03-21T20:31:43.4112232Z             quantized_decomposed_dequantize_per_tensor_default_532: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_283, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_283 = None
2025-03-21T20:31:43.4112438Z             
2025-03-21T20:31:43.4113102Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4113910Z             aten_permute_copy_default_70: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_454, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_454 = None
2025-03-21T20:31:43.4114834Z             quantized_decomposed_quantize_per_tensor_default_284: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_70, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_permute_copy_default_70 = None
2025-03-21T20:31:43.4115982Z             quantized_decomposed_dequantize_per_tensor_default_533: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_284, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_284 = None
2025-03-21T20:31:43.4116715Z             aten_select_copy_int_92: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_533, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_533 = None
2025-03-21T20:31:43.4117615Z             quantized_decomposed_quantize_per_tensor_default_285: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_92, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_select_copy_int_92 = None
2025-03-21T20:31:43.4118757Z             quantized_decomposed_dequantize_per_tensor_default_534: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_285, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_285 = None
2025-03-21T20:31:43.4119482Z             aten_select_copy_int_93: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_534, 0, 10);  quantized_decomposed_dequantize_per_tensor_default_534 = None
2025-03-21T20:31:43.4120399Z             quantized_decomposed_quantize_per_tensor_default_286: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_93, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_select_copy_int_93 = None
2025-03-21T20:31:43.4120514Z             
2025-03-21T20:31:43.4121446Z              # File: <eval_with_key>.50:1291 in forward, code: dequantize_per_tensor_default_436 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_436, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantize_per_tensor_default_436 = None
2025-03-21T20:31:43.4122594Z             quantized_decomposed_dequantize_per_tensor_default_535: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_286, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_286 = None
2025-03-21T20:31:43.4122699Z             
2025-03-21T20:31:43.4123338Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4124143Z             aten_permute_copy_default_71: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_453, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_453 = None
2025-03-21T20:31:43.4125099Z             quantized_decomposed_quantize_per_tensor_default_287: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_71, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_permute_copy_default_71 = None
2025-03-21T20:31:43.4126241Z             quantized_decomposed_dequantize_per_tensor_default_536: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_287, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_287 = None
2025-03-21T20:31:43.4126971Z             aten_select_copy_int_94: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_536, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_536 = None
2025-03-21T20:31:43.4127855Z             quantized_decomposed_quantize_per_tensor_default_288: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_94, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_select_copy_int_94 = None
2025-03-21T20:31:43.4128979Z             quantized_decomposed_dequantize_per_tensor_default_537: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_288, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_288 = None
2025-03-21T20:31:43.4129790Z             aten_select_copy_int_95: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_537, 0, 11);  quantized_decomposed_dequantize_per_tensor_default_537 = None
2025-03-21T20:31:43.4130667Z             quantized_decomposed_quantize_per_tensor_default_289: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_95, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_select_copy_int_95 = None
2025-03-21T20:31:43.4130769Z             
2025-03-21T20:31:43.4131689Z              # File: <eval_with_key>.50:1300 in forward, code: dequantize_per_tensor_default_439 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_439, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantize_per_tensor_default_439 = None
2025-03-21T20:31:43.4133086Z             quantized_decomposed_dequantize_per_tensor_default_538: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_289, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_289 = None
2025-03-21T20:31:43.4133182Z             
2025-03-21T20:31:43.4133833Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4139264Z             aten_cat_default_7: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_aten_cat_default([quantized_decomposed_dequantize_per_tensor_default_505, quantized_decomposed_dequantize_per_tensor_default_508, quantized_decomposed_dequantize_per_tensor_default_511, quantized_decomposed_dequantize_per_tensor_default_514, quantized_decomposed_dequantize_per_tensor_default_517, quantized_decomposed_dequantize_per_tensor_default_520, quantized_decomposed_dequantize_per_tensor_default_523, quantized_decomposed_dequantize_per_tensor_default_526, quantized_decomposed_dequantize_per_tensor_default_529, quantized_decomposed_dequantize_per_tensor_default_532, quantized_decomposed_dequantize_per_tensor_default_535, quantized_decomposed_dequantize_per_tensor_default_538]);  quantized_decomposed_dequantize_per_tensor_default_505 = quantized_decomposed_dequantize_per_tensor_default_508 = quantized_decomposed_dequantize_per_tensor_default_511 = quantized_decomposed_dequantize_per_tensor_default_514 = quantized_decomposed_dequantize_per_tensor_default_517 = quantized_decomposed_dequantize_per_tensor_default_520 = quantized_decomposed_dequantize_per_tensor_default_523 = quantized_decomposed_dequantize_per_tensor_default_526 = quantized_decomposed_dequantize_per_tensor_default_529 = quantized_decomposed_dequantize_per_tensor_default_532 = quantized_decomposed_dequantize_per_tensor_default_535 = quantized_decomposed_dequantize_per_tensor_default_538 = None
2025-03-21T20:31:43.4140162Z             quantized_decomposed_quantize_per_tensor_default_290: "i32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_7, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_cat_default_7 = None
2025-03-21T20:31:43.4141307Z             quantized_decomposed_dequantize_per_tensor_default_539: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_290, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_290 = None
2025-03-21T20:31:43.4142078Z             aten_view_copy_default_28: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_539, [1, 12, 128, 64]);  quantized_decomposed_dequantize_per_tensor_default_539 = None
2025-03-21T20:31:43.4142989Z             quantized_decomposed_quantize_per_tensor_default_291: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_28, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  aten_view_copy_default_28 = None
2025-03-21T20:31:43.4143080Z             
2025-03-21T20:31:43.4144018Z              # File: <eval_with_key>.50:1306 in forward, code: dequantize_per_tensor_default_441 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_441, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantize_per_tensor_default_441 = None
2025-03-21T20:31:43.4145148Z             quantized_decomposed_dequantize_per_tensor_default_540: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_291, 8.02720314823091e-05, 34074, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_291 = None
2025-03-21T20:31:43.4145312Z             
2025-03-21T20:31:43.4146239Z              # File: <eval_with_key>.50:1307 in forward, code: quantize_per_tensor_default_442 = torch.ops.quantized_decomposed.quantize_per_tensor.default(dequantize_per_tensor_default_441, 8.347312541445717e-05, 0, -32767, 32767, torch.int16);  dequantize_per_tensor_default_441 = None
2025-03-21T20:31:43.4147417Z             quantized_decomposed_quantize_per_tensor_default_292: "i16[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_540, 8.347312541445717e-05, 0, -32767, 32767, torch.int16);  quantized_decomposed_dequantize_per_tensor_default_540 = None
2025-03-21T20:31:43.4147510Z             
2025-03-21T20:31:43.4147989Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:163 in forward, code: y = attn_weight @ v
2025-03-21T20:31:43.4149130Z             quantized_decomposed_dequantize_per_tensor_default_541: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_292, 8.347312541445717e-05, 0, -32767, 32767, torch.int16);  quantized_decomposed_quantize_per_tensor_default_292 = None
2025-03-21T20:31:43.4149260Z             
2025-03-21T20:31:43.4149749Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:157 in forward, code: attn_mask = mask[input_pos]
2025-03-21T20:31:43.4150552Z             aten_index_tensor_3: "f32[1, 128]" = executorch_exir_dialects_edge__ops_aten_index_Tensor(quantized_decomposed_dequantize_per_tensor_default_118, [attn_options_input_pos]);  quantized_decomposed_dequantize_per_tensor_default_118 = None
2025-03-21T20:31:43.4151414Z             quantized_decomposed_quantize_per_tensor_default_293: "i32[1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_tensor_3, 0.0038910505827516317, 65535, 0, 65535, torch.int32);  aten_index_tensor_3 = None
2025-03-21T20:31:43.4151519Z             
2025-03-21T20:31:43.4152000Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:161 in forward, code: attn_weight += attn_mask
2025-03-21T20:31:43.4153147Z             quantized_decomposed_dequantize_per_tensor_default_542: "f32[1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_293, 0.0038910505827516317, 65535, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_293 = None
2025-03-21T20:31:43.4153239Z             
2025-03-21T20:31:43.4153829Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.4154623Z             aten_permute_copy_default_72: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_502, [0, 1, 3, 2]);  quantized_decomposed_dequantize_per_tensor_default_502 = None
2025-03-21T20:31:43.4155570Z             quantized_decomposed_quantize_per_tensor_default_294: "i32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_72, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  aten_permute_copy_default_72 = None
2025-03-21T20:31:43.4155662Z             
2025-03-21T20:31:43.4156604Z              # File: <eval_with_key>.50:1314 in forward, code: dequantize_per_tensor_default_444 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_444, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantize_per_tensor_default_444 = None
2025-03-21T20:31:43.4157775Z             quantized_decomposed_dequantize_per_tensor_default_543: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_294, 0.00035046463017351925, 33692, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_294 = None
2025-03-21T20:31:43.4157900Z             
2025-03-21T20:31:43.4158829Z              # File: <eval_with_key>.50:1315 in forward, code: quantize_per_tensor_default_445 = torch.ops.quantized_decomposed.quantize_per_tensor.default(dequantize_per_tensor_default_444, 0.00036035533412359655, 0, -32767, 32767, torch.int16);  dequantize_per_tensor_default_444 = None
2025-03-21T20:31:43.4160012Z             quantized_decomposed_quantize_per_tensor_default_295: "i16[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_543, 0.00036035533412359655, 0, -32767, 32767, torch.int16);  quantized_decomposed_dequantize_per_tensor_default_543 = None
2025-03-21T20:31:43.4160101Z             
2025-03-21T20:31:43.4160688Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.4161830Z             quantized_decomposed_dequantize_per_tensor_default_544: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_295, 0.00036035533412359655, 0, -32767, 32767, torch.int16);  quantized_decomposed_quantize_per_tensor_default_295 = None
2025-03-21T20:31:43.4162646Z             aten_expand_copy_default_4: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_438, [1, 12, 1, 64]);  quantized_decomposed_dequantize_per_tensor_default_438 = None
2025-03-21T20:31:43.4163189Z             aten_view_copy_default_29: "f32[12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_4, [12, 1, 64]);  aten_expand_copy_default_4 = None
2025-03-21T20:31:43.4163988Z             aten_expand_copy_default_5: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_544, [1, 12, 64, 128]);  quantized_decomposed_dequantize_per_tensor_default_544 = None
2025-03-21T20:31:43.4164545Z             aten_view_copy_default_30: "f32[12, 64, 128]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_5, [12, 64, 128]);  aten_expand_copy_default_5 = None
2025-03-21T20:31:43.4165206Z             aten_bmm_default_2: "f32[12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_bmm_default(aten_view_copy_default_29, aten_view_copy_default_30);  aten_view_copy_default_29 = aten_view_copy_default_30 = None
2025-03-21T20:31:43.4165709Z             aten_view_copy_default_31: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_bmm_default_2, [1, 12, 1, 128]);  aten_bmm_default_2 = None
2025-03-21T20:31:43.4166619Z             quantized_decomposed_quantize_per_tensor_default_296: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_31, 0.003841349622234702, 41763, 0, 65535, torch.int32);  aten_view_copy_default_31 = None
2025-03-21T20:31:43.4167747Z             quantized_decomposed_dequantize_per_tensor_default_545: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_296, 0.003841349622234702, 41763, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_296 = None
2025-03-21T20:31:43.4168608Z             quantized_decomposed_dequantize_per_tensor_default_546: "f32[1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param150, 1.9073777366429567e-06, 0, 0, 65535, torch.int32);  b__frozen_param150 = None
2025-03-21T20:31:43.4169825Z             aten_mul_tensor_25: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_545, quantized_decomposed_dequantize_per_tensor_default_546);  quantized_decomposed_dequantize_per_tensor_default_545 = quantized_decomposed_dequantize_per_tensor_default_546 = None
2025-03-21T20:31:43.4170721Z             quantized_decomposed_quantize_per_tensor_default_297: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_25, 0.00048016870277933776, 41763, 0, 65535, torch.int32);  aten_mul_tensor_25 = None
2025-03-21T20:31:43.4170809Z             
2025-03-21T20:31:43.4171340Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:161 in forward, code: attn_weight += attn_mask
2025-03-21T20:31:43.4172480Z             quantized_decomposed_dequantize_per_tensor_default_547: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_297, 0.00048016870277933776, 41763, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_297 = None
2025-03-21T20:31:43.4173603Z             aten_add_tensor_7: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_547, quantized_decomposed_dequantize_per_tensor_default_542);  quantized_decomposed_dequantize_per_tensor_default_547 = quantized_decomposed_dequantize_per_tensor_default_542 = None
2025-03-21T20:31:43.4174469Z             quantized_decomposed_quantize_per_tensor_default_298: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_7, 0.004258564207702875, 62855, 0, 65535, torch.int32);  aten_add_tensor_7 = None
2025-03-21T20:31:43.4174568Z             
2025-03-21T20:31:43.4175130Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:162 in forward, code: attn_weight = torch.softmax(attn_weight, dim=-1)
2025-03-21T20:31:43.4176276Z             quantized_decomposed_dequantize_per_tensor_default_548: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_298, 0.004258564207702875, 62855, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_298 = None
2025-03-21T20:31:43.4177046Z             aten__softmax_default_1: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten__softmax_default(quantized_decomposed_dequantize_per_tensor_default_548, -1, False);  quantized_decomposed_dequantize_per_tensor_default_548 = None
2025-03-21T20:31:43.4177930Z             quantized_decomposed_quantize_per_tensor_default_299: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten__softmax_default_1, 1.5259021893143654e-05, 0, 0, 65535, torch.int32);  aten__softmax_default_1 = None
2025-03-21T20:31:43.4178018Z             
2025-03-21T20:31:43.4178494Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:163 in forward, code: y = attn_weight @ v
2025-03-21T20:31:43.4179605Z             quantized_decomposed_dequantize_per_tensor_default_549: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_299, 1.5259021893143654e-05, 0, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_299 = None
2025-03-21T20:31:43.4180398Z             aten_expand_copy_default_6: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_549, [1, 12, 1, 128]);  quantized_decomposed_dequantize_per_tensor_default_549 = None
2025-03-21T20:31:43.4180979Z             aten_view_copy_default_32: "f32[12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_6, [12, 1, 128]);  aten_expand_copy_default_6 = None
2025-03-21T20:31:43.4181824Z             aten_expand_copy_default_7: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_541, [1, 12, 128, 64]);  quantized_decomposed_dequantize_per_tensor_default_541 = None
2025-03-21T20:31:43.4182382Z             aten_view_copy_default_33: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_7, [12, 128, 64]);  aten_expand_copy_default_7 = None
2025-03-21T20:31:43.4183051Z             aten_bmm_default_3: "f32[12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_bmm_default(aten_view_copy_default_32, aten_view_copy_default_33);  aten_view_copy_default_32 = aten_view_copy_default_33 = None
2025-03-21T20:31:43.4183550Z             aten_view_copy_default_34: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_bmm_default_3, [1, 12, 1, 64]);  aten_bmm_default_3 = None
2025-03-21T20:31:43.4184455Z             quantized_decomposed_quantize_per_tensor_default_300: "i32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_34, 5.015738497604616e-05, 34187, 0, 65535, torch.int32);  aten_view_copy_default_34 = None
2025-03-21T20:31:43.4184572Z             
2025-03-21T20:31:43.4185207Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:165 in forward, code: return y.transpose(1, 2).contiguous().view(bsz, seqlen, self.dim)
2025-03-21T20:31:43.4186339Z             quantized_decomposed_dequantize_per_tensor_default_550: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_300, 5.015738497604616e-05, 34187, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_300 = None
2025-03-21T20:31:43.4187133Z             aten_permute_copy_default_73: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_550, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_550 = None
2025-03-21T20:31:43.4188046Z             quantized_decomposed_quantize_per_tensor_default_301: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_73, 5.015738497604616e-05, 34187, 0, 65535, torch.int32);  aten_permute_copy_default_73 = None
2025-03-21T20:31:43.4189183Z             quantized_decomposed_dequantize_per_tensor_default_551: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_301, 5.015738497604616e-05, 34187, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_301 = None
2025-03-21T20:31:43.4189939Z             aten_view_copy_default_35: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_551, [1, 1, 768]);  quantized_decomposed_dequantize_per_tensor_default_551 = None
2025-03-21T20:31:43.4190849Z             quantized_decomposed_quantize_per_tensor_default_302: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_35, 5.015738497604616e-05, 34187, 0, 65535, torch.int32);  aten_view_copy_default_35 = None
2025-03-21T20:31:43.4190937Z             
2025-03-21T20:31:43.4191468Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.4192633Z             quantized_decomposed_dequantize_per_tensor_default_552: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_302, 5.015738497604616e-05, 34187, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_302 = None
2025-03-21T20:31:43.4193460Z             aten_unsqueeze_copy_default_18: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_552, -1);  quantized_decomposed_dequantize_per_tensor_default_552 = None
2025-03-21T20:31:43.4194396Z             quantized_decomposed_quantize_per_tensor_default_303: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_18, 5.015738497604616e-05, 34187, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_18 = None
2025-03-21T20:31:43.4194520Z             
2025-03-21T20:31:43.4194925Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.4196067Z             quantized_decomposed_dequantize_per_tensor_default_553: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_303, 5.015738497604616e-05, 34187, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_303 = None
2025-03-21T20:31:43.4196851Z             aten_permute_copy_default_74: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_553, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_553 = None
2025-03-21T20:31:43.4197811Z             quantized_decomposed_quantize_per_tensor_default_304: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_74, 5.015738497604616e-05, 34187, 0, 65535, torch.int32);  aten_permute_copy_default_74 = None
2025-03-21T20:31:43.4197898Z             
2025-03-21T20:31:43.4198274Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.4199409Z             quantized_decomposed_dequantize_per_tensor_default_554: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_304, 5.015738497604616e-05, 34187, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_304 = None
2025-03-21T20:31:43.4200680Z             aten_convolution_default_10: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_554, quantized_decomposed_dequantize_per_tensor_default_14, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_554 = quantized_decomposed_dequantize_per_tensor_default_14 = None
2025-03-21T20:31:43.4201596Z             quantized_decomposed_quantize_per_tensor_default_305: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_10, 6.624962406931445e-05, 32697, 0, 65535, torch.int32);  aten_convolution_default_10 = None
2025-03-21T20:31:43.4201695Z             
2025-03-21T20:31:43.4202114Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.4203367Z             quantized_decomposed_dequantize_per_tensor_default_555: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_305, 6.624962406931445e-05, 32697, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_305 = None
2025-03-21T20:31:43.4204157Z             aten_permute_copy_default_75: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_555, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_555 = None
2025-03-21T20:31:43.4205121Z             quantized_decomposed_quantize_per_tensor_default_306: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_75, 6.624962406931445e-05, 32697, 0, 65535, torch.int32);  aten_permute_copy_default_75 = None
2025-03-21T20:31:43.4205235Z             
2025-03-21T20:31:43.4205781Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.4206937Z             quantized_decomposed_dequantize_per_tensor_default_556: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_306, 6.624962406931445e-05, 32697, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_306 = None
2025-03-21T20:31:43.4207699Z             aten_squeeze_copy_dims_18: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_556, [-1]);  quantized_decomposed_dequantize_per_tensor_default_556 = None
2025-03-21T20:31:43.4208591Z             quantized_decomposed_quantize_per_tensor_default_307: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_18, 6.624962406931445e-05, 32697, 0, 65535, torch.int32);  aten_squeeze_copy_dims_18 = None
2025-03-21T20:31:43.4208710Z             
2025-03-21T20:31:43.4209081Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:111 in forward, code: h = x + h
2025-03-21T20:31:43.4210324Z             quantized_decomposed_dequantize_per_tensor_default_557: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_307, 6.624962406931445e-05, 32697, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_307 = None
2025-03-21T20:31:43.4211442Z             aten_add_tensor_8: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_377, quantized_decomposed_dequantize_per_tensor_default_557);  quantized_decomposed_dequantize_per_tensor_default_377 = quantized_decomposed_dequantize_per_tensor_default_557 = None
2025-03-21T20:31:43.4212307Z             quantized_decomposed_quantize_per_tensor_default_308: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_8, 0.00016923173097893596, 27235, 0, 65535, torch.int32);  aten_add_tensor_8 = None
2025-03-21T20:31:43.4212398Z             
2025-03-21T20:31:43.4212929Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:115 in forward, code: out = h + self.feed_forward(self.ffn_norm(h))
2025-03-21T20:31:43.4213988Z             quantized_decomposed_dequantize_per_tensor_default_558: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_308, 0.00016923173097893596, 27235, 0, 65535, torch.int32)
2025-03-21T20:31:43.4215267Z             quantized_decomposed_dequantize_per_tensor_default_559: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_308, 0.00016923173097893596, 27235, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_308 = None
2025-03-21T20:31:43.4215788Z             aten_pow_tensor_scalar_3: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_pow_Tensor_Scalar(quantized_decomposed_dequantize_per_tensor_default_559, 2)
2025-03-21T20:31:43.4216254Z             aten_mean_dim_3: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_mean_dim(aten_pow_tensor_scalar_3, [2], True);  aten_pow_tensor_scalar_3 = None
2025-03-21T20:31:43.4216744Z             aten_add_scalar_3: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_add_Scalar(aten_mean_dim_3, 9.999999747378752e-06);  aten_mean_dim_3 = None
2025-03-21T20:31:43.4217213Z             aten_rsqrt_default_3: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_rsqrt_default(aten_add_scalar_3);  aten_add_scalar_3 = None
2025-03-21T20:31:43.4218055Z             aten_mul_tensor_26: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_559, aten_rsqrt_default_3);  quantized_decomposed_dequantize_per_tensor_default_559 = aten_rsqrt_default_3 = None
2025-03-21T20:31:43.4218895Z             aten_mul_tensor_27: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(aten_mul_tensor_26, quantized_decomposed_dequantize_per_tensor_default_15);  aten_mul_tensor_26 = quantized_decomposed_dequantize_per_tensor_default_15 = None
2025-03-21T20:31:43.4219752Z             quantized_decomposed_quantize_per_tensor_default_309: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_27, 0.00021398279932327569, 31590, 0, 65535, torch.int32);  aten_mul_tensor_27 = None
2025-03-21T20:31:43.4219858Z             
2025-03-21T20:31:43.4220376Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.4221330Z             quantized_decomposed_dequantize_per_tensor_default_560: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_309, 0.00021398279932327569, 31590, 0, 65535, torch.int32)
2025-03-21T20:31:43.4222468Z             quantized_decomposed_dequantize_per_tensor_default_561: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_309, 0.00021398279932327569, 31590, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_309 = None
2025-03-21T20:31:43.4223280Z             aten_unsqueeze_copy_default_19: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_561, -1);  quantized_decomposed_dequantize_per_tensor_default_561 = None
2025-03-21T20:31:43.4224225Z             quantized_decomposed_quantize_per_tensor_default_310: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_19, 0.00021398279932327569, 31590, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_19 = None
2025-03-21T20:31:43.4224325Z             
2025-03-21T20:31:43.4224734Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.4225885Z             quantized_decomposed_dequantize_per_tensor_default_562: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_310, 0.00021398279932327569, 31590, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_310 = None
2025-03-21T20:31:43.4226669Z             aten_permute_copy_default_76: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_562, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_562 = None
2025-03-21T20:31:43.4227613Z             quantized_decomposed_quantize_per_tensor_default_311: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_76, 0.00021398279932327569, 31590, 0, 65535, torch.int32);  aten_permute_copy_default_76 = None
2025-03-21T20:31:43.4227699Z             
2025-03-21T20:31:43.4228075Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.4229238Z             quantized_decomposed_dequantize_per_tensor_default_563: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_311, 0.00021398279932327569, 31590, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_311 = None
2025-03-21T20:31:43.4230569Z             aten_convolution_default_11: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_563, quantized_decomposed_dequantize_per_tensor_default_16, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_563 = quantized_decomposed_dequantize_per_tensor_default_16 = None
2025-03-21T20:31:43.4231516Z             quantized_decomposed_quantize_per_tensor_default_312: "i32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_11, 0.00014935866056475788, 27447, 0, 65535, torch.int32);  aten_convolution_default_11 = None
2025-03-21T20:31:43.4231607Z             
2025-03-21T20:31:43.4232028Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.4233375Z             quantized_decomposed_dequantize_per_tensor_default_564: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_312, 0.00014935866056475788, 27447, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_312 = None
2025-03-21T20:31:43.4234235Z             aten_permute_copy_default_77: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_564, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_564 = None
2025-03-21T20:31:43.4235184Z             quantized_decomposed_quantize_per_tensor_default_313: "i32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_77, 0.00014935866056475788, 27447, 0, 65535, torch.int32);  aten_permute_copy_default_77 = None
2025-03-21T20:31:43.4235272Z             
2025-03-21T20:31:43.4235822Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.4236969Z             quantized_decomposed_dequantize_per_tensor_default_565: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_313, 0.00014935866056475788, 27447, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_313 = None
2025-03-21T20:31:43.4237733Z             aten_squeeze_copy_dims_19: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_565, [-1]);  quantized_decomposed_dequantize_per_tensor_default_565 = None
2025-03-21T20:31:43.4238644Z             quantized_decomposed_quantize_per_tensor_default_314: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_19, 0.00014935866056475788, 27447, 0, 65535, torch.int32);  aten_squeeze_copy_dims_19 = None
2025-03-21T20:31:43.4238746Z             
2025-03-21T20:31:43.4239260Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:36 in forward, code: return self.w2(F.silu(self.w1(x)) * self.w3(x))
2025-03-21T20:31:43.4240191Z             quantized_decomposed_dequantize_per_tensor_default_566: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_314, 0.00014935866056475788, 27447, 0, 65535, torch.int32)
2025-03-21T20:31:43.4241367Z             quantized_decomposed_dequantize_per_tensor_default_567: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_314, 0.00014935866056475788, 27447, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_314 = None
2025-03-21T20:31:43.4242150Z             aten_sigmoid_default_1: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_sigmoid_default(quantized_decomposed_dequantize_per_tensor_default_567);  quantized_decomposed_dequantize_per_tensor_default_567 = None
2025-03-21T20:31:43.4243041Z             quantized_decomposed_quantize_per_tensor_default_315: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_sigmoid_default_1, 1.52587890625e-05, 0, 0, 65535, torch.int32);  aten_sigmoid_default_1 = None
2025-03-21T20:31:43.4244143Z             quantized_decomposed_dequantize_per_tensor_default_568: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_315, 1.52587890625e-05, 0, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_315 = None
2025-03-21T20:31:43.4245275Z             aten_mul_tensor_28: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_566, quantized_decomposed_dequantize_per_tensor_default_568);  quantized_decomposed_dequantize_per_tensor_default_566 = quantized_decomposed_dequantize_per_tensor_default_568 = None
2025-03-21T20:31:43.4246151Z             quantized_decomposed_quantize_per_tensor_default_316: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_28, 9.076054266188294e-05, 3068, 0, 65535, torch.int32);  aten_mul_tensor_28 = None
2025-03-21T20:31:43.4247298Z             quantized_decomposed_dequantize_per_tensor_default_569: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_316, 9.076054266188294e-05, 3068, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_316 = None
2025-03-21T20:31:43.4247389Z             
2025-03-21T20:31:43.4247921Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.4248721Z             aten_unsqueeze_copy_default_20: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_560, -1);  quantized_decomposed_dequantize_per_tensor_default_560 = None
2025-03-21T20:31:43.4249749Z             quantized_decomposed_quantize_per_tensor_default_317: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_20, 0.00021398279932327569, 31590, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_20 = None
2025-03-21T20:31:43.4249840Z             
2025-03-21T20:31:43.4250261Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.4251400Z             quantized_decomposed_dequantize_per_tensor_default_570: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_317, 0.00021398279932327569, 31590, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_317 = None
2025-03-21T20:31:43.4252200Z             aten_permute_copy_default_78: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_570, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_570 = None
2025-03-21T20:31:43.4253159Z             quantized_decomposed_quantize_per_tensor_default_318: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_78, 0.00021398279932327569, 31590, 0, 65535, torch.int32);  aten_permute_copy_default_78 = None
2025-03-21T20:31:43.4253282Z             
2025-03-21T20:31:43.4253644Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.4254823Z             quantized_decomposed_dequantize_per_tensor_default_571: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_318, 0.00021398279932327569, 31590, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_318 = None
2025-03-21T20:31:43.4256094Z             aten_convolution_default_12: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_571, quantized_decomposed_dequantize_per_tensor_default_17, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_571 = quantized_decomposed_dequantize_per_tensor_default_17 = None
2025-03-21T20:31:43.4257042Z             quantized_decomposed_quantize_per_tensor_default_319: "i32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_12, 0.00023316948499996215, 31553, 0, 65535, torch.int32);  aten_convolution_default_12 = None
2025-03-21T20:31:43.4257157Z             
2025-03-21T20:31:43.4257589Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.4258740Z             quantized_decomposed_dequantize_per_tensor_default_572: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_319, 0.00023316948499996215, 31553, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_319 = None
2025-03-21T20:31:43.4259551Z             aten_permute_copy_default_79: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_572, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_572 = None
2025-03-21T20:31:43.4260489Z             quantized_decomposed_quantize_per_tensor_default_320: "i32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_79, 0.00023316948499996215, 31553, 0, 65535, torch.int32);  aten_permute_copy_default_79 = None
2025-03-21T20:31:43.4260591Z             
2025-03-21T20:31:43.4261131Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.4262294Z             quantized_decomposed_dequantize_per_tensor_default_573: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_320, 0.00023316948499996215, 31553, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_320 = None
2025-03-21T20:31:43.4263049Z             aten_squeeze_copy_dims_20: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_573, [-1]);  quantized_decomposed_dequantize_per_tensor_default_573 = None
2025-03-21T20:31:43.4263975Z             quantized_decomposed_quantize_per_tensor_default_321: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_20, 0.00023316948499996215, 31553, 0, 65535, torch.int32);  aten_squeeze_copy_dims_20 = None
2025-03-21T20:31:43.4264066Z             
2025-03-21T20:31:43.4264595Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:36 in forward, code: return self.w2(F.silu(self.w1(x)) * self.w3(x))
2025-03-21T20:31:43.4265776Z             quantized_decomposed_dequantize_per_tensor_default_574: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_321, 0.00023316948499996215, 31553, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_321 = None
2025-03-21T20:31:43.4266960Z             aten_mul_tensor_29: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_569, quantized_decomposed_dequantize_per_tensor_default_574);  quantized_decomposed_dequantize_per_tensor_default_569 = quantized_decomposed_dequantize_per_tensor_default_574 = None
2025-03-21T20:31:43.4267818Z             quantized_decomposed_quantize_per_tensor_default_322: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_29, 0.0009241419611498713, 33256, 0, 65535, torch.int32);  aten_mul_tensor_29 = None
2025-03-21T20:31:43.4267922Z             
2025-03-21T20:31:43.4268442Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.4269597Z             quantized_decomposed_dequantize_per_tensor_default_575: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_322, 0.0009241419611498713, 33256, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_322 = None
2025-03-21T20:31:43.4270426Z             aten_unsqueeze_copy_default_21: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_575, -1);  quantized_decomposed_dequantize_per_tensor_default_575 = None
2025-03-21T20:31:43.4271382Z             quantized_decomposed_quantize_per_tensor_default_323: "i32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_21, 0.0009241419611498713, 33256, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_21 = None
2025-03-21T20:31:43.4271475Z             
2025-03-21T20:31:43.4271896Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.4273044Z             quantized_decomposed_dequantize_per_tensor_default_576: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_323, 0.0009241419611498713, 33256, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_323 = None
2025-03-21T20:31:43.4273850Z             aten_permute_copy_default_80: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_576, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_576 = None
2025-03-21T20:31:43.4274784Z             quantized_decomposed_quantize_per_tensor_default_324: "i32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_80, 0.0009241419611498713, 33256, 0, 65535, torch.int32);  aten_permute_copy_default_80 = None
2025-03-21T20:31:43.4274891Z             
2025-03-21T20:31:43.4275256Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.4276415Z             quantized_decomposed_dequantize_per_tensor_default_577: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_324, 0.0009241419611498713, 33256, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_324 = None
2025-03-21T20:31:43.4277705Z             aten_convolution_default_13: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_577, quantized_decomposed_dequantize_per_tensor_default_18, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_577 = quantized_decomposed_dequantize_per_tensor_default_18 = None
2025-03-21T20:31:43.4278660Z             quantized_decomposed_quantize_per_tensor_default_325: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_13, 0.0008836374618113041, 9331, 0, 65535, torch.int32);  aten_convolution_default_13 = None
2025-03-21T20:31:43.4278750Z             
2025-03-21T20:31:43.4279208Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.4280347Z             quantized_decomposed_dequantize_per_tensor_default_578: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_325, 0.0008836374618113041, 9331, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_325 = None
2025-03-21T20:31:43.4281150Z             aten_permute_copy_default_81: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_578, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_578 = None
2025-03-21T20:31:43.4282091Z             quantized_decomposed_quantize_per_tensor_default_326: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_81, 0.0008836374618113041, 9331, 0, 65535, torch.int32);  aten_permute_copy_default_81 = None
2025-03-21T20:31:43.4282192Z             
2025-03-21T20:31:43.4282727Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.4283872Z             quantized_decomposed_dequantize_per_tensor_default_579: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_326, 0.0008836374618113041, 9331, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_326 = None
2025-03-21T20:31:43.4284620Z             aten_squeeze_copy_dims_21: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_579, [-1]);  quantized_decomposed_dequantize_per_tensor_default_579 = None
2025-03-21T20:31:43.4285525Z             quantized_decomposed_quantize_per_tensor_default_327: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_21, 0.0008836374618113041, 9331, 0, 65535, torch.int32);  aten_squeeze_copy_dims_21 = None
2025-03-21T20:31:43.4285614Z             
2025-03-21T20:31:43.4286138Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:115 in forward, code: out = h + self.feed_forward(self.ffn_norm(h))
2025-03-21T20:31:43.4287266Z             quantized_decomposed_dequantize_per_tensor_default_580: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_327, 0.0008836374618113041, 9331, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_327 = None
2025-03-21T20:31:43.4288396Z             aten_add_tensor_9: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_558, quantized_decomposed_dequantize_per_tensor_default_580);  quantized_decomposed_dequantize_per_tensor_default_558 = quantized_decomposed_dequantize_per_tensor_default_580 = None
2025-03-21T20:31:43.4289345Z             quantized_decomposed_quantize_per_tensor_default_328: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_9, 0.0010317935375496745, 12458, 0, 65535, torch.int32);  aten_add_tensor_9 = None
2025-03-21T20:31:43.4289490Z             
2025-03-21T20:31:43.4289861Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:111 in forward, code: h = x + h
2025-03-21T20:31:43.4290788Z             quantized_decomposed_dequantize_per_tensor_default_581: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_328, 0.0010317935375496745, 12458, 0, 65535, torch.int32)
2025-03-21T20:31:43.4290911Z             
2025-03-21T20:31:43.4291493Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:108 in forward, code: self.attention_norm(x), freqs_cos, freqs_sin, **attn_options
2025-03-21T20:31:43.4292629Z             quantized_decomposed_dequantize_per_tensor_default_582: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_328, 0.0010317935375496745, 12458, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_328 = None
2025-03-21T20:31:43.4293190Z             aten_pow_tensor_scalar_4: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_pow_Tensor_Scalar(quantized_decomposed_dequantize_per_tensor_default_582, 2)
2025-03-21T20:31:43.4293639Z             aten_mean_dim_4: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_mean_dim(aten_pow_tensor_scalar_4, [2], True);  aten_pow_tensor_scalar_4 = None
2025-03-21T20:31:43.4294092Z             aten_add_scalar_4: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_add_Scalar(aten_mean_dim_4, 9.999999747378752e-06);  aten_mean_dim_4 = None
2025-03-21T20:31:43.4294506Z             aten_rsqrt_default_4: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_rsqrt_default(aten_add_scalar_4);  aten_add_scalar_4 = None
2025-03-21T20:31:43.4295366Z             aten_mul_tensor_30: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_582, aten_rsqrt_default_4);  quantized_decomposed_dequantize_per_tensor_default_582 = aten_rsqrt_default_4 = None
2025-03-21T20:31:43.4296167Z             aten_mul_tensor_31: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(aten_mul_tensor_30, quantized_decomposed_dequantize_per_tensor_default_19);  aten_mul_tensor_30 = quantized_decomposed_dequantize_per_tensor_default_19 = None
2025-03-21T20:31:43.4297025Z             quantized_decomposed_quantize_per_tensor_default_329: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_31, 0.0003308423620183021, 21627, 0, 65535, torch.int32);  aten_mul_tensor_31 = None
2025-03-21T20:31:43.4297113Z             
2025-03-21T20:31:43.4297638Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.4298560Z             quantized_decomposed_dequantize_per_tensor_default_583: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_329, 0.0003308423620183021, 21627, 0, 65535, torch.int32)
2025-03-21T20:31:43.4299484Z             quantized_decomposed_dequantize_per_tensor_default_584: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_329, 0.0003308423620183021, 21627, 0, 65535, torch.int32)
2025-03-21T20:31:43.4300617Z             quantized_decomposed_dequantize_per_tensor_default_585: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_329, 0.0003308423620183021, 21627, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_329 = None
2025-03-21T20:31:43.4301490Z             aten_unsqueeze_copy_default_22: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_585, -1);  quantized_decomposed_dequantize_per_tensor_default_585 = None
2025-03-21T20:31:43.4302436Z             quantized_decomposed_quantize_per_tensor_default_330: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_22, 0.0003308423620183021, 21627, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_22 = None
2025-03-21T20:31:43.4302560Z             
2025-03-21T20:31:43.4302968Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.4304118Z             quantized_decomposed_dequantize_per_tensor_default_586: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_330, 0.0003308423620183021, 21627, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_330 = None
2025-03-21T20:31:43.4304907Z             aten_permute_copy_default_82: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_586, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_586 = None
2025-03-21T20:31:43.4305881Z             quantized_decomposed_quantize_per_tensor_default_331: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_82, 0.0003308423620183021, 21627, 0, 65535, torch.int32);  aten_permute_copy_default_82 = None
2025-03-21T20:31:43.4305974Z             
2025-03-21T20:31:43.4306348Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.4307482Z             quantized_decomposed_dequantize_per_tensor_default_587: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_331, 0.0003308423620183021, 21627, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_331 = None
2025-03-21T20:31:43.4308759Z             aten_convolution_default_14: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_587, quantized_decomposed_dequantize_per_tensor_default_20, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_587 = quantized_decomposed_dequantize_per_tensor_default_20 = None
2025-03-21T20:31:43.4309689Z             quantized_decomposed_quantize_per_tensor_default_332: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_14, 0.00036216730950400233, 19231, 0, 65535, torch.int32);  aten_convolution_default_14 = None
2025-03-21T20:31:43.4309793Z             
2025-03-21T20:31:43.4310213Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.4311369Z             quantized_decomposed_dequantize_per_tensor_default_588: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_332, 0.00036216730950400233, 19231, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_332 = None
2025-03-21T20:31:43.4312156Z             aten_permute_copy_default_83: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_588, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_588 = None
2025-03-21T20:31:43.4313124Z             quantized_decomposed_quantize_per_tensor_default_333: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_83, 0.00036216730950400233, 19231, 0, 65535, torch.int32);  aten_permute_copy_default_83 = None
2025-03-21T20:31:43.4313254Z             
2025-03-21T20:31:43.4313806Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.4314972Z             quantized_decomposed_dequantize_per_tensor_default_589: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_333, 0.00036216730950400233, 19231, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_333 = None
2025-03-21T20:31:43.4315873Z             aten_squeeze_copy_dims_22: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_589, [-1]);  quantized_decomposed_dequantize_per_tensor_default_589 = None
2025-03-21T20:31:43.4316789Z             quantized_decomposed_quantize_per_tensor_default_334: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_22, 0.00036216730950400233, 19231, 0, 65535, torch.int32);  aten_squeeze_copy_dims_22 = None
2025-03-21T20:31:43.4316923Z             
2025-03-21T20:31:43.4317442Z              # File: /pytorch/executorch/examples/models/llama/attention.py:242 in forward, code: q = q.view(bsz, seqlen, self.n_local_heads, self.head_dim)
2025-03-21T20:31:43.4318595Z             quantized_decomposed_dequantize_per_tensor_default_590: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_334, 0.00036216730950400233, 19231, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_334 = None
2025-03-21T20:31:43.4318685Z             
2025-03-21T20:31:43.4319203Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.4320015Z             aten_unsqueeze_copy_default_23: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_584, -1);  quantized_decomposed_dequantize_per_tensor_default_584 = None
2025-03-21T20:31:43.4320971Z             quantized_decomposed_quantize_per_tensor_default_335: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_23, 0.0003308423620183021, 21627, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_23 = None
2025-03-21T20:31:43.4321058Z             
2025-03-21T20:31:43.4321464Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.4322616Z             quantized_decomposed_dequantize_per_tensor_default_591: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_335, 0.0003308423620183021, 21627, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_335 = None
2025-03-21T20:31:43.4323403Z             aten_permute_copy_default_84: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_591, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_591 = None
2025-03-21T20:31:43.4324344Z             quantized_decomposed_quantize_per_tensor_default_336: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_84, 0.0003308423620183021, 21627, 0, 65535, torch.int32);  aten_permute_copy_default_84 = None
2025-03-21T20:31:43.4324433Z             
2025-03-21T20:31:43.4324861Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.4325994Z             quantized_decomposed_dequantize_per_tensor_default_592: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_336, 0.0003308423620183021, 21627, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_336 = None
2025-03-21T20:31:43.4327749Z             aten_convolution_default_15: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_592, quantized_decomposed_dequantize_per_tensor_default_21, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_592 = quantized_decomposed_dequantize_per_tensor_default_21 = None
2025-03-21T20:31:43.4328701Z             quantized_decomposed_quantize_per_tensor_default_337: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_15, 0.00037646826240234077, 30723, 0, 65535, torch.int32);  aten_convolution_default_15 = None
2025-03-21T20:31:43.4328825Z             
2025-03-21T20:31:43.4329247Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.4330508Z             quantized_decomposed_dequantize_per_tensor_default_593: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_337, 0.00037646826240234077, 30723, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_337 = None
2025-03-21T20:31:43.4331318Z             aten_permute_copy_default_85: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_593, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_593 = None
2025-03-21T20:31:43.4332407Z             quantized_decomposed_quantize_per_tensor_default_338: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_85, 0.00037646826240234077, 30723, 0, 65535, torch.int32);  aten_permute_copy_default_85 = None
2025-03-21T20:31:43.4332523Z             
2025-03-21T20:31:43.4333065Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.4334207Z             quantized_decomposed_dequantize_per_tensor_default_594: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_338, 0.00037646826240234077, 30723, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_338 = None
2025-03-21T20:31:43.4334970Z             aten_squeeze_copy_dims_23: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_594, [-1]);  quantized_decomposed_dequantize_per_tensor_default_594 = None
2025-03-21T20:31:43.4335889Z             quantized_decomposed_quantize_per_tensor_default_339: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_23, 0.00037646826240234077, 30723, 0, 65535, torch.int32);  aten_squeeze_copy_dims_23 = None
2025-03-21T20:31:43.4335978Z             
2025-03-21T20:31:43.4336505Z              # File: /pytorch/executorch/examples/models/llama/attention.py:243 in forward, code: k = k.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.4337722Z             quantized_decomposed_dequantize_per_tensor_default_595: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_339, 0.00037646826240234077, 30723, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_339 = None
2025-03-21T20:31:43.4337845Z             
2025-03-21T20:31:43.4338377Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.4339177Z             aten_unsqueeze_copy_default_24: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_583, -1);  quantized_decomposed_dequantize_per_tensor_default_583 = None
2025-03-21T20:31:43.4340177Z             quantized_decomposed_quantize_per_tensor_default_340: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_24, 0.0003308423620183021, 21627, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_24 = None
2025-03-21T20:31:43.4340268Z             
2025-03-21T20:31:43.4340689Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.4341826Z             quantized_decomposed_dequantize_per_tensor_default_596: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_340, 0.0003308423620183021, 21627, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_340 = None
2025-03-21T20:31:43.4342658Z             aten_permute_copy_default_86: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_596, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_596 = None
2025-03-21T20:31:43.4343584Z             quantized_decomposed_quantize_per_tensor_default_341: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_86, 0.0003308423620183021, 21627, 0, 65535, torch.int32);  aten_permute_copy_default_86 = None
2025-03-21T20:31:43.4343684Z             
2025-03-21T20:31:43.4344047Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.4345200Z             quantized_decomposed_dequantize_per_tensor_default_597: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_341, 0.0003308423620183021, 21627, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_341 = None
2025-03-21T20:31:43.4346463Z             aten_convolution_default_16: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_597, quantized_decomposed_dequantize_per_tensor_default_22, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_597 = quantized_decomposed_dequantize_per_tensor_default_22 = None
2025-03-21T20:31:43.4347397Z             quantized_decomposed_quantize_per_tensor_default_342: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_16, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_convolution_default_16 = None
2025-03-21T20:31:43.4347486Z             
2025-03-21T20:31:43.4347916Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.4349050Z             quantized_decomposed_dequantize_per_tensor_default_598: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_342, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_342 = None
2025-03-21T20:31:43.4349872Z             aten_permute_copy_default_87: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_598, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_598 = None
2025-03-21T20:31:43.4350820Z             quantized_decomposed_quantize_per_tensor_default_343: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_87, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_permute_copy_default_87 = None
2025-03-21T20:31:43.4350922Z             
2025-03-21T20:31:43.4351493Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.4352641Z             quantized_decomposed_dequantize_per_tensor_default_599: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_343, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_343 = None
2025-03-21T20:31:43.4353388Z             aten_squeeze_copy_dims_24: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_599, [-1]);  quantized_decomposed_dequantize_per_tensor_default_599 = None
2025-03-21T20:31:43.4354367Z             quantized_decomposed_quantize_per_tensor_default_344: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_24, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_squeeze_copy_dims_24 = None
2025-03-21T20:31:43.4354454Z             
2025-03-21T20:31:43.4354990Z              # File: /pytorch/executorch/examples/models/llama/attention.py:244 in forward, code: v = v.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.4356119Z             quantized_decomposed_dequantize_per_tensor_default_600: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_344, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_344 = None
2025-03-21T20:31:43.4356222Z             
2025-03-21T20:31:43.4356730Z              # File: /pytorch/executorch/examples/models/llama/attention.py:242 in forward, code: q = q.view(bsz, seqlen, self.n_local_heads, self.head_dim)
2025-03-21T20:31:43.4357506Z             aten_view_copy_default_36: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_590, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_590 = None
2025-03-21T20:31:43.4358403Z             quantized_decomposed_quantize_per_tensor_default_345: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_36, 0.00036216730950400233, 19231, 0, 65535, torch.int32);  aten_view_copy_default_36 = None
2025-03-21T20:31:43.4358505Z             
2025-03-21T20:31:43.4359437Z              # File: <eval_with_key>.50:1474 in forward, code: dequantize_per_tensor_default_496 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_496, 0.00036216730950400233, 19231, 0, 65535, torch.int32);  quantize_per_tensor_default_496 = None
2025-03-21T20:31:43.4360592Z             quantized_decomposed_dequantize_per_tensor_default_601: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_345, 0.00036216730950400233, 19231, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_345 = None
2025-03-21T20:31:43.4360681Z             
2025-03-21T20:31:43.4361217Z              # File: /pytorch/executorch/examples/models/llama/attention.py:243 in forward, code: k = k.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.4362039Z             aten_view_copy_default_37: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_595, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_595 = None
2025-03-21T20:31:43.4362962Z             quantized_decomposed_quantize_per_tensor_default_346: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_37, 0.00037646826240234077, 30723, 0, 65535, torch.int32);  aten_view_copy_default_37 = None
2025-03-21T20:31:43.4363075Z             
2025-03-21T20:31:43.4364022Z              # File: <eval_with_key>.50:1477 in forward, code: dequantize_per_tensor_default_497 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_497, 0.00037646826240234077, 30723, 0, 65535, torch.int32);  quantize_per_tensor_default_497 = None
2025-03-21T20:31:43.4365164Z             quantized_decomposed_dequantize_per_tensor_default_602: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_346, 0.00037646826240234077, 30723, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_346 = None
2025-03-21T20:31:43.4365289Z             
2025-03-21T20:31:43.4365809Z              # File: /pytorch/executorch/examples/models/llama/attention.py:244 in forward, code: v = v.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.4366585Z             aten_view_copy_default_38: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_600, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_600 = None
2025-03-21T20:31:43.4367476Z             quantized_decomposed_quantize_per_tensor_default_347: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_38, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_view_copy_default_38 = None
2025-03-21T20:31:43.4367578Z             
2025-03-21T20:31:43.4368244Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:346 in update, code: v_out = torch.ops.aten.index_put_(self.past_v_caches, [None, input_pos], v_val)
2025-03-21T20:31:43.4369466Z             quantized_decomposed_dequantize_per_tensor_default_603: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_347, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_347 = None
2025-03-21T20:31:43.4369557Z             
2025-03-21T20:31:43.4370328Z              # File: <eval_with_key>.50:1482 in forward, code: quantize_per_tensor_default_499 = torch.ops.quantized_decomposed.quantize_per_tensor.default(_to_copy_4, 0.00036216730950400233, 19231, 0, 65535, torch.int32);  _to_copy_4 = None
2025-03-21T20:31:43.4371470Z             quantized_decomposed_quantize_per_tensor_default_348: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_601, 0.00036216730950400233, 19231, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_601 = None
2025-03-21T20:31:43.4371578Z             
2025-03-21T20:31:43.4372101Z              # File: /pytorch/executorch/examples/models/llama/rope.py:84 in apply_rotary_emb, code: xq_r, xq_i = xq.float().reshape(xq.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.4373321Z             quantized_decomposed_dequantize_per_tensor_default_604: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_348, 0.00036216730950400233, 19231, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_348 = None
2025-03-21T20:31:43.4374114Z             aten_view_copy_default_39: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_604, [1, 1, 12, -1, 2]);  quantized_decomposed_dequantize_per_tensor_default_604 = None
2025-03-21T20:31:43.4375031Z             quantized_decomposed_quantize_per_tensor_default_349: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_39, 0.00036216730950400233, 19231, 0, 65535, torch.int32);  aten_view_copy_default_39 = None
2025-03-21T20:31:43.4376194Z             quantized_decomposed_dequantize_per_tensor_default_605: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_349, 0.00036216730950400233, 19231, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_349 = None
2025-03-21T20:31:43.4376739Z             aten_slice_copy_tensor_8: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_605, 4, 0, 1)
2025-03-21T20:31:43.4377517Z             aten_slice_copy_tensor_9: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_605, 4, 1, 2);  quantized_decomposed_dequantize_per_tensor_default_605 = None
2025-03-21T20:31:43.4378046Z             aten_squeeze_copy_dims_25: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_8, [4]);  aten_slice_copy_tensor_8 = None
2025-03-21T20:31:43.4378556Z             aten_squeeze_copy_dims_26: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_9, [4]);  aten_slice_copy_tensor_9 = None
2025-03-21T20:31:43.4379467Z             quantized_decomposed_quantize_per_tensor_default_350: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_25, 0.0002881281834561378, 24173, 0, 65535, torch.int32);  aten_squeeze_copy_dims_25 = None
2025-03-21T20:31:43.4379561Z             
2025-03-21T20:31:43.4380052Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.4380961Z             quantized_decomposed_dequantize_per_tensor_default_606: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_350, 0.0002881281834561378, 24173, 0, 65535, torch.int32)
2025-03-21T20:31:43.4381063Z             
2025-03-21T20:31:43.4381536Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.4382690Z             quantized_decomposed_dequantize_per_tensor_default_607: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_350, 0.0002881281834561378, 24173, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_350 = None
2025-03-21T20:31:43.4382782Z             
2025-03-21T20:31:43.4383305Z              # File: /pytorch/executorch/examples/models/llama/rope.py:84 in apply_rotary_emb, code: xq_r, xq_i = xq.float().reshape(xq.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.4384224Z             quantized_decomposed_quantize_per_tensor_default_351: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_26, 0.00034527943353168666, 16967, 0, 65535, torch.int32);  aten_squeeze_copy_dims_26 = None
2025-03-21T20:31:43.4384312Z             
2025-03-21T20:31:43.4384841Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.4385779Z             quantized_decomposed_dequantize_per_tensor_default_608: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_351, 0.00034527943353168666, 16967, 0, 65535, torch.int32)
2025-03-21T20:31:43.4385881Z             
2025-03-21T20:31:43.4386350Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.4387527Z             quantized_decomposed_dequantize_per_tensor_default_609: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_351, 0.00034527943353168666, 16967, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_351 = None
2025-03-21T20:31:43.4387617Z             
2025-03-21T20:31:43.4388397Z              # File: <eval_with_key>.50:1497 in forward, code: quantize_per_tensor_default_503 = torch.ops.quantized_decomposed.quantize_per_tensor.default(_to_copy_5, 0.00037646826240234077, 30723, 0, 65535, torch.int32);  _to_copy_5 = None
2025-03-21T20:31:43.4389561Z             quantized_decomposed_quantize_per_tensor_default_352: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_602, 0.00037646826240234077, 30723, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_602 = None
2025-03-21T20:31:43.4389666Z             
2025-03-21T20:31:43.4390188Z              # File: /pytorch/executorch/examples/models/llama/rope.py:85 in apply_rotary_emb, code: xk_r, xk_i = xk.float().reshape(xk.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.4391341Z             quantized_decomposed_dequantize_per_tensor_default_610: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_352, 0.00037646826240234077, 30723, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_352 = None
2025-03-21T20:31:43.4392108Z             aten_view_copy_default_40: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_610, [1, 1, 12, -1, 2]);  quantized_decomposed_dequantize_per_tensor_default_610 = None
2025-03-21T20:31:43.4393026Z             quantized_decomposed_quantize_per_tensor_default_353: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_40, 0.00037646826240234077, 30723, 0, 65535, torch.int32);  aten_view_copy_default_40 = None
2025-03-21T20:31:43.4394163Z             quantized_decomposed_dequantize_per_tensor_default_611: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_353, 0.00037646826240234077, 30723, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_353 = None
2025-03-21T20:31:43.4394711Z             aten_slice_copy_tensor_10: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_611, 4, 0, 1)
2025-03-21T20:31:43.4395465Z             aten_slice_copy_tensor_11: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_611, 4, 1, 2);  quantized_decomposed_dequantize_per_tensor_default_611 = None
2025-03-21T20:31:43.4395997Z             aten_squeeze_copy_dims_27: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_10, [4]);  aten_slice_copy_tensor_10 = None
2025-03-21T20:31:43.4396537Z             aten_squeeze_copy_dims_28: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_11, [4]);  aten_slice_copy_tensor_11 = None
2025-03-21T20:31:43.4397490Z             quantized_decomposed_quantize_per_tensor_default_354: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_27, 0.00029378890758380294, 23361, 0, 65535, torch.int32);  aten_squeeze_copy_dims_27 = None
2025-03-21T20:31:43.4397578Z             
2025-03-21T20:31:43.4398067Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.4399002Z             quantized_decomposed_dequantize_per_tensor_default_612: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_354, 0.00029378890758380294, 23361, 0, 65535, torch.int32)
2025-03-21T20:31:43.4399105Z             
2025-03-21T20:31:43.4399582Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.4400730Z             quantized_decomposed_dequantize_per_tensor_default_613: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_354, 0.00029378890758380294, 23361, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_354 = None
2025-03-21T20:31:43.4400842Z             
2025-03-21T20:31:43.4401371Z              # File: /pytorch/executorch/examples/models/llama/rope.py:85 in apply_rotary_emb, code: xk_r, xk_i = xk.float().reshape(xk.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.4402275Z             quantized_decomposed_quantize_per_tensor_default_355: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_28, 0.00037646826240234077, 30723, 0, 65535, torch.int32);  aten_squeeze_copy_dims_28 = None
2025-03-21T20:31:43.4402376Z             
2025-03-21T20:31:43.4402846Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.4403768Z             quantized_decomposed_dequantize_per_tensor_default_614: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_355, 0.00037646826240234077, 30723, 0, 65535, torch.int32)
2025-03-21T20:31:43.4403855Z             
2025-03-21T20:31:43.4404323Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.4405475Z             quantized_decomposed_dequantize_per_tensor_default_615: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_355, 0.00037646826240234077, 30723, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_355 = None
2025-03-21T20:31:43.4405565Z             
2025-03-21T20:31:43.4406013Z              # File: /pytorch/executorch/examples/models/llama/rope.py:78 in reshape_for_broadcast, code: return freqs_cis.view(shape)
2025-03-21T20:31:43.4406878Z             aten_view_copy_default_41: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_160, [1, 1, 1, 32]);  quantized_decomposed_dequantize_per_tensor_default_160 = None
2025-03-21T20:31:43.4407793Z             quantized_decomposed_quantize_per_tensor_default_356: "i32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_41, 3.051804378628731e-05, 32768, 0, 65535, torch.int32);  aten_view_copy_default_41 = None
2025-03-21T20:31:43.4407886Z             
2025-03-21T20:31:43.4408429Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.4409407Z             quantized_decomposed_dequantize_per_tensor_default_616: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_356, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.4409515Z             
2025-03-21T20:31:43.4410014Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.4410934Z             quantized_decomposed_dequantize_per_tensor_default_617: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_356, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.4411022Z             
2025-03-21T20:31:43.4411506Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.4412414Z             quantized_decomposed_dequantize_per_tensor_default_618: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_356, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.4412547Z             
2025-03-21T20:31:43.4413022Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.4414176Z             quantized_decomposed_dequantize_per_tensor_default_619: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_356, 3.051804378628731e-05, 32768, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_356 = None
2025-03-21T20:31:43.4414273Z             
2025-03-21T20:31:43.4414710Z              # File: /pytorch/executorch/examples/models/llama/rope.py:78 in reshape_for_broadcast, code: return freqs_cis.view(shape)
2025-03-21T20:31:43.4415479Z             aten_view_copy_default_42: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_172, [1, 1, 1, 32]);  quantized_decomposed_dequantize_per_tensor_default_172 = None
2025-03-21T20:31:43.4416376Z             quantized_decomposed_quantize_per_tensor_default_357: "i32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_42, 3.051786916330457e-05, 32767, 0, 65535, torch.int32);  aten_view_copy_default_42 = None
2025-03-21T20:31:43.4416483Z             
2025-03-21T20:31:43.4416978Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.4418172Z             quantized_decomposed_dequantize_per_tensor_default_620: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_357, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.4418276Z             
2025-03-21T20:31:43.4418768Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.4419680Z             quantized_decomposed_dequantize_per_tensor_default_621: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_357, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.4419779Z             
2025-03-21T20:31:43.4420294Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.4421243Z             quantized_decomposed_dequantize_per_tensor_default_622: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_357, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.4421332Z             
2025-03-21T20:31:43.4421810Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.4422965Z             quantized_decomposed_dequantize_per_tensor_default_623: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_357, 3.051786916330457e-05, 32767, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_357 = None
2025-03-21T20:31:43.4423067Z             
2025-03-21T20:31:43.4423538Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.4424666Z             aten_mul_tensor_32: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_607, quantized_decomposed_dequantize_per_tensor_default_619);  quantized_decomposed_dequantize_per_tensor_default_607 = quantized_decomposed_dequantize_per_tensor_default_619 = None
2025-03-21T20:31:43.4425541Z             quantized_decomposed_quantize_per_tensor_default_358: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_32, 0.0002832972095347941, 23707, 0, 65535, torch.int32);  aten_mul_tensor_32 = None
2025-03-21T20:31:43.4426687Z             quantized_decomposed_dequantize_per_tensor_default_624: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_358, 0.0002832972095347941, 23707, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_358 = None
2025-03-21T20:31:43.4427803Z             aten_mul_tensor_33: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_608, quantized_decomposed_dequantize_per_tensor_default_622);  quantized_decomposed_dequantize_per_tensor_default_608 = quantized_decomposed_dequantize_per_tensor_default_622 = None
2025-03-21T20:31:43.4428669Z             quantized_decomposed_quantize_per_tensor_default_359: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_33, 0.00015349165187217295, 32189, 0, 65535, torch.int32);  aten_mul_tensor_33 = None
2025-03-21T20:31:43.4429804Z             quantized_decomposed_dequantize_per_tensor_default_625: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_359, 0.00015349165187217295, 32189, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_359 = None
2025-03-21T20:31:43.4430923Z             aten_sub_tensor_4: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_sub_Tensor(quantized_decomposed_dequantize_per_tensor_default_624, quantized_decomposed_dequantize_per_tensor_default_625);  quantized_decomposed_dequantize_per_tensor_default_624 = quantized_decomposed_dequantize_per_tensor_default_625 = None
2025-03-21T20:31:43.4431763Z             quantized_decomposed_quantize_per_tensor_default_360: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_sub_tensor_4, 0.000280614010989666, 23955, 0, 65535, torch.int32);  aten_sub_tensor_4 = None
2025-03-21T20:31:43.4431863Z             
2025-03-21T20:31:43.4433048Z              # File: <eval_with_key>.50:1531 in forward, code: dequantize_per_tensor_default_511 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_511, 0.000280614010989666, 23955, 0, 65535, torch.int32);  quantize_per_tensor_default_511 = None
2025-03-21T20:31:43.4434232Z             quantized_decomposed_dequantize_per_tensor_default_626: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_360, 0.000280614010989666, 23955, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_360 = None
2025-03-21T20:31:43.4434326Z             
2025-03-21T20:31:43.4434846Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.4435963Z             aten_mul_tensor_34: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_606, quantized_decomposed_dequantize_per_tensor_default_623);  quantized_decomposed_dequantize_per_tensor_default_606 = quantized_decomposed_dequantize_per_tensor_default_623 = None
2025-03-21T20:31:43.4436828Z             quantized_decomposed_quantize_per_tensor_default_361: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_34, 0.00019744332530535758, 33781, 0, 65535, torch.int32);  aten_mul_tensor_34 = None
2025-03-21T20:31:43.4438010Z             quantized_decomposed_dequantize_per_tensor_default_627: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_361, 0.00019744332530535758, 33781, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_361 = None
2025-03-21T20:31:43.4439132Z             aten_mul_tensor_35: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_609, quantized_decomposed_dequantize_per_tensor_default_618);  quantized_decomposed_dequantize_per_tensor_default_609 = quantized_decomposed_dequantize_per_tensor_default_618 = None
2025-03-21T20:31:43.4439993Z             quantized_decomposed_quantize_per_tensor_default_362: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_35, 0.0003398616099730134, 16524, 0, 65535, torch.int32);  aten_mul_tensor_35 = None
2025-03-21T20:31:43.4441131Z             quantized_decomposed_dequantize_per_tensor_default_628: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_362, 0.0003398616099730134, 16524, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_362 = None
2025-03-21T20:31:43.4442254Z             aten_add_tensor_10: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_627, quantized_decomposed_dequantize_per_tensor_default_628);  quantized_decomposed_dequantize_per_tensor_default_627 = quantized_decomposed_dequantize_per_tensor_default_628 = None
2025-03-21T20:31:43.4443099Z             quantized_decomposed_quantize_per_tensor_default_363: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_10, 0.0003456322301644832, 18868, 0, 65535, torch.int32);  aten_add_tensor_10 = None
2025-03-21T20:31:43.4443201Z             
2025-03-21T20:31:43.4444129Z              # File: <eval_with_key>.50:1540 in forward, code: dequantize_per_tensor_default_514 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_514, 0.0003456322301644832, 18868, 0, 65535, torch.int32);  quantize_per_tensor_default_514 = None
2025-03-21T20:31:43.4445308Z             quantized_decomposed_dequantize_per_tensor_default_629: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_363, 0.0003456322301644832, 18868, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_363 = None
2025-03-21T20:31:43.4445421Z             
2025-03-21T20:31:43.4445910Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.4447045Z             aten_mul_tensor_36: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_613, quantized_decomposed_dequantize_per_tensor_default_617);  quantized_decomposed_dequantize_per_tensor_default_613 = quantized_decomposed_dequantize_per_tensor_default_617 = None
2025-03-21T20:31:43.4447905Z             quantized_decomposed_quantize_per_tensor_default_364: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_36, 0.0002919230901170522, 23481, 0, 65535, torch.int32);  aten_mul_tensor_36 = None
2025-03-21T20:31:43.4449037Z             quantized_decomposed_dequantize_per_tensor_default_630: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_364, 0.0002919230901170522, 23481, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_364 = None
2025-03-21T20:31:43.4450251Z             aten_mul_tensor_37: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_614, quantized_decomposed_dequantize_per_tensor_default_620);  quantized_decomposed_dequantize_per_tensor_default_614 = quantized_decomposed_dequantize_per_tensor_default_620 = None
2025-03-21T20:31:43.4451107Z             quantized_decomposed_quantize_per_tensor_default_365: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_37, 0.00021678538178093731, 35772, 0, 65535, torch.int32);  aten_mul_tensor_37 = None
2025-03-21T20:31:43.4452254Z             quantized_decomposed_dequantize_per_tensor_default_631: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_365, 0.00021678538178093731, 35772, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_365 = None
2025-03-21T20:31:43.4453360Z             aten_sub_tensor_5: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_sub_Tensor(quantized_decomposed_dequantize_per_tensor_default_630, quantized_decomposed_dequantize_per_tensor_default_631);  quantized_decomposed_dequantize_per_tensor_default_630 = quantized_decomposed_dequantize_per_tensor_default_631 = None
2025-03-21T20:31:43.4454213Z             quantized_decomposed_quantize_per_tensor_default_366: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_sub_tensor_5, 0.0002932342467829585, 23779, 0, 65535, torch.int32);  aten_sub_tensor_5 = None
2025-03-21T20:31:43.4454302Z             
2025-03-21T20:31:43.4455246Z              # File: <eval_with_key>.50:1549 in forward, code: dequantize_per_tensor_default_517 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_517, 0.0002932342467829585, 23779, 0, 65535, torch.int32);  quantize_per_tensor_default_517 = None
2025-03-21T20:31:43.4456380Z             quantized_decomposed_dequantize_per_tensor_default_632: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_366, 0.0002932342467829585, 23779, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_366 = None
2025-03-21T20:31:43.4456483Z             
2025-03-21T20:31:43.4456994Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.4458143Z             aten_mul_tensor_38: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_612, quantized_decomposed_dequantize_per_tensor_default_621);  quantized_decomposed_dequantize_per_tensor_default_612 = quantized_decomposed_dequantize_per_tensor_default_621 = None
2025-03-21T20:31:43.4459016Z             quantized_decomposed_quantize_per_tensor_default_367: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_38, 0.0001832414127420634, 33825, 0, 65535, torch.int32);  aten_mul_tensor_38 = None
2025-03-21T20:31:43.4460158Z             quantized_decomposed_dequantize_per_tensor_default_633: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_367, 0.0001832414127420634, 33825, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_367 = None
2025-03-21T20:31:43.4461278Z             aten_mul_tensor_39: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_615, quantized_decomposed_dequantize_per_tensor_default_616);  quantized_decomposed_dequantize_per_tensor_default_615 = quantized_decomposed_dequantize_per_tensor_default_616 = None
2025-03-21T20:31:43.4462147Z             quantized_decomposed_quantize_per_tensor_default_368: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_39, 0.0003678293142002076, 31068, 0, 65535, torch.int32);  aten_mul_tensor_39 = None
2025-03-21T20:31:43.4463291Z             quantized_decomposed_dequantize_per_tensor_default_634: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_368, 0.0003678293142002076, 31068, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_368 = None
2025-03-21T20:31:43.4464394Z             aten_add_tensor_11: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_633, quantized_decomposed_dequantize_per_tensor_default_634);  quantized_decomposed_dequantize_per_tensor_default_633 = quantized_decomposed_dequantize_per_tensor_default_634 = None
2025-03-21T20:31:43.4465258Z             quantized_decomposed_quantize_per_tensor_default_369: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_11, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_add_tensor_11 = None
2025-03-21T20:31:43.4465345Z             
2025-03-21T20:31:43.4466291Z              # File: <eval_with_key>.50:1558 in forward, code: dequantize_per_tensor_default_520 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_520, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantize_per_tensor_default_520 = None
2025-03-21T20:31:43.4467426Z             quantized_decomposed_dequantize_per_tensor_default_635: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_369, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_369 = None
2025-03-21T20:31:43.4467527Z             
2025-03-21T20:31:43.4468053Z              # File: /pytorch/executorch/examples/models/llama/rope.py:95 in apply_rotary_emb, code: xq_out = torch.stack([xq_out_r, xq_out_i], dim=-1).flatten(3)
2025-03-21T20:31:43.4468857Z             aten_unsqueeze_copy_default_25: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_626, 4);  quantized_decomposed_dequantize_per_tensor_default_626 = None
2025-03-21T20:31:43.4469691Z             aten_unsqueeze_copy_default_26: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_629, 4);  quantized_decomposed_dequantize_per_tensor_default_629 = None
2025-03-21T20:31:43.4470443Z             aten_cat_default_8: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_cat_default([aten_unsqueeze_copy_default_25, aten_unsqueeze_copy_default_26], -1);  aten_unsqueeze_copy_default_25 = aten_unsqueeze_copy_default_26 = None
2025-03-21T20:31:43.4471316Z             quantized_decomposed_quantize_per_tensor_default_370: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_8, 0.0003486985806375742, 19278, 0, 65535, torch.int32);  aten_cat_default_8 = None
2025-03-21T20:31:43.4472462Z             quantized_decomposed_dequantize_per_tensor_default_636: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_370, 0.0003486985806375742, 19278, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_370 = None
2025-03-21T20:31:43.4473215Z             aten_view_copy_default_43: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_636, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_636 = None
2025-03-21T20:31:43.4474147Z             quantized_decomposed_quantize_per_tensor_default_371: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_43, 0.0003486985806375742, 19278, 0, 65535, torch.int32);  aten_view_copy_default_43 = None
2025-03-21T20:31:43.4474234Z             
2025-03-21T20:31:43.4475179Z              # File: <eval_with_key>.50:1564 in forward, code: dequantize_per_tensor_default_522 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_522, 0.0003486985806375742, 19278, 0, 65535, torch.int32);  quantize_per_tensor_default_522 = None
2025-03-21T20:31:43.4476306Z             quantized_decomposed_dequantize_per_tensor_default_637: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_371, 0.0003486985806375742, 19278, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_371 = None
2025-03-21T20:31:43.4476408Z             
2025-03-21T20:31:43.4476927Z              # File: /pytorch/executorch/examples/models/llama/rope.py:96 in apply_rotary_emb, code: xk_out = torch.stack([xk_out_r, xk_out_i], dim=-1).flatten(3)
2025-03-21T20:31:43.4477734Z             aten_unsqueeze_copy_default_27: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_632, 4);  quantized_decomposed_dequantize_per_tensor_default_632 = None
2025-03-21T20:31:43.4478517Z             aten_unsqueeze_copy_default_28: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_635, 4);  quantized_decomposed_dequantize_per_tensor_default_635 = None
2025-03-21T20:31:43.4479258Z             aten_cat_default_9: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_cat_default([aten_unsqueeze_copy_default_27, aten_unsqueeze_copy_default_28], -1);  aten_unsqueeze_copy_default_27 = aten_unsqueeze_copy_default_28 = None
2025-03-21T20:31:43.4480121Z             quantized_decomposed_quantize_per_tensor_default_372: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_9, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_cat_default_9 = None
2025-03-21T20:31:43.4481296Z             quantized_decomposed_dequantize_per_tensor_default_638: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_372, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_372 = None
2025-03-21T20:31:43.4482083Z             aten_view_copy_default_44: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_638, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_638 = None
2025-03-21T20:31:43.4483018Z             quantized_decomposed_quantize_per_tensor_default_373: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_44, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_view_copy_default_44 = None
2025-03-21T20:31:43.4483108Z             
2025-03-21T20:31:43.4484057Z              # File: <eval_with_key>.50:1570 in forward, code: dequantize_per_tensor_default_524 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_524, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantize_per_tensor_default_524 = None
2025-03-21T20:31:43.4485196Z             quantized_decomposed_dequantize_per_tensor_default_639: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_373, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_373 = None
2025-03-21T20:31:43.4485334Z             
2025-03-21T20:31:43.4486084Z              # File: <eval_with_key>.50:1572 in forward, code: quantize_per_tensor_default_525 = torch.ops.quantized_decomposed.quantize_per_tensor.default(type_as_4, 0.0003486985806375742, 19278, 0, 65535, torch.int32);  type_as_4 = None
2025-03-21T20:31:43.4487226Z             quantized_decomposed_quantize_per_tensor_default_374: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_637, 0.0003486985806375742, 19278, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_637 = None
2025-03-21T20:31:43.4487316Z             
2025-03-21T20:31:43.4487858Z              # File: /pytorch/executorch/examples/models/llama/attention.py:249 in forward, code: q = q.transpose(1, 2)  # (bs, n_local_heads, seqlen, head_dim)
2025-03-21T20:31:43.4488990Z             quantized_decomposed_dequantize_per_tensor_default_640: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_374, 0.0003486985806375742, 19278, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_374 = None
2025-03-21T20:31:43.4489088Z             
2025-03-21T20:31:43.4489915Z              # File: <eval_with_key>.50:1575 in forward, code: quantize_per_tensor_default_526 = torch.ops.quantized_decomposed.quantize_per_tensor.default(type_as_5, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  type_as_5 = None
2025-03-21T20:31:43.4491065Z             quantized_decomposed_quantize_per_tensor_default_375: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_639, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_639 = None
2025-03-21T20:31:43.4491155Z             
2025-03-21T20:31:43.4491836Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:345 in update, code: k_out = torch.ops.aten.index_put_(self.past_k_caches, [None, input_pos], k_val)
2025-03-21T20:31:43.4493015Z             quantized_decomposed_dequantize_per_tensor_default_641: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_375, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_375 = None
2025-03-21T20:31:43.4493143Z             
2025-03-21T20:31:43.4493665Z              # File: /pytorch/executorch/examples/models/llama/attention.py:249 in forward, code: q = q.transpose(1, 2)  # (bs, n_local_heads, seqlen, head_dim)
2025-03-21T20:31:43.4494467Z             aten_permute_copy_default_88: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_640, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_640 = None
2025-03-21T20:31:43.4495427Z             quantized_decomposed_quantize_per_tensor_default_376: "i32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_88, 0.0003486985806375742, 19278, 0, 65535, torch.int32);  aten_permute_copy_default_88 = None
2025-03-21T20:31:43.4495527Z             
2025-03-21T20:31:43.4496103Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.4497258Z             quantized_decomposed_dequantize_per_tensor_default_642: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_376, 0.0003486985806375742, 19278, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_376 = None
2025-03-21T20:31:43.4497372Z             
2025-03-21T20:31:43.4498050Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:345 in update, code: k_out = torch.ops.aten.index_put_(self.past_k_caches, [None, input_pos], k_val)
2025-03-21T20:31:43.4499325Z             aten_index_put_default_4: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_index_put_default(quantized_decomposed_dequantize_per_tensor_default_119, [None, attn_options_input_pos], quantized_decomposed_dequantize_per_tensor_default_641);  quantized_decomposed_dequantize_per_tensor_default_119 = quantized_decomposed_dequantize_per_tensor_default_641 = None
2025-03-21T20:31:43.4500244Z             quantized_decomposed_quantize_per_tensor_default_377: "i32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_put_default_4, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_index_put_default_4 = None
2025-03-21T20:31:43.4500335Z             
2025-03-21T20:31:43.4501138Z              # File: <eval_with_key>.50:1582 in forward, code: dequantize_per_tensor_default_528 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_528, 0.00036907364847138524, 31320, 0, 65535, torch.int32)
2025-03-21T20:31:43.4502063Z             quantized_decomposed_dequantize_per_tensor_default_643: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_377, 0.00036907364847138524, 31320, 0, 65535, torch.int32)
2025-03-21T20:31:43.4502171Z             
2025-03-21T20:31:43.4502804Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4503738Z             quantized_decomposed_dequantize_per_tensor_default_644: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_377, 0.00036907364847138524, 31320, 0, 65535, torch.int32)
2025-03-21T20:31:43.4504657Z             quantized_decomposed_dequantize_per_tensor_default_645: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_377, 0.00036907364847138524, 31320, 0, 65535, torch.int32)
2025-03-21T20:31:43.4505613Z             quantized_decomposed_dequantize_per_tensor_default_646: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_377, 0.00036907364847138524, 31320, 0, 65535, torch.int32)
2025-03-21T20:31:43.4506554Z             quantized_decomposed_dequantize_per_tensor_default_647: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_377, 0.00036907364847138524, 31320, 0, 65535, torch.int32)
2025-03-21T20:31:43.4507502Z             quantized_decomposed_dequantize_per_tensor_default_648: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_377, 0.00036907364847138524, 31320, 0, 65535, torch.int32)
2025-03-21T20:31:43.4508419Z             quantized_decomposed_dequantize_per_tensor_default_649: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_377, 0.00036907364847138524, 31320, 0, 65535, torch.int32)
2025-03-21T20:31:43.4509349Z             quantized_decomposed_dequantize_per_tensor_default_650: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_377, 0.00036907364847138524, 31320, 0, 65535, torch.int32)
2025-03-21T20:31:43.4510286Z             quantized_decomposed_dequantize_per_tensor_default_651: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_377, 0.00036907364847138524, 31320, 0, 65535, torch.int32)
2025-03-21T20:31:43.4511209Z             quantized_decomposed_dequantize_per_tensor_default_652: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_377, 0.00036907364847138524, 31320, 0, 65535, torch.int32)
2025-03-21T20:31:43.4512125Z             quantized_decomposed_dequantize_per_tensor_default_653: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_377, 0.00036907364847138524, 31320, 0, 65535, torch.int32)
2025-03-21T20:31:43.4513059Z             quantized_decomposed_dequantize_per_tensor_default_654: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_377, 0.00036907364847138524, 31320, 0, 65535, torch.int32)
2025-03-21T20:31:43.4514210Z             quantized_decomposed_dequantize_per_tensor_default_655: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_377, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_377 = None
2025-03-21T20:31:43.4514319Z             
2025-03-21T20:31:43.4514990Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:346 in update, code: v_out = torch.ops.aten.index_put_(self.past_v_caches, [None, input_pos], v_val)
2025-03-21T20:31:43.4516283Z             aten_index_put_default_5: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_index_put_default(quantized_decomposed_dequantize_per_tensor_default_120, [None, attn_options_input_pos], quantized_decomposed_dequantize_per_tensor_default_603);  quantized_decomposed_dequantize_per_tensor_default_120 = quantized_decomposed_dequantize_per_tensor_default_603 = None
2025-03-21T20:31:43.4517211Z             quantized_decomposed_quantize_per_tensor_default_378: "i32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_put_default_5, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_index_put_default_5 = None
2025-03-21T20:31:43.4517342Z             
2025-03-21T20:31:43.4518132Z              # File: <eval_with_key>.50:1597 in forward, code: dequantize_per_tensor_default_529 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_529, 9.550915274303406e-05, 30065, 0, 65535, torch.int32)
2025-03-21T20:31:43.4519160Z             quantized_decomposed_dequantize_per_tensor_default_656: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_378, 9.550915274303406e-05, 30065, 0, 65535, torch.int32)
2025-03-21T20:31:43.4519271Z             
2025-03-21T20:31:43.4519980Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4520901Z             quantized_decomposed_dequantize_per_tensor_default_657: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_378, 9.550915274303406e-05, 30065, 0, 65535, torch.int32)
2025-03-21T20:31:43.4521859Z             quantized_decomposed_dequantize_per_tensor_default_658: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_378, 9.550915274303406e-05, 30065, 0, 65535, torch.int32)
2025-03-21T20:31:43.4522772Z             quantized_decomposed_dequantize_per_tensor_default_659: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_378, 9.550915274303406e-05, 30065, 0, 65535, torch.int32)
2025-03-21T20:31:43.4523695Z             quantized_decomposed_dequantize_per_tensor_default_660: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_378, 9.550915274303406e-05, 30065, 0, 65535, torch.int32)
2025-03-21T20:31:43.4524619Z             quantized_decomposed_dequantize_per_tensor_default_661: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_378, 9.550915274303406e-05, 30065, 0, 65535, torch.int32)
2025-03-21T20:31:43.4525530Z             quantized_decomposed_dequantize_per_tensor_default_662: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_378, 9.550915274303406e-05, 30065, 0, 65535, torch.int32)
2025-03-21T20:31:43.4526460Z             quantized_decomposed_dequantize_per_tensor_default_663: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_378, 9.550915274303406e-05, 30065, 0, 65535, torch.int32)
2025-03-21T20:31:43.4527366Z             quantized_decomposed_dequantize_per_tensor_default_664: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_378, 9.550915274303406e-05, 30065, 0, 65535, torch.int32)
2025-03-21T20:31:43.4528293Z             quantized_decomposed_dequantize_per_tensor_default_665: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_378, 9.550915274303406e-05, 30065, 0, 65535, torch.int32)
2025-03-21T20:31:43.4529200Z             quantized_decomposed_dequantize_per_tensor_default_666: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_378, 9.550915274303406e-05, 30065, 0, 65535, torch.int32)
2025-03-21T20:31:43.4530251Z             quantized_decomposed_dequantize_per_tensor_default_667: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_378, 9.550915274303406e-05, 30065, 0, 65535, torch.int32)
2025-03-21T20:31:43.4531422Z             quantized_decomposed_dequantize_per_tensor_default_668: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_378, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_378 = None
2025-03-21T20:31:43.4531523Z             
2025-03-21T20:31:43.4532153Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4533127Z             aten_permute_copy_default_89: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_655, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_655 = None
2025-03-21T20:31:43.4534068Z             quantized_decomposed_quantize_per_tensor_default_379: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_89, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_permute_copy_default_89 = None
2025-03-21T20:31:43.4535300Z             quantized_decomposed_dequantize_per_tensor_default_669: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_379, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_379 = None
2025-03-21T20:31:43.4536033Z             aten_select_copy_int_96: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_669, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_669 = None
2025-03-21T20:31:43.4536935Z             quantized_decomposed_quantize_per_tensor_default_380: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_96, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_select_copy_int_96 = None
2025-03-21T20:31:43.4538074Z             quantized_decomposed_dequantize_per_tensor_default_670: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_380, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_380 = None
2025-03-21T20:31:43.4538814Z             aten_select_copy_int_97: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_670, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_670 = None
2025-03-21T20:31:43.4539693Z             quantized_decomposed_quantize_per_tensor_default_381: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_97, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_select_copy_int_97 = None
2025-03-21T20:31:43.4539797Z             
2025-03-21T20:31:43.4540733Z              # File: <eval_with_key>.50:1618 in forward, code: dequantize_per_tensor_default_532 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_532, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantize_per_tensor_default_532 = None
2025-03-21T20:31:43.4541926Z             quantized_decomposed_dequantize_per_tensor_default_671: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_381, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_381 = None
2025-03-21T20:31:43.4542045Z             
2025-03-21T20:31:43.4542699Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4543491Z             aten_permute_copy_default_90: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_654, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_654 = None
2025-03-21T20:31:43.4544462Z             quantized_decomposed_quantize_per_tensor_default_382: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_90, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_permute_copy_default_90 = None
2025-03-21T20:31:43.4545611Z             quantized_decomposed_dequantize_per_tensor_default_672: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_382, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_382 = None
2025-03-21T20:31:43.4546377Z             aten_select_copy_int_98: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_672, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_672 = None
2025-03-21T20:31:43.4547281Z             quantized_decomposed_quantize_per_tensor_default_383: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_98, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_select_copy_int_98 = None
2025-03-21T20:31:43.4548422Z             quantized_decomposed_dequantize_per_tensor_default_673: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_383, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_383 = None
2025-03-21T20:31:43.4549161Z             aten_select_copy_int_99: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_673, 0, 1);  quantized_decomposed_dequantize_per_tensor_default_673 = None
2025-03-21T20:31:43.4550047Z             quantized_decomposed_quantize_per_tensor_default_384: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_99, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_select_copy_int_99 = None
2025-03-21T20:31:43.4550148Z             
2025-03-21T20:31:43.4551082Z              # File: <eval_with_key>.50:1627 in forward, code: dequantize_per_tensor_default_535 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_535, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantize_per_tensor_default_535 = None
2025-03-21T20:31:43.4552229Z             quantized_decomposed_dequantize_per_tensor_default_674: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_384, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_384 = None
2025-03-21T20:31:43.4552319Z             
2025-03-21T20:31:43.4552969Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4553782Z             aten_permute_copy_default_91: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_653, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_653 = None
2025-03-21T20:31:43.4554746Z             quantized_decomposed_quantize_per_tensor_default_385: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_91, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_permute_copy_default_91 = None
2025-03-21T20:31:43.4555910Z             quantized_decomposed_dequantize_per_tensor_default_675: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_385, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_385 = None
2025-03-21T20:31:43.4556657Z             aten_select_copy_int_100: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_675, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_675 = None
2025-03-21T20:31:43.4557551Z             quantized_decomposed_quantize_per_tensor_default_386: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_100, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_select_copy_int_100 = None
2025-03-21T20:31:43.4558749Z             quantized_decomposed_dequantize_per_tensor_default_676: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_386, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_386 = None
2025-03-21T20:31:43.4559475Z             aten_select_copy_int_101: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_676, 0, 2);  quantized_decomposed_dequantize_per_tensor_default_676 = None
2025-03-21T20:31:43.4560378Z             quantized_decomposed_quantize_per_tensor_default_387: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_101, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_select_copy_int_101 = None
2025-03-21T20:31:43.4560472Z             
2025-03-21T20:31:43.4561414Z              # File: <eval_with_key>.50:1636 in forward, code: dequantize_per_tensor_default_538 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_538, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantize_per_tensor_default_538 = None
2025-03-21T20:31:43.4562549Z             quantized_decomposed_dequantize_per_tensor_default_677: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_387, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_387 = None
2025-03-21T20:31:43.4562650Z             
2025-03-21T20:31:43.4563292Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4564095Z             aten_permute_copy_default_92: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_652, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_652 = None
2025-03-21T20:31:43.4565029Z             quantized_decomposed_quantize_per_tensor_default_388: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_92, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_permute_copy_default_92 = None
2025-03-21T20:31:43.4566207Z             quantized_decomposed_dequantize_per_tensor_default_678: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_388, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_388 = None
2025-03-21T20:31:43.4566966Z             aten_select_copy_int_102: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_678, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_678 = None
2025-03-21T20:31:43.4567894Z             quantized_decomposed_quantize_per_tensor_default_389: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_102, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_select_copy_int_102 = None
2025-03-21T20:31:43.4569033Z             quantized_decomposed_dequantize_per_tensor_default_679: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_389, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_389 = None
2025-03-21T20:31:43.4569844Z             aten_select_copy_int_103: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_679, 0, 3);  quantized_decomposed_dequantize_per_tensor_default_679 = None
2025-03-21T20:31:43.4570771Z             quantized_decomposed_quantize_per_tensor_default_390: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_103, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_select_copy_int_103 = None
2025-03-21T20:31:43.4570876Z             
2025-03-21T20:31:43.4571808Z              # File: <eval_with_key>.50:1645 in forward, code: dequantize_per_tensor_default_541 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_541, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantize_per_tensor_default_541 = None
2025-03-21T20:31:43.4572964Z             quantized_decomposed_dequantize_per_tensor_default_680: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_390, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_390 = None
2025-03-21T20:31:43.4573054Z             
2025-03-21T20:31:43.4573703Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4574493Z             aten_permute_copy_default_93: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_651, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_651 = None
2025-03-21T20:31:43.4575439Z             quantized_decomposed_quantize_per_tensor_default_391: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_93, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_permute_copy_default_93 = None
2025-03-21T20:31:43.4576582Z             quantized_decomposed_dequantize_per_tensor_default_681: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_391, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_391 = None
2025-03-21T20:31:43.4577338Z             aten_select_copy_int_104: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_681, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_681 = None
2025-03-21T20:31:43.4578266Z             quantized_decomposed_quantize_per_tensor_default_392: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_104, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_select_copy_int_104 = None
2025-03-21T20:31:43.4579440Z             quantized_decomposed_dequantize_per_tensor_default_682: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_392, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_392 = None
2025-03-21T20:31:43.4580204Z             aten_select_copy_int_105: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_682, 0, 4);  quantized_decomposed_dequantize_per_tensor_default_682 = None
2025-03-21T20:31:43.4581093Z             quantized_decomposed_quantize_per_tensor_default_393: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_105, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_select_copy_int_105 = None
2025-03-21T20:31:43.4581197Z             
2025-03-21T20:31:43.4582127Z              # File: <eval_with_key>.50:1654 in forward, code: dequantize_per_tensor_default_544 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_544, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantize_per_tensor_default_544 = None
2025-03-21T20:31:43.4583298Z             quantized_decomposed_dequantize_per_tensor_default_683: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_393, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_393 = None
2025-03-21T20:31:43.4583386Z             
2025-03-21T20:31:43.4584032Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4584825Z             aten_permute_copy_default_94: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_650, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_650 = None
2025-03-21T20:31:43.4585772Z             quantized_decomposed_quantize_per_tensor_default_394: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_94, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_permute_copy_default_94 = None
2025-03-21T20:31:43.4586910Z             quantized_decomposed_dequantize_per_tensor_default_684: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_394, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_394 = None
2025-03-21T20:31:43.4587658Z             aten_select_copy_int_106: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_684, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_684 = None
2025-03-21T20:31:43.4588549Z             quantized_decomposed_quantize_per_tensor_default_395: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_106, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_select_copy_int_106 = None
2025-03-21T20:31:43.4589699Z             quantized_decomposed_dequantize_per_tensor_default_685: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_395, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_395 = None
2025-03-21T20:31:43.4590450Z             aten_select_copy_int_107: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_685, 0, 5);  quantized_decomposed_dequantize_per_tensor_default_685 = None
2025-03-21T20:31:43.4591373Z             quantized_decomposed_quantize_per_tensor_default_396: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_107, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_select_copy_int_107 = None
2025-03-21T20:31:43.4591460Z             
2025-03-21T20:31:43.4592426Z              # File: <eval_with_key>.50:1663 in forward, code: dequantize_per_tensor_default_547 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_547, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantize_per_tensor_default_547 = None
2025-03-21T20:31:43.4593570Z             quantized_decomposed_dequantize_per_tensor_default_686: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_396, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_396 = None
2025-03-21T20:31:43.4593699Z             
2025-03-21T20:31:43.4594336Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4595136Z             aten_permute_copy_default_95: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_649, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_649 = None
2025-03-21T20:31:43.4596066Z             quantized_decomposed_quantize_per_tensor_default_397: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_95, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_permute_copy_default_95 = None
2025-03-21T20:31:43.4597215Z             quantized_decomposed_dequantize_per_tensor_default_687: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_397, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_397 = None
2025-03-21T20:31:43.4597952Z             aten_select_copy_int_108: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_687, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_687 = None
2025-03-21T20:31:43.4598854Z             quantized_decomposed_quantize_per_tensor_default_398: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_108, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_select_copy_int_108 = None
2025-03-21T20:31:43.4599992Z             quantized_decomposed_dequantize_per_tensor_default_688: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_398, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_398 = None
2025-03-21T20:31:43.4600734Z             aten_select_copy_int_109: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_688, 0, 6);  quantized_decomposed_dequantize_per_tensor_default_688 = None
2025-03-21T20:31:43.4601634Z             quantized_decomposed_quantize_per_tensor_default_399: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_109, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_select_copy_int_109 = None
2025-03-21T20:31:43.4601724Z             
2025-03-21T20:31:43.4602705Z              # File: <eval_with_key>.50:1672 in forward, code: dequantize_per_tensor_default_550 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_550, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantize_per_tensor_default_550 = None
2025-03-21T20:31:43.4603880Z             quantized_decomposed_dequantize_per_tensor_default_689: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_399, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_399 = None
2025-03-21T20:31:43.4603969Z             
2025-03-21T20:31:43.4604617Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4605407Z             aten_permute_copy_default_96: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_648, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_648 = None
2025-03-21T20:31:43.4606356Z             quantized_decomposed_quantize_per_tensor_default_400: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_96, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_permute_copy_default_96 = None
2025-03-21T20:31:43.4607532Z             quantized_decomposed_dequantize_per_tensor_default_690: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_400, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_400 = None
2025-03-21T20:31:43.4608267Z             aten_select_copy_int_110: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_690, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_690 = None
2025-03-21T20:31:43.4609172Z             quantized_decomposed_quantize_per_tensor_default_401: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_110, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_select_copy_int_110 = None
2025-03-21T20:31:43.4610481Z             quantized_decomposed_dequantize_per_tensor_default_691: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_401, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_401 = None
2025-03-21T20:31:43.4611235Z             aten_select_copy_int_111: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_691, 0, 7);  quantized_decomposed_dequantize_per_tensor_default_691 = None
2025-03-21T20:31:43.4612125Z             quantized_decomposed_quantize_per_tensor_default_402: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_111, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_select_copy_int_111 = None
2025-03-21T20:31:43.4612228Z             
2025-03-21T20:31:43.4613160Z              # File: <eval_with_key>.50:1681 in forward, code: dequantize_per_tensor_default_553 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_553, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantize_per_tensor_default_553 = None
2025-03-21T20:31:43.4614343Z             quantized_decomposed_dequantize_per_tensor_default_692: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_402, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_402 = None
2025-03-21T20:31:43.4614457Z             
2025-03-21T20:31:43.4615107Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4615902Z             aten_permute_copy_default_97: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_647, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_647 = None
2025-03-21T20:31:43.4616882Z             quantized_decomposed_quantize_per_tensor_default_403: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_97, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_permute_copy_default_97 = None
2025-03-21T20:31:43.4618033Z             quantized_decomposed_dequantize_per_tensor_default_693: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_403, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_403 = None
2025-03-21T20:31:43.4618809Z             aten_select_copy_int_112: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_693, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_693 = None
2025-03-21T20:31:43.4619708Z             quantized_decomposed_quantize_per_tensor_default_404: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_112, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_select_copy_int_112 = None
2025-03-21T20:31:43.4621052Z             quantized_decomposed_dequantize_per_tensor_default_694: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_404, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_404 = None
2025-03-21T20:31:43.4621842Z             aten_select_copy_int_113: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_694, 0, 8);  quantized_decomposed_dequantize_per_tensor_default_694 = None
2025-03-21T20:31:43.4622756Z             quantized_decomposed_quantize_per_tensor_default_405: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_113, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_select_copy_int_113 = None
2025-03-21T20:31:43.4622845Z             
2025-03-21T20:31:43.4623795Z              # File: <eval_with_key>.50:1690 in forward, code: dequantize_per_tensor_default_556 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_556, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantize_per_tensor_default_556 = None
2025-03-21T20:31:43.4624933Z             quantized_decomposed_dequantize_per_tensor_default_695: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_405, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_405 = None
2025-03-21T20:31:43.4625034Z             
2025-03-21T20:31:43.4625674Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4626525Z             aten_permute_copy_default_98: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_646, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_646 = None
2025-03-21T20:31:43.4627485Z             quantized_decomposed_quantize_per_tensor_default_406: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_98, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_permute_copy_default_98 = None
2025-03-21T20:31:43.4628668Z             quantized_decomposed_dequantize_per_tensor_default_696: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_406, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_406 = None
2025-03-21T20:31:43.4629403Z             aten_select_copy_int_114: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_696, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_696 = None
2025-03-21T20:31:43.4630308Z             quantized_decomposed_quantize_per_tensor_default_407: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_114, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_select_copy_int_114 = None
2025-03-21T20:31:43.4631473Z             quantized_decomposed_dequantize_per_tensor_default_697: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_407, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_407 = None
2025-03-21T20:31:43.4632369Z             aten_select_copy_int_115: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_697, 0, 9);  quantized_decomposed_dequantize_per_tensor_default_697 = None
2025-03-21T20:31:43.4633288Z             quantized_decomposed_quantize_per_tensor_default_408: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_115, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_select_copy_int_115 = None
2025-03-21T20:31:43.4633381Z             
2025-03-21T20:31:43.4634315Z              # File: <eval_with_key>.50:1699 in forward, code: dequantize_per_tensor_default_559 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_559, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantize_per_tensor_default_559 = None
2025-03-21T20:31:43.4635471Z             quantized_decomposed_dequantize_per_tensor_default_698: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_408, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_408 = None
2025-03-21T20:31:43.4635575Z             
2025-03-21T20:31:43.4636218Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4637008Z             aten_permute_copy_default_99: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_645, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_645 = None
2025-03-21T20:31:43.4637959Z             quantized_decomposed_quantize_per_tensor_default_409: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_99, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_permute_copy_default_99 = None
2025-03-21T20:31:43.4639180Z             quantized_decomposed_dequantize_per_tensor_default_699: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_409, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_409 = None
2025-03-21T20:31:43.4639950Z             aten_select_copy_int_116: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_699, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_699 = None
2025-03-21T20:31:43.4640897Z             quantized_decomposed_quantize_per_tensor_default_410: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_116, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_select_copy_int_116 = None
2025-03-21T20:31:43.4642038Z             quantized_decomposed_dequantize_per_tensor_default_700: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_410, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_410 = None
2025-03-21T20:31:43.4642787Z             aten_select_copy_int_117: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_700, 0, 10);  quantized_decomposed_dequantize_per_tensor_default_700 = None
2025-03-21T20:31:43.4643710Z             quantized_decomposed_quantize_per_tensor_default_411: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_117, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_select_copy_int_117 = None
2025-03-21T20:31:43.4643814Z             
2025-03-21T20:31:43.4644747Z              # File: <eval_with_key>.50:1708 in forward, code: dequantize_per_tensor_default_562 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_562, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantize_per_tensor_default_562 = None
2025-03-21T20:31:43.4645902Z             quantized_decomposed_dequantize_per_tensor_default_701: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_411, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_411 = None
2025-03-21T20:31:43.4645992Z             
2025-03-21T20:31:43.4646641Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4647438Z             aten_permute_copy_default_100: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_644, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_644 = None
2025-03-21T20:31:43.4648393Z             quantized_decomposed_quantize_per_tensor_default_412: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_100, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_permute_copy_default_100 = None
2025-03-21T20:31:43.4649603Z             quantized_decomposed_dequantize_per_tensor_default_702: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_412, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_412 = None
2025-03-21T20:31:43.4650357Z             aten_select_copy_int_118: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_702, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_702 = None
2025-03-21T20:31:43.4651285Z             quantized_decomposed_quantize_per_tensor_default_413: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_118, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_select_copy_int_118 = None
2025-03-21T20:31:43.4652524Z             quantized_decomposed_dequantize_per_tensor_default_703: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_413, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_413 = None
2025-03-21T20:31:43.4653296Z             aten_select_copy_int_119: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_703, 0, 11);  quantized_decomposed_dequantize_per_tensor_default_703 = None
2025-03-21T20:31:43.4654202Z             quantized_decomposed_quantize_per_tensor_default_414: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_119, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_select_copy_int_119 = None
2025-03-21T20:31:43.4654295Z             
2025-03-21T20:31:43.4655239Z              # File: <eval_with_key>.50:1717 in forward, code: dequantize_per_tensor_default_565 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_565, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantize_per_tensor_default_565 = None
2025-03-21T20:31:43.4656410Z             quantized_decomposed_dequantize_per_tensor_default_704: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_414, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_414 = None
2025-03-21T20:31:43.4656509Z             
2025-03-21T20:31:43.4657152Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4662554Z             aten_cat_default_10: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_aten_cat_default([quantized_decomposed_dequantize_per_tensor_default_671, quantized_decomposed_dequantize_per_tensor_default_674, quantized_decomposed_dequantize_per_tensor_default_677, quantized_decomposed_dequantize_per_tensor_default_680, quantized_decomposed_dequantize_per_tensor_default_683, quantized_decomposed_dequantize_per_tensor_default_686, quantized_decomposed_dequantize_per_tensor_default_689, quantized_decomposed_dequantize_per_tensor_default_692, quantized_decomposed_dequantize_per_tensor_default_695, quantized_decomposed_dequantize_per_tensor_default_698, quantized_decomposed_dequantize_per_tensor_default_701, quantized_decomposed_dequantize_per_tensor_default_704]);  quantized_decomposed_dequantize_per_tensor_default_671 = quantized_decomposed_dequantize_per_tensor_default_674 = quantized_decomposed_dequantize_per_tensor_default_677 = quantized_decomposed_dequantize_per_tensor_default_680 = quantized_decomposed_dequantize_per_tensor_default_683 = quantized_decomposed_dequantize_per_tensor_default_686 = quantized_decomposed_dequantize_per_tensor_default_689 = quantized_decomposed_dequantize_per_tensor_default_692 = quantized_decomposed_dequantize_per_tensor_default_695 = quantized_decomposed_dequantize_per_tensor_default_698 = quantized_decomposed_dequantize_per_tensor_default_701 = quantized_decomposed_dequantize_per_tensor_default_704 = None
2025-03-21T20:31:43.4663438Z             quantized_decomposed_quantize_per_tensor_default_415: "i32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_10, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_cat_default_10 = None
2025-03-21T20:31:43.4664615Z             quantized_decomposed_dequantize_per_tensor_default_705: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_415, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_415 = None
2025-03-21T20:31:43.4665419Z             aten_view_copy_default_45: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_705, [1, 12, 128, 64]);  quantized_decomposed_dequantize_per_tensor_default_705 = None
2025-03-21T20:31:43.4666364Z             quantized_decomposed_quantize_per_tensor_default_416: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_45, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_view_copy_default_45 = None
2025-03-21T20:31:43.4666454Z             
2025-03-21T20:31:43.4667030Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.4668191Z             quantized_decomposed_dequantize_per_tensor_default_706: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_416, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_416 = None
2025-03-21T20:31:43.4668313Z             
2025-03-21T20:31:43.4668958Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4669750Z             aten_permute_copy_default_101: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_668, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_668 = None
2025-03-21T20:31:43.4670697Z             quantized_decomposed_quantize_per_tensor_default_417: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_101, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_permute_copy_default_101 = None
2025-03-21T20:31:43.4671847Z             quantized_decomposed_dequantize_per_tensor_default_707: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_417, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_417 = None
2025-03-21T20:31:43.4672581Z             aten_select_copy_int_120: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_707, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_707 = None
2025-03-21T20:31:43.4673484Z             quantized_decomposed_quantize_per_tensor_default_418: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_120, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_select_copy_int_120 = None
2025-03-21T20:31:43.4674615Z             quantized_decomposed_dequantize_per_tensor_default_708: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_418, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_418 = None
2025-03-21T20:31:43.4675355Z             aten_select_copy_int_121: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_708, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_708 = None
2025-03-21T20:31:43.4676259Z             quantized_decomposed_quantize_per_tensor_default_419: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_121, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_select_copy_int_121 = None
2025-03-21T20:31:43.4676396Z             
2025-03-21T20:31:43.4677317Z              # File: <eval_with_key>.50:1732 in forward, code: dequantize_per_tensor_default_570 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_570, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantize_per_tensor_default_570 = None
2025-03-21T20:31:43.4678486Z             quantized_decomposed_dequantize_per_tensor_default_709: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_419, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_419 = None
2025-03-21T20:31:43.4678577Z             
2025-03-21T20:31:43.4679224Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4680017Z             aten_permute_copy_default_102: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_667, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_667 = None
2025-03-21T20:31:43.4680987Z             quantized_decomposed_quantize_per_tensor_default_420: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_102, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_permute_copy_default_102 = None
2025-03-21T20:31:43.4682121Z             quantized_decomposed_dequantize_per_tensor_default_710: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_420, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_420 = None
2025-03-21T20:31:43.4682873Z             aten_select_copy_int_122: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_710, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_710 = None
2025-03-21T20:31:43.4683761Z             quantized_decomposed_quantize_per_tensor_default_421: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_122, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_select_copy_int_122 = None
2025-03-21T20:31:43.4684907Z             quantized_decomposed_dequantize_per_tensor_default_711: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_421, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_421 = None
2025-03-21T20:31:43.4685638Z             aten_select_copy_int_123: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_711, 0, 1);  quantized_decomposed_dequantize_per_tensor_default_711 = None
2025-03-21T20:31:43.4686533Z             quantized_decomposed_quantize_per_tensor_default_422: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_123, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_select_copy_int_123 = None
2025-03-21T20:31:43.4686623Z             
2025-03-21T20:31:43.4687562Z              # File: <eval_with_key>.50:1741 in forward, code: dequantize_per_tensor_default_573 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_573, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantize_per_tensor_default_573 = None
2025-03-21T20:31:43.4688718Z             quantized_decomposed_dequantize_per_tensor_default_712: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_422, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_422 = None
2025-03-21T20:31:43.4688847Z             
2025-03-21T20:31:43.4689550Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4690390Z             aten_permute_copy_default_103: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_666, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_666 = None
2025-03-21T20:31:43.4691325Z             quantized_decomposed_quantize_per_tensor_default_423: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_103, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_permute_copy_default_103 = None
2025-03-21T20:31:43.4692471Z             quantized_decomposed_dequantize_per_tensor_default_713: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_423, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_423 = None
2025-03-21T20:31:43.4693229Z             aten_select_copy_int_124: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_713, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_713 = None
2025-03-21T20:31:43.4694126Z             quantized_decomposed_quantize_per_tensor_default_424: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_124, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_select_copy_int_124 = None
2025-03-21T20:31:43.4695261Z             quantized_decomposed_dequantize_per_tensor_default_714: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_424, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_424 = None
2025-03-21T20:31:43.4696003Z             aten_select_copy_int_125: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_714, 0, 2);  quantized_decomposed_dequantize_per_tensor_default_714 = None
2025-03-21T20:31:43.4696898Z             quantized_decomposed_quantize_per_tensor_default_425: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_125, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_select_copy_int_125 = None
2025-03-21T20:31:43.4696985Z             
2025-03-21T20:31:43.4697916Z              # File: <eval_with_key>.50:1750 in forward, code: dequantize_per_tensor_default_576 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_576, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantize_per_tensor_default_576 = None
2025-03-21T20:31:43.4699067Z             quantized_decomposed_dequantize_per_tensor_default_715: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_425, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_425 = None
2025-03-21T20:31:43.4699154Z             
2025-03-21T20:31:43.4699799Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4700617Z             aten_permute_copy_default_104: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_665, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_665 = None
2025-03-21T20:31:43.4701583Z             quantized_decomposed_quantize_per_tensor_default_426: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_104, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_permute_copy_default_104 = None
2025-03-21T20:31:43.4702781Z             quantized_decomposed_dequantize_per_tensor_default_716: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_426, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_426 = None
2025-03-21T20:31:43.4703517Z             aten_select_copy_int_126: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_716, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_716 = None
2025-03-21T20:31:43.4704415Z             quantized_decomposed_quantize_per_tensor_default_427: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_126, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_select_copy_int_126 = None
2025-03-21T20:31:43.4705572Z             quantized_decomposed_dequantize_per_tensor_default_717: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_427, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_427 = None
2025-03-21T20:31:43.4706315Z             aten_select_copy_int_127: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_717, 0, 3);  quantized_decomposed_dequantize_per_tensor_default_717 = None
2025-03-21T20:31:43.4707196Z             quantized_decomposed_quantize_per_tensor_default_428: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_127, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_select_copy_int_127 = None
2025-03-21T20:31:43.4707297Z             
2025-03-21T20:31:43.4708221Z              # File: <eval_with_key>.50:1759 in forward, code: dequantize_per_tensor_default_579 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_579, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantize_per_tensor_default_579 = None
2025-03-21T20:31:43.4709366Z             quantized_decomposed_dequantize_per_tensor_default_718: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_428, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_428 = None
2025-03-21T20:31:43.4709457Z             
2025-03-21T20:31:43.4710105Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4710906Z             aten_permute_copy_default_105: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_664, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_664 = None
2025-03-21T20:31:43.4711849Z             quantized_decomposed_quantize_per_tensor_default_429: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_105, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_permute_copy_default_105 = None
2025-03-21T20:31:43.4713005Z             quantized_decomposed_dequantize_per_tensor_default_719: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_429, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_429 = None
2025-03-21T20:31:43.4713775Z             aten_select_copy_int_128: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_719, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_719 = None
2025-03-21T20:31:43.4714693Z             quantized_decomposed_quantize_per_tensor_default_430: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_128, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_select_copy_int_128 = None
2025-03-21T20:31:43.4715836Z             quantized_decomposed_dequantize_per_tensor_default_720: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_430, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_430 = None
2025-03-21T20:31:43.4716591Z             aten_select_copy_int_129: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_720, 0, 4);  quantized_decomposed_dequantize_per_tensor_default_720 = None
2025-03-21T20:31:43.4717490Z             quantized_decomposed_quantize_per_tensor_default_431: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_129, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_select_copy_int_129 = None
2025-03-21T20:31:43.4717580Z             
2025-03-21T20:31:43.4718519Z              # File: <eval_with_key>.50:1768 in forward, code: dequantize_per_tensor_default_582 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_582, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantize_per_tensor_default_582 = None
2025-03-21T20:31:43.4719651Z             quantized_decomposed_dequantize_per_tensor_default_721: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_431, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_431 = None
2025-03-21T20:31:43.4719755Z             
2025-03-21T20:31:43.4720396Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4721205Z             aten_permute_copy_default_106: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_663, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_663 = None
2025-03-21T20:31:43.4722143Z             quantized_decomposed_quantize_per_tensor_default_432: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_106, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_permute_copy_default_106 = None
2025-03-21T20:31:43.4723424Z             quantized_decomposed_dequantize_per_tensor_default_722: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_432, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_432 = None
2025-03-21T20:31:43.4724165Z             aten_select_copy_int_130: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_722, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_722 = None
2025-03-21T20:31:43.4725121Z             quantized_decomposed_quantize_per_tensor_default_433: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_130, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_select_copy_int_130 = None
2025-03-21T20:31:43.4726273Z             quantized_decomposed_dequantize_per_tensor_default_723: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_433, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_433 = None
2025-03-21T20:31:43.4727014Z             aten_select_copy_int_131: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_723, 0, 5);  quantized_decomposed_dequantize_per_tensor_default_723 = None
2025-03-21T20:31:43.4727905Z             quantized_decomposed_quantize_per_tensor_default_434: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_131, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_select_copy_int_131 = None
2025-03-21T20:31:43.4728025Z             
2025-03-21T20:31:43.4728953Z              # File: <eval_with_key>.50:1777 in forward, code: dequantize_per_tensor_default_585 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_585, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantize_per_tensor_default_585 = None
2025-03-21T20:31:43.4730377Z             quantized_decomposed_dequantize_per_tensor_default_724: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_434, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_434 = None
2025-03-21T20:31:43.4730487Z             
2025-03-21T20:31:43.4731129Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4731926Z             aten_permute_copy_default_107: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_662, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_662 = None
2025-03-21T20:31:43.4733060Z             quantized_decomposed_quantize_per_tensor_default_435: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_107, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_permute_copy_default_107 = None
2025-03-21T20:31:43.4734209Z             quantized_decomposed_dequantize_per_tensor_default_725: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_435, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_435 = None
2025-03-21T20:31:43.4734942Z             aten_select_copy_int_132: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_725, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_725 = None
2025-03-21T20:31:43.4735843Z             quantized_decomposed_quantize_per_tensor_default_436: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_132, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_select_copy_int_132 = None
2025-03-21T20:31:43.4737042Z             quantized_decomposed_dequantize_per_tensor_default_726: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_436, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_436 = None
2025-03-21T20:31:43.4737821Z             aten_select_copy_int_133: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_726, 0, 6);  quantized_decomposed_dequantize_per_tensor_default_726 = None
2025-03-21T20:31:43.4738738Z             quantized_decomposed_quantize_per_tensor_default_437: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_133, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_select_copy_int_133 = None
2025-03-21T20:31:43.4738840Z             
2025-03-21T20:31:43.4739763Z              # File: <eval_with_key>.50:1786 in forward, code: dequantize_per_tensor_default_588 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_588, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantize_per_tensor_default_588 = None
2025-03-21T20:31:43.4740909Z             quantized_decomposed_dequantize_per_tensor_default_727: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_437, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_437 = None
2025-03-21T20:31:43.4741029Z             
2025-03-21T20:31:43.4741677Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4742471Z             aten_permute_copy_default_108: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_661, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_661 = None
2025-03-21T20:31:43.4743419Z             quantized_decomposed_quantize_per_tensor_default_438: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_108, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_permute_copy_default_108 = None
2025-03-21T20:31:43.4744552Z             quantized_decomposed_dequantize_per_tensor_default_728: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_438, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_438 = None
2025-03-21T20:31:43.4745299Z             aten_select_copy_int_134: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_728, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_728 = None
2025-03-21T20:31:43.4746184Z             quantized_decomposed_quantize_per_tensor_default_439: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_134, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_select_copy_int_134 = None
2025-03-21T20:31:43.4747327Z             quantized_decomposed_dequantize_per_tensor_default_729: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_439, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_439 = None
2025-03-21T20:31:43.4748057Z             aten_select_copy_int_135: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_729, 0, 7);  quantized_decomposed_dequantize_per_tensor_default_729 = None
2025-03-21T20:31:43.4748971Z             quantized_decomposed_quantize_per_tensor_default_440: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_135, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_select_copy_int_135 = None
2025-03-21T20:31:43.4749085Z             
2025-03-21T20:31:43.4750023Z              # File: <eval_with_key>.50:1795 in forward, code: dequantize_per_tensor_default_591 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_591, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantize_per_tensor_default_591 = None
2025-03-21T20:31:43.4751200Z             quantized_decomposed_dequantize_per_tensor_default_730: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_440, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_440 = None
2025-03-21T20:31:43.4751309Z             
2025-03-21T20:31:43.4751949Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4752757Z             aten_permute_copy_default_109: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_660, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_660 = None
2025-03-21T20:31:43.4753714Z             quantized_decomposed_quantize_per_tensor_default_441: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_109, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_permute_copy_default_109 = None
2025-03-21T20:31:43.4754863Z             quantized_decomposed_dequantize_per_tensor_default_731: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_441, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_441 = None
2025-03-21T20:31:43.4755599Z             aten_select_copy_int_136: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_731, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_731 = None
2025-03-21T20:31:43.4756499Z             quantized_decomposed_quantize_per_tensor_default_442: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_136, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_select_copy_int_136 = None
2025-03-21T20:31:43.4757641Z             quantized_decomposed_dequantize_per_tensor_default_732: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_442, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_442 = None
2025-03-21T20:31:43.4758369Z             aten_select_copy_int_137: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_732, 0, 8);  quantized_decomposed_dequantize_per_tensor_default_732 = None
2025-03-21T20:31:43.4759263Z             quantized_decomposed_quantize_per_tensor_default_443: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_137, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_select_copy_int_137 = None
2025-03-21T20:31:43.4759351Z             
2025-03-21T20:31:43.4760289Z              # File: <eval_with_key>.50:1804 in forward, code: dequantize_per_tensor_default_594 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_594, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantize_per_tensor_default_594 = None
2025-03-21T20:31:43.4761441Z             quantized_decomposed_dequantize_per_tensor_default_733: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_443, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_443 = None
2025-03-21T20:31:43.4761584Z             
2025-03-21T20:31:43.4762219Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4763048Z             aten_permute_copy_default_110: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_659, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_659 = None
2025-03-21T20:31:43.4763983Z             quantized_decomposed_quantize_per_tensor_default_444: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_110, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_permute_copy_default_110 = None
2025-03-21T20:31:43.4765129Z             quantized_decomposed_dequantize_per_tensor_default_734: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_444, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_444 = None
2025-03-21T20:31:43.4765889Z             aten_select_copy_int_138: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_734, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_734 = None
2025-03-21T20:31:43.4766787Z             quantized_decomposed_quantize_per_tensor_default_445: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_138, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_select_copy_int_138 = None
2025-03-21T20:31:43.4767919Z             quantized_decomposed_dequantize_per_tensor_default_735: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_445, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_445 = None
2025-03-21T20:31:43.4768678Z             aten_select_copy_int_139: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_735, 0, 9);  quantized_decomposed_dequantize_per_tensor_default_735 = None
2025-03-21T20:31:43.4769624Z             quantized_decomposed_quantize_per_tensor_default_446: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_139, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_select_copy_int_139 = None
2025-03-21T20:31:43.4769731Z             
2025-03-21T20:31:43.4770660Z              # File: <eval_with_key>.50:1813 in forward, code: dequantize_per_tensor_default_597 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_597, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantize_per_tensor_default_597 = None
2025-03-21T20:31:43.4771807Z             quantized_decomposed_dequantize_per_tensor_default_736: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_446, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_446 = None
2025-03-21T20:31:43.4771896Z             
2025-03-21T20:31:43.4772547Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4773375Z             aten_permute_copy_default_111: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_658, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_658 = None
2025-03-21T20:31:43.4774348Z             quantized_decomposed_quantize_per_tensor_default_447: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_111, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_permute_copy_default_111 = None
2025-03-21T20:31:43.4775506Z             quantized_decomposed_dequantize_per_tensor_default_737: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_447, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_447 = None
2025-03-21T20:31:43.4776252Z             aten_select_copy_int_140: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_737, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_737 = None
2025-03-21T20:31:43.4777138Z             quantized_decomposed_quantize_per_tensor_default_448: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_140, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_select_copy_int_140 = None
2025-03-21T20:31:43.4778308Z             quantized_decomposed_dequantize_per_tensor_default_738: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_448, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_448 = None
2025-03-21T20:31:43.4779043Z             aten_select_copy_int_141: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_738, 0, 10);  quantized_decomposed_dequantize_per_tensor_default_738 = None
2025-03-21T20:31:43.4779940Z             quantized_decomposed_quantize_per_tensor_default_449: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_141, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_select_copy_int_141 = None
2025-03-21T20:31:43.4780032Z             
2025-03-21T20:31:43.4780976Z              # File: <eval_with_key>.50:1822 in forward, code: dequantize_per_tensor_default_600 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_600, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantize_per_tensor_default_600 = None
2025-03-21T20:31:43.4782109Z             quantized_decomposed_dequantize_per_tensor_default_739: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_449, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_449 = None
2025-03-21T20:31:43.4782217Z             
2025-03-21T20:31:43.4782855Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4783665Z             aten_permute_copy_default_112: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_657, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_657 = None
2025-03-21T20:31:43.4784600Z             quantized_decomposed_quantize_per_tensor_default_450: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_112, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_permute_copy_default_112 = None
2025-03-21T20:31:43.4785770Z             quantized_decomposed_dequantize_per_tensor_default_740: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_450, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_450 = None
2025-03-21T20:31:43.4786530Z             aten_select_copy_int_142: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_740, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_740 = None
2025-03-21T20:31:43.4787449Z             quantized_decomposed_quantize_per_tensor_default_451: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_142, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_select_copy_int_142 = None
2025-03-21T20:31:43.4788598Z             quantized_decomposed_dequantize_per_tensor_default_741: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_451, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_451 = None
2025-03-21T20:31:43.4789354Z             aten_select_copy_int_143: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_741, 0, 11);  quantized_decomposed_dequantize_per_tensor_default_741 = None
2025-03-21T20:31:43.4790247Z             quantized_decomposed_quantize_per_tensor_default_452: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_143, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_select_copy_int_143 = None
2025-03-21T20:31:43.4790338Z             
2025-03-21T20:31:43.4791277Z              # File: <eval_with_key>.50:1831 in forward, code: dequantize_per_tensor_default_603 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_603, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantize_per_tensor_default_603 = None
2025-03-21T20:31:43.4792405Z             quantized_decomposed_dequantize_per_tensor_default_742: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_452, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_452 = None
2025-03-21T20:31:43.4792508Z             
2025-03-21T20:31:43.4793142Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.4798573Z             aten_cat_default_11: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_aten_cat_default([quantized_decomposed_dequantize_per_tensor_default_709, quantized_decomposed_dequantize_per_tensor_default_712, quantized_decomposed_dequantize_per_tensor_default_715, quantized_decomposed_dequantize_per_tensor_default_718, quantized_decomposed_dequantize_per_tensor_default_721, quantized_decomposed_dequantize_per_tensor_default_724, quantized_decomposed_dequantize_per_tensor_default_727, quantized_decomposed_dequantize_per_tensor_default_730, quantized_decomposed_dequantize_per_tensor_default_733, quantized_decomposed_dequantize_per_tensor_default_736, quantized_decomposed_dequantize_per_tensor_default_739, quantized_decomposed_dequantize_per_tensor_default_742]);  quantized_decomposed_dequantize_per_tensor_default_709 = quantized_decomposed_dequantize_per_tensor_default_712 = quantized_decomposed_dequantize_per_tensor_default_715 = quantized_decomposed_dequantize_per_tensor_default_718 = quantized_decomposed_dequantize_per_tensor_default_721 = quantized_decomposed_dequantize_per_tensor_default_724 = quantized_decomposed_dequantize_per_tensor_default_727 = quantized_decomposed_dequantize_per_tensor_default_730 = quantized_decomposed_dequantize_per_tensor_default_733 = quantized_decomposed_dequantize_per_tensor_default_736 = quantized_decomposed_dequantize_per_tensor_default_739 = quantized_decomposed_dequantize_per_tensor_default_742 = None
2025-03-21T20:31:43.4799474Z             quantized_decomposed_quantize_per_tensor_default_453: "i32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_11, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_cat_default_11 = None
2025-03-21T20:31:43.4800629Z             quantized_decomposed_dequantize_per_tensor_default_743: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_453, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_453 = None
2025-03-21T20:31:43.4801420Z             aten_view_copy_default_46: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_743, [1, 12, 128, 64]);  quantized_decomposed_dequantize_per_tensor_default_743 = None
2025-03-21T20:31:43.4802318Z             quantized_decomposed_quantize_per_tensor_default_454: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_46, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  aten_view_copy_default_46 = None
2025-03-21T20:31:43.4802442Z             
2025-03-21T20:31:43.4803370Z              # File: <eval_with_key>.50:1837 in forward, code: dequantize_per_tensor_default_605 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_605, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantize_per_tensor_default_605 = None
2025-03-21T20:31:43.4804515Z             quantized_decomposed_dequantize_per_tensor_default_744: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_454, 9.550915274303406e-05, 30065, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_454 = None
2025-03-21T20:31:43.4804605Z             
2025-03-21T20:31:43.4805547Z              # File: <eval_with_key>.50:1838 in forward, code: quantize_per_tensor_default_606 = torch.ops.quantized_decomposed.quantize_per_tensor.default(dequantize_per_tensor_default_605, 0.00010338902211515233, 0, -32767, 32767, torch.int16);  dequantize_per_tensor_default_605 = None
2025-03-21T20:31:43.4806690Z             quantized_decomposed_quantize_per_tensor_default_455: "i16[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_744, 0.00010338902211515233, 0, -32767, 32767, torch.int16);  quantized_decomposed_dequantize_per_tensor_default_744 = None
2025-03-21T20:31:43.4806789Z             
2025-03-21T20:31:43.4807254Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:163 in forward, code: y = attn_weight @ v
2025-03-21T20:31:43.4808411Z             quantized_decomposed_dequantize_per_tensor_default_745: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_455, 0.00010338902211515233, 0, -32767, 32767, torch.int16);  quantized_decomposed_quantize_per_tensor_default_455 = None
2025-03-21T20:31:43.4808500Z             
2025-03-21T20:31:43.4809003Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:157 in forward, code: attn_mask = mask[input_pos]
2025-03-21T20:31:43.4809881Z             aten_index_tensor_4: "f32[1, 128]" = executorch_exir_dialects_edge__ops_aten_index_Tensor(quantized_decomposed_dequantize_per_tensor_default_121, [attn_options_input_pos]);  quantized_decomposed_dequantize_per_tensor_default_121 = None
2025-03-21T20:31:43.4810803Z             quantized_decomposed_quantize_per_tensor_default_456: "i32[1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_tensor_4, 0.0038910505827516317, 65535, 0, 65535, torch.int32);  aten_index_tensor_4 = None
2025-03-21T20:31:43.4810918Z             
2025-03-21T20:31:43.4811410Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:161 in forward, code: attn_weight += attn_mask
2025-03-21T20:31:43.4812568Z             quantized_decomposed_dequantize_per_tensor_default_746: "f32[1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_456, 0.0038910505827516317, 65535, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_456 = None
2025-03-21T20:31:43.4812670Z             
2025-03-21T20:31:43.4813245Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.4814150Z             aten_permute_copy_default_113: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_706, [0, 1, 3, 2]);  quantized_decomposed_dequantize_per_tensor_default_706 = None
2025-03-21T20:31:43.4815154Z             quantized_decomposed_quantize_per_tensor_default_457: "i32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_113, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  aten_permute_copy_default_113 = None
2025-03-21T20:31:43.4815241Z             
2025-03-21T20:31:43.4816185Z              # File: <eval_with_key>.50:1845 in forward, code: dequantize_per_tensor_default_608 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_608, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantize_per_tensor_default_608 = None
2025-03-21T20:31:43.4817334Z             quantized_decomposed_dequantize_per_tensor_default_747: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_457, 0.00036907364847138524, 31320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_457 = None
2025-03-21T20:31:43.4817437Z             
2025-03-21T20:31:43.4818367Z              # File: <eval_with_key>.50:1846 in forward, code: quantize_per_tensor_default_609 = torch.ops.quantized_decomposed.quantize_per_tensor.default(dequantize_per_tensor_default_608, 0.00038538043736480176, 0, -32767, 32767, torch.int16);  dequantize_per_tensor_default_608 = None
2025-03-21T20:31:43.4819521Z             quantized_decomposed_quantize_per_tensor_default_458: "i16[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_747, 0.00038538043736480176, 0, -32767, 32767, torch.int16);  quantized_decomposed_dequantize_per_tensor_default_747 = None
2025-03-21T20:31:43.4819610Z             
2025-03-21T20:31:43.4820198Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.4821348Z             quantized_decomposed_dequantize_per_tensor_default_748: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_458, 0.00038538043736480176, 0, -32767, 32767, torch.int16);  quantized_decomposed_quantize_per_tensor_default_458 = None
2025-03-21T20:31:43.4822140Z             aten_expand_copy_default_8: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_642, [1, 12, 1, 64]);  quantized_decomposed_dequantize_per_tensor_default_642 = None
2025-03-21T20:31:43.4822744Z             aten_view_copy_default_47: "f32[12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_8, [12, 1, 64]);  aten_expand_copy_default_8 = None
2025-03-21T20:31:43.4823544Z             aten_expand_copy_default_9: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_748, [1, 12, 64, 128]);  quantized_decomposed_dequantize_per_tensor_default_748 = None
2025-03-21T20:31:43.4824183Z             aten_view_copy_default_48: "f32[12, 64, 128]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_9, [12, 64, 128]);  aten_expand_copy_default_9 = None
2025-03-21T20:31:43.4825072Z             aten_bmm_default_4: "f32[12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_bmm_default(aten_view_copy_default_47, aten_view_copy_default_48);  aten_view_copy_default_47 = aten_view_copy_default_48 = None
2025-03-21T20:31:43.4825608Z             aten_view_copy_default_49: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_bmm_default_4, [1, 12, 1, 128]);  aten_bmm_default_4 = None
2025-03-21T20:31:43.4826515Z             quantized_decomposed_quantize_per_tensor_default_459: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_49, 0.004083077888935804, 41914, 0, 65535, torch.int32);  aten_view_copy_default_49 = None
2025-03-21T20:31:43.4827706Z             quantized_decomposed_dequantize_per_tensor_default_749: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_459, 0.004083077888935804, 41914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_459 = None
2025-03-21T20:31:43.4828552Z             quantized_decomposed_dequantize_per_tensor_default_750: "f32[1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param151, 1.9073777366429567e-06, 0, 0, 65535, torch.int32);  b__frozen_param151 = None
2025-03-21T20:31:43.4829681Z             aten_mul_tensor_40: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_749, quantized_decomposed_dequantize_per_tensor_default_750);  quantized_decomposed_dequantize_per_tensor_default_749 = quantized_decomposed_dequantize_per_tensor_default_750 = None
2025-03-21T20:31:43.4830532Z             quantized_decomposed_quantize_per_tensor_default_460: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_40, 0.0005103847361169755, 41914, 0, 65535, torch.int32);  aten_mul_tensor_40 = None
2025-03-21T20:31:43.4830632Z             
2025-03-21T20:31:43.4831116Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:161 in forward, code: attn_weight += attn_mask
2025-03-21T20:31:43.4832758Z             quantized_decomposed_dequantize_per_tensor_default_751: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_460, 0.0005103847361169755, 41914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_460 = None
2025-03-21T20:31:43.4833886Z             aten_add_tensor_12: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_751, quantized_decomposed_dequantize_per_tensor_default_746);  quantized_decomposed_dequantize_per_tensor_default_751 = quantized_decomposed_dequantize_per_tensor_default_746 = None
2025-03-21T20:31:43.4834751Z             quantized_decomposed_quantize_per_tensor_default_461: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_12, 0.0043187374249100685, 62811, 0, 65535, torch.int32);  aten_add_tensor_12 = None
2025-03-21T20:31:43.4834906Z             
2025-03-21T20:31:43.4835524Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:162 in forward, code: attn_weight = torch.softmax(attn_weight, dim=-1)
2025-03-21T20:31:43.4836667Z             quantized_decomposed_dequantize_per_tensor_default_752: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_461, 0.0043187374249100685, 62811, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_461 = None
2025-03-21T20:31:43.4837491Z             aten__softmax_default_2: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten__softmax_default(quantized_decomposed_dequantize_per_tensor_default_752, -1, False);  quantized_decomposed_dequantize_per_tensor_default_752 = None
2025-03-21T20:31:43.4838376Z             quantized_decomposed_quantize_per_tensor_default_462: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten__softmax_default_2, 1.5259021893143654e-05, 0, 0, 65535, torch.int32);  aten__softmax_default_2 = None
2025-03-21T20:31:43.4838479Z             
2025-03-21T20:31:43.4838944Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:163 in forward, code: y = attn_weight @ v
2025-03-21T20:31:43.4840109Z             quantized_decomposed_dequantize_per_tensor_default_753: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_462, 1.5259021893143654e-05, 0, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_462 = None
2025-03-21T20:31:43.4840893Z             aten_expand_copy_default_10: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_753, [1, 12, 1, 128]);  quantized_decomposed_dequantize_per_tensor_default_753 = None
2025-03-21T20:31:43.4841466Z             aten_view_copy_default_50: "f32[12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_10, [12, 1, 128]);  aten_expand_copy_default_10 = None
2025-03-21T20:31:43.4842251Z             aten_expand_copy_default_11: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_745, [1, 12, 128, 64]);  quantized_decomposed_dequantize_per_tensor_default_745 = None
2025-03-21T20:31:43.4842824Z             aten_view_copy_default_51: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_11, [12, 128, 64]);  aten_expand_copy_default_11 = None
2025-03-21T20:31:43.4843464Z             aten_bmm_default_5: "f32[12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_bmm_default(aten_view_copy_default_50, aten_view_copy_default_51);  aten_view_copy_default_50 = aten_view_copy_default_51 = None
2025-03-21T20:31:43.4843980Z             aten_view_copy_default_52: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_bmm_default_5, [1, 12, 1, 64]);  aten_bmm_default_5 = None
2025-03-21T20:31:43.4844879Z             quantized_decomposed_quantize_per_tensor_default_463: "i32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_52, 5.6490640417905524e-05, 31487, 0, 65535, torch.int32);  aten_view_copy_default_52 = None
2025-03-21T20:31:43.4844984Z             
2025-03-21T20:31:43.4845606Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:165 in forward, code: return y.transpose(1, 2).contiguous().view(bsz, seqlen, self.dim)
2025-03-21T20:31:43.4846775Z             quantized_decomposed_dequantize_per_tensor_default_754: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_463, 5.6490640417905524e-05, 31487, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_463 = None
2025-03-21T20:31:43.4847583Z             aten_permute_copy_default_114: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_754, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_754 = None
2025-03-21T20:31:43.4848550Z             quantized_decomposed_quantize_per_tensor_default_464: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_114, 5.6490640417905524e-05, 31487, 0, 65535, torch.int32);  aten_permute_copy_default_114 = None
2025-03-21T20:31:43.4849758Z             quantized_decomposed_dequantize_per_tensor_default_755: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_464, 5.6490640417905524e-05, 31487, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_464 = None
2025-03-21T20:31:43.4850533Z             aten_view_copy_default_53: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_755, [1, 1, 768]);  quantized_decomposed_dequantize_per_tensor_default_755 = None
2025-03-21T20:31:43.4851473Z             quantized_decomposed_quantize_per_tensor_default_465: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_53, 5.6490640417905524e-05, 31487, 0, 65535, torch.int32);  aten_view_copy_default_53 = None
2025-03-21T20:31:43.4851575Z             
2025-03-21T20:31:43.4852096Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.4853250Z             quantized_decomposed_dequantize_per_tensor_default_756: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_465, 5.6490640417905524e-05, 31487, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_465 = None
2025-03-21T20:31:43.4854048Z             aten_unsqueeze_copy_default_29: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_756, -1);  quantized_decomposed_dequantize_per_tensor_default_756 = None
2025-03-21T20:31:43.4855003Z             quantized_decomposed_quantize_per_tensor_default_466: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_29, 5.6490640417905524e-05, 31487, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_29 = None
2025-03-21T20:31:43.4855090Z             
2025-03-21T20:31:43.4855508Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.4856646Z             quantized_decomposed_dequantize_per_tensor_default_757: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_466, 5.6490640417905524e-05, 31487, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_466 = None
2025-03-21T20:31:43.4857447Z             aten_permute_copy_default_115: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_757, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_757 = None
2025-03-21T20:31:43.4858374Z             quantized_decomposed_quantize_per_tensor_default_467: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_115, 5.6490640417905524e-05, 31487, 0, 65535, torch.int32);  aten_permute_copy_default_115 = None
2025-03-21T20:31:43.4858504Z             
2025-03-21T20:31:43.4858893Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.4860038Z             quantized_decomposed_dequantize_per_tensor_default_758: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_467, 5.6490640417905524e-05, 31487, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_467 = None
2025-03-21T20:31:43.4861327Z             aten_convolution_default_17: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_758, quantized_decomposed_dequantize_per_tensor_default_23, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_758 = quantized_decomposed_dequantize_per_tensor_default_23 = None
2025-03-21T20:31:43.4862275Z             quantized_decomposed_quantize_per_tensor_default_468: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_17, 0.00010611177276587114, 33703, 0, 65535, torch.int32);  aten_convolution_default_17 = None
2025-03-21T20:31:43.4862389Z             
2025-03-21T20:31:43.4862819Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.4863963Z             quantized_decomposed_dequantize_per_tensor_default_759: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_468, 0.00010611177276587114, 33703, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_468 = None
2025-03-21T20:31:43.4864765Z             aten_permute_copy_default_116: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_759, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_759 = None
2025-03-21T20:31:43.4865704Z             quantized_decomposed_quantize_per_tensor_default_469: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_116, 0.00010611177276587114, 33703, 0, 65535, torch.int32);  aten_permute_copy_default_116 = None
2025-03-21T20:31:43.4865804Z             
2025-03-21T20:31:43.4866341Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.4867490Z             quantized_decomposed_dequantize_per_tensor_default_760: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_469, 0.00010611177276587114, 33703, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_469 = None
2025-03-21T20:31:43.4868239Z             aten_squeeze_copy_dims_29: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_760, [-1]);  quantized_decomposed_dequantize_per_tensor_default_760 = None
2025-03-21T20:31:43.4869148Z             quantized_decomposed_quantize_per_tensor_default_470: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_29, 0.00010611177276587114, 33703, 0, 65535, torch.int32);  aten_squeeze_copy_dims_29 = None
2025-03-21T20:31:43.4869236Z             
2025-03-21T20:31:43.4869621Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:111 in forward, code: h = x + h
2025-03-21T20:31:43.4870779Z             quantized_decomposed_dequantize_per_tensor_default_761: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_470, 0.00010611177276587114, 33703, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_470 = None
2025-03-21T20:31:43.4871931Z             aten_add_tensor_13: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_581, quantized_decomposed_dequantize_per_tensor_default_761);  quantized_decomposed_dequantize_per_tensor_default_581 = quantized_decomposed_dequantize_per_tensor_default_761 = None
2025-03-21T20:31:43.4872798Z             quantized_decomposed_quantize_per_tensor_default_471: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_13, 0.001073345891200006, 11837, 0, 65535, torch.int32);  aten_add_tensor_13 = None
2025-03-21T20:31:43.4872899Z             
2025-03-21T20:31:43.4873406Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:115 in forward, code: out = h + self.feed_forward(self.ffn_norm(h))
2025-03-21T20:31:43.4874328Z             quantized_decomposed_dequantize_per_tensor_default_762: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_471, 0.001073345891200006, 11837, 0, 65535, torch.int32)
2025-03-21T20:31:43.4875480Z             quantized_decomposed_dequantize_per_tensor_default_763: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_471, 0.001073345891200006, 11837, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_471 = None
2025-03-21T20:31:43.4876005Z             aten_pow_tensor_scalar_5: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_pow_Tensor_Scalar(quantized_decomposed_dequantize_per_tensor_default_763, 2)
2025-03-21T20:31:43.4876455Z             aten_mean_dim_5: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_mean_dim(aten_pow_tensor_scalar_5, [2], True);  aten_pow_tensor_scalar_5 = None
2025-03-21T20:31:43.4876909Z             aten_add_scalar_5: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_add_Scalar(aten_mean_dim_5, 9.999999747378752e-06);  aten_mean_dim_5 = None
2025-03-21T20:31:43.4877323Z             aten_rsqrt_default_5: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_rsqrt_default(aten_add_scalar_5);  aten_add_scalar_5 = None
2025-03-21T20:31:43.4878179Z             aten_mul_tensor_41: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_763, aten_rsqrt_default_5);  quantized_decomposed_dequantize_per_tensor_default_763 = aten_rsqrt_default_5 = None
2025-03-21T20:31:43.4878981Z             aten_mul_tensor_42: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(aten_mul_tensor_41, quantized_decomposed_dequantize_per_tensor_default_24);  aten_mul_tensor_41 = quantized_decomposed_dequantize_per_tensor_default_24 = None
2025-03-21T20:31:43.4879848Z             quantized_decomposed_quantize_per_tensor_default_472: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_42, 0.00031091910204850137, 15960, 0, 65535, torch.int32);  aten_mul_tensor_42 = None
2025-03-21T20:31:43.4879940Z             
2025-03-21T20:31:43.4880471Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.4881386Z             quantized_decomposed_dequantize_per_tensor_default_764: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_472, 0.00031091910204850137, 15960, 0, 65535, torch.int32)
2025-03-21T20:31:43.4882560Z             quantized_decomposed_dequantize_per_tensor_default_765: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_472, 0.00031091910204850137, 15960, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_472 = None
2025-03-21T20:31:43.4883377Z             aten_unsqueeze_copy_default_30: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_765, -1);  quantized_decomposed_dequantize_per_tensor_default_765 = None
2025-03-21T20:31:43.4884357Z             quantized_decomposed_quantize_per_tensor_default_473: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_30, 0.00031091910204850137, 15960, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_30 = None
2025-03-21T20:31:43.4884447Z             
2025-03-21T20:31:43.4884866Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.4886005Z             quantized_decomposed_dequantize_per_tensor_default_766: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_473, 0.00031091910204850137, 15960, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_473 = None
2025-03-21T20:31:43.4886833Z             aten_permute_copy_default_117: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_766, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_766 = None
2025-03-21T20:31:43.4887767Z             quantized_decomposed_quantize_per_tensor_default_474: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_117, 0.00031091910204850137, 15960, 0, 65535, torch.int32);  aten_permute_copy_default_117 = None
2025-03-21T20:31:43.4887866Z             
2025-03-21T20:31:43.4888232Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.4889453Z             quantized_decomposed_dequantize_per_tensor_default_767: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_474, 0.00031091910204850137, 15960, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_474 = None
2025-03-21T20:31:43.4890803Z             aten_convolution_default_18: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_767, quantized_decomposed_dequantize_per_tensor_default_25, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_767 = quantized_decomposed_dequantize_per_tensor_default_25 = None
2025-03-21T20:31:43.4891828Z             quantized_decomposed_quantize_per_tensor_default_475: "i32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_18, 0.00018055648251902312, 33284, 0, 65535, torch.int32);  aten_convolution_default_18 = None
2025-03-21T20:31:43.4891953Z             
2025-03-21T20:31:43.4892600Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.4939074Z             quantized_decomposed_dequantize_per_tensor_default_768: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_475, 0.00018055648251902312, 33284, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_475 = None
2025-03-21T20:31:43.4940195Z             aten_permute_copy_default_118: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_768, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_768 = None
2025-03-21T20:31:43.4942530Z             quantized_decomposed_quantize_per_tensor_default_476: "i32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_118, 0.00018055648251902312, 33284, 0, 65535, torch.int32);  aten_permute_copy_default_118 = None
2025-03-21T20:31:43.4942635Z             
2025-03-21T20:31:43.4943185Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.4944391Z             quantized_decomposed_dequantize_per_tensor_default_769: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_476, 0.00018055648251902312, 33284, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_476 = None
2025-03-21T20:31:43.4945148Z             aten_squeeze_copy_dims_30: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_769, [-1]);  quantized_decomposed_dequantize_per_tensor_default_769 = None
2025-03-21T20:31:43.4946113Z             quantized_decomposed_quantize_per_tensor_default_477: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_30, 0.00018055648251902312, 33284, 0, 65535, torch.int32);  aten_squeeze_copy_dims_30 = None
2025-03-21T20:31:43.4946204Z             
2025-03-21T20:31:43.4946733Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:36 in forward, code: return self.w2(F.silu(self.w1(x)) * self.w3(x))
2025-03-21T20:31:43.4947650Z             quantized_decomposed_dequantize_per_tensor_default_770: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_477, 0.00018055648251902312, 33284, 0, 65535, torch.int32)
2025-03-21T20:31:43.4948798Z             quantized_decomposed_dequantize_per_tensor_default_771: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_477, 0.00018055648251902312, 33284, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_477 = None
2025-03-21T20:31:43.4949533Z             aten_sigmoid_default_2: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_sigmoid_default(quantized_decomposed_dequantize_per_tensor_default_771);  quantized_decomposed_dequantize_per_tensor_default_771 = None
2025-03-21T20:31:43.4950396Z             quantized_decomposed_quantize_per_tensor_default_478: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_sigmoid_default_2, 1.52587890625e-05, 0, 0, 65535, torch.int32);  aten_sigmoid_default_2 = None
2025-03-21T20:31:43.4951503Z             quantized_decomposed_dequantize_per_tensor_default_772: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_478, 1.52587890625e-05, 0, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_478 = None
2025-03-21T20:31:43.4952626Z             aten_mul_tensor_43: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_770, quantized_decomposed_dequantize_per_tensor_default_772);  quantized_decomposed_dequantize_per_tensor_default_770 = quantized_decomposed_dequantize_per_tensor_default_772 = None
2025-03-21T20:31:43.4953475Z             quantized_decomposed_quantize_per_tensor_default_479: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_43, 9.284297266276553e-05, 2999, 0, 65535, torch.int32);  aten_mul_tensor_43 = None
2025-03-21T20:31:43.4954652Z             quantized_decomposed_dequantize_per_tensor_default_773: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_479, 9.284297266276553e-05, 2999, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_479 = None
2025-03-21T20:31:43.4954748Z             
2025-03-21T20:31:43.4955268Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.4956099Z             aten_unsqueeze_copy_default_31: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_764, -1);  quantized_decomposed_dequantize_per_tensor_default_764 = None
2025-03-21T20:31:43.4957048Z             quantized_decomposed_quantize_per_tensor_default_480: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_31, 0.00031091910204850137, 15960, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_31 = None
2025-03-21T20:31:43.4957142Z             
2025-03-21T20:31:43.4957575Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.4958723Z             quantized_decomposed_dequantize_per_tensor_default_774: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_480, 0.00031091910204850137, 15960, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_480 = None
2025-03-21T20:31:43.4959513Z             aten_permute_copy_default_119: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_774, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_774 = None
2025-03-21T20:31:43.4960455Z             quantized_decomposed_quantize_per_tensor_default_481: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_119, 0.00031091910204850137, 15960, 0, 65535, torch.int32);  aten_permute_copy_default_119 = None
2025-03-21T20:31:43.4960542Z             
2025-03-21T20:31:43.4960915Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.4962052Z             quantized_decomposed_dequantize_per_tensor_default_775: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_481, 0.00031091910204850137, 15960, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_481 = None
2025-03-21T20:31:43.4963324Z             aten_convolution_default_19: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_775, quantized_decomposed_dequantize_per_tensor_default_26, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_775 = quantized_decomposed_dequantize_per_tensor_default_26 = None
2025-03-21T20:31:43.4964260Z             quantized_decomposed_quantize_per_tensor_default_482: "i32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_19, 0.00019716951646842062, 31579, 0, 65535, torch.int32);  aten_convolution_default_19 = None
2025-03-21T20:31:43.4964357Z             
2025-03-21T20:31:43.4964777Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.4965952Z             quantized_decomposed_dequantize_per_tensor_default_776: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_482, 0.00019716951646842062, 31579, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_482 = None
2025-03-21T20:31:43.4966767Z             aten_permute_copy_default_120: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_776, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_776 = None
2025-03-21T20:31:43.4967737Z             quantized_decomposed_quantize_per_tensor_default_483: "i32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_120, 0.00019716951646842062, 31579, 0, 65535, torch.int32);  aten_permute_copy_default_120 = None
2025-03-21T20:31:43.4967827Z             
2025-03-21T20:31:43.4968368Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.4969618Z             quantized_decomposed_dequantize_per_tensor_default_777: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_483, 0.00019716951646842062, 31579, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_483 = None
2025-03-21T20:31:43.4970419Z             aten_squeeze_copy_dims_31: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_777, [-1]);  quantized_decomposed_dequantize_per_tensor_default_777 = None
2025-03-21T20:31:43.4971322Z             quantized_decomposed_quantize_per_tensor_default_484: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_31, 0.00019716951646842062, 31579, 0, 65535, torch.int32);  aten_squeeze_copy_dims_31 = None
2025-03-21T20:31:43.4971418Z             
2025-03-21T20:31:43.4971929Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:36 in forward, code: return self.w2(F.silu(self.w1(x)) * self.w3(x))
2025-03-21T20:31:43.4973081Z             quantized_decomposed_dequantize_per_tensor_default_778: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_484, 0.00019716951646842062, 31579, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_484 = None
2025-03-21T20:31:43.4974194Z             aten_mul_tensor_44: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_773, quantized_decomposed_dequantize_per_tensor_default_778);  quantized_decomposed_dequantize_per_tensor_default_773 = quantized_decomposed_dequantize_per_tensor_default_778 = None
2025-03-21T20:31:43.4975056Z             quantized_decomposed_quantize_per_tensor_default_485: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_44, 0.0009127886733040214, 36679, 0, 65535, torch.int32);  aten_mul_tensor_44 = None
2025-03-21T20:31:43.4975140Z             
2025-03-21T20:31:43.4975664Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.4976797Z             quantized_decomposed_dequantize_per_tensor_default_779: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_485, 0.0009127886733040214, 36679, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_485 = None
2025-03-21T20:31:43.4977636Z             aten_unsqueeze_copy_default_32: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_779, -1);  quantized_decomposed_dequantize_per_tensor_default_779 = None
2025-03-21T20:31:43.4978601Z             quantized_decomposed_quantize_per_tensor_default_486: "i32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_32, 0.0009127886733040214, 36679, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_32 = None
2025-03-21T20:31:43.4978699Z             
2025-03-21T20:31:43.4979102Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.4980273Z             quantized_decomposed_dequantize_per_tensor_default_780: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_486, 0.0009127886733040214, 36679, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_486 = None
2025-03-21T20:31:43.4981066Z             aten_permute_copy_default_121: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_780, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_780 = None
2025-03-21T20:31:43.4982042Z             quantized_decomposed_quantize_per_tensor_default_487: "i32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_121, 0.0009127886733040214, 36679, 0, 65535, torch.int32);  aten_permute_copy_default_121 = None
2025-03-21T20:31:43.4982128Z             
2025-03-21T20:31:43.4982503Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.4983638Z             quantized_decomposed_dequantize_per_tensor_default_781: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_487, 0.0009127886733040214, 36679, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_487 = None
2025-03-21T20:31:43.4984915Z             aten_convolution_default_20: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_781, quantized_decomposed_dequantize_per_tensor_default_27, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_781 = quantized_decomposed_dequantize_per_tensor_default_27 = None
2025-03-21T20:31:43.4985837Z             quantized_decomposed_quantize_per_tensor_default_488: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_20, 0.0011877048527821898, 2626, 0, 65535, torch.int32);  aten_convolution_default_20 = None
2025-03-21T20:31:43.4985933Z             
2025-03-21T20:31:43.4986347Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.4987491Z             quantized_decomposed_dequantize_per_tensor_default_782: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_488, 0.0011877048527821898, 2626, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_488 = None
2025-03-21T20:31:43.4988276Z             aten_permute_copy_default_122: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_782, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_782 = None
2025-03-21T20:31:43.4989210Z             quantized_decomposed_quantize_per_tensor_default_489: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_122, 0.0011877048527821898, 2626, 0, 65535, torch.int32);  aten_permute_copy_default_122 = None
2025-03-21T20:31:43.4989320Z             
2025-03-21T20:31:43.4989885Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.4991012Z             quantized_decomposed_dequantize_per_tensor_default_783: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_489, 0.0011877048527821898, 2626, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_489 = None
2025-03-21T20:31:43.4991799Z             aten_squeeze_copy_dims_32: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_783, [-1]);  quantized_decomposed_dequantize_per_tensor_default_783 = None
2025-03-21T20:31:43.4992689Z             quantized_decomposed_quantize_per_tensor_default_490: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_32, 0.0011877048527821898, 2626, 0, 65535, torch.int32);  aten_squeeze_copy_dims_32 = None
2025-03-21T20:31:43.4992790Z             
2025-03-21T20:31:43.4993293Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:115 in forward, code: out = h + self.feed_forward(self.ffn_norm(h))
2025-03-21T20:31:43.4994460Z             quantized_decomposed_dequantize_per_tensor_default_784: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_490, 0.0011877048527821898, 2626, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_490 = None
2025-03-21T20:31:43.4995568Z             aten_add_tensor_14: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_762, quantized_decomposed_dequantize_per_tensor_default_784);  quantized_decomposed_dequantize_per_tensor_default_762 = quantized_decomposed_dequantize_per_tensor_default_784 = None
2025-03-21T20:31:43.4996421Z             quantized_decomposed_quantize_per_tensor_default_491: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_14, 0.0020524393767118454, 7490, 0, 65535, torch.int32);  aten_add_tensor_14 = None
2025-03-21T20:31:43.4996512Z             
2025-03-21T20:31:43.4996893Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:111 in forward, code: h = x + h
2025-03-21T20:31:43.4997795Z             quantized_decomposed_dequantize_per_tensor_default_785: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_491, 0.0020524393767118454, 7490, 0, 65535, torch.int32)
2025-03-21T20:31:43.4997892Z             
2025-03-21T20:31:43.4998451Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:108 in forward, code: self.attention_norm(x), freqs_cos, freqs_sin, **attn_options
2025-03-21T20:31:43.4999587Z             quantized_decomposed_dequantize_per_tensor_default_786: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_491, 0.0020524393767118454, 7490, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_491 = None
2025-03-21T20:31:43.5000094Z             aten_pow_tensor_scalar_6: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_pow_Tensor_Scalar(quantized_decomposed_dequantize_per_tensor_default_786, 2)
2025-03-21T20:31:43.5000552Z             aten_mean_dim_6: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_mean_dim(aten_pow_tensor_scalar_6, [2], True);  aten_pow_tensor_scalar_6 = None
2025-03-21T20:31:43.5000988Z             aten_add_scalar_6: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_add_Scalar(aten_mean_dim_6, 9.999999747378752e-06);  aten_mean_dim_6 = None
2025-03-21T20:31:43.5001449Z             aten_rsqrt_default_6: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_rsqrt_default(aten_add_scalar_6);  aten_add_scalar_6 = None
2025-03-21T20:31:43.5002294Z             aten_mul_tensor_45: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_786, aten_rsqrt_default_6);  quantized_decomposed_dequantize_per_tensor_default_786 = aten_rsqrt_default_6 = None
2025-03-21T20:31:43.5003129Z             aten_mul_tensor_46: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(aten_mul_tensor_45, quantized_decomposed_dequantize_per_tensor_default_28);  aten_mul_tensor_45 = quantized_decomposed_dequantize_per_tensor_default_28 = None
2025-03-21T20:31:43.5003979Z             quantized_decomposed_quantize_per_tensor_default_492: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_46, 0.00036565581103786826, 25893, 0, 65535, torch.int32);  aten_mul_tensor_46 = None
2025-03-21T20:31:43.5004075Z             
2025-03-21T20:31:43.5004588Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.5005521Z             quantized_decomposed_dequantize_per_tensor_default_787: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_492, 0.00036565581103786826, 25893, 0, 65535, torch.int32)
2025-03-21T20:31:43.5006433Z             quantized_decomposed_dequantize_per_tensor_default_788: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_492, 0.00036565581103786826, 25893, 0, 65535, torch.int32)
2025-03-21T20:31:43.5007576Z             quantized_decomposed_dequantize_per_tensor_default_789: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_492, 0.00036565581103786826, 25893, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_492 = None
2025-03-21T20:31:43.5008374Z             aten_unsqueeze_copy_default_33: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_789, -1);  quantized_decomposed_dequantize_per_tensor_default_789 = None
2025-03-21T20:31:43.5009393Z             quantized_decomposed_quantize_per_tensor_default_493: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_33, 0.00036565581103786826, 25893, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_33 = None
2025-03-21T20:31:43.5009488Z             
2025-03-21T20:31:43.5009908Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.5011052Z             quantized_decomposed_dequantize_per_tensor_default_790: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_493, 0.00036565581103786826, 25893, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_493 = None
2025-03-21T20:31:43.5011861Z             aten_permute_copy_default_123: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_790, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_790 = None
2025-03-21T20:31:43.5012796Z             quantized_decomposed_quantize_per_tensor_default_494: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_123, 0.00036565581103786826, 25893, 0, 65535, torch.int32);  aten_permute_copy_default_123 = None
2025-03-21T20:31:43.5012955Z             
2025-03-21T20:31:43.5013324Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.5014480Z             quantized_decomposed_dequantize_per_tensor_default_791: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_494, 0.00036565581103786826, 25893, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_494 = None
2025-03-21T20:31:43.5015771Z             aten_convolution_default_21: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_791, quantized_decomposed_dequantize_per_tensor_default_29, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_791 = quantized_decomposed_dequantize_per_tensor_default_29 = None
2025-03-21T20:31:43.5016708Z             quantized_decomposed_quantize_per_tensor_default_495: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_21, 0.00035187334287911654, 29898, 0, 65535, torch.int32);  aten_convolution_default_21 = None
2025-03-21T20:31:43.5016821Z             
2025-03-21T20:31:43.5017250Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.5018396Z             quantized_decomposed_dequantize_per_tensor_default_792: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_495, 0.00035187334287911654, 29898, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_495 = None
2025-03-21T20:31:43.5019190Z             aten_permute_copy_default_124: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_792, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_792 = None
2025-03-21T20:31:43.5020119Z             quantized_decomposed_quantize_per_tensor_default_496: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_124, 0.00035187334287911654, 29898, 0, 65535, torch.int32);  aten_permute_copy_default_124 = None
2025-03-21T20:31:43.5020214Z             
2025-03-21T20:31:43.5020747Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.5021895Z             quantized_decomposed_dequantize_per_tensor_default_793: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_496, 0.00035187334287911654, 29898, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_496 = None
2025-03-21T20:31:43.5022638Z             aten_squeeze_copy_dims_33: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_793, [-1]);  quantized_decomposed_dequantize_per_tensor_default_793 = None
2025-03-21T20:31:43.5023544Z             quantized_decomposed_quantize_per_tensor_default_497: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_33, 0.00035187334287911654, 29898, 0, 65535, torch.int32);  aten_squeeze_copy_dims_33 = None
2025-03-21T20:31:43.5023631Z             
2025-03-21T20:31:43.5024152Z              # File: /pytorch/executorch/examples/models/llama/attention.py:242 in forward, code: q = q.view(bsz, seqlen, self.n_local_heads, self.head_dim)
2025-03-21T20:31:43.5025312Z             quantized_decomposed_dequantize_per_tensor_default_794: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_497, 0.00035187334287911654, 29898, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_497 = None
2025-03-21T20:31:43.5025428Z             
2025-03-21T20:31:43.5025942Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.5026824Z             aten_unsqueeze_copy_default_34: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_788, -1);  quantized_decomposed_dequantize_per_tensor_default_788 = None
2025-03-21T20:31:43.5028031Z             quantized_decomposed_quantize_per_tensor_default_498: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_34, 0.00036565581103786826, 25893, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_34 = None
2025-03-21T20:31:43.5028124Z             
2025-03-21T20:31:43.5028543Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.5029719Z             quantized_decomposed_dequantize_per_tensor_default_795: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_498, 0.00036565581103786826, 25893, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_498 = None
2025-03-21T20:31:43.5030520Z             aten_permute_copy_default_125: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_795, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_795 = None
2025-03-21T20:31:43.5031449Z             quantized_decomposed_quantize_per_tensor_default_499: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_125, 0.00036565581103786826, 25893, 0, 65535, torch.int32);  aten_permute_copy_default_125 = None
2025-03-21T20:31:43.5031550Z             
2025-03-21T20:31:43.5031909Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.5033230Z             quantized_decomposed_dequantize_per_tensor_default_796: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_499, 0.00036565581103786826, 25893, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_499 = None
2025-03-21T20:31:43.5034496Z             aten_convolution_default_22: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_796, quantized_decomposed_dequantize_per_tensor_default_30, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_796 = quantized_decomposed_dequantize_per_tensor_default_30 = None
2025-03-21T20:31:43.5035437Z             quantized_decomposed_quantize_per_tensor_default_500: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_22, 0.00039280077908188105, 32440, 0, 65535, torch.int32);  aten_convolution_default_22 = None
2025-03-21T20:31:43.5035534Z             
2025-03-21T20:31:43.5035955Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.5037091Z             quantized_decomposed_dequantize_per_tensor_default_797: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_500, 0.00039280077908188105, 32440, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_500 = None
2025-03-21T20:31:43.5038004Z             aten_permute_copy_default_126: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_797, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_797 = None
2025-03-21T20:31:43.5038947Z             quantized_decomposed_quantize_per_tensor_default_501: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_126, 0.00039280077908188105, 32440, 0, 65535, torch.int32);  aten_permute_copy_default_126 = None
2025-03-21T20:31:43.5039071Z             
2025-03-21T20:31:43.5039605Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.5040763Z             quantized_decomposed_dequantize_per_tensor_default_798: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_501, 0.00039280077908188105, 32440, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_501 = None
2025-03-21T20:31:43.5041566Z             aten_squeeze_copy_dims_34: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_798, [-1]);  quantized_decomposed_dequantize_per_tensor_default_798 = None
2025-03-21T20:31:43.5042464Z             quantized_decomposed_quantize_per_tensor_default_502: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_34, 0.00039280077908188105, 32440, 0, 65535, torch.int32);  aten_squeeze_copy_dims_34 = None
2025-03-21T20:31:43.5042548Z             
2025-03-21T20:31:43.5043087Z              # File: /pytorch/executorch/examples/models/llama/attention.py:243 in forward, code: k = k.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.5044225Z             quantized_decomposed_dequantize_per_tensor_default_799: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_502, 0.00039280077908188105, 32440, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_502 = None
2025-03-21T20:31:43.5044321Z             
2025-03-21T20:31:43.5044834Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.5045644Z             aten_unsqueeze_copy_default_35: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_787, -1);  quantized_decomposed_dequantize_per_tensor_default_787 = None
2025-03-21T20:31:43.5046586Z             quantized_decomposed_quantize_per_tensor_default_503: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_35, 0.00036565581103786826, 25893, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_35 = None
2025-03-21T20:31:43.5046685Z             
2025-03-21T20:31:43.5047085Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.5048228Z             quantized_decomposed_dequantize_per_tensor_default_800: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_503, 0.00036565581103786826, 25893, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_503 = None
2025-03-21T20:31:43.5049012Z             aten_permute_copy_default_127: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_800, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_800 = None
2025-03-21T20:31:43.5050079Z             quantized_decomposed_quantize_per_tensor_default_504: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_127, 0.00036565581103786826, 25893, 0, 65535, torch.int32);  aten_permute_copy_default_127 = None
2025-03-21T20:31:43.5050168Z             
2025-03-21T20:31:43.5050546Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.5051701Z             quantized_decomposed_dequantize_per_tensor_default_801: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_504, 0.00036565581103786826, 25893, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_504 = None
2025-03-21T20:31:43.5052971Z             aten_convolution_default_23: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_801, quantized_decomposed_dequantize_per_tensor_default_31, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_801 = quantized_decomposed_dequantize_per_tensor_default_31 = None
2025-03-21T20:31:43.5053945Z             quantized_decomposed_quantize_per_tensor_default_505: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_23, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_convolution_default_23 = None
2025-03-21T20:31:43.5054045Z             
2025-03-21T20:31:43.5054463Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.5055613Z             quantized_decomposed_dequantize_per_tensor_default_802: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_505, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_505 = None
2025-03-21T20:31:43.5056398Z             aten_permute_copy_default_128: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_802, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_802 = None
2025-03-21T20:31:43.5057341Z             quantized_decomposed_quantize_per_tensor_default_506: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_128, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_permute_copy_default_128 = None
2025-03-21T20:31:43.5057425Z             
2025-03-21T20:31:43.5057962Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.5059101Z             quantized_decomposed_dequantize_per_tensor_default_803: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_506, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_506 = None
2025-03-21T20:31:43.5059856Z             aten_squeeze_copy_dims_35: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_803, [-1]);  quantized_decomposed_dequantize_per_tensor_default_803 = None
2025-03-21T20:31:43.5060748Z             quantized_decomposed_quantize_per_tensor_default_507: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_35, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_squeeze_copy_dims_35 = None
2025-03-21T20:31:43.5060866Z             
2025-03-21T20:31:43.5061412Z              # File: /pytorch/executorch/examples/models/llama/attention.py:244 in forward, code: v = v.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.5062552Z             quantized_decomposed_dequantize_per_tensor_default_804: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_507, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_507 = None
2025-03-21T20:31:43.5062641Z             
2025-03-21T20:31:43.5063184Z              # File: /pytorch/executorch/examples/models/llama/attention.py:242 in forward, code: q = q.view(bsz, seqlen, self.n_local_heads, self.head_dim)
2025-03-21T20:31:43.5063946Z             aten_view_copy_default_54: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_794, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_794 = None
2025-03-21T20:31:43.5064855Z             quantized_decomposed_quantize_per_tensor_default_508: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_54, 0.00035187334287911654, 29898, 0, 65535, torch.int32);  aten_view_copy_default_54 = None
2025-03-21T20:31:43.5064969Z             
2025-03-21T20:31:43.5065915Z              # File: <eval_with_key>.50:2005 in forward, code: dequantize_per_tensor_default_660 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_660, 0.00035187334287911654, 29898, 0, 65535, torch.int32);  quantize_per_tensor_default_660 = None
2025-03-21T20:31:43.5067057Z             quantized_decomposed_dequantize_per_tensor_default_805: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_508, 0.00035187334287911654, 29898, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_508 = None
2025-03-21T20:31:43.5067153Z             
2025-03-21T20:31:43.5067674Z              # File: /pytorch/executorch/examples/models/llama/attention.py:243 in forward, code: k = k.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.5068440Z             aten_view_copy_default_55: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_799, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_799 = None
2025-03-21T20:31:43.5069337Z             quantized_decomposed_quantize_per_tensor_default_509: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_55, 0.00039280077908188105, 32440, 0, 65535, torch.int32);  aten_view_copy_default_55 = None
2025-03-21T20:31:43.5069438Z             
2025-03-21T20:31:43.5070368Z              # File: <eval_with_key>.50:2008 in forward, code: dequantize_per_tensor_default_661 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_661, 0.00039280077908188105, 32440, 0, 65535, torch.int32);  quantize_per_tensor_default_661 = None
2025-03-21T20:31:43.5071518Z             quantized_decomposed_dequantize_per_tensor_default_806: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_509, 0.00039280077908188105, 32440, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_509 = None
2025-03-21T20:31:43.5071608Z             
2025-03-21T20:31:43.5072136Z              # File: /pytorch/executorch/examples/models/llama/attention.py:244 in forward, code: v = v.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.5072915Z             aten_view_copy_default_56: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_804, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_804 = None
2025-03-21T20:31:43.5073843Z             quantized_decomposed_quantize_per_tensor_default_510: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_56, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_view_copy_default_56 = None
2025-03-21T20:31:43.5073930Z             
2025-03-21T20:31:43.5074628Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:346 in update, code: v_out = torch.ops.aten.index_put_(self.past_v_caches, [None, input_pos], v_val)
2025-03-21T20:31:43.5075769Z             quantized_decomposed_dequantize_per_tensor_default_807: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_510, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_510 = None
2025-03-21T20:31:43.5075869Z             
2025-03-21T20:31:43.5076620Z              # File: <eval_with_key>.50:2013 in forward, code: quantize_per_tensor_default_663 = torch.ops.quantized_decomposed.quantize_per_tensor.default(_to_copy_6, 0.00035187334287911654, 29898, 0, 65535, torch.int32);  _to_copy_6 = None
2025-03-21T20:31:43.5077791Z             quantized_decomposed_quantize_per_tensor_default_511: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_805, 0.00035187334287911654, 29898, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_805 = None
2025-03-21T20:31:43.5077871Z             
2025-03-21T20:31:43.5078405Z              # File: /pytorch/executorch/examples/models/llama/rope.py:84 in apply_rotary_emb, code: xq_r, xq_i = xq.float().reshape(xq.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.5079535Z             quantized_decomposed_dequantize_per_tensor_default_808: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_511, 0.00035187334287911654, 29898, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_511 = None
2025-03-21T20:31:43.5080314Z             aten_view_copy_default_57: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_808, [1, 1, 12, -1, 2]);  quantized_decomposed_dequantize_per_tensor_default_808 = None
2025-03-21T20:31:43.5081208Z             quantized_decomposed_quantize_per_tensor_default_512: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_57, 0.00035187334287911654, 29898, 0, 65535, torch.int32);  aten_view_copy_default_57 = None
2025-03-21T20:31:43.5082353Z             quantized_decomposed_dequantize_per_tensor_default_809: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_512, 0.00035187334287911654, 29898, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_512 = None
2025-03-21T20:31:43.5082883Z             aten_slice_copy_tensor_12: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_809, 4, 0, 1)
2025-03-21T20:31:43.5083642Z             aten_slice_copy_tensor_13: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_809, 4, 1, 2);  quantized_decomposed_dequantize_per_tensor_default_809 = None
2025-03-21T20:31:43.5084156Z             aten_squeeze_copy_dims_36: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_12, [4]);  aten_slice_copy_tensor_12 = None
2025-03-21T20:31:43.5084740Z             aten_squeeze_copy_dims_37: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_13, [4]);  aten_slice_copy_tensor_13 = None
2025-03-21T20:31:43.5085635Z             quantized_decomposed_quantize_per_tensor_default_513: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_36, 0.00035187334287911654, 29898, 0, 65535, torch.int32);  aten_squeeze_copy_dims_36 = None
2025-03-21T20:31:43.5085733Z             
2025-03-21T20:31:43.5086225Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.5087143Z             quantized_decomposed_dequantize_per_tensor_default_810: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_513, 0.00035187334287911654, 29898, 0, 65535, torch.int32)
2025-03-21T20:31:43.5087230Z             
2025-03-21T20:31:43.5087711Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.5088862Z             quantized_decomposed_dequantize_per_tensor_default_811: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_513, 0.00035187334287911654, 29898, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_513 = None
2025-03-21T20:31:43.5088961Z             
2025-03-21T20:31:43.5089554Z              # File: /pytorch/executorch/examples/models/llama/rope.py:84 in apply_rotary_emb, code: xq_r, xq_i = xq.float().reshape(xq.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.5090455Z             quantized_decomposed_quantize_per_tensor_default_514: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_37, 0.0003007998166140169, 27134, 0, 65535, torch.int32);  aten_squeeze_copy_dims_37 = None
2025-03-21T20:31:43.5090550Z             
2025-03-21T20:31:43.5091022Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.5091940Z             quantized_decomposed_dequantize_per_tensor_default_812: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_514, 0.0003007998166140169, 27134, 0, 65535, torch.int32)
2025-03-21T20:31:43.5092029Z             
2025-03-21T20:31:43.5092508Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.5093640Z             quantized_decomposed_dequantize_per_tensor_default_813: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_514, 0.0003007998166140169, 27134, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_514 = None
2025-03-21T20:31:43.5093738Z             
2025-03-21T20:31:43.5094490Z              # File: <eval_with_key>.50:2028 in forward, code: quantize_per_tensor_default_667 = torch.ops.quantized_decomposed.quantize_per_tensor.default(_to_copy_7, 0.00039280077908188105, 32440, 0, 65535, torch.int32);  _to_copy_7 = None
2025-03-21T20:31:43.5095630Z             quantized_decomposed_quantize_per_tensor_default_515: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_806, 0.00039280077908188105, 32440, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_806 = None
2025-03-21T20:31:43.5095716Z             
2025-03-21T20:31:43.5096273Z              # File: /pytorch/executorch/examples/models/llama/rope.py:85 in apply_rotary_emb, code: xk_r, xk_i = xk.float().reshape(xk.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.5097433Z             quantized_decomposed_dequantize_per_tensor_default_814: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_515, 0.00039280077908188105, 32440, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_515 = None
2025-03-21T20:31:43.5098235Z             aten_view_copy_default_58: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_814, [1, 1, 12, -1, 2]);  quantized_decomposed_dequantize_per_tensor_default_814 = None
2025-03-21T20:31:43.5099134Z             quantized_decomposed_quantize_per_tensor_default_516: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_58, 0.00039280077908188105, 32440, 0, 65535, torch.int32);  aten_view_copy_default_58 = None
2025-03-21T20:31:43.5100274Z             quantized_decomposed_dequantize_per_tensor_default_815: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_516, 0.00039280077908188105, 32440, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_516 = None
2025-03-21T20:31:43.5100828Z             aten_slice_copy_tensor_14: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_815, 4, 0, 1)
2025-03-21T20:31:43.5101579Z             aten_slice_copy_tensor_15: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_815, 4, 1, 2);  quantized_decomposed_dequantize_per_tensor_default_815 = None
2025-03-21T20:31:43.5102097Z             aten_squeeze_copy_dims_38: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_14, [4]);  aten_slice_copy_tensor_14 = None
2025-03-21T20:31:43.5102621Z             aten_squeeze_copy_dims_39: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_15, [4]);  aten_slice_copy_tensor_15 = None
2025-03-21T20:31:43.5103518Z             quantized_decomposed_quantize_per_tensor_default_517: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_38, 0.0003777415840886533, 31121, 0, 65535, torch.int32);  aten_squeeze_copy_dims_38 = None
2025-03-21T20:31:43.5103609Z             
2025-03-21T20:31:43.5104081Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.5104993Z             quantized_decomposed_dequantize_per_tensor_default_816: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_517, 0.0003777415840886533, 31121, 0, 65535, torch.int32)
2025-03-21T20:31:43.5105083Z             
2025-03-21T20:31:43.5105559Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.5106692Z             quantized_decomposed_dequantize_per_tensor_default_817: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_517, 0.0003777415840886533, 31121, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_517 = None
2025-03-21T20:31:43.5106782Z             
2025-03-21T20:31:43.5107297Z              # File: /pytorch/executorch/examples/models/llama/rope.py:85 in apply_rotary_emb, code: xk_r, xk_i = xk.float().reshape(xk.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.5108256Z             quantized_decomposed_quantize_per_tensor_default_518: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_39, 0.00037405197508633137, 34066, 0, 65535, torch.int32);  aten_squeeze_copy_dims_39 = None
2025-03-21T20:31:43.5108346Z             
2025-03-21T20:31:43.5108822Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.5109758Z             quantized_decomposed_dequantize_per_tensor_default_818: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_518, 0.00037405197508633137, 34066, 0, 65535, torch.int32)
2025-03-21T20:31:43.5109855Z             
2025-03-21T20:31:43.5110326Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.5111466Z             quantized_decomposed_dequantize_per_tensor_default_819: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_518, 0.00037405197508633137, 34066, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_518 = None
2025-03-21T20:31:43.5111592Z             
2025-03-21T20:31:43.5112030Z              # File: /pytorch/executorch/examples/models/llama/rope.py:78 in reshape_for_broadcast, code: return freqs_cis.view(shape)
2025-03-21T20:31:43.5112801Z             aten_view_copy_default_59: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_159, [1, 1, 1, 32]);  quantized_decomposed_dequantize_per_tensor_default_159 = None
2025-03-21T20:31:43.5113689Z             quantized_decomposed_quantize_per_tensor_default_519: "i32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_59, 3.051804378628731e-05, 32768, 0, 65535, torch.int32);  aten_view_copy_default_59 = None
2025-03-21T20:31:43.5113796Z             
2025-03-21T20:31:43.5114267Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.5115191Z             quantized_decomposed_dequantize_per_tensor_default_820: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_519, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.5115278Z             
2025-03-21T20:31:43.5115760Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.5116665Z             quantized_decomposed_dequantize_per_tensor_default_821: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_519, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.5116764Z             
2025-03-21T20:31:43.5117229Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.5118143Z             quantized_decomposed_dequantize_per_tensor_default_822: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_519, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.5118226Z             
2025-03-21T20:31:43.5118701Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.5119875Z             quantized_decomposed_dequantize_per_tensor_default_823: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_519, 3.051804378628731e-05, 32768, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_519 = None
2025-03-21T20:31:43.5119975Z             
2025-03-21T20:31:43.5120407Z              # File: /pytorch/executorch/examples/models/llama/rope.py:78 in reshape_for_broadcast, code: return freqs_cis.view(shape)
2025-03-21T20:31:43.5121180Z             aten_view_copy_default_60: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_171, [1, 1, 1, 32]);  quantized_decomposed_dequantize_per_tensor_default_171 = None
2025-03-21T20:31:43.5122078Z             quantized_decomposed_quantize_per_tensor_default_520: "i32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_60, 3.051786916330457e-05, 32767, 0, 65535, torch.int32);  aten_view_copy_default_60 = None
2025-03-21T20:31:43.5122165Z             
2025-03-21T20:31:43.5122637Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.5123579Z             quantized_decomposed_dequantize_per_tensor_default_824: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_520, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.5123669Z             
2025-03-21T20:31:43.5124136Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.5125042Z             quantized_decomposed_dequantize_per_tensor_default_825: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_520, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.5125130Z             
2025-03-21T20:31:43.5125606Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.5126505Z             quantized_decomposed_dequantize_per_tensor_default_826: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_520, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.5126593Z             
2025-03-21T20:31:43.5127057Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.5128183Z             quantized_decomposed_dequantize_per_tensor_default_827: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_520, 3.051786916330457e-05, 32767, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_520 = None
2025-03-21T20:31:43.5128274Z             
2025-03-21T20:31:43.5128833Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.5130072Z             aten_mul_tensor_47: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_811, quantized_decomposed_dequantize_per_tensor_default_823);  quantized_decomposed_dequantize_per_tensor_default_811 = quantized_decomposed_dequantize_per_tensor_default_823 = None
2025-03-21T20:31:43.5130972Z             quantized_decomposed_quantize_per_tensor_default_521: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_47, 0.00034635368501767516, 29709, 0, 65535, torch.int32);  aten_mul_tensor_47 = None
2025-03-21T20:31:43.5132144Z             quantized_decomposed_dequantize_per_tensor_default_828: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_521, 0.00034635368501767516, 29709, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_521 = None
2025-03-21T20:31:43.5133490Z             aten_mul_tensor_48: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_812, quantized_decomposed_dequantize_per_tensor_default_826);  quantized_decomposed_dequantize_per_tensor_default_812 = quantized_decomposed_dequantize_per_tensor_default_826 = None
2025-03-21T20:31:43.5134343Z             quantized_decomposed_quantize_per_tensor_default_522: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_48, 0.00016881964984349906, 32450, 0, 65535, torch.int32);  aten_mul_tensor_48 = None
2025-03-21T20:31:43.5135487Z             quantized_decomposed_dequantize_per_tensor_default_829: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_522, 0.00016881964984349906, 32450, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_522 = None
2025-03-21T20:31:43.5136630Z             aten_sub_tensor_6: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_sub_Tensor(quantized_decomposed_dequantize_per_tensor_default_828, quantized_decomposed_dequantize_per_tensor_default_829);  quantized_decomposed_dequantize_per_tensor_default_828 = quantized_decomposed_dequantize_per_tensor_default_829 = None
2025-03-21T20:31:43.5137478Z             quantized_decomposed_quantize_per_tensor_default_523: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_sub_tensor_6, 0.0003396201936993748, 29394, 0, 65535, torch.int32);  aten_sub_tensor_6 = None
2025-03-21T20:31:43.5137566Z             
2025-03-21T20:31:43.5138508Z              # File: <eval_with_key>.50:2062 in forward, code: dequantize_per_tensor_default_675 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_675, 0.0003396201936993748, 29394, 0, 65535, torch.int32);  quantize_per_tensor_default_675 = None
2025-03-21T20:31:43.5139638Z             quantized_decomposed_dequantize_per_tensor_default_830: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_523, 0.0003396201936993748, 29394, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_523 = None
2025-03-21T20:31:43.5139736Z             
2025-03-21T20:31:43.5140210Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.5141323Z             aten_mul_tensor_49: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_810, quantized_decomposed_dequantize_per_tensor_default_827);  quantized_decomposed_dequantize_per_tensor_default_810 = quantized_decomposed_dequantize_per_tensor_default_827 = None
2025-03-21T20:31:43.5142169Z             quantized_decomposed_quantize_per_tensor_default_524: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_49, 0.0001840081822592765, 33501, 0, 65535, torch.int32);  aten_mul_tensor_49 = None
2025-03-21T20:31:43.5143338Z             quantized_decomposed_dequantize_per_tensor_default_831: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_524, 0.0001840081822592765, 33501, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_524 = None
2025-03-21T20:31:43.5144474Z             aten_mul_tensor_50: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_813, quantized_decomposed_dequantize_per_tensor_default_822);  quantized_decomposed_dequantize_per_tensor_default_813 = quantized_decomposed_dequantize_per_tensor_default_822 = None
2025-03-21T20:31:43.5145353Z             quantized_decomposed_quantize_per_tensor_default_525: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_50, 0.00029949701274745166, 27196, 0, 65535, torch.int32);  aten_mul_tensor_50 = None
2025-03-21T20:31:43.5146494Z             quantized_decomposed_dequantize_per_tensor_default_832: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_525, 0.00029949701274745166, 27196, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_525 = None
2025-03-21T20:31:43.5147597Z             aten_add_tensor_15: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_831, quantized_decomposed_dequantize_per_tensor_default_832);  quantized_decomposed_dequantize_per_tensor_default_831 = quantized_decomposed_dequantize_per_tensor_default_832 = None
2025-03-21T20:31:43.5148477Z             quantized_decomposed_quantize_per_tensor_default_526: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_15, 0.0002954587689600885, 27289, 0, 65535, torch.int32);  aten_add_tensor_15 = None
2025-03-21T20:31:43.5148561Z             
2025-03-21T20:31:43.5149498Z              # File: <eval_with_key>.50:2071 in forward, code: dequantize_per_tensor_default_678 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_678, 0.0002954587689600885, 27289, 0, 65535, torch.int32);  quantize_per_tensor_default_678 = None
2025-03-21T20:31:43.5150628Z             quantized_decomposed_dequantize_per_tensor_default_833: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_526, 0.0002954587689600885, 27289, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_526 = None
2025-03-21T20:31:43.5150727Z             
2025-03-21T20:31:43.5151201Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.5152318Z             aten_mul_tensor_51: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_817, quantized_decomposed_dequantize_per_tensor_default_821);  quantized_decomposed_dequantize_per_tensor_default_817 = quantized_decomposed_dequantize_per_tensor_default_821 = None
2025-03-21T20:31:43.5153166Z             quantized_decomposed_quantize_per_tensor_default_527: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_51, 0.00037480672472156584, 31015, 0, 65535, torch.int32);  aten_mul_tensor_51 = None
2025-03-21T20:31:43.5154312Z             quantized_decomposed_dequantize_per_tensor_default_834: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_527, 0.00037480672472156584, 31015, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_527 = None
2025-03-21T20:31:43.5155446Z             aten_mul_tensor_52: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_818, quantized_decomposed_dequantize_per_tensor_default_824);  quantized_decomposed_dequantize_per_tensor_default_818 = quantized_decomposed_dequantize_per_tensor_default_824 = None
2025-03-21T20:31:43.5156320Z             quantized_decomposed_quantize_per_tensor_default_528: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_52, 0.0001904213277157396, 33744, 0, 65535, torch.int32);  aten_mul_tensor_52 = None
2025-03-21T20:31:43.5157476Z             quantized_decomposed_dequantize_per_tensor_default_835: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_528, 0.0001904213277157396, 33744, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_528 = None
2025-03-21T20:31:43.5158589Z             aten_sub_tensor_7: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_sub_Tensor(quantized_decomposed_dequantize_per_tensor_default_834, quantized_decomposed_dequantize_per_tensor_default_835);  quantized_decomposed_dequantize_per_tensor_default_834 = quantized_decomposed_dequantize_per_tensor_default_835 = None
2025-03-21T20:31:43.5159429Z             quantized_decomposed_quantize_per_tensor_default_529: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_sub_tensor_7, 0.0003823137958534062, 31137, 0, 65535, torch.int32);  aten_sub_tensor_7 = None
2025-03-21T20:31:43.5159548Z             
2025-03-21T20:31:43.5160476Z              # File: <eval_with_key>.50:2080 in forward, code: dequantize_per_tensor_default_681 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_681, 0.0003823137958534062, 31137, 0, 65535, torch.int32);  quantize_per_tensor_default_681 = None
2025-03-21T20:31:43.5161616Z             quantized_decomposed_dequantize_per_tensor_default_836: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_529, 0.0003823137958534062, 31137, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_529 = None
2025-03-21T20:31:43.5161705Z             
2025-03-21T20:31:43.5162182Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.5163292Z             aten_mul_tensor_53: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_816, quantized_decomposed_dequantize_per_tensor_default_825);  quantized_decomposed_dequantize_per_tensor_default_816 = quantized_decomposed_dequantize_per_tensor_default_825 = None
2025-03-21T20:31:43.5164146Z             quantized_decomposed_quantize_per_tensor_default_530: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_53, 0.00017462005780544132, 35580, 0, 65535, torch.int32);  aten_mul_tensor_53 = None
2025-03-21T20:31:43.5165281Z             quantized_decomposed_dequantize_per_tensor_default_837: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_530, 0.00017462005780544132, 35580, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_530 = None
2025-03-21T20:31:43.5166396Z             aten_mul_tensor_54: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_819, quantized_decomposed_dequantize_per_tensor_default_820);  quantized_decomposed_dequantize_per_tensor_default_819 = quantized_decomposed_dequantize_per_tensor_default_820 = None
2025-03-21T20:31:43.5167271Z             quantized_decomposed_quantize_per_tensor_default_531: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_54, 0.00036741403164342046, 33632, 0, 65535, torch.int32);  aten_mul_tensor_54 = None
2025-03-21T20:31:43.5168455Z             quantized_decomposed_dequantize_per_tensor_default_838: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_531, 0.00036741403164342046, 33632, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_531 = None
2025-03-21T20:31:43.5169688Z             aten_add_tensor_16: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_837, quantized_decomposed_dequantize_per_tensor_default_838);  quantized_decomposed_dequantize_per_tensor_default_837 = quantized_decomposed_dequantize_per_tensor_default_838 = None
2025-03-21T20:31:43.5170541Z             quantized_decomposed_quantize_per_tensor_default_532: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_16, 0.00036854256177321076, 33858, 0, 65535, torch.int32);  aten_add_tensor_16 = None
2025-03-21T20:31:43.5170648Z             
2025-03-21T20:31:43.5171585Z              # File: <eval_with_key>.50:2089 in forward, code: dequantize_per_tensor_default_684 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_684, 0.00036854256177321076, 33858, 0, 65535, torch.int32);  quantize_per_tensor_default_684 = None
2025-03-21T20:31:43.5172773Z             quantized_decomposed_dequantize_per_tensor_default_839: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_532, 0.00036854256177321076, 33858, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_532 = None
2025-03-21T20:31:43.5172862Z             
2025-03-21T20:31:43.5173403Z              # File: /pytorch/executorch/examples/models/llama/rope.py:95 in apply_rotary_emb, code: xq_out = torch.stack([xq_out_r, xq_out_i], dim=-1).flatten(3)
2025-03-21T20:31:43.5174200Z             aten_unsqueeze_copy_default_36: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_830, 4);  quantized_decomposed_dequantize_per_tensor_default_830 = None
2025-03-21T20:31:43.5175002Z             aten_unsqueeze_copy_default_37: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_833, 4);  quantized_decomposed_dequantize_per_tensor_default_833 = None
2025-03-21T20:31:43.5175739Z             aten_cat_default_12: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_cat_default([aten_unsqueeze_copy_default_36, aten_unsqueeze_copy_default_37], -1);  aten_unsqueeze_copy_default_36 = aten_unsqueeze_copy_default_37 = None
2025-03-21T20:31:43.5176613Z             quantized_decomposed_quantize_per_tensor_default_533: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_12, 0.0003396201936993748, 29394, 0, 65535, torch.int32);  aten_cat_default_12 = None
2025-03-21T20:31:43.5177750Z             quantized_decomposed_dequantize_per_tensor_default_840: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_533, 0.0003396201936993748, 29394, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_533 = None
2025-03-21T20:31:43.5178524Z             aten_view_copy_default_61: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_840, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_840 = None
2025-03-21T20:31:43.5179447Z             quantized_decomposed_quantize_per_tensor_default_534: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_61, 0.0003396201936993748, 29394, 0, 65535, torch.int32);  aten_view_copy_default_61 = None
2025-03-21T20:31:43.5179572Z             
2025-03-21T20:31:43.5180496Z              # File: <eval_with_key>.50:2095 in forward, code: dequantize_per_tensor_default_686 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_686, 0.0003396201936993748, 29394, 0, 65535, torch.int32);  quantize_per_tensor_default_686 = None
2025-03-21T20:31:43.5181669Z             quantized_decomposed_dequantize_per_tensor_default_841: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_534, 0.0003396201936993748, 29394, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_534 = None
2025-03-21T20:31:43.5181759Z             
2025-03-21T20:31:43.5182290Z              # File: /pytorch/executorch/examples/models/llama/rope.py:96 in apply_rotary_emb, code: xk_out = torch.stack([xk_out_r, xk_out_i], dim=-1).flatten(3)
2025-03-21T20:31:43.5183086Z             aten_unsqueeze_copy_default_38: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_836, 4);  quantized_decomposed_dequantize_per_tensor_default_836 = None
2025-03-21T20:31:43.5183908Z             aten_unsqueeze_copy_default_39: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_839, 4);  quantized_decomposed_dequantize_per_tensor_default_839 = None
2025-03-21T20:31:43.5184645Z             aten_cat_default_13: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_cat_default([aten_unsqueeze_copy_default_38, aten_unsqueeze_copy_default_39], -1);  aten_unsqueeze_copy_default_38 = aten_unsqueeze_copy_default_39 = None
2025-03-21T20:31:43.5185523Z             quantized_decomposed_quantize_per_tensor_default_535: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_13, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_cat_default_13 = None
2025-03-21T20:31:43.5186659Z             quantized_decomposed_dequantize_per_tensor_default_842: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_535, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_535 = None
2025-03-21T20:31:43.5187431Z             aten_view_copy_default_62: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_842, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_842 = None
2025-03-21T20:31:43.5188329Z             quantized_decomposed_quantize_per_tensor_default_536: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_62, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_view_copy_default_62 = None
2025-03-21T20:31:43.5188431Z             
2025-03-21T20:31:43.5189357Z              # File: <eval_with_key>.50:2101 in forward, code: dequantize_per_tensor_default_688 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_688, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantize_per_tensor_default_688 = None
2025-03-21T20:31:43.5190507Z             quantized_decomposed_dequantize_per_tensor_default_843: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_536, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_536 = None
2025-03-21T20:31:43.5190597Z             
2025-03-21T20:31:43.5191374Z              # File: <eval_with_key>.50:2103 in forward, code: quantize_per_tensor_default_689 = torch.ops.quantized_decomposed.quantize_per_tensor.default(type_as_6, 0.0003396201936993748, 29394, 0, 65535, torch.int32);  type_as_6 = None
2025-03-21T20:31:43.5192531Z             quantized_decomposed_quantize_per_tensor_default_537: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_841, 0.0003396201936993748, 29394, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_841 = None
2025-03-21T20:31:43.5192634Z             
2025-03-21T20:31:43.5193181Z              # File: /pytorch/executorch/examples/models/llama/attention.py:249 in forward, code: q = q.transpose(1, 2)  # (bs, n_local_heads, seqlen, head_dim)
2025-03-21T20:31:43.5194325Z             quantized_decomposed_dequantize_per_tensor_default_844: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_537, 0.0003396201936993748, 29394, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_537 = None
2025-03-21T20:31:43.5194418Z             
2025-03-21T20:31:43.5195177Z              # File: <eval_with_key>.50:2106 in forward, code: quantize_per_tensor_default_690 = torch.ops.quantized_decomposed.quantize_per_tensor.default(type_as_7, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  type_as_7 = None
2025-03-21T20:31:43.5196336Z             quantized_decomposed_quantize_per_tensor_default_538: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_843, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_843 = None
2025-03-21T20:31:43.5196435Z             
2025-03-21T20:31:43.5197101Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:345 in update, code: k_out = torch.ops.aten.index_put_(self.past_k_caches, [None, input_pos], k_val)
2025-03-21T20:31:43.5198250Z             quantized_decomposed_dequantize_per_tensor_default_845: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_538, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_538 = None
2025-03-21T20:31:43.5198338Z             
2025-03-21T20:31:43.5198873Z              # File: /pytorch/executorch/examples/models/llama/attention.py:249 in forward, code: q = q.transpose(1, 2)  # (bs, n_local_heads, seqlen, head_dim)
2025-03-21T20:31:43.5199662Z             aten_permute_copy_default_129: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_844, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_844 = None
2025-03-21T20:31:43.5200597Z             quantized_decomposed_quantize_per_tensor_default_539: "i32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_129, 0.0003396201936993748, 29394, 0, 65535, torch.int32);  aten_permute_copy_default_129 = None
2025-03-21T20:31:43.5200686Z             
2025-03-21T20:31:43.5201274Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.5202406Z             quantized_decomposed_dequantize_per_tensor_default_846: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_539, 0.0003396201936993748, 29394, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_539 = None
2025-03-21T20:31:43.5202507Z             
2025-03-21T20:31:43.5203171Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:345 in update, code: k_out = torch.ops.aten.index_put_(self.past_k_caches, [None, input_pos], k_val)
2025-03-21T20:31:43.5204509Z             aten_index_put_default_6: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_index_put_default(quantized_decomposed_dequantize_per_tensor_default_122, [None, attn_options_input_pos], quantized_decomposed_dequantize_per_tensor_default_845);  quantized_decomposed_dequantize_per_tensor_default_122 = quantized_decomposed_dequantize_per_tensor_default_845 = None
2025-03-21T20:31:43.5205431Z             quantized_decomposed_quantize_per_tensor_default_540: "i32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_put_default_6, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_index_put_default_6 = None
2025-03-21T20:31:43.5205532Z             
2025-03-21T20:31:43.5206315Z              # File: <eval_with_key>.50:2113 in forward, code: dequantize_per_tensor_default_692 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_692, 0.0003910682280547917, 31907, 0, 65535, torch.int32)
2025-03-21T20:31:43.5207248Z             quantized_decomposed_dequantize_per_tensor_default_847: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_540, 0.0003910682280547917, 31907, 0, 65535, torch.int32)
2025-03-21T20:31:43.5207360Z             
2025-03-21T20:31:43.5208005Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5208927Z             quantized_decomposed_dequantize_per_tensor_default_848: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_540, 0.0003910682280547917, 31907, 0, 65535, torch.int32)
2025-03-21T20:31:43.5209915Z             quantized_decomposed_dequantize_per_tensor_default_849: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_540, 0.0003910682280547917, 31907, 0, 65535, torch.int32)
2025-03-21T20:31:43.5210832Z             quantized_decomposed_dequantize_per_tensor_default_850: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_540, 0.0003910682280547917, 31907, 0, 65535, torch.int32)
2025-03-21T20:31:43.5211761Z             quantized_decomposed_dequantize_per_tensor_default_851: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_540, 0.0003910682280547917, 31907, 0, 65535, torch.int32)
2025-03-21T20:31:43.5212672Z             quantized_decomposed_dequantize_per_tensor_default_852: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_540, 0.0003910682280547917, 31907, 0, 65535, torch.int32)
2025-03-21T20:31:43.5213599Z             quantized_decomposed_dequantize_per_tensor_default_853: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_540, 0.0003910682280547917, 31907, 0, 65535, torch.int32)
2025-03-21T20:31:43.5214516Z             quantized_decomposed_dequantize_per_tensor_default_854: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_540, 0.0003910682280547917, 31907, 0, 65535, torch.int32)
2025-03-21T20:31:43.5215473Z             quantized_decomposed_dequantize_per_tensor_default_855: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_540, 0.0003910682280547917, 31907, 0, 65535, torch.int32)
2025-03-21T20:31:43.5216416Z             quantized_decomposed_dequantize_per_tensor_default_856: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_540, 0.0003910682280547917, 31907, 0, 65535, torch.int32)
2025-03-21T20:31:43.5217369Z             quantized_decomposed_dequantize_per_tensor_default_857: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_540, 0.0003910682280547917, 31907, 0, 65535, torch.int32)
2025-03-21T20:31:43.5218285Z             quantized_decomposed_dequantize_per_tensor_default_858: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_540, 0.0003910682280547917, 31907, 0, 65535, torch.int32)
2025-03-21T20:31:43.5219469Z             quantized_decomposed_dequantize_per_tensor_default_859: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_540, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_540 = None
2025-03-21T20:31:43.5219640Z             
2025-03-21T20:31:43.5220335Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:346 in update, code: v_out = torch.ops.aten.index_put_(self.past_v_caches, [None, input_pos], v_val)
2025-03-21T20:31:43.5221610Z             aten_index_put_default_7: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_index_put_default(quantized_decomposed_dequantize_per_tensor_default_123, [None, attn_options_input_pos], quantized_decomposed_dequantize_per_tensor_default_807);  quantized_decomposed_dequantize_per_tensor_default_123 = quantized_decomposed_dequantize_per_tensor_default_807 = None
2025-03-21T20:31:43.5222527Z             quantized_decomposed_quantize_per_tensor_default_541: "i32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_put_default_7, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_index_put_default_7 = None
2025-03-21T20:31:43.5222615Z             
2025-03-21T20:31:43.5223413Z              # File: <eval_with_key>.50:2128 in forward, code: dequantize_per_tensor_default_693 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_693, 0.00011123115109512582, 26424, 0, 65535, torch.int32)
2025-03-21T20:31:43.5224331Z             quantized_decomposed_dequantize_per_tensor_default_860: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_541, 0.00011123115109512582, 26424, 0, 65535, torch.int32)
2025-03-21T20:31:43.5224430Z             
2025-03-21T20:31:43.5225067Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5225995Z             quantized_decomposed_dequantize_per_tensor_default_861: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_541, 0.00011123115109512582, 26424, 0, 65535, torch.int32)
2025-03-21T20:31:43.5226908Z             quantized_decomposed_dequantize_per_tensor_default_862: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_541, 0.00011123115109512582, 26424, 0, 65535, torch.int32)
2025-03-21T20:31:43.5227858Z             quantized_decomposed_dequantize_per_tensor_default_863: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_541, 0.00011123115109512582, 26424, 0, 65535, torch.int32)
2025-03-21T20:31:43.5228790Z             quantized_decomposed_dequantize_per_tensor_default_864: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_541, 0.00011123115109512582, 26424, 0, 65535, torch.int32)
2025-03-21T20:31:43.5229738Z             quantized_decomposed_dequantize_per_tensor_default_865: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_541, 0.00011123115109512582, 26424, 0, 65535, torch.int32)
2025-03-21T20:31:43.5230936Z             quantized_decomposed_dequantize_per_tensor_default_866: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_541, 0.00011123115109512582, 26424, 0, 65535, torch.int32)
2025-03-21T20:31:43.5231853Z             quantized_decomposed_dequantize_per_tensor_default_867: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_541, 0.00011123115109512582, 26424, 0, 65535, torch.int32)
2025-03-21T20:31:43.5232995Z             quantized_decomposed_dequantize_per_tensor_default_868: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_541, 0.00011123115109512582, 26424, 0, 65535, torch.int32)
2025-03-21T20:31:43.5233914Z             quantized_decomposed_dequantize_per_tensor_default_869: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_541, 0.00011123115109512582, 26424, 0, 65535, torch.int32)
2025-03-21T20:31:43.5234843Z             quantized_decomposed_dequantize_per_tensor_default_870: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_541, 0.00011123115109512582, 26424, 0, 65535, torch.int32)
2025-03-21T20:31:43.5235755Z             quantized_decomposed_dequantize_per_tensor_default_871: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_541, 0.00011123115109512582, 26424, 0, 65535, torch.int32)
2025-03-21T20:31:43.5236918Z             quantized_decomposed_dequantize_per_tensor_default_872: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_541, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_541 = None
2025-03-21T20:31:43.5237010Z             
2025-03-21T20:31:43.5237663Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5238462Z             aten_permute_copy_default_130: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_859, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_859 = None
2025-03-21T20:31:43.5239410Z             quantized_decomposed_quantize_per_tensor_default_542: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_130, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_permute_copy_default_130 = None
2025-03-21T20:31:43.5240609Z             quantized_decomposed_dequantize_per_tensor_default_873: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_542, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_542 = None
2025-03-21T20:31:43.5241391Z             aten_select_copy_int_144: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_873, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_873 = None
2025-03-21T20:31:43.5242348Z             quantized_decomposed_quantize_per_tensor_default_543: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_144, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_select_copy_int_144 = None
2025-03-21T20:31:43.5243497Z             quantized_decomposed_dequantize_per_tensor_default_874: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_543, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_543 = None
2025-03-21T20:31:43.5244230Z             aten_select_copy_int_145: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_874, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_874 = None
2025-03-21T20:31:43.5245161Z             quantized_decomposed_quantize_per_tensor_default_544: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_145, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_select_copy_int_145 = None
2025-03-21T20:31:43.5245249Z             
2025-03-21T20:31:43.5246197Z              # File: <eval_with_key>.50:2149 in forward, code: dequantize_per_tensor_default_696 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_696, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantize_per_tensor_default_696 = None
2025-03-21T20:31:43.5247336Z             quantized_decomposed_dequantize_per_tensor_default_875: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_544, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_544 = None
2025-03-21T20:31:43.5247441Z             
2025-03-21T20:31:43.5248078Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5248883Z             aten_permute_copy_default_131: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_858, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_858 = None
2025-03-21T20:31:43.5249882Z             quantized_decomposed_quantize_per_tensor_default_545: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_131, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_permute_copy_default_131 = None
2025-03-21T20:31:43.5251036Z             quantized_decomposed_dequantize_per_tensor_default_876: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_545, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_545 = None
2025-03-21T20:31:43.5251772Z             aten_select_copy_int_146: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_876, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_876 = None
2025-03-21T20:31:43.5252702Z             quantized_decomposed_quantize_per_tensor_default_546: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_146, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_select_copy_int_146 = None
2025-03-21T20:31:43.5253876Z             quantized_decomposed_dequantize_per_tensor_default_877: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_546, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_546 = None
2025-03-21T20:31:43.5254633Z             aten_select_copy_int_147: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_877, 0, 1);  quantized_decomposed_dequantize_per_tensor_default_877 = None
2025-03-21T20:31:43.5255536Z             quantized_decomposed_quantize_per_tensor_default_547: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_147, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_select_copy_int_147 = None
2025-03-21T20:31:43.5255625Z             
2025-03-21T20:31:43.5256563Z              # File: <eval_with_key>.50:2158 in forward, code: dequantize_per_tensor_default_699 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_699, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantize_per_tensor_default_699 = None
2025-03-21T20:31:43.5257719Z             quantized_decomposed_dequantize_per_tensor_default_878: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_547, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_547 = None
2025-03-21T20:31:43.5257819Z             
2025-03-21T20:31:43.5258457Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5259267Z             aten_permute_copy_default_132: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_857, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_857 = None
2025-03-21T20:31:43.5260204Z             quantized_decomposed_quantize_per_tensor_default_548: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_132, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_permute_copy_default_132 = None
2025-03-21T20:31:43.5261349Z             quantized_decomposed_dequantize_per_tensor_default_879: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_548, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_548 = None
2025-03-21T20:31:43.5262084Z             aten_select_copy_int_148: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_879, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_879 = None
2025-03-21T20:31:43.5262984Z             quantized_decomposed_quantize_per_tensor_default_549: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_148, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_select_copy_int_148 = None
2025-03-21T20:31:43.5264115Z             quantized_decomposed_dequantize_per_tensor_default_880: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_549, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_549 = None
2025-03-21T20:31:43.5264890Z             aten_select_copy_int_149: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_880, 0, 2);  quantized_decomposed_dequantize_per_tensor_default_880 = None
2025-03-21T20:31:43.5265801Z             quantized_decomposed_quantize_per_tensor_default_550: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_149, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_select_copy_int_149 = None
2025-03-21T20:31:43.5265901Z             
2025-03-21T20:31:43.5266848Z              # File: <eval_with_key>.50:2167 in forward, code: dequantize_per_tensor_default_702 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_702, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantize_per_tensor_default_702 = None
2025-03-21T20:31:43.5267997Z             quantized_decomposed_dequantize_per_tensor_default_881: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_550, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_550 = None
2025-03-21T20:31:43.5268109Z             
2025-03-21T20:31:43.5268754Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5269546Z             aten_permute_copy_default_133: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_856, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_856 = None
2025-03-21T20:31:43.5270495Z             quantized_decomposed_quantize_per_tensor_default_551: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_133, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_permute_copy_default_133 = None
2025-03-21T20:31:43.5271628Z             quantized_decomposed_dequantize_per_tensor_default_882: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_551, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_551 = None
2025-03-21T20:31:43.5272374Z             aten_select_copy_int_150: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_882, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_882 = None
2025-03-21T20:31:43.5273259Z             quantized_decomposed_quantize_per_tensor_default_552: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_150, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_select_copy_int_150 = None
2025-03-21T20:31:43.5274410Z             quantized_decomposed_dequantize_per_tensor_default_883: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_552, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_552 = None
2025-03-21T20:31:43.5275141Z             aten_select_copy_int_151: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_883, 0, 3);  quantized_decomposed_dequantize_per_tensor_default_883 = None
2025-03-21T20:31:43.5276037Z             quantized_decomposed_quantize_per_tensor_default_553: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_151, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_select_copy_int_151 = None
2025-03-21T20:31:43.5276125Z             
2025-03-21T20:31:43.5277117Z              # File: <eval_with_key>.50:2176 in forward, code: dequantize_per_tensor_default_705 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_705, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantize_per_tensor_default_705 = None
2025-03-21T20:31:43.5278276Z             quantized_decomposed_dequantize_per_tensor_default_884: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_553, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_553 = None
2025-03-21T20:31:43.5278379Z             
2025-03-21T20:31:43.5279014Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5279819Z             aten_permute_copy_default_134: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_855, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_855 = None
2025-03-21T20:31:43.5280754Z             quantized_decomposed_quantize_per_tensor_default_554: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_134, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_permute_copy_default_134 = None
2025-03-21T20:31:43.5281935Z             quantized_decomposed_dequantize_per_tensor_default_885: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_554, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_554 = None
2025-03-21T20:31:43.5282683Z             aten_select_copy_int_152: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_885, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_885 = None
2025-03-21T20:31:43.5283573Z             quantized_decomposed_quantize_per_tensor_default_555: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_152, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_select_copy_int_152 = None
2025-03-21T20:31:43.5284722Z             quantized_decomposed_dequantize_per_tensor_default_886: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_555, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_555 = None
2025-03-21T20:31:43.5285454Z             aten_select_copy_int_153: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_886, 0, 4);  quantized_decomposed_dequantize_per_tensor_default_886 = None
2025-03-21T20:31:43.5286352Z             quantized_decomposed_quantize_per_tensor_default_556: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_153, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_select_copy_int_153 = None
2025-03-21T20:31:43.5286444Z             
2025-03-21T20:31:43.5287381Z              # File: <eval_with_key>.50:2185 in forward, code: dequantize_per_tensor_default_708 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_708, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantize_per_tensor_default_708 = None
2025-03-21T20:31:43.5288537Z             quantized_decomposed_dequantize_per_tensor_default_887: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_556, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_556 = None
2025-03-21T20:31:43.5288660Z             
2025-03-21T20:31:43.5289351Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5290165Z             aten_permute_copy_default_135: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_854, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_854 = None
2025-03-21T20:31:43.5291134Z             quantized_decomposed_quantize_per_tensor_default_557: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_135, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_permute_copy_default_135 = None
2025-03-21T20:31:43.5292290Z             quantized_decomposed_dequantize_per_tensor_default_888: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_557, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_557 = None
2025-03-21T20:31:43.5293051Z             aten_select_copy_int_154: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_888, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_888 = None
2025-03-21T20:31:43.5293951Z             quantized_decomposed_quantize_per_tensor_default_558: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_154, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_select_copy_int_154 = None
2025-03-21T20:31:43.5295085Z             quantized_decomposed_dequantize_per_tensor_default_889: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_558, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_558 = None
2025-03-21T20:31:43.5295833Z             aten_select_copy_int_155: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_889, 0, 5);  quantized_decomposed_dequantize_per_tensor_default_889 = None
2025-03-21T20:31:43.5296722Z             quantized_decomposed_quantize_per_tensor_default_559: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_155, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_select_copy_int_155 = None
2025-03-21T20:31:43.5296827Z             
2025-03-21T20:31:43.5297753Z              # File: <eval_with_key>.50:2194 in forward, code: dequantize_per_tensor_default_711 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_711, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantize_per_tensor_default_711 = None
2025-03-21T20:31:43.5298901Z             quantized_decomposed_dequantize_per_tensor_default_890: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_559, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_559 = None
2025-03-21T20:31:43.5298994Z             
2025-03-21T20:31:43.5299642Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5300462Z             aten_permute_copy_default_136: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_853, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_853 = None
2025-03-21T20:31:43.5301437Z             quantized_decomposed_quantize_per_tensor_default_560: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_136, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_permute_copy_default_136 = None
2025-03-21T20:31:43.5302598Z             quantized_decomposed_dequantize_per_tensor_default_891: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_560, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_560 = None
2025-03-21T20:31:43.5303346Z             aten_select_copy_int_156: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_891, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_891 = None
2025-03-21T20:31:43.5304244Z             quantized_decomposed_quantize_per_tensor_default_561: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_156, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_select_copy_int_156 = None
2025-03-21T20:31:43.5305430Z             quantized_decomposed_dequantize_per_tensor_default_892: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_561, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_561 = None
2025-03-21T20:31:43.5306157Z             aten_select_copy_int_157: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_892, 0, 6);  quantized_decomposed_dequantize_per_tensor_default_892 = None
2025-03-21T20:31:43.5307058Z             quantized_decomposed_quantize_per_tensor_default_562: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_157, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_select_copy_int_157 = None
2025-03-21T20:31:43.5307150Z             
2025-03-21T20:31:43.5308093Z              # File: <eval_with_key>.50:2203 in forward, code: dequantize_per_tensor_default_714 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_714, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantize_per_tensor_default_714 = None
2025-03-21T20:31:43.5309232Z             quantized_decomposed_dequantize_per_tensor_default_893: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_562, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_562 = None
2025-03-21T20:31:43.5309339Z             
2025-03-21T20:31:43.5309977Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5310789Z             aten_permute_copy_default_137: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_852, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_852 = None
2025-03-21T20:31:43.5311728Z             quantized_decomposed_quantize_per_tensor_default_563: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_137, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_permute_copy_default_137 = None
2025-03-21T20:31:43.5312901Z             quantized_decomposed_dequantize_per_tensor_default_894: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_563, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_563 = None
2025-03-21T20:31:43.5313674Z             aten_select_copy_int_158: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_894, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_894 = None
2025-03-21T20:31:43.5314591Z             quantized_decomposed_quantize_per_tensor_default_564: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_158, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_select_copy_int_158 = None
2025-03-21T20:31:43.5315744Z             quantized_decomposed_dequantize_per_tensor_default_895: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_564, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_564 = None
2025-03-21T20:31:43.5316473Z             aten_select_copy_int_159: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_895, 0, 7);  quantized_decomposed_dequantize_per_tensor_default_895 = None
2025-03-21T20:31:43.5317406Z             quantized_decomposed_quantize_per_tensor_default_565: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_159, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_select_copy_int_159 = None
2025-03-21T20:31:43.5317502Z             
2025-03-21T20:31:43.5318443Z              # File: <eval_with_key>.50:2212 in forward, code: dequantize_per_tensor_default_717 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_717, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantize_per_tensor_default_717 = None
2025-03-21T20:31:43.5319584Z             quantized_decomposed_dequantize_per_tensor_default_896: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_565, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_565 = None
2025-03-21T20:31:43.5319691Z             
2025-03-21T20:31:43.5320325Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5321141Z             aten_permute_copy_default_138: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_851, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_851 = None
2025-03-21T20:31:43.5322081Z             quantized_decomposed_quantize_per_tensor_default_566: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_138, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_permute_copy_default_138 = None
2025-03-21T20:31:43.5323239Z             quantized_decomposed_dequantize_per_tensor_default_897: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_566, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_566 = None
2025-03-21T20:31:43.5323974Z             aten_select_copy_int_160: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_897, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_897 = None
2025-03-21T20:31:43.5324901Z             quantized_decomposed_quantize_per_tensor_default_567: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_160, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_select_copy_int_160 = None
2025-03-21T20:31:43.5326057Z             quantized_decomposed_dequantize_per_tensor_default_898: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_567, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_567 = None
2025-03-21T20:31:43.5326825Z             aten_select_copy_int_161: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_898, 0, 8);  quantized_decomposed_dequantize_per_tensor_default_898 = None
2025-03-21T20:31:43.5327708Z             quantized_decomposed_quantize_per_tensor_default_568: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_161, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_select_copy_int_161 = None
2025-03-21T20:31:43.5327808Z             
2025-03-21T20:31:43.5328732Z              # File: <eval_with_key>.50:2221 in forward, code: dequantize_per_tensor_default_720 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_720, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantize_per_tensor_default_720 = None
2025-03-21T20:31:43.5329973Z             quantized_decomposed_dequantize_per_tensor_default_899: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_568, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_568 = None
2025-03-21T20:31:43.5330063Z             
2025-03-21T20:31:43.5330709Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5331504Z             aten_permute_copy_default_139: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_850, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_850 = None
2025-03-21T20:31:43.5332735Z             quantized_decomposed_quantize_per_tensor_default_569: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_139, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_permute_copy_default_139 = None
2025-03-21T20:31:43.5333879Z             quantized_decomposed_dequantize_per_tensor_default_900: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_569, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_569 = None
2025-03-21T20:31:43.5334628Z             aten_select_copy_int_162: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_900, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_900 = None
2025-03-21T20:31:43.5335516Z             quantized_decomposed_quantize_per_tensor_default_570: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_162, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_select_copy_int_162 = None
2025-03-21T20:31:43.5336664Z             quantized_decomposed_dequantize_per_tensor_default_901: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_570, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_570 = None
2025-03-21T20:31:43.5337472Z             aten_select_copy_int_163: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_901, 0, 9);  quantized_decomposed_dequantize_per_tensor_default_901 = None
2025-03-21T20:31:43.5338391Z             quantized_decomposed_quantize_per_tensor_default_571: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_163, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_select_copy_int_163 = None
2025-03-21T20:31:43.5338495Z             
2025-03-21T20:31:43.5339456Z              # File: <eval_with_key>.50:2230 in forward, code: dequantize_per_tensor_default_723 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_723, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantize_per_tensor_default_723 = None
2025-03-21T20:31:43.5340607Z             quantized_decomposed_dequantize_per_tensor_default_902: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_571, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_571 = None
2025-03-21T20:31:43.5340728Z             
2025-03-21T20:31:43.5341360Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5342166Z             aten_permute_copy_default_140: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_849, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_849 = None
2025-03-21T20:31:43.5343104Z             quantized_decomposed_quantize_per_tensor_default_572: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_140, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_permute_copy_default_140 = None
2025-03-21T20:31:43.5344252Z             quantized_decomposed_dequantize_per_tensor_default_903: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_572, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_572 = None
2025-03-21T20:31:43.5345001Z             aten_select_copy_int_164: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_903, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_903 = None
2025-03-21T20:31:43.5345892Z             quantized_decomposed_quantize_per_tensor_default_573: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_164, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_select_copy_int_164 = None
2025-03-21T20:31:43.5347040Z             quantized_decomposed_dequantize_per_tensor_default_904: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_573, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_573 = None
2025-03-21T20:31:43.5347772Z             aten_select_copy_int_165: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_904, 0, 10);  quantized_decomposed_dequantize_per_tensor_default_904 = None
2025-03-21T20:31:43.5348671Z             quantized_decomposed_quantize_per_tensor_default_574: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_165, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_select_copy_int_165 = None
2025-03-21T20:31:43.5348761Z             
2025-03-21T20:31:43.5349749Z              # File: <eval_with_key>.50:2239 in forward, code: dequantize_per_tensor_default_726 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_726, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantize_per_tensor_default_726 = None
2025-03-21T20:31:43.5350921Z             quantized_decomposed_dequantize_per_tensor_default_905: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_574, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_574 = None
2025-03-21T20:31:43.5351024Z             
2025-03-21T20:31:43.5351657Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5352465Z             aten_permute_copy_default_141: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_848, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_848 = None
2025-03-21T20:31:43.5353397Z             quantized_decomposed_quantize_per_tensor_default_575: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_141, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_permute_copy_default_141 = None
2025-03-21T20:31:43.5354571Z             quantized_decomposed_dequantize_per_tensor_default_906: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_575, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_575 = None
2025-03-21T20:31:43.5355309Z             aten_select_copy_int_166: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_906, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_906 = None
2025-03-21T20:31:43.5356208Z             quantized_decomposed_quantize_per_tensor_default_576: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_166, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_select_copy_int_166 = None
2025-03-21T20:31:43.5357338Z             quantized_decomposed_dequantize_per_tensor_default_907: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_576, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_576 = None
2025-03-21T20:31:43.5358085Z             aten_select_copy_int_167: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_907, 0, 11);  quantized_decomposed_dequantize_per_tensor_default_907 = None
2025-03-21T20:31:43.5358971Z             quantized_decomposed_quantize_per_tensor_default_577: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_167, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_select_copy_int_167 = None
2025-03-21T20:31:43.5359073Z             
2025-03-21T20:31:43.5359997Z              # File: <eval_with_key>.50:2248 in forward, code: dequantize_per_tensor_default_729 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_729, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantize_per_tensor_default_729 = None
2025-03-21T20:31:43.5361162Z             quantized_decomposed_dequantize_per_tensor_default_908: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_577, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_577 = None
2025-03-21T20:31:43.5361276Z             
2025-03-21T20:31:43.5361920Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5367337Z             aten_cat_default_14: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_aten_cat_default([quantized_decomposed_dequantize_per_tensor_default_875, quantized_decomposed_dequantize_per_tensor_default_878, quantized_decomposed_dequantize_per_tensor_default_881, quantized_decomposed_dequantize_per_tensor_default_884, quantized_decomposed_dequantize_per_tensor_default_887, quantized_decomposed_dequantize_per_tensor_default_890, quantized_decomposed_dequantize_per_tensor_default_893, quantized_decomposed_dequantize_per_tensor_default_896, quantized_decomposed_dequantize_per_tensor_default_899, quantized_decomposed_dequantize_per_tensor_default_902, quantized_decomposed_dequantize_per_tensor_default_905, quantized_decomposed_dequantize_per_tensor_default_908]);  quantized_decomposed_dequantize_per_tensor_default_875 = quantized_decomposed_dequantize_per_tensor_default_878 = quantized_decomposed_dequantize_per_tensor_default_881 = quantized_decomposed_dequantize_per_tensor_default_884 = quantized_decomposed_dequantize_per_tensor_default_887 = quantized_decomposed_dequantize_per_tensor_default_890 = quantized_decomposed_dequantize_per_tensor_default_893 = quantized_decomposed_dequantize_per_tensor_default_896 = quantized_decomposed_dequantize_per_tensor_default_899 = quantized_decomposed_dequantize_per_tensor_default_902 = quantized_decomposed_dequantize_per_tensor_default_905 = quantized_decomposed_dequantize_per_tensor_default_908 = None
2025-03-21T20:31:43.5368224Z             quantized_decomposed_quantize_per_tensor_default_578: "i32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_14, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_cat_default_14 = None
2025-03-21T20:31:43.5369441Z             quantized_decomposed_dequantize_per_tensor_default_909: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_578, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_578 = None
2025-03-21T20:31:43.5370238Z             aten_view_copy_default_63: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_909, [1, 12, 128, 64]);  quantized_decomposed_dequantize_per_tensor_default_909 = None
2025-03-21T20:31:43.5371138Z             quantized_decomposed_quantize_per_tensor_default_579: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_63, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_view_copy_default_63 = None
2025-03-21T20:31:43.5371248Z             
2025-03-21T20:31:43.5371830Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.5372974Z             quantized_decomposed_dequantize_per_tensor_default_910: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_579, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_579 = None
2025-03-21T20:31:43.5373082Z             
2025-03-21T20:31:43.5373717Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5374556Z             aten_permute_copy_default_142: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_872, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_872 = None
2025-03-21T20:31:43.5375519Z             quantized_decomposed_quantize_per_tensor_default_580: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_142, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_permute_copy_default_142 = None
2025-03-21T20:31:43.5376696Z             quantized_decomposed_dequantize_per_tensor_default_911: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_580, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_580 = None
2025-03-21T20:31:43.5377445Z             aten_select_copy_int_168: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_911, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_911 = None
2025-03-21T20:31:43.5378338Z             quantized_decomposed_quantize_per_tensor_default_581: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_168, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_select_copy_int_168 = None
2025-03-21T20:31:43.5379507Z             quantized_decomposed_dequantize_per_tensor_default_912: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_581, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_581 = None
2025-03-21T20:31:43.5380238Z             aten_select_copy_int_169: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_912, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_912 = None
2025-03-21T20:31:43.5381136Z             quantized_decomposed_quantize_per_tensor_default_582: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_169, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_select_copy_int_169 = None
2025-03-21T20:31:43.5381226Z             
2025-03-21T20:31:43.5382172Z              # File: <eval_with_key>.50:2263 in forward, code: dequantize_per_tensor_default_734 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_734, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantize_per_tensor_default_734 = None
2025-03-21T20:31:43.5383310Z             quantized_decomposed_dequantize_per_tensor_default_913: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_582, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_582 = None
2025-03-21T20:31:43.5383408Z             
2025-03-21T20:31:43.5384041Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5384846Z             aten_permute_copy_default_143: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_871, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_871 = None
2025-03-21T20:31:43.5385786Z             quantized_decomposed_quantize_per_tensor_default_583: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_143, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_permute_copy_default_143 = None
2025-03-21T20:31:43.5386961Z             quantized_decomposed_dequantize_per_tensor_default_914: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_583, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_583 = None
2025-03-21T20:31:43.5387722Z             aten_select_copy_int_170: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_914, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_914 = None
2025-03-21T20:31:43.5388649Z             quantized_decomposed_quantize_per_tensor_default_584: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_170, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_select_copy_int_170 = None
2025-03-21T20:31:43.5389789Z             quantized_decomposed_dequantize_per_tensor_default_915: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_584, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_584 = None
2025-03-21T20:31:43.5390552Z             aten_select_copy_int_171: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_915, 0, 1);  quantized_decomposed_dequantize_per_tensor_default_915 = None
2025-03-21T20:31:43.5391438Z             quantized_decomposed_quantize_per_tensor_default_585: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_171, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_select_copy_int_171 = None
2025-03-21T20:31:43.5391540Z             
2025-03-21T20:31:43.5392470Z              # File: <eval_with_key>.50:2272 in forward, code: dequantize_per_tensor_default_737 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_737, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantize_per_tensor_default_737 = None
2025-03-21T20:31:43.5393616Z             quantized_decomposed_dequantize_per_tensor_default_916: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_585, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_585 = None
2025-03-21T20:31:43.5393709Z             
2025-03-21T20:31:43.5394356Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5395150Z             aten_permute_copy_default_144: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_870, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_870 = None
2025-03-21T20:31:43.5396105Z             quantized_decomposed_quantize_per_tensor_default_586: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_144, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_permute_copy_default_144 = None
2025-03-21T20:31:43.5397250Z             quantized_decomposed_dequantize_per_tensor_default_917: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_586, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_586 = None
2025-03-21T20:31:43.5397993Z             aten_select_copy_int_172: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_917, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_917 = None
2025-03-21T20:31:43.5398946Z             quantized_decomposed_quantize_per_tensor_default_587: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_172, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_select_copy_int_172 = None
2025-03-21T20:31:43.5400117Z             quantized_decomposed_dequantize_per_tensor_default_918: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_587, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_587 = None
2025-03-21T20:31:43.5400858Z             aten_select_copy_int_173: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_918, 0, 2);  quantized_decomposed_dequantize_per_tensor_default_918 = None
2025-03-21T20:31:43.5401743Z             quantized_decomposed_quantize_per_tensor_default_588: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_173, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_select_copy_int_173 = None
2025-03-21T20:31:43.5401866Z             
2025-03-21T20:31:43.5402795Z              # File: <eval_with_key>.50:2281 in forward, code: dequantize_per_tensor_default_740 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_740, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantize_per_tensor_default_740 = None
2025-03-21T20:31:43.5403947Z             quantized_decomposed_dequantize_per_tensor_default_919: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_588, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_588 = None
2025-03-21T20:31:43.5404035Z             
2025-03-21T20:31:43.5404671Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5405474Z             aten_permute_copy_default_145: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_869, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_869 = None
2025-03-21T20:31:43.5406417Z             quantized_decomposed_quantize_per_tensor_default_589: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_145, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_permute_copy_default_145 = None
2025-03-21T20:31:43.5407568Z             quantized_decomposed_dequantize_per_tensor_default_920: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_589, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_589 = None
2025-03-21T20:31:43.5408310Z             aten_select_copy_int_174: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_920, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_920 = None
2025-03-21T20:31:43.5409209Z             quantized_decomposed_quantize_per_tensor_default_590: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_174, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_select_copy_int_174 = None
2025-03-21T20:31:43.5410498Z             quantized_decomposed_dequantize_per_tensor_default_921: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_590, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_590 = None
2025-03-21T20:31:43.5411255Z             aten_select_copy_int_175: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_921, 0, 3);  quantized_decomposed_dequantize_per_tensor_default_921 = None
2025-03-21T20:31:43.5412183Z             quantized_decomposed_quantize_per_tensor_default_591: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_175, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_select_copy_int_175 = None
2025-03-21T20:31:43.5412271Z             
2025-03-21T20:31:43.5413216Z              # File: <eval_with_key>.50:2290 in forward, code: dequantize_per_tensor_default_743 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_743, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantize_per_tensor_default_743 = None
2025-03-21T20:31:43.5414357Z             quantized_decomposed_dequantize_per_tensor_default_922: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_591, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_591 = None
2025-03-21T20:31:43.5414488Z             
2025-03-21T20:31:43.5415119Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5415928Z             aten_permute_copy_default_146: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_868, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_868 = None
2025-03-21T20:31:43.5416869Z             quantized_decomposed_quantize_per_tensor_default_592: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_146, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_permute_copy_default_146 = None
2025-03-21T20:31:43.5418031Z             quantized_decomposed_dequantize_per_tensor_default_923: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_592, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_592 = None
2025-03-21T20:31:43.5418763Z             aten_select_copy_int_176: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_923, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_923 = None
2025-03-21T20:31:43.5419672Z             quantized_decomposed_quantize_per_tensor_default_593: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_176, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_select_copy_int_176 = None
2025-03-21T20:31:43.5420811Z             quantized_decomposed_dequantize_per_tensor_default_924: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_593, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_593 = None
2025-03-21T20:31:43.5421563Z             aten_select_copy_int_177: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_924, 0, 4);  quantized_decomposed_dequantize_per_tensor_default_924 = None
2025-03-21T20:31:43.5422483Z             quantized_decomposed_quantize_per_tensor_default_594: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_177, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_select_copy_int_177 = None
2025-03-21T20:31:43.5422615Z             
2025-03-21T20:31:43.5423651Z              # File: <eval_with_key>.50:2299 in forward, code: dequantize_per_tensor_default_746 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_746, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantize_per_tensor_default_746 = None
2025-03-21T20:31:43.5424845Z             quantized_decomposed_dequantize_per_tensor_default_925: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_594, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_594 = None
2025-03-21T20:31:43.5424939Z             
2025-03-21T20:31:43.5425592Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5426396Z             aten_permute_copy_default_147: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_867, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_867 = None
2025-03-21T20:31:43.5427379Z             quantized_decomposed_quantize_per_tensor_default_595: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_147, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_permute_copy_default_147 = None
2025-03-21T20:31:43.5428522Z             quantized_decomposed_dequantize_per_tensor_default_926: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_595, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_595 = None
2025-03-21T20:31:43.5429272Z             aten_select_copy_int_178: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_926, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_926 = None
2025-03-21T20:31:43.5430166Z             quantized_decomposed_quantize_per_tensor_default_596: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_178, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_select_copy_int_178 = None
2025-03-21T20:31:43.5431313Z             quantized_decomposed_dequantize_per_tensor_default_927: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_596, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_596 = None
2025-03-21T20:31:43.5432052Z             aten_select_copy_int_179: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_927, 0, 5);  quantized_decomposed_dequantize_per_tensor_default_927 = None
2025-03-21T20:31:43.5433295Z             quantized_decomposed_quantize_per_tensor_default_597: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_179, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_select_copy_int_179 = None
2025-03-21T20:31:43.5433452Z             
2025-03-21T20:31:43.5434579Z              # File: <eval_with_key>.50:2308 in forward, code: dequantize_per_tensor_default_749 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_749, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantize_per_tensor_default_749 = None
2025-03-21T20:31:43.5435822Z             quantized_decomposed_dequantize_per_tensor_default_928: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_597, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_597 = None
2025-03-21T20:31:43.5435977Z             
2025-03-21T20:31:43.5436624Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5437468Z             aten_permute_copy_default_148: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_866, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_866 = None
2025-03-21T20:31:43.5438434Z             quantized_decomposed_quantize_per_tensor_default_598: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_148, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_permute_copy_default_148 = None
2025-03-21T20:31:43.5439579Z             quantized_decomposed_dequantize_per_tensor_default_929: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_598, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_598 = None
2025-03-21T20:31:43.5440366Z             aten_select_copy_int_180: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_929, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_929 = None
2025-03-21T20:31:43.5441259Z             quantized_decomposed_quantize_per_tensor_default_599: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_180, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_select_copy_int_180 = None
2025-03-21T20:31:43.5442415Z             quantized_decomposed_dequantize_per_tensor_default_930: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_599, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_599 = None
2025-03-21T20:31:43.5443150Z             aten_select_copy_int_181: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_930, 0, 6);  quantized_decomposed_dequantize_per_tensor_default_930 = None
2025-03-21T20:31:43.5444057Z             quantized_decomposed_quantize_per_tensor_default_600: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_181, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_select_copy_int_181 = None
2025-03-21T20:31:43.5444146Z             
2025-03-21T20:31:43.5445096Z              # File: <eval_with_key>.50:2317 in forward, code: dequantize_per_tensor_default_752 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_752, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantize_per_tensor_default_752 = None
2025-03-21T20:31:43.5446238Z             quantized_decomposed_dequantize_per_tensor_default_931: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_600, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_600 = None
2025-03-21T20:31:43.5446341Z             
2025-03-21T20:31:43.5446978Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5447826Z             aten_permute_copy_default_149: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_865, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_865 = None
2025-03-21T20:31:43.5448792Z             quantized_decomposed_quantize_per_tensor_default_601: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_149, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_permute_copy_default_149 = None
2025-03-21T20:31:43.5450052Z             quantized_decomposed_dequantize_per_tensor_default_932: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_601, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_601 = None
2025-03-21T20:31:43.5450794Z             aten_select_copy_int_182: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_932, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_932 = None
2025-03-21T20:31:43.5451703Z             quantized_decomposed_quantize_per_tensor_default_602: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_182, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_select_copy_int_182 = None
2025-03-21T20:31:43.5452868Z             quantized_decomposed_dequantize_per_tensor_default_933: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_602, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_602 = None
2025-03-21T20:31:43.5453613Z             aten_select_copy_int_183: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_933, 0, 7);  quantized_decomposed_dequantize_per_tensor_default_933 = None
2025-03-21T20:31:43.5454501Z             quantized_decomposed_quantize_per_tensor_default_603: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_183, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_select_copy_int_183 = None
2025-03-21T20:31:43.5454608Z             
2025-03-21T20:31:43.5455538Z              # File: <eval_with_key>.50:2326 in forward, code: dequantize_per_tensor_default_755 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_755, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantize_per_tensor_default_755 = None
2025-03-21T20:31:43.5456693Z             quantized_decomposed_dequantize_per_tensor_default_934: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_603, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_603 = None
2025-03-21T20:31:43.5456785Z             
2025-03-21T20:31:43.5457434Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5458234Z             aten_permute_copy_default_150: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_864, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_864 = None
2025-03-21T20:31:43.5459185Z             quantized_decomposed_quantize_per_tensor_default_604: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_150, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_permute_copy_default_150 = None
2025-03-21T20:31:43.5460354Z             quantized_decomposed_dequantize_per_tensor_default_935: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_604, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_604 = None
2025-03-21T20:31:43.5461127Z             aten_select_copy_int_184: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_935, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_935 = None
2025-03-21T20:31:43.5462056Z             quantized_decomposed_quantize_per_tensor_default_605: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_184, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_select_copy_int_184 = None
2025-03-21T20:31:43.5463193Z             quantized_decomposed_dequantize_per_tensor_default_936: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_605, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_605 = None
2025-03-21T20:31:43.5463959Z             aten_select_copy_int_185: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_936, 0, 8);  quantized_decomposed_dequantize_per_tensor_default_936 = None
2025-03-21T20:31:43.5464850Z             quantized_decomposed_quantize_per_tensor_default_606: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_185, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_select_copy_int_185 = None
2025-03-21T20:31:43.5464954Z             
2025-03-21T20:31:43.5465885Z              # File: <eval_with_key>.50:2335 in forward, code: dequantize_per_tensor_default_758 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_758, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantize_per_tensor_default_758 = None
2025-03-21T20:31:43.5467038Z             quantized_decomposed_dequantize_per_tensor_default_937: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_606, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_606 = None
2025-03-21T20:31:43.5467127Z             
2025-03-21T20:31:43.5467777Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5468571Z             aten_permute_copy_default_151: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_863, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_863 = None
2025-03-21T20:31:43.5469525Z             quantized_decomposed_quantize_per_tensor_default_607: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_151, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_permute_copy_default_151 = None
2025-03-21T20:31:43.5470667Z             quantized_decomposed_dequantize_per_tensor_default_938: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_607, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_607 = None
2025-03-21T20:31:43.5471411Z             aten_select_copy_int_186: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_938, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_938 = None
2025-03-21T20:31:43.5472352Z             quantized_decomposed_quantize_per_tensor_default_608: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_186, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_select_copy_int_186 = None
2025-03-21T20:31:43.5473527Z             quantized_decomposed_dequantize_per_tensor_default_939: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_608, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_608 = None
2025-03-21T20:31:43.5474253Z             aten_select_copy_int_187: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_939, 0, 9);  quantized_decomposed_dequantize_per_tensor_default_939 = None
2025-03-21T20:31:43.5475156Z             quantized_decomposed_quantize_per_tensor_default_609: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_187, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_select_copy_int_187 = None
2025-03-21T20:31:43.5475269Z             
2025-03-21T20:31:43.5476212Z              # File: <eval_with_key>.50:2344 in forward, code: dequantize_per_tensor_default_761 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_761, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantize_per_tensor_default_761 = None
2025-03-21T20:31:43.5477350Z             quantized_decomposed_dequantize_per_tensor_default_940: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_609, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_609 = None
2025-03-21T20:31:43.5477451Z             
2025-03-21T20:31:43.5478083Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5478889Z             aten_permute_copy_default_152: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_862, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_862 = None
2025-03-21T20:31:43.5479832Z             quantized_decomposed_quantize_per_tensor_default_610: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_152, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_permute_copy_default_152 = None
2025-03-21T20:31:43.5480987Z             quantized_decomposed_dequantize_per_tensor_default_941: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_610, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_610 = None
2025-03-21T20:31:43.5481719Z             aten_select_copy_int_188: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_941, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_941 = None
2025-03-21T20:31:43.5482624Z             quantized_decomposed_quantize_per_tensor_default_611: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_188, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_select_copy_int_188 = None
2025-03-21T20:31:43.5483795Z             quantized_decomposed_dequantize_per_tensor_default_942: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_611, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_611 = None
2025-03-21T20:31:43.5484567Z             aten_select_copy_int_189: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_942, 0, 10);  quantized_decomposed_dequantize_per_tensor_default_942 = None
2025-03-21T20:31:43.5485481Z             quantized_decomposed_quantize_per_tensor_default_612: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_189, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_select_copy_int_189 = None
2025-03-21T20:31:43.5485586Z             
2025-03-21T20:31:43.5486513Z              # File: <eval_with_key>.50:2353 in forward, code: dequantize_per_tensor_default_764 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_764, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantize_per_tensor_default_764 = None
2025-03-21T20:31:43.5487667Z             quantized_decomposed_dequantize_per_tensor_default_943: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_612, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_612 = None
2025-03-21T20:31:43.5487795Z             
2025-03-21T20:31:43.5488445Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5489242Z             aten_permute_copy_default_153: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_861, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_861 = None
2025-03-21T20:31:43.5490266Z             quantized_decomposed_quantize_per_tensor_default_613: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_153, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_permute_copy_default_153 = None
2025-03-21T20:31:43.5491412Z             quantized_decomposed_dequantize_per_tensor_default_944: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_613, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_613 = None
2025-03-21T20:31:43.5492166Z             aten_select_copy_int_190: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_944, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_944 = None
2025-03-21T20:31:43.5493074Z             quantized_decomposed_quantize_per_tensor_default_614: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_190, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_select_copy_int_190 = None
2025-03-21T20:31:43.5494212Z             quantized_decomposed_dequantize_per_tensor_default_945: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_614, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_614 = None
2025-03-21T20:31:43.5494962Z             aten_select_copy_int_191: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_945, 0, 11);  quantized_decomposed_dequantize_per_tensor_default_945 = None
2025-03-21T20:31:43.5495879Z             quantized_decomposed_quantize_per_tensor_default_615: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_191, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_select_copy_int_191 = None
2025-03-21T20:31:43.5496004Z             
2025-03-21T20:31:43.5496930Z              # File: <eval_with_key>.50:2362 in forward, code: dequantize_per_tensor_default_767 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_767, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantize_per_tensor_default_767 = None
2025-03-21T20:31:43.5498103Z             quantized_decomposed_dequantize_per_tensor_default_946: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_615, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_615 = None
2025-03-21T20:31:43.5498192Z             
2025-03-21T20:31:43.5498838Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5504219Z             aten_cat_default_15: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_aten_cat_default([quantized_decomposed_dequantize_per_tensor_default_913, quantized_decomposed_dequantize_per_tensor_default_916, quantized_decomposed_dequantize_per_tensor_default_919, quantized_decomposed_dequantize_per_tensor_default_922, quantized_decomposed_dequantize_per_tensor_default_925, quantized_decomposed_dequantize_per_tensor_default_928, quantized_decomposed_dequantize_per_tensor_default_931, quantized_decomposed_dequantize_per_tensor_default_934, quantized_decomposed_dequantize_per_tensor_default_937, quantized_decomposed_dequantize_per_tensor_default_940, quantized_decomposed_dequantize_per_tensor_default_943, quantized_decomposed_dequantize_per_tensor_default_946]);  quantized_decomposed_dequantize_per_tensor_default_913 = quantized_decomposed_dequantize_per_tensor_default_916 = quantized_decomposed_dequantize_per_tensor_default_919 = quantized_decomposed_dequantize_per_tensor_default_922 = quantized_decomposed_dequantize_per_tensor_default_925 = quantized_decomposed_dequantize_per_tensor_default_928 = quantized_decomposed_dequantize_per_tensor_default_931 = quantized_decomposed_dequantize_per_tensor_default_934 = quantized_decomposed_dequantize_per_tensor_default_937 = quantized_decomposed_dequantize_per_tensor_default_940 = quantized_decomposed_dequantize_per_tensor_default_943 = quantized_decomposed_dequantize_per_tensor_default_946 = None
2025-03-21T20:31:43.5505127Z             quantized_decomposed_quantize_per_tensor_default_616: "i32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_15, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_cat_default_15 = None
2025-03-21T20:31:43.5506282Z             quantized_decomposed_dequantize_per_tensor_default_947: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_616, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_616 = None
2025-03-21T20:31:43.5507052Z             aten_view_copy_default_64: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_947, [1, 12, 128, 64]);  quantized_decomposed_dequantize_per_tensor_default_947 = None
2025-03-21T20:31:43.5507972Z             quantized_decomposed_quantize_per_tensor_default_617: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_64, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  aten_view_copy_default_64 = None
2025-03-21T20:31:43.5508060Z             
2025-03-21T20:31:43.5509026Z              # File: <eval_with_key>.50:2368 in forward, code: dequantize_per_tensor_default_769 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_769, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantize_per_tensor_default_769 = None
2025-03-21T20:31:43.5510198Z             quantized_decomposed_dequantize_per_tensor_default_948: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_617, 0.00011123115109512582, 26424, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_617 = None
2025-03-21T20:31:43.5510299Z             
2025-03-21T20:31:43.5511248Z              # File: <eval_with_key>.50:2369 in forward, code: quantize_per_tensor_default_770 = torch.ops.quantized_decomposed.quantize_per_tensor.default(dequantize_per_tensor_default_769, 0.0001327675417996943, 0, -32767, 32767, torch.int16);  dequantize_per_tensor_default_769 = None
2025-03-21T20:31:43.5512404Z             quantized_decomposed_quantize_per_tensor_default_618: "i16[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_948, 0.0001327675417996943, 0, -32767, 32767, torch.int16);  quantized_decomposed_dequantize_per_tensor_default_948 = None
2025-03-21T20:31:43.5512518Z             
2025-03-21T20:31:43.5512996Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:163 in forward, code: y = attn_weight @ v
2025-03-21T20:31:43.5514136Z             quantized_decomposed_dequantize_per_tensor_default_949: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_618, 0.0001327675417996943, 0, -32767, 32767, torch.int16);  quantized_decomposed_quantize_per_tensor_default_618 = None
2025-03-21T20:31:43.5514236Z             
2025-03-21T20:31:43.5514755Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:157 in forward, code: attn_mask = mask[input_pos]
2025-03-21T20:31:43.5515599Z             aten_index_tensor_5: "f32[1, 128]" = executorch_exir_dialects_edge__ops_aten_index_Tensor(quantized_decomposed_dequantize_per_tensor_default_124, [attn_options_input_pos]);  quantized_decomposed_dequantize_per_tensor_default_124 = None
2025-03-21T20:31:43.5516456Z             quantized_decomposed_quantize_per_tensor_default_619: "i32[1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_tensor_5, 0.0038910505827516317, 65535, 0, 65535, torch.int32);  aten_index_tensor_5 = None
2025-03-21T20:31:43.5516558Z             
2025-03-21T20:31:43.5517040Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:161 in forward, code: attn_weight += attn_mask
2025-03-21T20:31:43.5518186Z             quantized_decomposed_dequantize_per_tensor_default_950: "f32[1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_619, 0.0038910505827516317, 65535, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_619 = None
2025-03-21T20:31:43.5518276Z             
2025-03-21T20:31:43.5518863Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.5519659Z             aten_permute_copy_default_154: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_910, [0, 1, 3, 2]);  quantized_decomposed_dequantize_per_tensor_default_910 = None
2025-03-21T20:31:43.5520605Z             quantized_decomposed_quantize_per_tensor_default_620: "i32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_154, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  aten_permute_copy_default_154 = None
2025-03-21T20:31:43.5520722Z             
2025-03-21T20:31:43.5521671Z              # File: <eval_with_key>.50:2376 in forward, code: dequantize_per_tensor_default_772 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_772, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantize_per_tensor_default_772 = None
2025-03-21T20:31:43.5522857Z             quantized_decomposed_dequantize_per_tensor_default_951: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_620, 0.0003910682280547917, 31907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_620 = None
2025-03-21T20:31:43.5522958Z             
2025-03-21T20:31:43.5523892Z              # File: <eval_with_key>.50:2377 in forward, code: quantize_per_tensor_default_773 = torch.ops.quantized_decomposed.quantize_per_tensor.default(dequantize_per_tensor_default_772, 0.00040133832953870296, 0, -32767, 32767, torch.int16);  dequantize_per_tensor_default_772 = None
2025-03-21T20:31:43.5525049Z             quantized_decomposed_quantize_per_tensor_default_621: "i16[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_951, 0.00040133832953870296, 0, -32767, 32767, torch.int16);  quantized_decomposed_dequantize_per_tensor_default_951 = None
2025-03-21T20:31:43.5525161Z             
2025-03-21T20:31:43.5525738Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.5526898Z             quantized_decomposed_dequantize_per_tensor_default_952: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_621, 0.00040133832953870296, 0, -32767, 32767, torch.int16);  quantized_decomposed_quantize_per_tensor_default_621 = None
2025-03-21T20:31:43.5527693Z             aten_expand_copy_default_12: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_846, [1, 12, 1, 64]);  quantized_decomposed_dequantize_per_tensor_default_846 = None
2025-03-21T20:31:43.5528247Z             aten_view_copy_default_65: "f32[12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_12, [12, 1, 64]);  aten_expand_copy_default_12 = None
2025-03-21T20:31:43.5529051Z             aten_expand_copy_default_13: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_952, [1, 12, 64, 128]);  quantized_decomposed_dequantize_per_tensor_default_952 = None
2025-03-21T20:31:43.5529684Z             aten_view_copy_default_66: "f32[12, 64, 128]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_13, [12, 64, 128]);  aten_expand_copy_default_13 = None
2025-03-21T20:31:43.5530357Z             aten_bmm_default_6: "f32[12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_bmm_default(aten_view_copy_default_65, aten_view_copy_default_66);  aten_view_copy_default_65 = aten_view_copy_default_66 = None
2025-03-21T20:31:43.5530872Z             aten_view_copy_default_67: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_bmm_default_6, [1, 12, 1, 128]);  aten_bmm_default_6 = None
2025-03-21T20:31:43.5531799Z             quantized_decomposed_quantize_per_tensor_default_622: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_67, 0.0038027865812182426, 39476, 0, 65535, torch.int32);  aten_view_copy_default_67 = None
2025-03-21T20:31:43.5533175Z             quantized_decomposed_dequantize_per_tensor_default_953: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_622, 0.0038027865812182426, 39476, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_622 = None
2025-03-21T20:31:43.5534081Z             quantized_decomposed_dequantize_per_tensor_default_954: "f32[1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param152, 1.9073777366429567e-06, 0, 0, 65535, torch.int32);  b__frozen_param152 = None
2025-03-21T20:31:43.5535245Z             aten_mul_tensor_55: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_953, quantized_decomposed_dequantize_per_tensor_default_954);  quantized_decomposed_dequantize_per_tensor_default_953 = quantized_decomposed_dequantize_per_tensor_default_954 = None
2025-03-21T20:31:43.5536246Z             quantized_decomposed_quantize_per_tensor_default_623: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_55, 0.00047534832265228033, 39476, 0, 65535, torch.int32);  aten_mul_tensor_55 = None
2025-03-21T20:31:43.5536342Z             
2025-03-21T20:31:43.5536843Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:161 in forward, code: attn_weight += attn_mask
2025-03-21T20:31:43.5538028Z             quantized_decomposed_dequantize_per_tensor_default_955: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_623, 0.00047534832265228033, 39476, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_623 = None
2025-03-21T20:31:43.5539155Z             aten_add_tensor_17: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_955, quantized_decomposed_dequantize_per_tensor_default_950);  quantized_decomposed_dequantize_per_tensor_default_955 = quantized_decomposed_dequantize_per_tensor_default_950 = None
2025-03-21T20:31:43.5540003Z             quantized_decomposed_quantize_per_tensor_default_624: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_17, 0.004309757146984339, 62661, 0, 65535, torch.int32);  aten_add_tensor_17 = None
2025-03-21T20:31:43.5540108Z             
2025-03-21T20:31:43.5540671Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:162 in forward, code: attn_weight = torch.softmax(attn_weight, dim=-1)
2025-03-21T20:31:43.5541815Z             quantized_decomposed_dequantize_per_tensor_default_956: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_624, 0.004309757146984339, 62661, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_624 = None
2025-03-21T20:31:43.5542585Z             aten__softmax_default_3: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten__softmax_default(quantized_decomposed_dequantize_per_tensor_default_956, -1, False);  quantized_decomposed_dequantize_per_tensor_default_956 = None
2025-03-21T20:31:43.5543473Z             quantized_decomposed_quantize_per_tensor_default_625: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten__softmax_default_3, 1.5259021893143654e-05, 0, 0, 65535, torch.int32);  aten__softmax_default_3 = None
2025-03-21T20:31:43.5543563Z             
2025-03-21T20:31:43.5544036Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:163 in forward, code: y = attn_weight @ v
2025-03-21T20:31:43.5545178Z             quantized_decomposed_dequantize_per_tensor_default_957: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_625, 1.5259021893143654e-05, 0, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_625 = None
2025-03-21T20:31:43.5546002Z             aten_expand_copy_default_14: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_957, [1, 12, 1, 128]);  quantized_decomposed_dequantize_per_tensor_default_957 = None
2025-03-21T20:31:43.5546561Z             aten_view_copy_default_68: "f32[12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_14, [12, 1, 128]);  aten_expand_copy_default_14 = None
2025-03-21T20:31:43.5547382Z             aten_expand_copy_default_15: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_949, [1, 12, 128, 64]);  quantized_decomposed_dequantize_per_tensor_default_949 = None
2025-03-21T20:31:43.5547946Z             aten_view_copy_default_69: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_15, [12, 128, 64]);  aten_expand_copy_default_15 = None
2025-03-21T20:31:43.5548599Z             aten_bmm_default_7: "f32[12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_bmm_default(aten_view_copy_default_68, aten_view_copy_default_69);  aten_view_copy_default_68 = aten_view_copy_default_69 = None
2025-03-21T20:31:43.5549125Z             aten_view_copy_default_70: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_bmm_default_7, [1, 12, 1, 64]);  aten_bmm_default_7 = None
2025-03-21T20:31:43.5550034Z             quantized_decomposed_quantize_per_tensor_default_626: "i32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_70, 6.451566150644794e-05, 32814, 0, 65535, torch.int32);  aten_view_copy_default_70 = None
2025-03-21T20:31:43.5550123Z             
2025-03-21T20:31:43.5550765Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:165 in forward, code: return y.transpose(1, 2).contiguous().view(bsz, seqlen, self.dim)
2025-03-21T20:31:43.5551894Z             quantized_decomposed_dequantize_per_tensor_default_958: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_626, 6.451566150644794e-05, 32814, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_626 = None
2025-03-21T20:31:43.5552696Z             aten_permute_copy_default_155: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_958, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_958 = None
2025-03-21T20:31:43.5553623Z             quantized_decomposed_quantize_per_tensor_default_627: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_155, 6.451566150644794e-05, 32814, 0, 65535, torch.int32);  aten_permute_copy_default_155 = None
2025-03-21T20:31:43.5554766Z             quantized_decomposed_dequantize_per_tensor_default_959: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_627, 6.451566150644794e-05, 32814, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_627 = None
2025-03-21T20:31:43.5555528Z             aten_view_copy_default_71: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_959, [1, 1, 768]);  quantized_decomposed_dequantize_per_tensor_default_959 = None
2025-03-21T20:31:43.5556430Z             quantized_decomposed_quantize_per_tensor_default_628: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_71, 6.451566150644794e-05, 32814, 0, 65535, torch.int32);  aten_view_copy_default_71 = None
2025-03-21T20:31:43.5556542Z             
2025-03-21T20:31:43.5557100Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.5558240Z             quantized_decomposed_dequantize_per_tensor_default_960: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_628, 6.451566150644794e-05, 32814, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_628 = None
2025-03-21T20:31:43.5559069Z             aten_unsqueeze_copy_default_40: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_960, -1);  quantized_decomposed_dequantize_per_tensor_default_960 = None
2025-03-21T20:31:43.5560011Z             quantized_decomposed_quantize_per_tensor_default_629: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_40, 6.451566150644794e-05, 32814, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_40 = None
2025-03-21T20:31:43.5560112Z             
2025-03-21T20:31:43.5560546Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.5561690Z             quantized_decomposed_dequantize_per_tensor_default_961: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_629, 6.451566150644794e-05, 32814, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_629 = None
2025-03-21T20:31:43.5562481Z             aten_permute_copy_default_156: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_961, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_961 = None
2025-03-21T20:31:43.5563423Z             quantized_decomposed_quantize_per_tensor_default_630: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_156, 6.451566150644794e-05, 32814, 0, 65535, torch.int32);  aten_permute_copy_default_156 = None
2025-03-21T20:31:43.5563514Z             
2025-03-21T20:31:43.5563892Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.5565023Z             quantized_decomposed_dequantize_per_tensor_default_962: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_630, 6.451566150644794e-05, 32814, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_630 = None
2025-03-21T20:31:43.5566299Z             aten_convolution_default_24: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_962, quantized_decomposed_dequantize_per_tensor_default_32, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_962 = quantized_decomposed_dequantize_per_tensor_default_32 = None
2025-03-21T20:31:43.5567221Z             quantized_decomposed_quantize_per_tensor_default_631: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_24, 5.919613249716349e-05, 40616, 0, 65535, torch.int32);  aten_convolution_default_24 = None
2025-03-21T20:31:43.5567320Z             
2025-03-21T20:31:43.5567743Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.5568909Z             quantized_decomposed_dequantize_per_tensor_default_963: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_631, 5.919613249716349e-05, 40616, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_631 = None
2025-03-21T20:31:43.5569792Z             aten_permute_copy_default_157: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_963, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_963 = None
2025-03-21T20:31:43.5570771Z             quantized_decomposed_quantize_per_tensor_default_632: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_157, 5.919613249716349e-05, 40616, 0, 65535, torch.int32);  aten_permute_copy_default_157 = None
2025-03-21T20:31:43.5570865Z             
2025-03-21T20:31:43.5571416Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.5572552Z             quantized_decomposed_dequantize_per_tensor_default_964: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_632, 5.919613249716349e-05, 40616, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_632 = None
2025-03-21T20:31:43.5573339Z             aten_squeeze_copy_dims_40: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_964, [-1]);  quantized_decomposed_dequantize_per_tensor_default_964 = None
2025-03-21T20:31:43.5574237Z             quantized_decomposed_quantize_per_tensor_default_633: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_40, 5.919613249716349e-05, 40616, 0, 65535, torch.int32);  aten_squeeze_copy_dims_40 = None
2025-03-21T20:31:43.5574340Z             
2025-03-21T20:31:43.5574716Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:111 in forward, code: h = x + h
2025-03-21T20:31:43.5575858Z             quantized_decomposed_dequantize_per_tensor_default_965: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_633, 5.919613249716349e-05, 40616, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_633 = None
2025-03-21T20:31:43.5576976Z             aten_add_tensor_18: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_785, quantized_decomposed_dequantize_per_tensor_default_965);  quantized_decomposed_dequantize_per_tensor_default_785 = quantized_decomposed_dequantize_per_tensor_default_965 = None
2025-03-21T20:31:43.5577838Z             quantized_decomposed_quantize_per_tensor_default_634: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_18, 0.0020493771880865097, 7471, 0, 65535, torch.int32);  aten_add_tensor_18 = None
2025-03-21T20:31:43.5577933Z             
2025-03-21T20:31:43.5578458Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:115 in forward, code: out = h + self.feed_forward(self.ffn_norm(h))
2025-03-21T20:31:43.5579367Z             quantized_decomposed_dequantize_per_tensor_default_966: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_634, 0.0020493771880865097, 7471, 0, 65535, torch.int32)
2025-03-21T20:31:43.5580508Z             quantized_decomposed_dequantize_per_tensor_default_967: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_634, 0.0020493771880865097, 7471, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_634 = None
2025-03-21T20:31:43.5581092Z             aten_pow_tensor_scalar_7: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_pow_Tensor_Scalar(quantized_decomposed_dequantize_per_tensor_default_967, 2)
2025-03-21T20:31:43.5581560Z             aten_mean_dim_7: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_mean_dim(aten_pow_tensor_scalar_7, [2], True);  aten_pow_tensor_scalar_7 = None
2025-03-21T20:31:43.5582004Z             aten_add_scalar_7: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_add_Scalar(aten_mean_dim_7, 9.999999747378752e-06);  aten_mean_dim_7 = None
2025-03-21T20:31:43.5582457Z             aten_rsqrt_default_7: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_rsqrt_default(aten_add_scalar_7);  aten_add_scalar_7 = None
2025-03-21T20:31:43.5583302Z             aten_mul_tensor_56: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_967, aten_rsqrt_default_7);  quantized_decomposed_dequantize_per_tensor_default_967 = aten_rsqrt_default_7 = None
2025-03-21T20:31:43.5584120Z             aten_mul_tensor_57: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(aten_mul_tensor_56, quantized_decomposed_dequantize_per_tensor_default_33);  aten_mul_tensor_56 = quantized_decomposed_dequantize_per_tensor_default_33 = None
2025-03-21T20:31:43.5584996Z             quantized_decomposed_quantize_per_tensor_default_635: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_57, 0.00031500012846663594, 14572, 0, 65535, torch.int32);  aten_mul_tensor_57 = None
2025-03-21T20:31:43.5585103Z             
2025-03-21T20:31:43.5585623Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.5586551Z             quantized_decomposed_dequantize_per_tensor_default_968: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_635, 0.00031500012846663594, 14572, 0, 65535, torch.int32)
2025-03-21T20:31:43.5587687Z             quantized_decomposed_dequantize_per_tensor_default_969: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_635, 0.00031500012846663594, 14572, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_635 = None
2025-03-21T20:31:43.5588498Z             aten_unsqueeze_copy_default_41: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_969, -1);  quantized_decomposed_dequantize_per_tensor_default_969 = None
2025-03-21T20:31:43.5589449Z             quantized_decomposed_quantize_per_tensor_default_636: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_41, 0.00031500012846663594, 14572, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_41 = None
2025-03-21T20:31:43.5589555Z             
2025-03-21T20:31:43.5589960Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.5591121Z             quantized_decomposed_dequantize_per_tensor_default_970: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_636, 0.00031500012846663594, 14572, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_636 = None
2025-03-21T20:31:43.5591910Z             aten_permute_copy_default_158: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_970, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_970 = None
2025-03-21T20:31:43.5592876Z             quantized_decomposed_quantize_per_tensor_default_637: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_158, 0.00031500012846663594, 14572, 0, 65535, torch.int32);  aten_permute_copy_default_158 = None
2025-03-21T20:31:43.5592990Z             
2025-03-21T20:31:43.5593366Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.5594530Z             quantized_decomposed_dequantize_per_tensor_default_971: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_637, 0.00031500012846663594, 14572, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_637 = None
2025-03-21T20:31:43.5595812Z             aten_convolution_default_25: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_971, quantized_decomposed_dequantize_per_tensor_default_34, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_971 = quantized_decomposed_dequantize_per_tensor_default_34 = None
2025-03-21T20:31:43.5596771Z             quantized_decomposed_quantize_per_tensor_default_638: "i32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_25, 0.00022086942044552416, 31371, 0, 65535, torch.int32);  aten_convolution_default_25 = None
2025-03-21T20:31:43.5596875Z             
2025-03-21T20:31:43.5597296Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.5598452Z             quantized_decomposed_dequantize_per_tensor_default_972: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_638, 0.00022086942044552416, 31371, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_638 = None
2025-03-21T20:31:43.5599246Z             aten_permute_copy_default_159: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_972, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_972 = None
2025-03-21T20:31:43.5600199Z             quantized_decomposed_quantize_per_tensor_default_639: "i32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_159, 0.00022086942044552416, 31371, 0, 65535, torch.int32);  aten_permute_copy_default_159 = None
2025-03-21T20:31:43.5600288Z             
2025-03-21T20:31:43.5600832Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.5601977Z             quantized_decomposed_dequantize_per_tensor_default_973: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_639, 0.00022086942044552416, 31371, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_639 = None
2025-03-21T20:31:43.5602743Z             aten_squeeze_copy_dims_41: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_973, [-1]);  quantized_decomposed_dequantize_per_tensor_default_973 = None
2025-03-21T20:31:43.5603644Z             quantized_decomposed_quantize_per_tensor_default_640: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_41, 0.00022086942044552416, 31371, 0, 65535, torch.int32);  aten_squeeze_copy_dims_41 = None
2025-03-21T20:31:43.5603743Z             
2025-03-21T20:31:43.5604278Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:36 in forward, code: return self.w2(F.silu(self.w1(x)) * self.w3(x))
2025-03-21T20:31:43.5605228Z             quantized_decomposed_dequantize_per_tensor_default_974: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_640, 0.00022086942044552416, 31371, 0, 65535, torch.int32)
2025-03-21T20:31:43.5606392Z             quantized_decomposed_dequantize_per_tensor_default_975: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_640, 0.00022086942044552416, 31371, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_640 = None
2025-03-21T20:31:43.5607140Z             aten_sigmoid_default_3: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_sigmoid_default(quantized_decomposed_dequantize_per_tensor_default_975);  quantized_decomposed_dequantize_per_tensor_default_975 = None
2025-03-21T20:31:43.5607994Z             quantized_decomposed_quantize_per_tensor_default_641: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_sigmoid_default_3, 1.52587890625e-05, 0, 0, 65535, torch.int32);  aten_sigmoid_default_3 = None
2025-03-21T20:31:43.5609127Z             quantized_decomposed_dequantize_per_tensor_default_976: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_641, 1.52587890625e-05, 0, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_641 = None
2025-03-21T20:31:43.5610312Z             aten_mul_tensor_58: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_974, quantized_decomposed_dequantize_per_tensor_default_976);  quantized_decomposed_dequantize_per_tensor_default_974 = quantized_decomposed_dequantize_per_tensor_default_976 = None
2025-03-21T20:31:43.5611173Z             quantized_decomposed_quantize_per_tensor_default_642: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_58, 0.00011932865891139954, 2334, 0, 65535, torch.int32);  aten_mul_tensor_58 = None
2025-03-21T20:31:43.5612324Z             quantized_decomposed_dequantize_per_tensor_default_977: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_642, 0.00011932865891139954, 2334, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_642 = None
2025-03-21T20:31:43.5612413Z             
2025-03-21T20:31:43.5612947Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.5613746Z             aten_unsqueeze_copy_default_42: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_968, -1);  quantized_decomposed_dequantize_per_tensor_default_968 = None
2025-03-21T20:31:43.5614708Z             quantized_decomposed_quantize_per_tensor_default_643: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_42, 0.00031500012846663594, 14572, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_42 = None
2025-03-21T20:31:43.5614798Z             
2025-03-21T20:31:43.5615208Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.5616392Z             quantized_decomposed_dequantize_per_tensor_default_978: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_643, 0.00031500012846663594, 14572, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_643 = None
2025-03-21T20:31:43.5617224Z             aten_permute_copy_default_160: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_978, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_978 = None
2025-03-21T20:31:43.5618186Z             quantized_decomposed_quantize_per_tensor_default_644: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_160, 0.00031500012846663594, 14572, 0, 65535, torch.int32);  aten_permute_copy_default_160 = None
2025-03-21T20:31:43.5618289Z             
2025-03-21T20:31:43.5618652Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.5619792Z             quantized_decomposed_dequantize_per_tensor_default_979: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_644, 0.00031500012846663594, 14572, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_644 = None
2025-03-21T20:31:43.5621098Z             aten_convolution_default_26: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_979, quantized_decomposed_dequantize_per_tensor_default_35, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_979 = quantized_decomposed_dequantize_per_tensor_default_35 = None
2025-03-21T20:31:43.5622045Z             quantized_decomposed_quantize_per_tensor_default_645: "i32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_26, 0.00024752813624218106, 33708, 0, 65535, torch.int32);  aten_convolution_default_26 = None
2025-03-21T20:31:43.5622132Z             
2025-03-21T20:31:43.5622556Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.5623711Z             quantized_decomposed_dequantize_per_tensor_default_980: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_645, 0.00024752813624218106, 33708, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_645 = None
2025-03-21T20:31:43.5624517Z             aten_permute_copy_default_161: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_980, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_980 = None
2025-03-21T20:31:43.5625461Z             quantized_decomposed_quantize_per_tensor_default_646: "i32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_161, 0.00024752813624218106, 33708, 0, 65535, torch.int32);  aten_permute_copy_default_161 = None
2025-03-21T20:31:43.5625561Z             
2025-03-21T20:31:43.5626094Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.5627354Z             quantized_decomposed_dequantize_per_tensor_default_981: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_646, 0.00024752813624218106, 33708, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_646 = None
2025-03-21T20:31:43.5628113Z             aten_squeeze_copy_dims_42: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_981, [-1]);  quantized_decomposed_dequantize_per_tensor_default_981 = None
2025-03-21T20:31:43.5629127Z             quantized_decomposed_quantize_per_tensor_default_647: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_42, 0.00024752813624218106, 33708, 0, 65535, torch.int32);  aten_squeeze_copy_dims_42 = None
2025-03-21T20:31:43.5629224Z             
2025-03-21T20:31:43.5629742Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:36 in forward, code: return self.w2(F.silu(self.w1(x)) * self.w3(x))
2025-03-21T20:31:43.5630929Z             quantized_decomposed_dequantize_per_tensor_default_982: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_647, 0.00024752813624218106, 33708, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_647 = None
2025-03-21T20:31:43.5632068Z             aten_mul_tensor_59: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_977, quantized_decomposed_dequantize_per_tensor_default_982);  quantized_decomposed_dequantize_per_tensor_default_977 = quantized_decomposed_dequantize_per_tensor_default_982 = None
2025-03-21T20:31:43.5633109Z             quantized_decomposed_quantize_per_tensor_default_648: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_59, 0.0006538353045471013, 38748, 0, 65535, torch.int32);  aten_mul_tensor_59 = None
2025-03-21T20:31:43.5633222Z             
2025-03-21T20:31:43.5633752Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.5634910Z             quantized_decomposed_dequantize_per_tensor_default_983: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_648, 0.0006538353045471013, 38748, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_648 = None
2025-03-21T20:31:43.5635715Z             aten_unsqueeze_copy_default_43: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_983, -1);  quantized_decomposed_dequantize_per_tensor_default_983 = None
2025-03-21T20:31:43.5636675Z             quantized_decomposed_quantize_per_tensor_default_649: "i32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_43, 0.0006538353045471013, 38748, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_43 = None
2025-03-21T20:31:43.5636765Z             
2025-03-21T20:31:43.5637185Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.5638595Z             quantized_decomposed_dequantize_per_tensor_default_984: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_649, 0.0006538353045471013, 38748, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_649 = None
2025-03-21T20:31:43.5639417Z             aten_permute_copy_default_162: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_984, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_984 = None
2025-03-21T20:31:43.5640359Z             quantized_decomposed_quantize_per_tensor_default_650: "i32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_162, 0.0006538353045471013, 38748, 0, 65535, torch.int32);  aten_permute_copy_default_162 = None
2025-03-21T20:31:43.5640461Z             
2025-03-21T20:31:43.5640827Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.5642097Z             quantized_decomposed_dequantize_per_tensor_default_985: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_650, 0.0006538353045471013, 38748, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_650 = None
2025-03-21T20:31:43.5643396Z             aten_convolution_default_27: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_985, quantized_decomposed_dequantize_per_tensor_default_36, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_985 = quantized_decomposed_dequantize_per_tensor_default_36 = None
2025-03-21T20:31:43.5644328Z             quantized_decomposed_quantize_per_tensor_default_651: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_27, 0.000476505549158901, 4992, 0, 65535, torch.int32);  aten_convolution_default_27 = None
2025-03-21T20:31:43.5644417Z             
2025-03-21T20:31:43.5644852Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.5646026Z             quantized_decomposed_dequantize_per_tensor_default_986: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_651, 0.000476505549158901, 4992, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_651 = None
2025-03-21T20:31:43.5646829Z             aten_permute_copy_default_163: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_986, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_986 = None
2025-03-21T20:31:43.5647752Z             quantized_decomposed_quantize_per_tensor_default_652: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_163, 0.000476505549158901, 4992, 0, 65535, torch.int32);  aten_permute_copy_default_163 = None
2025-03-21T20:31:43.5647854Z             
2025-03-21T20:31:43.5648386Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.5649611Z             quantized_decomposed_dequantize_per_tensor_default_987: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_652, 0.000476505549158901, 4992, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_652 = None
2025-03-21T20:31:43.5650359Z             aten_squeeze_copy_dims_43: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_987, [-1]);  quantized_decomposed_dequantize_per_tensor_default_987 = None
2025-03-21T20:31:43.5651263Z             quantized_decomposed_quantize_per_tensor_default_653: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_43, 0.000476505549158901, 4992, 0, 65535, torch.int32);  aten_squeeze_copy_dims_43 = None
2025-03-21T20:31:43.5651355Z             
2025-03-21T20:31:43.5651878Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:115 in forward, code: out = h + self.feed_forward(self.ffn_norm(h))
2025-03-21T20:31:43.5653002Z             quantized_decomposed_dequantize_per_tensor_default_988: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_653, 0.000476505549158901, 4992, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_653 = None
2025-03-21T20:31:43.5654179Z             aten_add_tensor_19: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_966, quantized_decomposed_dequantize_per_tensor_default_988);  quantized_decomposed_dequantize_per_tensor_default_966 = quantized_decomposed_dequantize_per_tensor_default_988 = None
2025-03-21T20:31:43.5655044Z             quantized_decomposed_quantize_per_tensor_default_654: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_19, 0.002495231805369258, 6285, 0, 65535, torch.int32);  aten_add_tensor_19 = None
2025-03-21T20:31:43.5655147Z             
2025-03-21T20:31:43.5655518Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:111 in forward, code: h = x + h
2025-03-21T20:31:43.5656429Z             quantized_decomposed_dequantize_per_tensor_default_989: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_654, 0.002495231805369258, 6285, 0, 65535, torch.int32)
2025-03-21T20:31:43.5656519Z             
2025-03-21T20:31:43.5657077Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:108 in forward, code: self.attention_norm(x), freqs_cos, freqs_sin, **attn_options
2025-03-21T20:31:43.5658244Z             quantized_decomposed_dequantize_per_tensor_default_990: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_654, 0.002495231805369258, 6285, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_654 = None
2025-03-21T20:31:43.5658754Z             aten_pow_tensor_scalar_8: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_pow_Tensor_Scalar(quantized_decomposed_dequantize_per_tensor_default_990, 2)
2025-03-21T20:31:43.5659219Z             aten_mean_dim_8: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_mean_dim(aten_pow_tensor_scalar_8, [2], True);  aten_pow_tensor_scalar_8 = None
2025-03-21T20:31:43.5659660Z             aten_add_scalar_8: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_add_Scalar(aten_mean_dim_8, 9.999999747378752e-06);  aten_mean_dim_8 = None
2025-03-21T20:31:43.5660087Z             aten_rsqrt_default_8: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_rsqrt_default(aten_add_scalar_8);  aten_add_scalar_8 = None
2025-03-21T20:31:43.5660930Z             aten_mul_tensor_60: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_990, aten_rsqrt_default_8);  quantized_decomposed_dequantize_per_tensor_default_990 = aten_rsqrt_default_8 = None
2025-03-21T20:31:43.5661747Z             aten_mul_tensor_61: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(aten_mul_tensor_60, quantized_decomposed_dequantize_per_tensor_default_37);  aten_mul_tensor_60 = quantized_decomposed_dequantize_per_tensor_default_37 = None
2025-03-21T20:31:43.5662597Z             quantized_decomposed_quantize_per_tensor_default_655: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_61, 0.00039765422116033733, 28522, 0, 65535, torch.int32);  aten_mul_tensor_61 = None
2025-03-21T20:31:43.5662697Z             
2025-03-21T20:31:43.5663215Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.5664138Z             quantized_decomposed_dequantize_per_tensor_default_991: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_655, 0.00039765422116033733, 28522, 0, 65535, torch.int32)
2025-03-21T20:31:43.5665068Z             quantized_decomposed_dequantize_per_tensor_default_992: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_655, 0.00039765422116033733, 28522, 0, 65535, torch.int32)
2025-03-21T20:31:43.5666239Z             quantized_decomposed_dequantize_per_tensor_default_993: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_655, 0.00039765422116033733, 28522, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_655 = None
2025-03-21T20:31:43.5667059Z             aten_unsqueeze_copy_default_44: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_993, -1);  quantized_decomposed_dequantize_per_tensor_default_993 = None
2025-03-21T20:31:43.5668017Z             quantized_decomposed_quantize_per_tensor_default_656: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_44, 0.00039765422116033733, 28522, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_44 = None
2025-03-21T20:31:43.5668108Z             
2025-03-21T20:31:43.5668525Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.5669702Z             quantized_decomposed_dequantize_per_tensor_default_994: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_656, 0.00039765422116033733, 28522, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_656 = None
2025-03-21T20:31:43.5670504Z             aten_permute_copy_default_164: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_994, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_994 = None
2025-03-21T20:31:43.5671454Z             quantized_decomposed_quantize_per_tensor_default_657: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_164, 0.00039765422116033733, 28522, 0, 65535, torch.int32);  aten_permute_copy_default_164 = None
2025-03-21T20:31:43.5671543Z             
2025-03-21T20:31:43.5671908Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.5673064Z             quantized_decomposed_dequantize_per_tensor_default_995: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_657, 0.00039765422116033733, 28522, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_657 = None
2025-03-21T20:31:43.5674342Z             aten_convolution_default_28: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_995, quantized_decomposed_dequantize_per_tensor_default_38, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_995 = quantized_decomposed_dequantize_per_tensor_default_38 = None
2025-03-21T20:31:43.5675270Z             quantized_decomposed_quantize_per_tensor_default_658: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_28, 0.00031367456540465355, 28419, 0, 65535, torch.int32);  aten_convolution_default_28 = None
2025-03-21T20:31:43.5675370Z             
2025-03-21T20:31:43.5675795Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.5676964Z             quantized_decomposed_dequantize_per_tensor_default_996: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_658, 0.00031367456540465355, 28419, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_658 = None
2025-03-21T20:31:43.5677787Z             aten_permute_copy_default_165: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_996, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_996 = None
2025-03-21T20:31:43.5678759Z             quantized_decomposed_quantize_per_tensor_default_659: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_165, 0.00031367456540465355, 28419, 0, 65535, torch.int32);  aten_permute_copy_default_165 = None
2025-03-21T20:31:43.5678848Z             
2025-03-21T20:31:43.5679384Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.5680537Z             quantized_decomposed_dequantize_per_tensor_default_997: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_659, 0.00031367456540465355, 28419, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_659 = None
2025-03-21T20:31:43.5681317Z             aten_squeeze_copy_dims_44: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_997, [-1]);  quantized_decomposed_dequantize_per_tensor_default_997 = None
2025-03-21T20:31:43.5682216Z             quantized_decomposed_quantize_per_tensor_default_660: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_44, 0.00031367456540465355, 28419, 0, 65535, torch.int32);  aten_squeeze_copy_dims_44 = None
2025-03-21T20:31:43.5682318Z             
2025-03-21T20:31:43.5682833Z              # File: /pytorch/executorch/examples/models/llama/attention.py:242 in forward, code: q = q.view(bsz, seqlen, self.n_local_heads, self.head_dim)
2025-03-21T20:31:43.5683967Z             quantized_decomposed_dequantize_per_tensor_default_998: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_660, 0.00031367456540465355, 28419, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_660 = None
2025-03-21T20:31:43.5684069Z             
2025-03-21T20:31:43.5684585Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.5685391Z             aten_unsqueeze_copy_default_45: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_992, -1);  quantized_decomposed_dequantize_per_tensor_default_992 = None
2025-03-21T20:31:43.5686341Z             quantized_decomposed_quantize_per_tensor_default_661: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_45, 0.00039765422116033733, 28522, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_45 = None
2025-03-21T20:31:43.5686443Z             
2025-03-21T20:31:43.5686850Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.5688000Z             quantized_decomposed_dequantize_per_tensor_default_999: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_661, 0.00039765422116033733, 28522, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_661 = None
2025-03-21T20:31:43.5688814Z             aten_permute_copy_default_166: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_999, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_999 = None
2025-03-21T20:31:43.5689855Z             quantized_decomposed_quantize_per_tensor_default_662: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_166, 0.00039765422116033733, 28522, 0, 65535, torch.int32);  aten_permute_copy_default_166 = None
2025-03-21T20:31:43.5689946Z             
2025-03-21T20:31:43.5690351Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.5691495Z             quantized_decomposed_dequantize_per_tensor_default_1000: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_662, 0.00039765422116033733, 28522, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_662 = None
2025-03-21T20:31:43.5692777Z             aten_convolution_default_29: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_1000, quantized_decomposed_dequantize_per_tensor_default_39, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_1000 = quantized_decomposed_dequantize_per_tensor_default_39 = None
2025-03-21T20:31:43.5693724Z             quantized_decomposed_quantize_per_tensor_default_663: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_29, 0.0004061445069964975, 31842, 0, 65535, torch.int32);  aten_convolution_default_29 = None
2025-03-21T20:31:43.5693827Z             
2025-03-21T20:31:43.5694250Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.5695415Z             quantized_decomposed_dequantize_per_tensor_default_1001: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_663, 0.0004061445069964975, 31842, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_663 = None
2025-03-21T20:31:43.5696214Z             aten_permute_copy_default_167: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1001, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1001 = None
2025-03-21T20:31:43.5697160Z             quantized_decomposed_quantize_per_tensor_default_664: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_167, 0.0004061445069964975, 31842, 0, 65535, torch.int32);  aten_permute_copy_default_167 = None
2025-03-21T20:31:43.5697248Z             
2025-03-21T20:31:43.5697801Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.5698945Z             quantized_decomposed_dequantize_per_tensor_default_1002: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_664, 0.0004061445069964975, 31842, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_664 = None
2025-03-21T20:31:43.5699720Z             aten_squeeze_copy_dims_45: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_1002, [-1]);  quantized_decomposed_dequantize_per_tensor_default_1002 = None
2025-03-21T20:31:43.5700640Z             quantized_decomposed_quantize_per_tensor_default_665: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_45, 0.0004061445069964975, 31842, 0, 65535, torch.int32);  aten_squeeze_copy_dims_45 = None
2025-03-21T20:31:43.5700770Z             
2025-03-21T20:31:43.5701295Z              # File: /pytorch/executorch/examples/models/llama/attention.py:243 in forward, code: k = k.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.5702478Z             quantized_decomposed_dequantize_per_tensor_default_1003: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_665, 0.0004061445069964975, 31842, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_665 = None
2025-03-21T20:31:43.5702567Z             
2025-03-21T20:31:43.5703093Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.5703891Z             aten_unsqueeze_copy_default_46: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_991, -1);  quantized_decomposed_dequantize_per_tensor_default_991 = None
2025-03-21T20:31:43.5704851Z             quantized_decomposed_quantize_per_tensor_default_666: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_46, 0.00039765422116033733, 28522, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_46 = None
2025-03-21T20:31:43.5704966Z             
2025-03-21T20:31:43.5705387Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.5706537Z             quantized_decomposed_dequantize_per_tensor_default_1004: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_666, 0.00039765422116033733, 28522, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_666 = None
2025-03-21T20:31:43.5707348Z             aten_permute_copy_default_168: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1004, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1004 = None
2025-03-21T20:31:43.5708284Z             quantized_decomposed_quantize_per_tensor_default_667: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_168, 0.00039765422116033733, 28522, 0, 65535, torch.int32);  aten_permute_copy_default_168 = None
2025-03-21T20:31:43.5708384Z             
2025-03-21T20:31:43.5708748Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.5709901Z             quantized_decomposed_dequantize_per_tensor_default_1005: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_667, 0.00039765422116033733, 28522, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_667 = None
2025-03-21T20:31:43.5711174Z             aten_convolution_default_30: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_1005, quantized_decomposed_dequantize_per_tensor_default_40, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_1005 = quantized_decomposed_dequantize_per_tensor_default_40 = None
2025-03-21T20:31:43.5712115Z             quantized_decomposed_quantize_per_tensor_default_668: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_30, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_convolution_default_30 = None
2025-03-21T20:31:43.5712203Z             
2025-03-21T20:31:43.5712684Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.5713832Z             quantized_decomposed_dequantize_per_tensor_default_1006: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_668, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_668 = None
2025-03-21T20:31:43.5714676Z             aten_permute_copy_default_169: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1006, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1006 = None
2025-03-21T20:31:43.5715609Z             quantized_decomposed_quantize_per_tensor_default_669: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_169, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_permute_copy_default_169 = None
2025-03-21T20:31:43.5715710Z             
2025-03-21T20:31:43.5716251Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.5717437Z             quantized_decomposed_dequantize_per_tensor_default_1007: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_669, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_669 = None
2025-03-21T20:31:43.5718190Z             aten_squeeze_copy_dims_46: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_1007, [-1]);  quantized_decomposed_dequantize_per_tensor_default_1007 = None
2025-03-21T20:31:43.5719106Z             quantized_decomposed_quantize_per_tensor_default_670: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_46, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_squeeze_copy_dims_46 = None
2025-03-21T20:31:43.5719194Z             
2025-03-21T20:31:43.5719728Z              # File: /pytorch/executorch/examples/models/llama/attention.py:244 in forward, code: v = v.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.5720870Z             quantized_decomposed_dequantize_per_tensor_default_1008: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_670, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_670 = None
2025-03-21T20:31:43.5720968Z             
2025-03-21T20:31:43.5721480Z              # File: /pytorch/executorch/examples/models/llama/attention.py:242 in forward, code: q = q.view(bsz, seqlen, self.n_local_heads, self.head_dim)
2025-03-21T20:31:43.5722247Z             aten_view_copy_default_72: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_998, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_998 = None
2025-03-21T20:31:43.5723147Z             quantized_decomposed_quantize_per_tensor_default_671: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_72, 0.00031367456540465355, 28419, 0, 65535, torch.int32);  aten_view_copy_default_72 = None
2025-03-21T20:31:43.5723247Z             
2025-03-21T20:31:43.5724177Z              # File: <eval_with_key>.50:2536 in forward, code: dequantize_per_tensor_default_824 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_824, 0.00031367456540465355, 28419, 0, 65535, torch.int32);  quantize_per_tensor_default_824 = None
2025-03-21T20:31:43.5725377Z             quantized_decomposed_dequantize_per_tensor_default_1009: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_671, 0.00031367456540465355, 28419, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_671 = None
2025-03-21T20:31:43.5725467Z             
2025-03-21T20:31:43.5726002Z              # File: /pytorch/executorch/examples/models/llama/attention.py:243 in forward, code: k = k.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.5726788Z             aten_view_copy_default_73: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1003, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_1003 = None
2025-03-21T20:31:43.5727698Z             quantized_decomposed_quantize_per_tensor_default_672: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_73, 0.0004061445069964975, 31842, 0, 65535, torch.int32);  aten_view_copy_default_73 = None
2025-03-21T20:31:43.5727812Z             
2025-03-21T20:31:43.5728756Z              # File: <eval_with_key>.50:2539 in forward, code: dequantize_per_tensor_default_825 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_825, 0.0004061445069964975, 31842, 0, 65535, torch.int32);  quantize_per_tensor_default_825 = None
2025-03-21T20:31:43.5729966Z             quantized_decomposed_dequantize_per_tensor_default_1010: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_672, 0.0004061445069964975, 31842, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_672 = None
2025-03-21T20:31:43.5730071Z             
2025-03-21T20:31:43.5730597Z              # File: /pytorch/executorch/examples/models/llama/attention.py:244 in forward, code: v = v.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.5731377Z             aten_view_copy_default_74: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1008, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_1008 = None
2025-03-21T20:31:43.5732446Z             quantized_decomposed_quantize_per_tensor_default_673: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_74, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_view_copy_default_74 = None
2025-03-21T20:31:43.5732559Z             
2025-03-21T20:31:43.5733235Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:346 in update, code: v_out = torch.ops.aten.index_put_(self.past_v_caches, [None, input_pos], v_val)
2025-03-21T20:31:43.5734400Z             quantized_decomposed_dequantize_per_tensor_default_1011: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_673, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_673 = None
2025-03-21T20:31:43.5734494Z             
2025-03-21T20:31:43.5735256Z              # File: <eval_with_key>.50:2544 in forward, code: quantize_per_tensor_default_827 = torch.ops.quantized_decomposed.quantize_per_tensor.default(_to_copy_8, 0.00031367456540465355, 28419, 0, 65535, torch.int32);  _to_copy_8 = None
2025-03-21T20:31:43.5736483Z             quantized_decomposed_quantize_per_tensor_default_674: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_1009, 0.00031367456540465355, 28419, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_1009 = None
2025-03-21T20:31:43.5736621Z             
2025-03-21T20:31:43.5737149Z              # File: /pytorch/executorch/examples/models/llama/rope.py:84 in apply_rotary_emb, code: xq_r, xq_i = xq.float().reshape(xq.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.5738329Z             quantized_decomposed_dequantize_per_tensor_default_1012: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_674, 0.00031367456540465355, 28419, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_674 = None
2025-03-21T20:31:43.5739118Z             aten_view_copy_default_75: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1012, [1, 1, 12, -1, 2]);  quantized_decomposed_dequantize_per_tensor_default_1012 = None
2025-03-21T20:31:43.5740172Z             quantized_decomposed_quantize_per_tensor_default_675: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_75, 0.00031367456540465355, 28419, 0, 65535, torch.int32);  aten_view_copy_default_75 = None
2025-03-21T20:31:43.5741365Z             quantized_decomposed_dequantize_per_tensor_default_1013: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_675, 0.00031367456540465355, 28419, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_675 = None
2025-03-21T20:31:43.5741915Z             aten_slice_copy_tensor_16: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_1013, 4, 0, 1)
2025-03-21T20:31:43.5742671Z             aten_slice_copy_tensor_17: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_1013, 4, 1, 2);  quantized_decomposed_dequantize_per_tensor_default_1013 = None
2025-03-21T20:31:43.5743205Z             aten_squeeze_copy_dims_47: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_16, [4]);  aten_slice_copy_tensor_16 = None
2025-03-21T20:31:43.5743721Z             aten_squeeze_copy_dims_48: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_17, [4]);  aten_slice_copy_tensor_17 = None
2025-03-21T20:31:43.5744633Z             quantized_decomposed_quantize_per_tensor_default_676: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_47, 0.00031367456540465355, 28419, 0, 65535, torch.int32);  aten_squeeze_copy_dims_47 = None
2025-03-21T20:31:43.5744720Z             
2025-03-21T20:31:43.5745209Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.5746124Z             quantized_decomposed_dequantize_per_tensor_default_1014: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_676, 0.00031367456540465355, 28419, 0, 65535, torch.int32)
2025-03-21T20:31:43.5746227Z             
2025-03-21T20:31:43.5746698Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.5747837Z             quantized_decomposed_dequantize_per_tensor_default_1015: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_676, 0.00031367456540465355, 28419, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_676 = None
2025-03-21T20:31:43.5747939Z             
2025-03-21T20:31:43.5748510Z              # File: /pytorch/executorch/examples/models/llama/rope.py:84 in apply_rotary_emb, code: xq_r, xq_i = xq.float().reshape(xq.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.5749426Z             quantized_decomposed_quantize_per_tensor_default_677: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_48, 0.00029694687691517174, 29660, 0, 65535, torch.int32);  aten_squeeze_copy_dims_48 = None
2025-03-21T20:31:43.5749516Z             
2025-03-21T20:31:43.5750023Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.5750940Z             quantized_decomposed_dequantize_per_tensor_default_1016: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_677, 0.00029694687691517174, 29660, 0, 65535, torch.int32)
2025-03-21T20:31:43.5751044Z             
2025-03-21T20:31:43.5751513Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.5752688Z             quantized_decomposed_dequantize_per_tensor_default_1017: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_677, 0.00029694687691517174, 29660, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_677 = None
2025-03-21T20:31:43.5752775Z             
2025-03-21T20:31:43.5753541Z              # File: <eval_with_key>.50:2559 in forward, code: quantize_per_tensor_default_831 = torch.ops.quantized_decomposed.quantize_per_tensor.default(_to_copy_9, 0.0004061445069964975, 31842, 0, 65535, torch.int32);  _to_copy_9 = None
2025-03-21T20:31:43.5754682Z             quantized_decomposed_quantize_per_tensor_default_678: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_1010, 0.0004061445069964975, 31842, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_1010 = None
2025-03-21T20:31:43.5754785Z             
2025-03-21T20:31:43.5755305Z              # File: /pytorch/executorch/examples/models/llama/rope.py:85 in apply_rotary_emb, code: xk_r, xk_i = xk.float().reshape(xk.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.5756454Z             quantized_decomposed_dequantize_per_tensor_default_1018: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_678, 0.0004061445069964975, 31842, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_678 = None
2025-03-21T20:31:43.5757228Z             aten_view_copy_default_76: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1018, [1, 1, 12, -1, 2]);  quantized_decomposed_dequantize_per_tensor_default_1018 = None
2025-03-21T20:31:43.5758134Z             quantized_decomposed_quantize_per_tensor_default_679: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_76, 0.0004061445069964975, 31842, 0, 65535, torch.int32);  aten_view_copy_default_76 = None
2025-03-21T20:31:43.5759277Z             quantized_decomposed_dequantize_per_tensor_default_1019: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_679, 0.0004061445069964975, 31842, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_679 = None
2025-03-21T20:31:43.5759823Z             aten_slice_copy_tensor_18: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_1019, 4, 0, 1)
2025-03-21T20:31:43.5760634Z             aten_slice_copy_tensor_19: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_1019, 4, 1, 2);  quantized_decomposed_dequantize_per_tensor_default_1019 = None
2025-03-21T20:31:43.5761168Z             aten_squeeze_copy_dims_49: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_18, [4]);  aten_slice_copy_tensor_18 = None
2025-03-21T20:31:43.5761708Z             aten_squeeze_copy_dims_50: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_19, [4]);  aten_slice_copy_tensor_19 = None
2025-03-21T20:31:43.5762617Z             quantized_decomposed_quantize_per_tensor_default_680: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_49, 0.00040076454752124846, 31390, 0, 65535, torch.int32);  aten_squeeze_copy_dims_49 = None
2025-03-21T20:31:43.5762706Z             
2025-03-21T20:31:43.5763191Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.5764128Z             quantized_decomposed_dequantize_per_tensor_default_1020: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_680, 0.00040076454752124846, 31390, 0, 65535, torch.int32)
2025-03-21T20:31:43.5764228Z             
2025-03-21T20:31:43.5764703Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.5765857Z             quantized_decomposed_dequantize_per_tensor_default_1021: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_680, 0.00040076454752124846, 31390, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_680 = None
2025-03-21T20:31:43.5765946Z             
2025-03-21T20:31:43.5766473Z              # File: /pytorch/executorch/examples/models/llama/rope.py:85 in apply_rotary_emb, code: xk_r, xk_i = xk.float().reshape(xk.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.5767373Z             quantized_decomposed_quantize_per_tensor_default_681: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_50, 0.0003823413862846792, 33824, 0, 65535, torch.int32);  aten_squeeze_copy_dims_50 = None
2025-03-21T20:31:43.5767474Z             
2025-03-21T20:31:43.5767943Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.5768858Z             quantized_decomposed_dequantize_per_tensor_default_1022: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_681, 0.0003823413862846792, 33824, 0, 65535, torch.int32)
2025-03-21T20:31:43.5768959Z             
2025-03-21T20:31:43.5769509Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.5770669Z             quantized_decomposed_dequantize_per_tensor_default_1023: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_681, 0.0003823413862846792, 33824, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_681 = None
2025-03-21T20:31:43.5770756Z             
2025-03-21T20:31:43.5771205Z              # File: /pytorch/executorch/examples/models/llama/rope.py:78 in reshape_for_broadcast, code: return freqs_cis.view(shape)
2025-03-21T20:31:43.5772016Z             aten_view_copy_default_77: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_158, [1, 1, 1, 32]);  quantized_decomposed_dequantize_per_tensor_default_158 = None
2025-03-21T20:31:43.5772920Z             quantized_decomposed_quantize_per_tensor_default_682: "i32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_77, 3.051804378628731e-05, 32768, 0, 65535, torch.int32);  aten_view_copy_default_77 = None
2025-03-21T20:31:43.5773007Z             
2025-03-21T20:31:43.5773518Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.5774432Z             quantized_decomposed_dequantize_per_tensor_default_1024: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_682, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.5774535Z             
2025-03-21T20:31:43.5775002Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.5775945Z             quantized_decomposed_dequantize_per_tensor_default_1025: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_682, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.5776034Z             
2025-03-21T20:31:43.5776512Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.5777419Z             quantized_decomposed_dequantize_per_tensor_default_1026: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_682, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.5777519Z             
2025-03-21T20:31:43.5777987Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.5779125Z             quantized_decomposed_dequantize_per_tensor_default_1027: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_682, 3.051804378628731e-05, 32768, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_682 = None
2025-03-21T20:31:43.5779228Z             
2025-03-21T20:31:43.5779663Z              # File: /pytorch/executorch/examples/models/llama/rope.py:78 in reshape_for_broadcast, code: return freqs_cis.view(shape)
2025-03-21T20:31:43.5780429Z             aten_view_copy_default_78: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_170, [1, 1, 1, 32]);  quantized_decomposed_dequantize_per_tensor_default_170 = None
2025-03-21T20:31:43.5781321Z             quantized_decomposed_quantize_per_tensor_default_683: "i32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_78, 3.051786916330457e-05, 32767, 0, 65535, torch.int32);  aten_view_copy_default_78 = None
2025-03-21T20:31:43.5781422Z             
2025-03-21T20:31:43.5781896Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.5782817Z             quantized_decomposed_dequantize_per_tensor_default_1028: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_683, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.5782956Z             
2025-03-21T20:31:43.5783440Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.5784350Z             quantized_decomposed_dequantize_per_tensor_default_1029: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_683, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.5784458Z             
2025-03-21T20:31:43.5784949Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.5785872Z             quantized_decomposed_dequantize_per_tensor_default_1030: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_683, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.5785963Z             
2025-03-21T20:31:43.5786445Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.5787600Z             quantized_decomposed_dequantize_per_tensor_default_1031: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_683, 3.051786916330457e-05, 32767, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_683 = None
2025-03-21T20:31:43.5787705Z             
2025-03-21T20:31:43.5788172Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.5789299Z             aten_mul_tensor_62: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1015, quantized_decomposed_dequantize_per_tensor_default_1027);  quantized_decomposed_dequantize_per_tensor_default_1015 = quantized_decomposed_dequantize_per_tensor_default_1027 = None
2025-03-21T20:31:43.5790159Z             quantized_decomposed_quantize_per_tensor_default_684: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_62, 0.0003092595434281975, 28515, 0, 65535, torch.int32);  aten_mul_tensor_62 = None
2025-03-21T20:31:43.5791311Z             quantized_decomposed_dequantize_per_tensor_default_1032: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_684, 0.0003092595434281975, 28515, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_684 = None
2025-03-21T20:31:43.5792431Z             aten_mul_tensor_63: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1016, quantized_decomposed_dequantize_per_tensor_default_1030);  quantized_decomposed_dequantize_per_tensor_default_1016 = quantized_decomposed_dequantize_per_tensor_default_1030 = None
2025-03-21T20:31:43.5793298Z             quantized_decomposed_quantize_per_tensor_default_685: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_63, 0.00020828904234804213, 31612, 0, 65535, torch.int32);  aten_mul_tensor_63 = None
2025-03-21T20:31:43.5794436Z             quantized_decomposed_dequantize_per_tensor_default_1033: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_685, 0.00020828904234804213, 31612, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_685 = None
2025-03-21T20:31:43.5795589Z             aten_sub_tensor_8: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_sub_Tensor(quantized_decomposed_dequantize_per_tensor_default_1032, quantized_decomposed_dequantize_per_tensor_default_1033);  quantized_decomposed_dequantize_per_tensor_default_1032 = quantized_decomposed_dequantize_per_tensor_default_1033 = None
2025-03-21T20:31:43.5796458Z             quantized_decomposed_quantize_per_tensor_default_686: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_sub_tensor_8, 0.00030704005621373653, 28921, 0, 65535, torch.int32);  aten_sub_tensor_8 = None
2025-03-21T20:31:43.5796558Z             
2025-03-21T20:31:43.5797513Z              # File: <eval_with_key>.50:2593 in forward, code: dequantize_per_tensor_default_839 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_839, 0.00030704005621373653, 28921, 0, 65535, torch.int32);  quantize_per_tensor_default_839 = None
2025-03-21T20:31:43.5798668Z             quantized_decomposed_dequantize_per_tensor_default_1034: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_686, 0.00030704005621373653, 28921, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_686 = None
2025-03-21T20:31:43.5798781Z             
2025-03-21T20:31:43.5799269Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.5800393Z             aten_mul_tensor_64: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1014, quantized_decomposed_dequantize_per_tensor_default_1031);  quantized_decomposed_dequantize_per_tensor_default_1014 = quantized_decomposed_dequantize_per_tensor_default_1031 = None
2025-03-21T20:31:43.5801261Z             quantized_decomposed_quantize_per_tensor_default_687: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_64, 0.00016941409558057785, 33259, 0, 65535, torch.int32);  aten_mul_tensor_64 = None
2025-03-21T20:31:43.5802399Z             quantized_decomposed_dequantize_per_tensor_default_1035: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_687, 0.00016941409558057785, 33259, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_687 = None
2025-03-21T20:31:43.5803538Z             aten_mul_tensor_65: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1017, quantized_decomposed_dequantize_per_tensor_default_1026);  quantized_decomposed_dequantize_per_tensor_default_1017 = quantized_decomposed_dequantize_per_tensor_default_1026 = None
2025-03-21T20:31:43.5804386Z             quantized_decomposed_quantize_per_tensor_default_688: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_65, 0.00029095596983097494, 29320, 0, 65535, torch.int32);  aten_mul_tensor_65 = None
2025-03-21T20:31:43.5805538Z             quantized_decomposed_dequantize_per_tensor_default_1036: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_688, 0.00029095596983097494, 29320, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_688 = None
2025-03-21T20:31:43.5806682Z             aten_add_tensor_20: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_1035, quantized_decomposed_dequantize_per_tensor_default_1036);  quantized_decomposed_dequantize_per_tensor_default_1035 = quantized_decomposed_dequantize_per_tensor_default_1036 = None
2025-03-21T20:31:43.5807557Z             quantized_decomposed_quantize_per_tensor_default_689: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_20, 0.00028711769846268, 29314, 0, 65535, torch.int32);  aten_add_tensor_20 = None
2025-03-21T20:31:43.5807680Z             
2025-03-21T20:31:43.5808603Z              # File: <eval_with_key>.50:2602 in forward, code: dequantize_per_tensor_default_842 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_842, 0.00028711769846268, 29314, 0, 65535, torch.int32);  quantize_per_tensor_default_842 = None
2025-03-21T20:31:43.5809842Z             quantized_decomposed_dequantize_per_tensor_default_1037: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_689, 0.00028711769846268, 29314, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_689 = None
2025-03-21T20:31:43.5809938Z             
2025-03-21T20:31:43.5810428Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.5811565Z             aten_mul_tensor_66: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1021, quantized_decomposed_dequantize_per_tensor_default_1025);  quantized_decomposed_dequantize_per_tensor_default_1021 = quantized_decomposed_dequantize_per_tensor_default_1025 = None
2025-03-21T20:31:43.5812482Z             quantized_decomposed_quantize_per_tensor_default_690: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_66, 0.0003889426589012146, 30723, 0, 65535, torch.int32);  aten_mul_tensor_66 = None
2025-03-21T20:31:43.5813621Z             quantized_decomposed_dequantize_per_tensor_default_1038: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_690, 0.0003889426589012146, 30723, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_690 = None
2025-03-21T20:31:43.5814758Z             aten_mul_tensor_67: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1022, quantized_decomposed_dequantize_per_tensor_default_1028);  quantized_decomposed_dequantize_per_tensor_default_1022 = quantized_decomposed_dequantize_per_tensor_default_1028 = None
2025-03-21T20:31:43.5815607Z             quantized_decomposed_quantize_per_tensor_default_691: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_67, 0.00020149449119344354, 31475, 0, 65535, torch.int32);  aten_mul_tensor_67 = None
2025-03-21T20:31:43.5816765Z             quantized_decomposed_dequantize_per_tensor_default_1039: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_691, 0.00020149449119344354, 31475, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_691 = None
2025-03-21T20:31:43.5817886Z             aten_sub_tensor_9: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_sub_Tensor(quantized_decomposed_dequantize_per_tensor_default_1038, quantized_decomposed_dequantize_per_tensor_default_1039);  quantized_decomposed_dequantize_per_tensor_default_1038 = quantized_decomposed_dequantize_per_tensor_default_1039 = None
2025-03-21T20:31:43.5818746Z             quantized_decomposed_quantize_per_tensor_default_692: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_sub_tensor_9, 0.0003881677403114736, 30645, 0, 65535, torch.int32);  aten_sub_tensor_9 = None
2025-03-21T20:31:43.5818835Z             
2025-03-21T20:31:43.5819803Z              # File: <eval_with_key>.50:2611 in forward, code: dequantize_per_tensor_default_845 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_845, 0.0003881677403114736, 30645, 0, 65535, torch.int32);  quantize_per_tensor_default_845 = None
2025-03-21T20:31:43.5820971Z             quantized_decomposed_dequantize_per_tensor_default_1040: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_692, 0.0003881677403114736, 30645, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_692 = None
2025-03-21T20:31:43.5821075Z             
2025-03-21T20:31:43.5821572Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.5822713Z             aten_mul_tensor_68: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1020, quantized_decomposed_dequantize_per_tensor_default_1029);  quantized_decomposed_dequantize_per_tensor_default_1020 = quantized_decomposed_dequantize_per_tensor_default_1029 = None
2025-03-21T20:31:43.5823567Z             quantized_decomposed_quantize_per_tensor_default_693: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_68, 0.00017219017900060862, 30798, 0, 65535, torch.int32);  aten_mul_tensor_68 = None
2025-03-21T20:31:43.5824753Z             quantized_decomposed_dequantize_per_tensor_default_1041: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_693, 0.00017219017900060862, 30798, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_693 = None
2025-03-21T20:31:43.5825875Z             aten_mul_tensor_69: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1023, quantized_decomposed_dequantize_per_tensor_default_1024);  quantized_decomposed_dequantize_per_tensor_default_1023 = quantized_decomposed_dequantize_per_tensor_default_1024 = None
2025-03-21T20:31:43.5826730Z             quantized_decomposed_quantize_per_tensor_default_694: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_69, 0.0003756027726922184, 33266, 0, 65535, torch.int32);  aten_mul_tensor_69 = None
2025-03-21T20:31:43.5827887Z             quantized_decomposed_dequantize_per_tensor_default_1042: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_694, 0.0003756027726922184, 33266, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_694 = None
2025-03-21T20:31:43.5829010Z             aten_add_tensor_21: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_1041, quantized_decomposed_dequantize_per_tensor_default_1042);  quantized_decomposed_dequantize_per_tensor_default_1041 = quantized_decomposed_dequantize_per_tensor_default_1042 = None
2025-03-21T20:31:43.5829870Z             quantized_decomposed_quantize_per_tensor_default_695: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_21, 0.00038093022885732353, 33710, 0, 65535, torch.int32);  aten_add_tensor_21 = None
2025-03-21T20:31:43.5829988Z             
2025-03-21T20:31:43.5830999Z              # File: <eval_with_key>.50:2620 in forward, code: dequantize_per_tensor_default_848 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_848, 0.00038093022885732353, 33710, 0, 65535, torch.int32);  quantize_per_tensor_default_848 = None
2025-03-21T20:31:43.5832176Z             quantized_decomposed_dequantize_per_tensor_default_1043: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_695, 0.00038093022885732353, 33710, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_695 = None
2025-03-21T20:31:43.5832470Z             
2025-03-21T20:31:43.5832996Z              # File: /pytorch/executorch/examples/models/llama/rope.py:95 in apply_rotary_emb, code: xq_out = torch.stack([xq_out_r, xq_out_i], dim=-1).flatten(3)
2025-03-21T20:31:43.5833878Z             aten_unsqueeze_copy_default_47: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1034, 4);  quantized_decomposed_dequantize_per_tensor_default_1034 = None
2025-03-21T20:31:43.5834673Z             aten_unsqueeze_copy_default_48: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1037, 4);  quantized_decomposed_dequantize_per_tensor_default_1037 = None
2025-03-21T20:31:43.5835428Z             aten_cat_default_16: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_cat_default([aten_unsqueeze_copy_default_47, aten_unsqueeze_copy_default_48], -1);  aten_unsqueeze_copy_default_47 = aten_unsqueeze_copy_default_48 = None
2025-03-21T20:31:43.5836330Z             quantized_decomposed_quantize_per_tensor_default_696: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_16, 0.00030704005621373653, 28921, 0, 65535, torch.int32);  aten_cat_default_16 = None
2025-03-21T20:31:43.5837492Z             quantized_decomposed_dequantize_per_tensor_default_1044: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_696, 0.00030704005621373653, 28921, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_696 = None
2025-03-21T20:31:43.5838260Z             aten_view_copy_default_79: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1044, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_1044 = None
2025-03-21T20:31:43.5839179Z             quantized_decomposed_quantize_per_tensor_default_697: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_79, 0.00030704005621373653, 28921, 0, 65535, torch.int32);  aten_view_copy_default_79 = None
2025-03-21T20:31:43.5839272Z             
2025-03-21T20:31:43.5840225Z              # File: <eval_with_key>.50:2626 in forward, code: dequantize_per_tensor_default_850 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_850, 0.00030704005621373653, 28921, 0, 65535, torch.int32);  quantize_per_tensor_default_850 = None
2025-03-21T20:31:43.5841619Z             quantized_decomposed_dequantize_per_tensor_default_1045: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_697, 0.00030704005621373653, 28921, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_697 = None
2025-03-21T20:31:43.5841729Z             
2025-03-21T20:31:43.5842250Z              # File: /pytorch/executorch/examples/models/llama/rope.py:96 in apply_rotary_emb, code: xk_out = torch.stack([xk_out_r, xk_out_i], dim=-1).flatten(3)
2025-03-21T20:31:43.5843058Z             aten_unsqueeze_copy_default_49: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1040, 4);  quantized_decomposed_dequantize_per_tensor_default_1040 = None
2025-03-21T20:31:43.5843848Z             aten_unsqueeze_copy_default_50: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1043, 4);  quantized_decomposed_dequantize_per_tensor_default_1043 = None
2025-03-21T20:31:43.5844687Z             aten_cat_default_17: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_cat_default([aten_unsqueeze_copy_default_49, aten_unsqueeze_copy_default_50], -1);  aten_unsqueeze_copy_default_49 = aten_unsqueeze_copy_default_50 = None
2025-03-21T20:31:43.5845549Z             quantized_decomposed_quantize_per_tensor_default_698: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_17, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_cat_default_17 = None
2025-03-21T20:31:43.5846729Z             quantized_decomposed_dequantize_per_tensor_default_1046: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_698, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_698 = None
2025-03-21T20:31:43.5847494Z             aten_view_copy_default_80: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1046, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_1046 = None
2025-03-21T20:31:43.5848441Z             quantized_decomposed_quantize_per_tensor_default_699: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_80, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_view_copy_default_80 = None
2025-03-21T20:31:43.5848530Z             
2025-03-21T20:31:43.5849552Z              # File: <eval_with_key>.50:2632 in forward, code: dequantize_per_tensor_default_852 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_852, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantize_per_tensor_default_852 = None
2025-03-21T20:31:43.5850700Z             quantized_decomposed_dequantize_per_tensor_default_1047: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_699, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_699 = None
2025-03-21T20:31:43.5850805Z             
2025-03-21T20:31:43.5851552Z              # File: <eval_with_key>.50:2634 in forward, code: quantize_per_tensor_default_853 = torch.ops.quantized_decomposed.quantize_per_tensor.default(type_as_8, 0.00030704005621373653, 28921, 0, 65535, torch.int32);  type_as_8 = None
2025-03-21T20:31:43.5852719Z             quantized_decomposed_quantize_per_tensor_default_700: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_1045, 0.00030704005621373653, 28921, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_1045 = None
2025-03-21T20:31:43.5852811Z             
2025-03-21T20:31:43.5853351Z              # File: /pytorch/executorch/examples/models/llama/attention.py:249 in forward, code: q = q.transpose(1, 2)  # (bs, n_local_heads, seqlen, head_dim)
2025-03-21T20:31:43.5854492Z             quantized_decomposed_dequantize_per_tensor_default_1048: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_700, 0.00030704005621373653, 28921, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_700 = None
2025-03-21T20:31:43.5854595Z             
2025-03-21T20:31:43.5855347Z              # File: <eval_with_key>.50:2637 in forward, code: quantize_per_tensor_default_854 = torch.ops.quantized_decomposed.quantize_per_tensor.default(type_as_9, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  type_as_9 = None
2025-03-21T20:31:43.5856529Z             quantized_decomposed_quantize_per_tensor_default_701: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_1047, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_1047 = None
2025-03-21T20:31:43.5856643Z             
2025-03-21T20:31:43.5857323Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:345 in update, code: k_out = torch.ops.aten.index_put_(self.past_k_caches, [None, input_pos], k_val)
2025-03-21T20:31:43.5858490Z             quantized_decomposed_dequantize_per_tensor_default_1049: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_701, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_701 = None
2025-03-21T20:31:43.5858594Z             
2025-03-21T20:31:43.5859113Z              # File: /pytorch/executorch/examples/models/llama/attention.py:249 in forward, code: q = q.transpose(1, 2)  # (bs, n_local_heads, seqlen, head_dim)
2025-03-21T20:31:43.5859928Z             aten_permute_copy_default_170: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1048, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1048 = None
2025-03-21T20:31:43.5860883Z             quantized_decomposed_quantize_per_tensor_default_702: "i32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_170, 0.00030704005621373653, 28921, 0, 65535, torch.int32);  aten_permute_copy_default_170 = None
2025-03-21T20:31:43.5860983Z             
2025-03-21T20:31:43.5861557Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.5862711Z             quantized_decomposed_dequantize_per_tensor_default_1050: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_702, 0.00030704005621373653, 28921, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_702 = None
2025-03-21T20:31:43.5862805Z             
2025-03-21T20:31:43.5863484Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:345 in update, code: k_out = torch.ops.aten.index_put_(self.past_k_caches, [None, input_pos], k_val)
2025-03-21T20:31:43.5864770Z             aten_index_put_default_8: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_index_put_default(quantized_decomposed_dequantize_per_tensor_default_125, [None, attn_options_input_pos], quantized_decomposed_dequantize_per_tensor_default_1049);  quantized_decomposed_dequantize_per_tensor_default_125 = quantized_decomposed_dequantize_per_tensor_default_1049 = None
2025-03-21T20:31:43.5865687Z             quantized_decomposed_quantize_per_tensor_default_703: "i32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_put_default_8, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_index_put_default_8 = None
2025-03-21T20:31:43.5865779Z             
2025-03-21T20:31:43.5866577Z              # File: <eval_with_key>.50:2644 in forward, code: dequantize_per_tensor_default_856 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_856, 0.00040260335663333535, 31896, 0, 65535, torch.int32)
2025-03-21T20:31:43.5867502Z             quantized_decomposed_dequantize_per_tensor_default_1051: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_703, 0.00040260335663333535, 31896, 0, 65535, torch.int32)
2025-03-21T20:31:43.5867602Z             
2025-03-21T20:31:43.5868261Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5869226Z             quantized_decomposed_dequantize_per_tensor_default_1052: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_703, 0.00040260335663333535, 31896, 0, 65535, torch.int32)
2025-03-21T20:31:43.5870166Z             quantized_decomposed_dequantize_per_tensor_default_1053: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_703, 0.00040260335663333535, 31896, 0, 65535, torch.int32)
2025-03-21T20:31:43.5871090Z             quantized_decomposed_dequantize_per_tensor_default_1054: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_703, 0.00040260335663333535, 31896, 0, 65535, torch.int32)
2025-03-21T20:31:43.5872007Z             quantized_decomposed_dequantize_per_tensor_default_1055: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_703, 0.00040260335663333535, 31896, 0, 65535, torch.int32)
2025-03-21T20:31:43.5872960Z             quantized_decomposed_dequantize_per_tensor_default_1056: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_703, 0.00040260335663333535, 31896, 0, 65535, torch.int32)
2025-03-21T20:31:43.5873877Z             quantized_decomposed_dequantize_per_tensor_default_1057: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_703, 0.00040260335663333535, 31896, 0, 65535, torch.int32)
2025-03-21T20:31:43.5874803Z             quantized_decomposed_dequantize_per_tensor_default_1058: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_703, 0.00040260335663333535, 31896, 0, 65535, torch.int32)
2025-03-21T20:31:43.5875720Z             quantized_decomposed_dequantize_per_tensor_default_1059: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_703, 0.00040260335663333535, 31896, 0, 65535, torch.int32)
2025-03-21T20:31:43.5876642Z             quantized_decomposed_dequantize_per_tensor_default_1060: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_703, 0.00040260335663333535, 31896, 0, 65535, torch.int32)
2025-03-21T20:31:43.5877556Z             quantized_decomposed_dequantize_per_tensor_default_1061: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_703, 0.00040260335663333535, 31896, 0, 65535, torch.int32)
2025-03-21T20:31:43.5878485Z             quantized_decomposed_dequantize_per_tensor_default_1062: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_703, 0.00040260335663333535, 31896, 0, 65535, torch.int32)
2025-03-21T20:31:43.5879635Z             quantized_decomposed_dequantize_per_tensor_default_1063: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_703, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_703 = None
2025-03-21T20:31:43.5879738Z             
2025-03-21T20:31:43.5880434Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:346 in update, code: v_out = torch.ops.aten.index_put_(self.past_v_caches, [None, input_pos], v_val)
2025-03-21T20:31:43.5881749Z             aten_index_put_default_9: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_index_put_default(quantized_decomposed_dequantize_per_tensor_default_126, [None, attn_options_input_pos], quantized_decomposed_dequantize_per_tensor_default_1011);  quantized_decomposed_dequantize_per_tensor_default_126 = quantized_decomposed_dequantize_per_tensor_default_1011 = None
2025-03-21T20:31:43.5882689Z             quantized_decomposed_quantize_per_tensor_default_704: "i32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_put_default_9, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_index_put_default_9 = None
2025-03-21T20:31:43.5882777Z             
2025-03-21T20:31:43.5883562Z              # File: <eval_with_key>.50:2659 in forward, code: dequantize_per_tensor_default_857 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_857, 0.00012666585098486394, 35736, 0, 65535, torch.int32)
2025-03-21T20:31:43.5884497Z             quantized_decomposed_dequantize_per_tensor_default_1064: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_704, 0.00012666585098486394, 35736, 0, 65535, torch.int32)
2025-03-21T20:31:43.5884608Z             
2025-03-21T20:31:43.5885253Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5886174Z             quantized_decomposed_dequantize_per_tensor_default_1065: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_704, 0.00012666585098486394, 35736, 0, 65535, torch.int32)
2025-03-21T20:31:43.5887105Z             quantized_decomposed_dequantize_per_tensor_default_1066: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_704, 0.00012666585098486394, 35736, 0, 65535, torch.int32)
2025-03-21T20:31:43.5888020Z             quantized_decomposed_dequantize_per_tensor_default_1067: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_704, 0.00012666585098486394, 35736, 0, 65535, torch.int32)
2025-03-21T20:31:43.5888948Z             quantized_decomposed_dequantize_per_tensor_default_1068: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_704, 0.00012666585098486394, 35736, 0, 65535, torch.int32)
2025-03-21T20:31:43.5889939Z             quantized_decomposed_dequantize_per_tensor_default_1069: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_704, 0.00012666585098486394, 35736, 0, 65535, torch.int32)
2025-03-21T20:31:43.5890859Z             quantized_decomposed_dequantize_per_tensor_default_1070: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_704, 0.00012666585098486394, 35736, 0, 65535, torch.int32)
2025-03-21T20:31:43.5891791Z             quantized_decomposed_dequantize_per_tensor_default_1071: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_704, 0.00012666585098486394, 35736, 0, 65535, torch.int32)
2025-03-21T20:31:43.5892741Z             quantized_decomposed_dequantize_per_tensor_default_1072: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_704, 0.00012666585098486394, 35736, 0, 65535, torch.int32)
2025-03-21T20:31:43.5893694Z             quantized_decomposed_dequantize_per_tensor_default_1073: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_704, 0.00012666585098486394, 35736, 0, 65535, torch.int32)
2025-03-21T20:31:43.5894646Z             quantized_decomposed_dequantize_per_tensor_default_1074: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_704, 0.00012666585098486394, 35736, 0, 65535, torch.int32)
2025-03-21T20:31:43.5895581Z             quantized_decomposed_dequantize_per_tensor_default_1075: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_704, 0.00012666585098486394, 35736, 0, 65535, torch.int32)
2025-03-21T20:31:43.5896729Z             quantized_decomposed_dequantize_per_tensor_default_1076: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_704, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_704 = None
2025-03-21T20:31:43.5896857Z             
2025-03-21T20:31:43.5897490Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5898305Z             aten_permute_copy_default_171: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1063, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1063 = None
2025-03-21T20:31:43.5899247Z             quantized_decomposed_quantize_per_tensor_default_705: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_171, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_permute_copy_default_171 = None
2025-03-21T20:31:43.5900405Z             quantized_decomposed_dequantize_per_tensor_default_1077: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_705, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_705 = None
2025-03-21T20:31:43.5901146Z             aten_select_copy_int_192: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1077, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1077 = None
2025-03-21T20:31:43.5902053Z             quantized_decomposed_quantize_per_tensor_default_706: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_192, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_select_copy_int_192 = None
2025-03-21T20:31:43.5903197Z             quantized_decomposed_dequantize_per_tensor_default_1078: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_706, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_706 = None
2025-03-21T20:31:43.5903944Z             aten_select_copy_int_193: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1078, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1078 = None
2025-03-21T20:31:43.5904870Z             quantized_decomposed_quantize_per_tensor_default_707: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_193, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_select_copy_int_193 = None
2025-03-21T20:31:43.5904998Z             
2025-03-21T20:31:43.5905930Z              # File: <eval_with_key>.50:2680 in forward, code: dequantize_per_tensor_default_860 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_860, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantize_per_tensor_default_860 = None
2025-03-21T20:31:43.5907103Z             quantized_decomposed_dequantize_per_tensor_default_1079: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_707, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_707 = None
2025-03-21T20:31:43.5907192Z             
2025-03-21T20:31:43.5907841Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5908644Z             aten_permute_copy_default_172: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1062, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1062 = None
2025-03-21T20:31:43.5909625Z             quantized_decomposed_quantize_per_tensor_default_708: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_172, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_permute_copy_default_172 = None
2025-03-21T20:31:43.5910784Z             quantized_decomposed_dequantize_per_tensor_default_1080: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_708, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_708 = None
2025-03-21T20:31:43.5911530Z             aten_select_copy_int_194: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1080, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1080 = None
2025-03-21T20:31:43.5912438Z             quantized_decomposed_quantize_per_tensor_default_709: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_194, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_select_copy_int_194 = None
2025-03-21T20:31:43.5913583Z             quantized_decomposed_dequantize_per_tensor_default_1081: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_709, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_709 = None
2025-03-21T20:31:43.5914338Z             aten_select_copy_int_195: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1081, 0, 1);  quantized_decomposed_dequantize_per_tensor_default_1081 = None
2025-03-21T20:31:43.5915227Z             quantized_decomposed_quantize_per_tensor_default_710: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_195, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_select_copy_int_195 = None
2025-03-21T20:31:43.5915335Z             
2025-03-21T20:31:43.5916268Z              # File: <eval_with_key>.50:2689 in forward, code: dequantize_per_tensor_default_863 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_863, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantize_per_tensor_default_863 = None
2025-03-21T20:31:43.5917478Z             quantized_decomposed_dequantize_per_tensor_default_1082: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_710, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_710 = None
2025-03-21T20:31:43.5917571Z             
2025-03-21T20:31:43.5918220Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5919351Z             aten_permute_copy_default_173: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1061, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1061 = None
2025-03-21T20:31:43.5920309Z             quantized_decomposed_quantize_per_tensor_default_711: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_173, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_permute_copy_default_173 = None
2025-03-21T20:31:43.5921454Z             quantized_decomposed_dequantize_per_tensor_default_1083: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_711, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_711 = None
2025-03-21T20:31:43.5922242Z             aten_select_copy_int_196: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1083, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1083 = None
2025-03-21T20:31:43.5923134Z             quantized_decomposed_quantize_per_tensor_default_712: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_196, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_select_copy_int_196 = None
2025-03-21T20:31:43.5924292Z             quantized_decomposed_dequantize_per_tensor_default_1084: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_712, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_712 = None
2025-03-21T20:31:43.5925032Z             aten_select_copy_int_197: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1084, 0, 2);  quantized_decomposed_dequantize_per_tensor_default_1084 = None
2025-03-21T20:31:43.5925939Z             quantized_decomposed_quantize_per_tensor_default_713: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_197, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_select_copy_int_197 = None
2025-03-21T20:31:43.5926030Z             
2025-03-21T20:31:43.5926978Z              # File: <eval_with_key>.50:2698 in forward, code: dequantize_per_tensor_default_866 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_866, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantize_per_tensor_default_866 = None
2025-03-21T20:31:43.5928122Z             quantized_decomposed_dequantize_per_tensor_default_1085: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_713, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_713 = None
2025-03-21T20:31:43.5928223Z             
2025-03-21T20:31:43.5928859Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5929813Z             aten_permute_copy_default_174: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1060, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1060 = None
2025-03-21T20:31:43.5930761Z             quantized_decomposed_quantize_per_tensor_default_714: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_174, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_permute_copy_default_174 = None
2025-03-21T20:31:43.5931951Z             quantized_decomposed_dequantize_per_tensor_default_1086: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_714, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_714 = None
2025-03-21T20:31:43.5932856Z             aten_select_copy_int_198: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1086, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1086 = None
2025-03-21T20:31:43.5933834Z             quantized_decomposed_quantize_per_tensor_default_715: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_198, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_select_copy_int_198 = None
2025-03-21T20:31:43.5935001Z             quantized_decomposed_dequantize_per_tensor_default_1087: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_715, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_715 = None
2025-03-21T20:31:43.5935743Z             aten_select_copy_int_199: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1087, 0, 3);  quantized_decomposed_dequantize_per_tensor_default_1087 = None
2025-03-21T20:31:43.5936651Z             quantized_decomposed_quantize_per_tensor_default_716: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_199, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_select_copy_int_199 = None
2025-03-21T20:31:43.5936738Z             
2025-03-21T20:31:43.5937686Z              # File: <eval_with_key>.50:2707 in forward, code: dequantize_per_tensor_default_869 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_869, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantize_per_tensor_default_869 = None
2025-03-21T20:31:43.5938834Z             quantized_decomposed_dequantize_per_tensor_default_1088: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_716, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_716 = None
2025-03-21T20:31:43.5938944Z             
2025-03-21T20:31:43.5939583Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5940406Z             aten_permute_copy_default_175: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1059, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1059 = None
2025-03-21T20:31:43.5941381Z             quantized_decomposed_quantize_per_tensor_default_717: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_175, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_permute_copy_default_175 = None
2025-03-21T20:31:43.5942709Z             quantized_decomposed_dequantize_per_tensor_default_1089: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_717, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_717 = None
2025-03-21T20:31:43.5943506Z             aten_select_copy_int_200: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1089, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1089 = None
2025-03-21T20:31:43.5944422Z             quantized_decomposed_quantize_per_tensor_default_718: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_200, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_select_copy_int_200 = None
2025-03-21T20:31:43.5945569Z             quantized_decomposed_dequantize_per_tensor_default_1090: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_718, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_718 = None
2025-03-21T20:31:43.5946355Z             aten_select_copy_int_201: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1090, 0, 4);  quantized_decomposed_dequantize_per_tensor_default_1090 = None
2025-03-21T20:31:43.5947243Z             quantized_decomposed_quantize_per_tensor_default_719: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_201, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_select_copy_int_201 = None
2025-03-21T20:31:43.5947346Z             
2025-03-21T20:31:43.5948280Z              # File: <eval_with_key>.50:2716 in forward, code: dequantize_per_tensor_default_872 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_872, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantize_per_tensor_default_872 = None
2025-03-21T20:31:43.5949438Z             quantized_decomposed_dequantize_per_tensor_default_1091: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_719, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_719 = None
2025-03-21T20:31:43.5949528Z             
2025-03-21T20:31:43.5950174Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5950975Z             aten_permute_copy_default_176: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1058, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1058 = None
2025-03-21T20:31:43.5951929Z             quantized_decomposed_quantize_per_tensor_default_720: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_176, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_permute_copy_default_176 = None
2025-03-21T20:31:43.5953076Z             quantized_decomposed_dequantize_per_tensor_default_1092: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_720, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_720 = None
2025-03-21T20:31:43.5953863Z             aten_select_copy_int_202: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1092, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1092 = None
2025-03-21T20:31:43.5954781Z             quantized_decomposed_quantize_per_tensor_default_721: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_202, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_select_copy_int_202 = None
2025-03-21T20:31:43.5955966Z             quantized_decomposed_dequantize_per_tensor_default_1093: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_721, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_721 = None
2025-03-21T20:31:43.5956706Z             aten_select_copy_int_203: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1093, 0, 5);  quantized_decomposed_dequantize_per_tensor_default_1093 = None
2025-03-21T20:31:43.5957605Z             quantized_decomposed_quantize_per_tensor_default_722: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_203, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_select_copy_int_203 = None
2025-03-21T20:31:43.5957715Z             
2025-03-21T20:31:43.5958658Z              # File: <eval_with_key>.50:2725 in forward, code: dequantize_per_tensor_default_875 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_875, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantize_per_tensor_default_875 = None
2025-03-21T20:31:43.5962449Z             quantized_decomposed_dequantize_per_tensor_default_1094: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_722, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_722 = None
2025-03-21T20:31:43.5962559Z             
2025-03-21T20:31:43.5963200Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5964016Z             aten_permute_copy_default_177: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1057, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1057 = None
2025-03-21T20:31:43.5964954Z             quantized_decomposed_quantize_per_tensor_default_723: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_177, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_permute_copy_default_177 = None
2025-03-21T20:31:43.5966136Z             quantized_decomposed_dequantize_per_tensor_default_1095: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_723, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_723 = None
2025-03-21T20:31:43.5966894Z             aten_select_copy_int_204: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1095, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1095 = None
2025-03-21T20:31:43.5967789Z             quantized_decomposed_quantize_per_tensor_default_724: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_204, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_select_copy_int_204 = None
2025-03-21T20:31:43.5969002Z             quantized_decomposed_dequantize_per_tensor_default_1096: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_724, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_724 = None
2025-03-21T20:31:43.5969844Z             aten_select_copy_int_205: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1096, 0, 6);  quantized_decomposed_dequantize_per_tensor_default_1096 = None
2025-03-21T20:31:43.5970783Z             quantized_decomposed_quantize_per_tensor_default_725: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_205, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_select_copy_int_205 = None
2025-03-21T20:31:43.5970876Z             
2025-03-21T20:31:43.5971823Z              # File: <eval_with_key>.50:2734 in forward, code: dequantize_per_tensor_default_878 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_878, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantize_per_tensor_default_878 = None
2025-03-21T20:31:43.5972981Z             quantized_decomposed_dequantize_per_tensor_default_1097: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_725, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_725 = None
2025-03-21T20:31:43.5973070Z             
2025-03-21T20:31:43.5973705Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5974582Z             aten_permute_copy_default_178: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1056, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1056 = None
2025-03-21T20:31:43.5975522Z             quantized_decomposed_quantize_per_tensor_default_726: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_178, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_permute_copy_default_178 = None
2025-03-21T20:31:43.5976680Z             quantized_decomposed_dequantize_per_tensor_default_1098: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_726, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_726 = None
2025-03-21T20:31:43.5977432Z             aten_select_copy_int_206: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1098, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1098 = None
2025-03-21T20:31:43.5978322Z             quantized_decomposed_quantize_per_tensor_default_727: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_206, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_select_copy_int_206 = None
2025-03-21T20:31:43.5979476Z             quantized_decomposed_dequantize_per_tensor_default_1099: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_727, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_727 = None
2025-03-21T20:31:43.5980210Z             aten_select_copy_int_207: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1099, 0, 7);  quantized_decomposed_dequantize_per_tensor_default_1099 = None
2025-03-21T20:31:43.5981161Z             quantized_decomposed_quantize_per_tensor_default_728: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_207, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_select_copy_int_207 = None
2025-03-21T20:31:43.5981249Z             
2025-03-21T20:31:43.5982194Z              # File: <eval_with_key>.50:2743 in forward, code: dequantize_per_tensor_default_881 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_881, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantize_per_tensor_default_881 = None
2025-03-21T20:31:43.5983359Z             quantized_decomposed_dequantize_per_tensor_default_1100: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_728, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_728 = None
2025-03-21T20:31:43.5983460Z             
2025-03-21T20:31:43.5984100Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5984913Z             aten_permute_copy_default_179: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1055, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1055 = None
2025-03-21T20:31:43.5985851Z             quantized_decomposed_quantize_per_tensor_default_729: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_179, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_permute_copy_default_179 = None
2025-03-21T20:31:43.5987061Z             quantized_decomposed_dequantize_per_tensor_default_1101: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_729, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_729 = None
2025-03-21T20:31:43.5987803Z             aten_select_copy_int_208: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1101, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1101 = None
2025-03-21T20:31:43.5988710Z             quantized_decomposed_quantize_per_tensor_default_730: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_208, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_select_copy_int_208 = None
2025-03-21T20:31:43.5989854Z             quantized_decomposed_dequantize_per_tensor_default_1102: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_730, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_730 = None
2025-03-21T20:31:43.5990602Z             aten_select_copy_int_209: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1102, 0, 8);  quantized_decomposed_dequantize_per_tensor_default_1102 = None
2025-03-21T20:31:43.5991491Z             quantized_decomposed_quantize_per_tensor_default_731: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_209, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_select_copy_int_209 = None
2025-03-21T20:31:43.5991591Z             
2025-03-21T20:31:43.5992545Z              # File: <eval_with_key>.50:2752 in forward, code: dequantize_per_tensor_default_884 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_884, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantize_per_tensor_default_884 = None
2025-03-21T20:31:43.5993720Z             quantized_decomposed_dequantize_per_tensor_default_1103: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_731, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_731 = None
2025-03-21T20:31:43.5993808Z             
2025-03-21T20:31:43.5994481Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.5995283Z             aten_permute_copy_default_180: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1054, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1054 = None
2025-03-21T20:31:43.5996236Z             quantized_decomposed_quantize_per_tensor_default_732: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_180, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_permute_copy_default_180 = None
2025-03-21T20:31:43.5997376Z             quantized_decomposed_dequantize_per_tensor_default_1104: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_732, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_732 = None
2025-03-21T20:31:43.5998131Z             aten_select_copy_int_210: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1104, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1104 = None
2025-03-21T20:31:43.5999050Z             quantized_decomposed_quantize_per_tensor_default_733: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_210, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_select_copy_int_210 = None
2025-03-21T20:31:43.6000216Z             quantized_decomposed_dequantize_per_tensor_default_1105: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_733, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_733 = None
2025-03-21T20:31:43.6000968Z             aten_select_copy_int_211: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1105, 0, 9);  quantized_decomposed_dequantize_per_tensor_default_1105 = None
2025-03-21T20:31:43.6001858Z             quantized_decomposed_quantize_per_tensor_default_734: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_211, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_select_copy_int_211 = None
2025-03-21T20:31:43.6001960Z             
2025-03-21T20:31:43.6002889Z              # File: <eval_with_key>.50:2761 in forward, code: dequantize_per_tensor_default_887 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_887, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantize_per_tensor_default_887 = None
2025-03-21T20:31:43.6004038Z             quantized_decomposed_dequantize_per_tensor_default_1106: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_734, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_734 = None
2025-03-21T20:31:43.6004127Z             
2025-03-21T20:31:43.6004782Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6005645Z             aten_permute_copy_default_181: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1053, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1053 = None
2025-03-21T20:31:43.6006622Z             quantized_decomposed_quantize_per_tensor_default_735: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_181, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_permute_copy_default_181 = None
2025-03-21T20:31:43.6007778Z             quantized_decomposed_dequantize_per_tensor_default_1107: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_735, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_735 = None
2025-03-21T20:31:43.6008533Z             aten_select_copy_int_212: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1107, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1107 = None
2025-03-21T20:31:43.6009570Z             quantized_decomposed_quantize_per_tensor_default_736: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_212, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_select_copy_int_212 = None
2025-03-21T20:31:43.6010729Z             quantized_decomposed_dequantize_per_tensor_default_1108: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_736, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_736 = None
2025-03-21T20:31:43.6011510Z             aten_select_copy_int_213: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1108, 0, 10);  quantized_decomposed_dequantize_per_tensor_default_1108 = None
2025-03-21T20:31:43.6012409Z             quantized_decomposed_quantize_per_tensor_default_737: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_213, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_select_copy_int_213 = None
2025-03-21T20:31:43.6012502Z             
2025-03-21T20:31:43.6013447Z              # File: <eval_with_key>.50:2770 in forward, code: dequantize_per_tensor_default_890 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_890, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantize_per_tensor_default_890 = None
2025-03-21T20:31:43.6014592Z             quantized_decomposed_dequantize_per_tensor_default_1109: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_737, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_737 = None
2025-03-21T20:31:43.6014695Z             
2025-03-21T20:31:43.6015334Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6016148Z             aten_permute_copy_default_182: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1052, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1052 = None
2025-03-21T20:31:43.6017114Z             quantized_decomposed_quantize_per_tensor_default_738: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_182, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_permute_copy_default_182 = None
2025-03-21T20:31:43.6018296Z             quantized_decomposed_dequantize_per_tensor_default_1110: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_738, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_738 = None
2025-03-21T20:31:43.6019060Z             aten_select_copy_int_214: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1110, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1110 = None
2025-03-21T20:31:43.6019969Z             quantized_decomposed_quantize_per_tensor_default_739: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_214, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_select_copy_int_214 = None
2025-03-21T20:31:43.6021112Z             quantized_decomposed_dequantize_per_tensor_default_1111: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_739, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_739 = None
2025-03-21T20:31:43.6021863Z             aten_select_copy_int_215: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1111, 0, 11);  quantized_decomposed_dequantize_per_tensor_default_1111 = None
2025-03-21T20:31:43.6022775Z             quantized_decomposed_quantize_per_tensor_default_740: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_215, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_select_copy_int_215 = None
2025-03-21T20:31:43.6022879Z             
2025-03-21T20:31:43.6023807Z              # File: <eval_with_key>.50:2779 in forward, code: dequantize_per_tensor_default_893 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_893, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantize_per_tensor_default_893 = None
2025-03-21T20:31:43.6024959Z             quantized_decomposed_dequantize_per_tensor_default_1112: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_740, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_740 = None
2025-03-21T20:31:43.6025052Z             
2025-03-21T20:31:43.6025698Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6031204Z             aten_cat_default_18: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_aten_cat_default([quantized_decomposed_dequantize_per_tensor_default_1079, quantized_decomposed_dequantize_per_tensor_default_1082, quantized_decomposed_dequantize_per_tensor_default_1085, quantized_decomposed_dequantize_per_tensor_default_1088, quantized_decomposed_dequantize_per_tensor_default_1091, quantized_decomposed_dequantize_per_tensor_default_1094, quantized_decomposed_dequantize_per_tensor_default_1097, quantized_decomposed_dequantize_per_tensor_default_1100, quantized_decomposed_dequantize_per_tensor_default_1103, quantized_decomposed_dequantize_per_tensor_default_1106, quantized_decomposed_dequantize_per_tensor_default_1109, quantized_decomposed_dequantize_per_tensor_default_1112]);  quantized_decomposed_dequantize_per_tensor_default_1079 = quantized_decomposed_dequantize_per_tensor_default_1082 = quantized_decomposed_dequantize_per_tensor_default_1085 = quantized_decomposed_dequantize_per_tensor_default_1088 = quantized_decomposed_dequantize_per_tensor_default_1091 = quantized_decomposed_dequantize_per_tensor_default_1094 = quantized_decomposed_dequantize_per_tensor_default_1097 = quantized_decomposed_dequantize_per_tensor_default_1100 = quantized_decomposed_dequantize_per_tensor_default_1103 = quantized_decomposed_dequantize_per_tensor_default_1106 = quantized_decomposed_dequantize_per_tensor_default_1109 = quantized_decomposed_dequantize_per_tensor_default_1112 = None
2025-03-21T20:31:43.6032125Z             quantized_decomposed_quantize_per_tensor_default_741: "i32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_18, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_cat_default_18 = None
2025-03-21T20:31:43.6033578Z             quantized_decomposed_dequantize_per_tensor_default_1113: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_741, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_741 = None
2025-03-21T20:31:43.6034381Z             aten_view_copy_default_81: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1113, [1, 12, 128, 64]);  quantized_decomposed_dequantize_per_tensor_default_1113 = None
2025-03-21T20:31:43.6035285Z             quantized_decomposed_quantize_per_tensor_default_742: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_81, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_view_copy_default_81 = None
2025-03-21T20:31:43.6035462Z             
2025-03-21T20:31:43.6036040Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.6037204Z             quantized_decomposed_dequantize_per_tensor_default_1114: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_742, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_742 = None
2025-03-21T20:31:43.6037294Z             
2025-03-21T20:31:43.6037926Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6038745Z             aten_permute_copy_default_183: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1076, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1076 = None
2025-03-21T20:31:43.6039701Z             quantized_decomposed_quantize_per_tensor_default_743: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_183, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_permute_copy_default_183 = None
2025-03-21T20:31:43.6040846Z             quantized_decomposed_dequantize_per_tensor_default_1115: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_743, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_743 = None
2025-03-21T20:31:43.6041600Z             aten_select_copy_int_216: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1115, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1115 = None
2025-03-21T20:31:43.6042534Z             quantized_decomposed_quantize_per_tensor_default_744: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_216, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_select_copy_int_216 = None
2025-03-21T20:31:43.6043731Z             quantized_decomposed_dequantize_per_tensor_default_1116: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_744, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_744 = None
2025-03-21T20:31:43.6044774Z             aten_select_copy_int_217: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1116, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1116 = None
2025-03-21T20:31:43.6045694Z             quantized_decomposed_quantize_per_tensor_default_745: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_217, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_select_copy_int_217 = None
2025-03-21T20:31:43.6045788Z             
2025-03-21T20:31:43.6046733Z              # File: <eval_with_key>.50:2794 in forward, code: dequantize_per_tensor_default_898 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_898, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantize_per_tensor_default_898 = None
2025-03-21T20:31:43.6047878Z             quantized_decomposed_dequantize_per_tensor_default_1117: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_745, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_745 = None
2025-03-21T20:31:43.6048014Z             
2025-03-21T20:31:43.6048658Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6049552Z             aten_permute_copy_default_184: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1075, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1075 = None
2025-03-21T20:31:43.6050497Z             quantized_decomposed_quantize_per_tensor_default_746: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_184, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_permute_copy_default_184 = None
2025-03-21T20:31:43.6051657Z             quantized_decomposed_dequantize_per_tensor_default_1118: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_746, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_746 = None
2025-03-21T20:31:43.6052402Z             aten_select_copy_int_218: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1118, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1118 = None
2025-03-21T20:31:43.6053307Z             quantized_decomposed_quantize_per_tensor_default_747: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_218, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_select_copy_int_218 = None
2025-03-21T20:31:43.6054456Z             quantized_decomposed_dequantize_per_tensor_default_1119: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_747, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_747 = None
2025-03-21T20:31:43.6055240Z             aten_select_copy_int_219: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1119, 0, 1);  quantized_decomposed_dequantize_per_tensor_default_1119 = None
2025-03-21T20:31:43.6056149Z             quantized_decomposed_quantize_per_tensor_default_748: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_219, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_select_copy_int_219 = None
2025-03-21T20:31:43.6056250Z             
2025-03-21T20:31:43.6057205Z              # File: <eval_with_key>.50:2803 in forward, code: dequantize_per_tensor_default_901 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_901, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantize_per_tensor_default_901 = None
2025-03-21T20:31:43.6058360Z             quantized_decomposed_dequantize_per_tensor_default_1120: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_748, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_748 = None
2025-03-21T20:31:43.6058450Z             
2025-03-21T20:31:43.6059097Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6059897Z             aten_permute_copy_default_185: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1074, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1074 = None
2025-03-21T20:31:43.6060876Z             quantized_decomposed_quantize_per_tensor_default_749: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_185, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_permute_copy_default_185 = None
2025-03-21T20:31:43.6062021Z             quantized_decomposed_dequantize_per_tensor_default_1121: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_749, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_749 = None
2025-03-21T20:31:43.6062777Z             aten_select_copy_int_220: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1121, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1121 = None
2025-03-21T20:31:43.6063683Z             quantized_decomposed_quantize_per_tensor_default_750: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_220, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_select_copy_int_220 = None
2025-03-21T20:31:43.6064831Z             quantized_decomposed_dequantize_per_tensor_default_1122: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_750, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_750 = None
2025-03-21T20:31:43.6072576Z             aten_select_copy_int_221: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1122, 0, 2);  quantized_decomposed_dequantize_per_tensor_default_1122 = None
2025-03-21T20:31:43.6074125Z             quantized_decomposed_quantize_per_tensor_default_751: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_221, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_select_copy_int_221 = None
2025-03-21T20:31:43.6074395Z             
2025-03-21T20:31:43.6075942Z              # File: <eval_with_key>.50:2812 in forward, code: dequantize_per_tensor_default_904 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_904, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantize_per_tensor_default_904 = None
2025-03-21T20:31:43.6077899Z             quantized_decomposed_dequantize_per_tensor_default_1123: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_751, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_751 = None
2025-03-21T20:31:43.6078044Z             
2025-03-21T20:31:43.6079108Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6080475Z             aten_permute_copy_default_186: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1073, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1073 = None
2025-03-21T20:31:43.6082004Z             quantized_decomposed_quantize_per_tensor_default_752: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_186, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_permute_copy_default_186 = None
2025-03-21T20:31:43.6083745Z             quantized_decomposed_dequantize_per_tensor_default_1124: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_752, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_752 = None
2025-03-21T20:31:43.6085065Z             aten_select_copy_int_222: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1124, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1124 = None
2025-03-21T20:31:43.6086563Z             quantized_decomposed_quantize_per_tensor_default_753: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_222, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_select_copy_int_222 = None
2025-03-21T20:31:43.6088557Z             quantized_decomposed_dequantize_per_tensor_default_1125: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_753, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_753 = None
2025-03-21T20:31:43.6089884Z             aten_select_copy_int_223: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1125, 0, 3);  quantized_decomposed_dequantize_per_tensor_default_1125 = None
2025-03-21T20:31:43.6091382Z             quantized_decomposed_quantize_per_tensor_default_754: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_223, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_select_copy_int_223 = None
2025-03-21T20:31:43.6091541Z             
2025-03-21T20:31:43.6093048Z              # File: <eval_with_key>.50:2821 in forward, code: dequantize_per_tensor_default_907 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_907, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantize_per_tensor_default_907 = None
2025-03-21T20:31:43.6095056Z             quantized_decomposed_dequantize_per_tensor_default_1126: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_754, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_754 = None
2025-03-21T20:31:43.6095265Z             
2025-03-21T20:31:43.6096312Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6097584Z             aten_permute_copy_default_187: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1072, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1072 = None
2025-03-21T20:31:43.6098893Z             quantized_decomposed_quantize_per_tensor_default_755: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_187, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_permute_copy_default_187 = None
2025-03-21T20:31:43.6104177Z             quantized_decomposed_dequantize_per_tensor_default_1127: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_755, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_755 = None
2025-03-21T20:31:43.6105728Z             aten_select_copy_int_224: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1127, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1127 = None
2025-03-21T20:31:43.6107556Z             quantized_decomposed_quantize_per_tensor_default_756: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_224, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_select_copy_int_224 = None
2025-03-21T20:31:43.6110032Z             quantized_decomposed_dequantize_per_tensor_default_1128: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_756, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_756 = None
2025-03-21T20:31:43.6111514Z             aten_select_copy_int_225: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1128, 0, 4);  quantized_decomposed_dequantize_per_tensor_default_1128 = None
2025-03-21T20:31:43.6113284Z             quantized_decomposed_quantize_per_tensor_default_757: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_225, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_select_copy_int_225 = None
2025-03-21T20:31:43.6113453Z             
2025-03-21T20:31:43.6115296Z              # File: <eval_with_key>.50:2830 in forward, code: dequantize_per_tensor_default_910 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_910, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantize_per_tensor_default_910 = None
2025-03-21T20:31:43.6117688Z             quantized_decomposed_dequantize_per_tensor_default_1129: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_757, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_757 = None
2025-03-21T20:31:43.6117846Z             
2025-03-21T20:31:43.6119165Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6120942Z             aten_permute_copy_default_188: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1071, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1071 = None
2025-03-21T20:31:43.6122984Z             quantized_decomposed_quantize_per_tensor_default_758: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_188, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_permute_copy_default_188 = None
2025-03-21T20:31:43.6125178Z             quantized_decomposed_dequantize_per_tensor_default_1130: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_758, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_758 = None
2025-03-21T20:31:43.6126366Z             aten_select_copy_int_226: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1130, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1130 = None
2025-03-21T20:31:43.6127842Z             quantized_decomposed_quantize_per_tensor_default_759: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_226, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_select_copy_int_226 = None
2025-03-21T20:31:43.6129054Z             quantized_decomposed_dequantize_per_tensor_default_1131: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_759, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_759 = None
2025-03-21T20:31:43.6129901Z             aten_select_copy_int_227: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1131, 0, 5);  quantized_decomposed_dequantize_per_tensor_default_1131 = None
2025-03-21T20:31:43.6130853Z             quantized_decomposed_quantize_per_tensor_default_760: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_227, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_select_copy_int_227 = None
2025-03-21T20:31:43.6130942Z             
2025-03-21T20:31:43.6131872Z              # File: <eval_with_key>.50:2839 in forward, code: dequantize_per_tensor_default_913 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_913, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantize_per_tensor_default_913 = None
2025-03-21T20:31:43.6133290Z             quantized_decomposed_dequantize_per_tensor_default_1132: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_760, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_760 = None
2025-03-21T20:31:43.6133399Z             
2025-03-21T20:31:43.6134039Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6134855Z             aten_permute_copy_default_189: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1070, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1070 = None
2025-03-21T20:31:43.6135793Z             quantized_decomposed_quantize_per_tensor_default_761: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_189, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_permute_copy_default_189 = None
2025-03-21T20:31:43.6137020Z             quantized_decomposed_dequantize_per_tensor_default_1133: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_761, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_761 = None
2025-03-21T20:31:43.6137795Z             aten_select_copy_int_228: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1133, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1133 = None
2025-03-21T20:31:43.6138740Z             quantized_decomposed_quantize_per_tensor_default_762: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_228, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_select_copy_int_228 = None
2025-03-21T20:31:43.6139887Z             quantized_decomposed_dequantize_per_tensor_default_1134: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_762, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_762 = None
2025-03-21T20:31:43.6140636Z             aten_select_copy_int_229: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1134, 0, 6);  quantized_decomposed_dequantize_per_tensor_default_1134 = None
2025-03-21T20:31:43.6141537Z             quantized_decomposed_quantize_per_tensor_default_763: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_229, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_select_copy_int_229 = None
2025-03-21T20:31:43.6141627Z             
2025-03-21T20:31:43.6142615Z              # File: <eval_with_key>.50:2848 in forward, code: dequantize_per_tensor_default_916 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_916, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantize_per_tensor_default_916 = None
2025-03-21T20:31:43.6143768Z             quantized_decomposed_dequantize_per_tensor_default_1135: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_763, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_763 = None
2025-03-21T20:31:43.6143864Z             
2025-03-21T20:31:43.6144500Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6145301Z             aten_permute_copy_default_190: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1069, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1069 = None
2025-03-21T20:31:43.6146397Z             quantized_decomposed_quantize_per_tensor_default_764: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_190, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_permute_copy_default_190 = None
2025-03-21T20:31:43.6147557Z             quantized_decomposed_dequantize_per_tensor_default_1136: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_764, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_764 = None
2025-03-21T20:31:43.6148296Z             aten_select_copy_int_230: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1136, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1136 = None
2025-03-21T20:31:43.6149233Z             quantized_decomposed_quantize_per_tensor_default_765: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_230, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_select_copy_int_230 = None
2025-03-21T20:31:43.6150404Z             quantized_decomposed_dequantize_per_tensor_default_1137: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_765, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_765 = None
2025-03-21T20:31:43.6151174Z             aten_select_copy_int_231: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1137, 0, 7);  quantized_decomposed_dequantize_per_tensor_default_1137 = None
2025-03-21T20:31:43.6152066Z             quantized_decomposed_quantize_per_tensor_default_766: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_231, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_select_copy_int_231 = None
2025-03-21T20:31:43.6152165Z             
2025-03-21T20:31:43.6153096Z              # File: <eval_with_key>.50:2857 in forward, code: dequantize_per_tensor_default_919 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_919, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantize_per_tensor_default_919 = None
2025-03-21T20:31:43.6154260Z             quantized_decomposed_dequantize_per_tensor_default_1138: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_766, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_766 = None
2025-03-21T20:31:43.6154379Z             
2025-03-21T20:31:43.6155024Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6155826Z             aten_permute_copy_default_191: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1068, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1068 = None
2025-03-21T20:31:43.6156777Z             quantized_decomposed_quantize_per_tensor_default_767: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_191, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_permute_copy_default_191 = None
2025-03-21T20:31:43.6157922Z             quantized_decomposed_dequantize_per_tensor_default_1139: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_767, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_767 = None
2025-03-21T20:31:43.6158672Z             aten_select_copy_int_232: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1139, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1139 = None
2025-03-21T20:31:43.6159568Z             quantized_decomposed_quantize_per_tensor_default_768: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_232, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_select_copy_int_232 = None
2025-03-21T20:31:43.6160756Z             quantized_decomposed_dequantize_per_tensor_default_1140: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_768, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_768 = None
2025-03-21T20:31:43.6161517Z             aten_select_copy_int_233: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1140, 0, 8);  quantized_decomposed_dequantize_per_tensor_default_1140 = None
2025-03-21T20:31:43.6162412Z             quantized_decomposed_quantize_per_tensor_default_769: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_233, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_select_copy_int_233 = None
2025-03-21T20:31:43.6162523Z             
2025-03-21T20:31:43.6163466Z              # File: <eval_with_key>.50:2866 in forward, code: dequantize_per_tensor_default_922 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_922, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantize_per_tensor_default_922 = None
2025-03-21T20:31:43.6164609Z             quantized_decomposed_dequantize_per_tensor_default_1141: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_769, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_769 = None
2025-03-21T20:31:43.6164702Z             
2025-03-21T20:31:43.6165338Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6166146Z             aten_permute_copy_default_192: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1067, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1067 = None
2025-03-21T20:31:43.6167114Z             quantized_decomposed_quantize_per_tensor_default_770: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_192, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_permute_copy_default_192 = None
2025-03-21T20:31:43.6168264Z             quantized_decomposed_dequantize_per_tensor_default_1142: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_770, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_770 = None
2025-03-21T20:31:43.6169005Z             aten_select_copy_int_234: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1142, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1142 = None
2025-03-21T20:31:43.6169978Z             quantized_decomposed_quantize_per_tensor_default_771: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_234, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_select_copy_int_234 = None
2025-03-21T20:31:43.6171129Z             quantized_decomposed_dequantize_per_tensor_default_1143: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_771, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_771 = None
2025-03-21T20:31:43.6171865Z             aten_select_copy_int_235: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1143, 0, 9);  quantized_decomposed_dequantize_per_tensor_default_1143 = None
2025-03-21T20:31:43.6172792Z             quantized_decomposed_quantize_per_tensor_default_772: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_235, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_select_copy_int_235 = None
2025-03-21T20:31:43.6172902Z             
2025-03-21T20:31:43.6173843Z              # File: <eval_with_key>.50:2875 in forward, code: dequantize_per_tensor_default_925 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_925, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantize_per_tensor_default_925 = None
2025-03-21T20:31:43.6175008Z             quantized_decomposed_dequantize_per_tensor_default_1144: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_772, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_772 = None
2025-03-21T20:31:43.6175105Z             
2025-03-21T20:31:43.6175736Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6176546Z             aten_permute_copy_default_193: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1066, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1066 = None
2025-03-21T20:31:43.6177479Z             quantized_decomposed_quantize_per_tensor_default_773: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_193, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_permute_copy_default_193 = None
2025-03-21T20:31:43.6178633Z             quantized_decomposed_dequantize_per_tensor_default_1145: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_773, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_773 = None
2025-03-21T20:31:43.6179403Z             aten_select_copy_int_236: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1145, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1145 = None
2025-03-21T20:31:43.6180305Z             quantized_decomposed_quantize_per_tensor_default_774: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_236, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_select_copy_int_236 = None
2025-03-21T20:31:43.6181449Z             quantized_decomposed_dequantize_per_tensor_default_1146: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_774, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_774 = None
2025-03-21T20:31:43.6182202Z             aten_select_copy_int_237: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1146, 0, 10);  quantized_decomposed_dequantize_per_tensor_default_1146 = None
2025-03-21T20:31:43.6183099Z             quantized_decomposed_quantize_per_tensor_default_775: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_237, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_select_copy_int_237 = None
2025-03-21T20:31:43.6183202Z             
2025-03-21T20:31:43.6184136Z              # File: <eval_with_key>.50:2884 in forward, code: dequantize_per_tensor_default_928 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_928, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantize_per_tensor_default_928 = None
2025-03-21T20:31:43.6185317Z             quantized_decomposed_dequantize_per_tensor_default_1147: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_775, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_775 = None
2025-03-21T20:31:43.6185432Z             
2025-03-21T20:31:43.6186084Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6186909Z             aten_permute_copy_default_194: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1065, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1065 = None
2025-03-21T20:31:43.6187862Z             quantized_decomposed_quantize_per_tensor_default_776: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_194, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_permute_copy_default_194 = None
2025-03-21T20:31:43.6189012Z             quantized_decomposed_dequantize_per_tensor_default_1148: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_776, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_776 = None
2025-03-21T20:31:43.6189761Z             aten_select_copy_int_238: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1148, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1148 = None
2025-03-21T20:31:43.6190652Z             quantized_decomposed_quantize_per_tensor_default_777: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_238, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_select_copy_int_238 = None
2025-03-21T20:31:43.6191844Z             quantized_decomposed_dequantize_per_tensor_default_1149: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_777, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_777 = None
2025-03-21T20:31:43.6192577Z             aten_select_copy_int_239: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1149, 0, 11);  quantized_decomposed_dequantize_per_tensor_default_1149 = None
2025-03-21T20:31:43.6193478Z             quantized_decomposed_quantize_per_tensor_default_778: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_239, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_select_copy_int_239 = None
2025-03-21T20:31:43.6193565Z             
2025-03-21T20:31:43.6194511Z              # File: <eval_with_key>.50:2893 in forward, code: dequantize_per_tensor_default_931 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_931, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantize_per_tensor_default_931 = None
2025-03-21T20:31:43.6195650Z             quantized_decomposed_dequantize_per_tensor_default_1150: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_778, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_778 = None
2025-03-21T20:31:43.6195748Z             
2025-03-21T20:31:43.6196378Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6201916Z             aten_cat_default_19: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_aten_cat_default([quantized_decomposed_dequantize_per_tensor_default_1117, quantized_decomposed_dequantize_per_tensor_default_1120, quantized_decomposed_dequantize_per_tensor_default_1123, quantized_decomposed_dequantize_per_tensor_default_1126, quantized_decomposed_dequantize_per_tensor_default_1129, quantized_decomposed_dequantize_per_tensor_default_1132, quantized_decomposed_dequantize_per_tensor_default_1135, quantized_decomposed_dequantize_per_tensor_default_1138, quantized_decomposed_dequantize_per_tensor_default_1141, quantized_decomposed_dequantize_per_tensor_default_1144, quantized_decomposed_dequantize_per_tensor_default_1147, quantized_decomposed_dequantize_per_tensor_default_1150]);  quantized_decomposed_dequantize_per_tensor_default_1117 = quantized_decomposed_dequantize_per_tensor_default_1120 = quantized_decomposed_dequantize_per_tensor_default_1123 = quantized_decomposed_dequantize_per_tensor_default_1126 = quantized_decomposed_dequantize_per_tensor_default_1129 = quantized_decomposed_dequantize_per_tensor_default_1132 = quantized_decomposed_dequantize_per_tensor_default_1135 = quantized_decomposed_dequantize_per_tensor_default_1138 = quantized_decomposed_dequantize_per_tensor_default_1141 = quantized_decomposed_dequantize_per_tensor_default_1144 = quantized_decomposed_dequantize_per_tensor_default_1147 = quantized_decomposed_dequantize_per_tensor_default_1150 = None
2025-03-21T20:31:43.6202829Z             quantized_decomposed_quantize_per_tensor_default_779: "i32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_19, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_cat_default_19 = None
2025-03-21T20:31:43.6203983Z             quantized_decomposed_dequantize_per_tensor_default_1151: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_779, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_779 = None
2025-03-21T20:31:43.6204817Z             aten_view_copy_default_82: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1151, [1, 12, 128, 64]);  quantized_decomposed_dequantize_per_tensor_default_1151 = None
2025-03-21T20:31:43.6205731Z             quantized_decomposed_quantize_per_tensor_default_780: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_82, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  aten_view_copy_default_82 = None
2025-03-21T20:31:43.6205817Z             
2025-03-21T20:31:43.6206757Z              # File: <eval_with_key>.50:2899 in forward, code: dequantize_per_tensor_default_933 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_933, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantize_per_tensor_default_933 = None
2025-03-21T20:31:43.6207907Z             quantized_decomposed_dequantize_per_tensor_default_1152: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_780, 0.00012666585098486394, 35736, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_780 = None
2025-03-21T20:31:43.6208005Z             
2025-03-21T20:31:43.6208937Z              # File: <eval_with_key>.50:2900 in forward, code: quantize_per_tensor_default_934 = torch.ops.quantized_decomposed.quantize_per_tensor.default(dequantize_per_tensor_default_933, 0.00013814217527396977, 0, -32767, 32767, torch.int16);  dequantize_per_tensor_default_933 = None
2025-03-21T20:31:43.6210205Z             quantized_decomposed_quantize_per_tensor_default_781: "i16[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_1152, 0.00013814217527396977, 0, -32767, 32767, torch.int16);  quantized_decomposed_dequantize_per_tensor_default_1152 = None
2025-03-21T20:31:43.6210321Z             
2025-03-21T20:31:43.6210799Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:163 in forward, code: y = attn_weight @ v
2025-03-21T20:31:43.6211969Z             quantized_decomposed_dequantize_per_tensor_default_1153: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_781, 0.00013814217527396977, 0, -32767, 32767, torch.int16);  quantized_decomposed_quantize_per_tensor_default_781 = None
2025-03-21T20:31:43.6212071Z             
2025-03-21T20:31:43.6212558Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:157 in forward, code: attn_mask = mask[input_pos]
2025-03-21T20:31:43.6213355Z             aten_index_tensor_6: "f32[1, 128]" = executorch_exir_dialects_edge__ops_aten_index_Tensor(quantized_decomposed_dequantize_per_tensor_default_127, [attn_options_input_pos]);  quantized_decomposed_dequantize_per_tensor_default_127 = None
2025-03-21T20:31:43.6214217Z             quantized_decomposed_quantize_per_tensor_default_782: "i32[1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_tensor_6, 0.0038910505827516317, 65535, 0, 65535, torch.int32);  aten_index_tensor_6 = None
2025-03-21T20:31:43.6214305Z             
2025-03-21T20:31:43.6214795Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:161 in forward, code: attn_weight += attn_mask
2025-03-21T20:31:43.6215939Z             quantized_decomposed_dequantize_per_tensor_default_1154: "f32[1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_782, 0.0038910505827516317, 65535, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_782 = None
2025-03-21T20:31:43.6216068Z             
2025-03-21T20:31:43.6216639Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.6217452Z             aten_permute_copy_default_195: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1114, [0, 1, 3, 2]);  quantized_decomposed_dequantize_per_tensor_default_1114 = None
2025-03-21T20:31:43.6218394Z             quantized_decomposed_quantize_per_tensor_default_783: "i32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_195, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  aten_permute_copy_default_195 = None
2025-03-21T20:31:43.6218496Z             
2025-03-21T20:31:43.6219425Z              # File: <eval_with_key>.50:2907 in forward, code: dequantize_per_tensor_default_936 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_936, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantize_per_tensor_default_936 = None
2025-03-21T20:31:43.6220588Z             quantized_decomposed_dequantize_per_tensor_default_1155: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_783, 0.00040260335663333535, 31896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_783 = None
2025-03-21T20:31:43.6220675Z             
2025-03-21T20:31:43.6221611Z              # File: <eval_with_key>.50:2908 in forward, code: quantize_per_tensor_default_937 = torch.ops.quantized_decomposed.quantize_per_tensor.default(dequantize_per_tensor_default_936, 0.0004133212787564844, 0, -32767, 32767, torch.int16);  dequantize_per_tensor_default_936 = None
2025-03-21T20:31:43.6222790Z             quantized_decomposed_quantize_per_tensor_default_784: "i16[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_1155, 0.0004133212787564844, 0, -32767, 32767, torch.int16);  quantized_decomposed_dequantize_per_tensor_default_1155 = None
2025-03-21T20:31:43.6222916Z             
2025-03-21T20:31:43.6223484Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.6224664Z             quantized_decomposed_dequantize_per_tensor_default_1156: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_784, 0.0004133212787564844, 0, -32767, 32767, torch.int16);  quantized_decomposed_quantize_per_tensor_default_784 = None
2025-03-21T20:31:43.6225449Z             aten_expand_copy_default_16: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_1050, [1, 12, 1, 64]);  quantized_decomposed_dequantize_per_tensor_default_1050 = None
2025-03-21T20:31:43.6226010Z             aten_view_copy_default_83: "f32[12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_16, [12, 1, 64]);  aten_expand_copy_default_16 = None
2025-03-21T20:31:43.6226801Z             aten_expand_copy_default_17: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_1156, [1, 12, 64, 128]);  quantized_decomposed_dequantize_per_tensor_default_1156 = None
2025-03-21T20:31:43.6227369Z             aten_view_copy_default_84: "f32[12, 64, 128]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_17, [12, 64, 128]);  aten_expand_copy_default_17 = None
2025-03-21T20:31:43.6228039Z             aten_bmm_default_8: "f32[12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_bmm_default(aten_view_copy_default_83, aten_view_copy_default_84);  aten_view_copy_default_83 = aten_view_copy_default_84 = None
2025-03-21T20:31:43.6228559Z             aten_view_copy_default_85: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_bmm_default_8, [1, 12, 1, 128]);  aten_bmm_default_8 = None
2025-03-21T20:31:43.6229459Z             quantized_decomposed_quantize_per_tensor_default_785: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_85, 0.0038901909720152617, 41062, 0, 65535, torch.int32);  aten_view_copy_default_85 = None
2025-03-21T20:31:43.6230608Z             quantized_decomposed_dequantize_per_tensor_default_1157: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_785, 0.0038901909720152617, 41062, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_785 = None
2025-03-21T20:31:43.6231463Z             quantized_decomposed_dequantize_per_tensor_default_1158: "f32[1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param153, 1.9073777366429567e-06, 0, 0, 65535, torch.int32);  b__frozen_param153 = None
2025-03-21T20:31:43.6232779Z             aten_mul_tensor_70: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1157, quantized_decomposed_dequantize_per_tensor_default_1158);  quantized_decomposed_dequantize_per_tensor_default_1157 = quantized_decomposed_dequantize_per_tensor_default_1158 = None
2025-03-21T20:31:43.6233643Z             quantized_decomposed_quantize_per_tensor_default_786: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_70, 0.0004862738715019077, 41062, 0, 65535, torch.int32);  aten_mul_tensor_70 = None
2025-03-21T20:31:43.6233799Z             
2025-03-21T20:31:43.6234315Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:161 in forward, code: attn_weight += attn_mask
2025-03-21T20:31:43.6235474Z             quantized_decomposed_dequantize_per_tensor_default_1159: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_786, 0.0004862738715019077, 41062, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_786 = None
2025-03-21T20:31:43.6236701Z             aten_add_tensor_22: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_1159, quantized_decomposed_dequantize_per_tensor_default_1154);  quantized_decomposed_dequantize_per_tensor_default_1159 = quantized_decomposed_dequantize_per_tensor_default_1154 = None
2025-03-21T20:31:43.6237586Z             quantized_decomposed_quantize_per_tensor_default_787: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_22, 0.004292679484933615, 62763, 0, 65535, torch.int32);  aten_add_tensor_22 = None
2025-03-21T20:31:43.6237690Z             
2025-03-21T20:31:43.6238256Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:162 in forward, code: attn_weight = torch.softmax(attn_weight, dim=-1)
2025-03-21T20:31:43.6239407Z             quantized_decomposed_dequantize_per_tensor_default_1160: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_787, 0.004292679484933615, 62763, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_787 = None
2025-03-21T20:31:43.6240226Z             aten__softmax_default_4: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten__softmax_default(quantized_decomposed_dequantize_per_tensor_default_1160, -1, False);  quantized_decomposed_dequantize_per_tensor_default_1160 = None
2025-03-21T20:31:43.6241114Z             quantized_decomposed_quantize_per_tensor_default_788: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten__softmax_default_4, 1.5259021893143654e-05, 0, 0, 65535, torch.int32);  aten__softmax_default_4 = None
2025-03-21T20:31:43.6241201Z             
2025-03-21T20:31:43.6241671Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:163 in forward, code: y = attn_weight @ v
2025-03-21T20:31:43.6242800Z             quantized_decomposed_dequantize_per_tensor_default_1161: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_788, 1.5259021893143654e-05, 0, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_788 = None
2025-03-21T20:31:43.6243604Z             aten_expand_copy_default_18: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_1161, [1, 12, 1, 128]);  quantized_decomposed_dequantize_per_tensor_default_1161 = None
2025-03-21T20:31:43.6244160Z             aten_view_copy_default_86: "f32[12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_18, [12, 1, 128]);  aten_expand_copy_default_18 = None
2025-03-21T20:31:43.6244967Z             aten_expand_copy_default_19: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_1153, [1, 12, 128, 64]);  quantized_decomposed_dequantize_per_tensor_default_1153 = None
2025-03-21T20:31:43.6245525Z             aten_view_copy_default_87: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_19, [12, 128, 64]);  aten_expand_copy_default_19 = None
2025-03-21T20:31:43.6246197Z             aten_bmm_default_9: "f32[12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_bmm_default(aten_view_copy_default_86, aten_view_copy_default_87);  aten_view_copy_default_86 = aten_view_copy_default_87 = None
2025-03-21T20:31:43.6246720Z             aten_view_copy_default_88: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_bmm_default_9, [1, 12, 1, 64]);  aten_bmm_default_9 = None
2025-03-21T20:31:43.6247938Z             quantized_decomposed_quantize_per_tensor_default_789: "i32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_88, 7.019092299742624e-05, 30970, 0, 65535, torch.int32);  aten_view_copy_default_88 = None
2025-03-21T20:31:43.6248043Z             
2025-03-21T20:31:43.6248687Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:165 in forward, code: return y.transpose(1, 2).contiguous().view(bsz, seqlen, self.dim)
2025-03-21T20:31:43.6249899Z             quantized_decomposed_dequantize_per_tensor_default_1162: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_789, 7.019092299742624e-05, 30970, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_789 = None
2025-03-21T20:31:43.6250712Z             aten_permute_copy_default_196: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1162, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1162 = None
2025-03-21T20:31:43.6251637Z             quantized_decomposed_quantize_per_tensor_default_790: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_196, 7.019092299742624e-05, 30970, 0, 65535, torch.int32);  aten_permute_copy_default_196 = None
2025-03-21T20:31:43.6252817Z             quantized_decomposed_dequantize_per_tensor_default_1163: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_790, 7.019092299742624e-05, 30970, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_790 = None
2025-03-21T20:31:43.6253584Z             aten_view_copy_default_89: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1163, [1, 1, 768]);  quantized_decomposed_dequantize_per_tensor_default_1163 = None
2025-03-21T20:31:43.6254497Z             quantized_decomposed_quantize_per_tensor_default_791: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_89, 7.019092299742624e-05, 30970, 0, 65535, torch.int32);  aten_view_copy_default_89 = None
2025-03-21T20:31:43.6254590Z             
2025-03-21T20:31:43.6255127Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.6256260Z             quantized_decomposed_dequantize_per_tensor_default_1164: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_791, 7.019092299742624e-05, 30970, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_791 = None
2025-03-21T20:31:43.6257077Z             aten_unsqueeze_copy_default_51: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1164, -1);  quantized_decomposed_dequantize_per_tensor_default_1164 = None
2025-03-21T20:31:43.6258039Z             quantized_decomposed_quantize_per_tensor_default_792: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_51, 7.019092299742624e-05, 30970, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_51 = None
2025-03-21T20:31:43.6258168Z             
2025-03-21T20:31:43.6258573Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.6259722Z             quantized_decomposed_dequantize_per_tensor_default_1165: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_792, 7.019092299742624e-05, 30970, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_792 = None
2025-03-21T20:31:43.6260546Z             aten_permute_copy_default_197: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1165, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1165 = None
2025-03-21T20:31:43.6261483Z             quantized_decomposed_quantize_per_tensor_default_793: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_197, 7.019092299742624e-05, 30970, 0, 65535, torch.int32);  aten_permute_copy_default_197 = None
2025-03-21T20:31:43.6261577Z             
2025-03-21T20:31:43.6261957Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.6263094Z             quantized_decomposed_dequantize_per_tensor_default_1166: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_793, 7.019092299742624e-05, 30970, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_793 = None
2025-03-21T20:31:43.6264411Z             aten_convolution_default_31: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_1166, quantized_decomposed_dequantize_per_tensor_default_41, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_1166 = quantized_decomposed_dequantize_per_tensor_default_41 = None
2025-03-21T20:31:43.6265327Z             quantized_decomposed_quantize_per_tensor_default_794: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_31, 5.287839303491637e-05, 36634, 0, 65535, torch.int32);  aten_convolution_default_31 = None
2025-03-21T20:31:43.6265428Z             
2025-03-21T20:31:43.6265849Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.6267001Z             quantized_decomposed_dequantize_per_tensor_default_1167: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_794, 5.287839303491637e-05, 36634, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_794 = None
2025-03-21T20:31:43.6267799Z             aten_permute_copy_default_198: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1167, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1167 = None
2025-03-21T20:31:43.6268739Z             quantized_decomposed_quantize_per_tensor_default_795: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_198, 5.287839303491637e-05, 36634, 0, 65535, torch.int32);  aten_permute_copy_default_198 = None
2025-03-21T20:31:43.6268828Z             
2025-03-21T20:31:43.6269378Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.6270540Z             quantized_decomposed_dequantize_per_tensor_default_1168: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_795, 5.287839303491637e-05, 36634, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_795 = None
2025-03-21T20:31:43.6271334Z             aten_squeeze_copy_dims_51: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_1168, [-1]);  quantized_decomposed_dequantize_per_tensor_default_1168 = None
2025-03-21T20:31:43.6272248Z             quantized_decomposed_quantize_per_tensor_default_796: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_51, 5.287839303491637e-05, 36634, 0, 65535, torch.int32);  aten_squeeze_copy_dims_51 = None
2025-03-21T20:31:43.6272351Z             
2025-03-21T20:31:43.6272719Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:111 in forward, code: h = x + h
2025-03-21T20:31:43.6273869Z             quantized_decomposed_dequantize_per_tensor_default_1169: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_796, 5.287839303491637e-05, 36634, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_796 = None
2025-03-21T20:31:43.6274985Z             aten_add_tensor_23: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_989, quantized_decomposed_dequantize_per_tensor_default_1169);  quantized_decomposed_dequantize_per_tensor_default_989 = quantized_decomposed_dequantize_per_tensor_default_1169 = None
2025-03-21T20:31:43.6275844Z             quantized_decomposed_quantize_per_tensor_default_797: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_23, 0.0024935125838965178, 6282, 0, 65535, torch.int32);  aten_add_tensor_23 = None
2025-03-21T20:31:43.6275956Z             
2025-03-21T20:31:43.6276478Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:115 in forward, code: out = h + self.feed_forward(self.ffn_norm(h))
2025-03-21T20:31:43.6277385Z             quantized_decomposed_dequantize_per_tensor_default_1170: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_797, 0.0024935125838965178, 6282, 0, 65535, torch.int32)
2025-03-21T20:31:43.6278527Z             quantized_decomposed_dequantize_per_tensor_default_1171: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_797, 0.0024935125838965178, 6282, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_797 = None
2025-03-21T20:31:43.6279038Z             aten_pow_tensor_scalar_9: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_pow_Tensor_Scalar(quantized_decomposed_dequantize_per_tensor_default_1171, 2)
2025-03-21T20:31:43.6279502Z             aten_mean_dim_9: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_mean_dim(aten_pow_tensor_scalar_9, [2], True);  aten_pow_tensor_scalar_9 = None
2025-03-21T20:31:43.6279938Z             aten_add_scalar_9: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_add_Scalar(aten_mean_dim_9, 9.999999747378752e-06);  aten_mean_dim_9 = None
2025-03-21T20:31:43.6280368Z             aten_rsqrt_default_9: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_rsqrt_default(aten_add_scalar_9);  aten_add_scalar_9 = None
2025-03-21T20:31:43.6281208Z             aten_mul_tensor_71: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1171, aten_rsqrt_default_9);  quantized_decomposed_dequantize_per_tensor_default_1171 = aten_rsqrt_default_9 = None
2025-03-21T20:31:43.6282045Z             aten_mul_tensor_72: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(aten_mul_tensor_71, quantized_decomposed_dequantize_per_tensor_default_42);  aten_mul_tensor_71 = quantized_decomposed_dequantize_per_tensor_default_42 = None
2025-03-21T20:31:43.6282914Z             quantized_decomposed_quantize_per_tensor_default_798: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_72, 0.0003157795872539282, 17787, 0, 65535, torch.int32);  aten_mul_tensor_72 = None
2025-03-21T20:31:43.6283011Z             
2025-03-21T20:31:43.6283551Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.6284484Z             quantized_decomposed_dequantize_per_tensor_default_1172: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_798, 0.0003157795872539282, 17787, 0, 65535, torch.int32)
2025-03-21T20:31:43.6285623Z             quantized_decomposed_dequantize_per_tensor_default_1173: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_798, 0.0003157795872539282, 17787, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_798 = None
2025-03-21T20:31:43.6286443Z             aten_unsqueeze_copy_default_52: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1173, -1);  quantized_decomposed_dequantize_per_tensor_default_1173 = None
2025-03-21T20:31:43.6287381Z             quantized_decomposed_quantize_per_tensor_default_799: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_52, 0.0003157795872539282, 17787, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_52 = None
2025-03-21T20:31:43.6287517Z             
2025-03-21T20:31:43.6287924Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.6289078Z             quantized_decomposed_dequantize_per_tensor_default_1174: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_799, 0.0003157795872539282, 17787, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_799 = None
2025-03-21T20:31:43.6289953Z             aten_permute_copy_default_199: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1174, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1174 = None
2025-03-21T20:31:43.6290903Z             quantized_decomposed_quantize_per_tensor_default_800: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_199, 0.0003157795872539282, 17787, 0, 65535, torch.int32);  aten_permute_copy_default_199 = None
2025-03-21T20:31:43.6290998Z             
2025-03-21T20:31:43.6291379Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.6292521Z             quantized_decomposed_dequantize_per_tensor_default_1175: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_800, 0.0003157795872539282, 17787, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_800 = None
2025-03-21T20:31:43.6293861Z             aten_convolution_default_32: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_1175, quantized_decomposed_dequantize_per_tensor_default_43, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_1175 = quantized_decomposed_dequantize_per_tensor_default_43 = None
2025-03-21T20:31:43.6294831Z             quantized_decomposed_quantize_per_tensor_default_801: "i32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_32, 0.00021449536143336445, 27755, 0, 65535, torch.int32);  aten_convolution_default_32 = None
2025-03-21T20:31:43.6294929Z             
2025-03-21T20:31:43.6295373Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.6296537Z             quantized_decomposed_dequantize_per_tensor_default_1176: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_801, 0.00021449536143336445, 27755, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_801 = None
2025-03-21T20:31:43.6297339Z             aten_permute_copy_default_200: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1176, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1176 = None
2025-03-21T20:31:43.6298291Z             quantized_decomposed_quantize_per_tensor_default_802: "i32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_200, 0.00021449536143336445, 27755, 0, 65535, torch.int32);  aten_permute_copy_default_200 = None
2025-03-21T20:31:43.6298378Z             
2025-03-21T20:31:43.6298925Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.6300102Z             quantized_decomposed_dequantize_per_tensor_default_1177: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_802, 0.00021449536143336445, 27755, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_802 = None
2025-03-21T20:31:43.6300873Z             aten_squeeze_copy_dims_52: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_1177, [-1]);  quantized_decomposed_dequantize_per_tensor_default_1177 = None
2025-03-21T20:31:43.6301776Z             quantized_decomposed_quantize_per_tensor_default_803: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_52, 0.00021449536143336445, 27755, 0, 65535, torch.int32);  aten_squeeze_copy_dims_52 = None
2025-03-21T20:31:43.6301877Z             
2025-03-21T20:31:43.6302387Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:36 in forward, code: return self.w2(F.silu(self.w1(x)) * self.w3(x))
2025-03-21T20:31:43.6303323Z             quantized_decomposed_dequantize_per_tensor_default_1178: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_803, 0.00021449536143336445, 27755, 0, 65535, torch.int32)
2025-03-21T20:31:43.6304465Z             quantized_decomposed_dequantize_per_tensor_default_1179: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_803, 0.00021449536143336445, 27755, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_803 = None
2025-03-21T20:31:43.6305216Z             aten_sigmoid_default_4: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_sigmoid_default(quantized_decomposed_dequantize_per_tensor_default_1179);  quantized_decomposed_dequantize_per_tensor_default_1179 = None
2025-03-21T20:31:43.6306095Z             quantized_decomposed_quantize_per_tensor_default_804: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_sigmoid_default_4, 1.52587890625e-05, 0, 0, 65535, torch.int32);  aten_sigmoid_default_4 = None
2025-03-21T20:31:43.6307233Z             quantized_decomposed_dequantize_per_tensor_default_1180: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_804, 1.52587890625e-05, 0, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_804 = None
2025-03-21T20:31:43.6308387Z             aten_mul_tensor_73: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1178, quantized_decomposed_dequantize_per_tensor_default_1180);  quantized_decomposed_dequantize_per_tensor_default_1178 = quantized_decomposed_dequantize_per_tensor_default_1180 = None
2025-03-21T20:31:43.6309256Z             quantized_decomposed_quantize_per_tensor_default_805: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_73, 0.0001278657728107646, 2178, 0, 65535, torch.int32);  aten_mul_tensor_73 = None
2025-03-21T20:31:43.6310387Z             quantized_decomposed_dequantize_per_tensor_default_1181: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_805, 0.0001278657728107646, 2178, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_805 = None
2025-03-21T20:31:43.6310491Z             
2025-03-21T20:31:43.6311007Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.6311854Z             aten_unsqueeze_copy_default_53: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1172, -1);  quantized_decomposed_dequantize_per_tensor_default_1172 = None
2025-03-21T20:31:43.6312794Z             quantized_decomposed_quantize_per_tensor_default_806: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_53, 0.0003157795872539282, 17787, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_53 = None
2025-03-21T20:31:43.6312895Z             
2025-03-21T20:31:43.6313303Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.6314458Z             quantized_decomposed_dequantize_per_tensor_default_1182: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_806, 0.0003157795872539282, 17787, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_806 = None
2025-03-21T20:31:43.6315261Z             aten_permute_copy_default_201: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1182, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1182 = None
2025-03-21T20:31:43.6316204Z             quantized_decomposed_quantize_per_tensor_default_807: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_201, 0.0003157795872539282, 17787, 0, 65535, torch.int32);  aten_permute_copy_default_201 = None
2025-03-21T20:31:43.6316290Z             
2025-03-21T20:31:43.6316665Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.6317830Z             quantized_decomposed_dequantize_per_tensor_default_1183: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_807, 0.0003157795872539282, 17787, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_807 = None
2025-03-21T20:31:43.6319208Z             aten_convolution_default_33: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_1183, quantized_decomposed_dequantize_per_tensor_default_44, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_1183 = quantized_decomposed_dequantize_per_tensor_default_44 = None
2025-03-21T20:31:43.6320158Z             quantized_decomposed_quantize_per_tensor_default_808: "i32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_33, 0.0002493332722224295, 30131, 0, 65535, torch.int32);  aten_convolution_default_33 = None
2025-03-21T20:31:43.6320260Z             
2025-03-21T20:31:43.6320681Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.6321846Z             quantized_decomposed_dequantize_per_tensor_default_1184: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_808, 0.0002493332722224295, 30131, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_808 = None
2025-03-21T20:31:43.6322650Z             aten_permute_copy_default_202: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1184, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1184 = None
2025-03-21T20:31:43.6323604Z             quantized_decomposed_quantize_per_tensor_default_809: "i32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_202, 0.0002493332722224295, 30131, 0, 65535, torch.int32);  aten_permute_copy_default_202 = None
2025-03-21T20:31:43.6323723Z             
2025-03-21T20:31:43.6324273Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.6325422Z             quantized_decomposed_dequantize_per_tensor_default_1185: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_809, 0.0002493332722224295, 30131, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_809 = None
2025-03-21T20:31:43.6326188Z             aten_squeeze_copy_dims_53: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_1185, [-1]);  quantized_decomposed_dequantize_per_tensor_default_1185 = None
2025-03-21T20:31:43.6327090Z             quantized_decomposed_quantize_per_tensor_default_810: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_53, 0.0002493332722224295, 30131, 0, 65535, torch.int32);  aten_squeeze_copy_dims_53 = None
2025-03-21T20:31:43.6327190Z             
2025-03-21T20:31:43.6327701Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:36 in forward, code: return self.w2(F.silu(self.w1(x)) * self.w3(x))
2025-03-21T20:31:43.6328859Z             quantized_decomposed_dequantize_per_tensor_default_1186: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_810, 0.0002493332722224295, 30131, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_810 = None
2025-03-21T20:31:43.6330083Z             aten_mul_tensor_74: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1181, quantized_decomposed_dequantize_per_tensor_default_1186);  quantized_decomposed_dequantize_per_tensor_default_1181 = quantized_decomposed_dequantize_per_tensor_default_1186 = None
2025-03-21T20:31:43.6330976Z             quantized_decomposed_quantize_per_tensor_default_811: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_74, 0.0006259557558223605, 32226, 0, 65535, torch.int32);  aten_mul_tensor_74 = None
2025-03-21T20:31:43.6331064Z             
2025-03-21T20:31:43.6331636Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.6332936Z             quantized_decomposed_dequantize_per_tensor_default_1187: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_811, 0.0006259557558223605, 32226, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_811 = None
2025-03-21T20:31:43.6333768Z             aten_unsqueeze_copy_default_54: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1187, -1);  quantized_decomposed_dequantize_per_tensor_default_1187 = None
2025-03-21T20:31:43.6334733Z             quantized_decomposed_quantize_per_tensor_default_812: "i32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_54, 0.0006259557558223605, 32226, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_54 = None
2025-03-21T20:31:43.6334823Z             
2025-03-21T20:31:43.6335228Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.6336457Z             quantized_decomposed_dequantize_per_tensor_default_1188: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_812, 0.0006259557558223605, 32226, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_812 = None
2025-03-21T20:31:43.6337258Z             aten_permute_copy_default_203: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1188, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1188 = None
2025-03-21T20:31:43.6338207Z             quantized_decomposed_quantize_per_tensor_default_813: "i32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_203, 0.0006259557558223605, 32226, 0, 65535, torch.int32);  aten_permute_copy_default_203 = None
2025-03-21T20:31:43.6338296Z             
2025-03-21T20:31:43.6338674Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.6339816Z             quantized_decomposed_dequantize_per_tensor_default_1189: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_813, 0.0006259557558223605, 32226, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_813 = None
2025-03-21T20:31:43.6341098Z             aten_convolution_default_34: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_1189, quantized_decomposed_dequantize_per_tensor_default_45, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_1189 = quantized_decomposed_dequantize_per_tensor_default_45 = None
2025-03-21T20:31:43.6342075Z             quantized_decomposed_quantize_per_tensor_default_814: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_34, 0.0005451498436741531, 6186, 0, 65535, torch.int32);  aten_convolution_default_34 = None
2025-03-21T20:31:43.6342193Z             
2025-03-21T20:31:43.6342613Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.6343755Z             quantized_decomposed_dequantize_per_tensor_default_1190: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_814, 0.0005451498436741531, 6186, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_814 = None
2025-03-21T20:31:43.6344593Z             aten_permute_copy_default_204: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1190, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1190 = None
2025-03-21T20:31:43.6348331Z             quantized_decomposed_quantize_per_tensor_default_815: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_204, 0.0005451498436741531, 6186, 0, 65535, torch.int32);  aten_permute_copy_default_204 = None
2025-03-21T20:31:43.6348447Z             
2025-03-21T20:31:43.6349002Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.6350289Z             quantized_decomposed_dequantize_per_tensor_default_1191: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_815, 0.0005451498436741531, 6186, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_815 = None
2025-03-21T20:31:43.6351118Z             aten_squeeze_copy_dims_54: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_1191, [-1]);  quantized_decomposed_dequantize_per_tensor_default_1191 = None
2025-03-21T20:31:43.6352054Z             quantized_decomposed_quantize_per_tensor_default_816: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_54, 0.0005451498436741531, 6186, 0, 65535, torch.int32);  aten_squeeze_copy_dims_54 = None
2025-03-21T20:31:43.6352146Z             
2025-03-21T20:31:43.6352665Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:115 in forward, code: out = h + self.feed_forward(self.ffn_norm(h))
2025-03-21T20:31:43.6353796Z             quantized_decomposed_dequantize_per_tensor_default_1192: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_816, 0.0005451498436741531, 6186, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_816 = None
2025-03-21T20:31:43.6354939Z             aten_add_tensor_24: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_1170, quantized_decomposed_dequantize_per_tensor_default_1192);  quantized_decomposed_dequantize_per_tensor_default_1170 = quantized_decomposed_dequantize_per_tensor_default_1192 = None
2025-03-21T20:31:43.6355784Z             quantized_decomposed_quantize_per_tensor_default_817: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_24, 0.0026261727325618267, 6169, 0, 65535, torch.int32);  aten_add_tensor_24 = None
2025-03-21T20:31:43.6355886Z             
2025-03-21T20:31:43.6356257Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:111 in forward, code: h = x + h
2025-03-21T20:31:43.6357208Z             quantized_decomposed_dequantize_per_tensor_default_1193: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_817, 0.0026261727325618267, 6169, 0, 65535, torch.int32)
2025-03-21T20:31:43.6357318Z             
2025-03-21T20:31:43.6357894Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:108 in forward, code: self.attention_norm(x), freqs_cos, freqs_sin, **attn_options
2025-03-21T20:31:43.6359027Z             quantized_decomposed_dequantize_per_tensor_default_1194: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_817, 0.0026261727325618267, 6169, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_817 = None
2025-03-21T20:31:43.6359553Z             aten_pow_tensor_scalar_10: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_pow_Tensor_Scalar(quantized_decomposed_dequantize_per_tensor_default_1194, 2)
2025-03-21T20:31:43.6360011Z             aten_mean_dim_10: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_mean_dim(aten_pow_tensor_scalar_10, [2], True);  aten_pow_tensor_scalar_10 = None
2025-03-21T20:31:43.6360534Z             aten_add_scalar_10: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_add_Scalar(aten_mean_dim_10, 9.999999747378752e-06);  aten_mean_dim_10 = None
2025-03-21T20:31:43.6360958Z             aten_rsqrt_default_10: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_rsqrt_default(aten_add_scalar_10);  aten_add_scalar_10 = None
2025-03-21T20:31:43.6361823Z             aten_mul_tensor_75: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1194, aten_rsqrt_default_10);  quantized_decomposed_dequantize_per_tensor_default_1194 = aten_rsqrt_default_10 = None
2025-03-21T20:31:43.6362655Z             aten_mul_tensor_76: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(aten_mul_tensor_75, quantized_decomposed_dequantize_per_tensor_default_46);  aten_mul_tensor_75 = quantized_decomposed_dequantize_per_tensor_default_46 = None
2025-03-21T20:31:43.6363512Z             quantized_decomposed_quantize_per_tensor_default_818: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_76, 0.000380539771867916, 30682, 0, 65535, torch.int32);  aten_mul_tensor_76 = None
2025-03-21T20:31:43.6363597Z             
2025-03-21T20:31:43.6364131Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.6365039Z             quantized_decomposed_dequantize_per_tensor_default_1195: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_818, 0.000380539771867916, 30682, 0, 65535, torch.int32)
2025-03-21T20:31:43.6365963Z             quantized_decomposed_dequantize_per_tensor_default_1196: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_818, 0.000380539771867916, 30682, 0, 65535, torch.int32)
2025-03-21T20:31:43.6367097Z             quantized_decomposed_dequantize_per_tensor_default_1197: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_818, 0.000380539771867916, 30682, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_818 = None
2025-03-21T20:31:43.6367912Z             aten_unsqueeze_copy_default_55: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1197, -1);  quantized_decomposed_dequantize_per_tensor_default_1197 = None
2025-03-21T20:31:43.6368869Z             quantized_decomposed_quantize_per_tensor_default_819: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_55, 0.000380539771867916, 30682, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_55 = None
2025-03-21T20:31:43.6368997Z             
2025-03-21T20:31:43.6369496Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.6370639Z             quantized_decomposed_dequantize_per_tensor_default_1198: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_819, 0.000380539771867916, 30682, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_819 = None
2025-03-21T20:31:43.6371437Z             aten_permute_copy_default_205: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1198, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1198 = None
2025-03-21T20:31:43.6372431Z             quantized_decomposed_quantize_per_tensor_default_820: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_205, 0.000380539771867916, 30682, 0, 65535, torch.int32);  aten_permute_copy_default_205 = None
2025-03-21T20:31:43.6372536Z             
2025-03-21T20:31:43.6372907Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.6374057Z             quantized_decomposed_dequantize_per_tensor_default_1199: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_820, 0.000380539771867916, 30682, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_820 = None
2025-03-21T20:31:43.6375360Z             aten_convolution_default_35: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_1199, quantized_decomposed_dequantize_per_tensor_default_47, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_1199 = quantized_decomposed_dequantize_per_tensor_default_47 = None
2025-03-21T20:31:43.6376295Z             quantized_decomposed_quantize_per_tensor_default_821: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_35, 0.0003648563288152218, 32914, 0, 65535, torch.int32);  aten_convolution_default_35 = None
2025-03-21T20:31:43.6376384Z             
2025-03-21T20:31:43.6376820Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.6377965Z             quantized_decomposed_dequantize_per_tensor_default_1200: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_821, 0.0003648563288152218, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_821 = None
2025-03-21T20:31:43.6378777Z             aten_permute_copy_default_206: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1200, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1200 = None
2025-03-21T20:31:43.6379706Z             quantized_decomposed_quantize_per_tensor_default_822: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_206, 0.0003648563288152218, 32914, 0, 65535, torch.int32);  aten_permute_copy_default_206 = None
2025-03-21T20:31:43.6379808Z             
2025-03-21T20:31:43.6380345Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.6381557Z             quantized_decomposed_dequantize_per_tensor_default_1201: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_822, 0.0003648563288152218, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_822 = None
2025-03-21T20:31:43.6382314Z             aten_squeeze_copy_dims_55: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_1201, [-1]);  quantized_decomposed_dequantize_per_tensor_default_1201 = None
2025-03-21T20:31:43.6383220Z             quantized_decomposed_quantize_per_tensor_default_823: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_55, 0.0003648563288152218, 32914, 0, 65535, torch.int32);  aten_squeeze_copy_dims_55 = None
2025-03-21T20:31:43.6383312Z             
2025-03-21T20:31:43.6383845Z              # File: /pytorch/executorch/examples/models/llama/attention.py:242 in forward, code: q = q.view(bsz, seqlen, self.n_local_heads, self.head_dim)
2025-03-21T20:31:43.6385028Z             quantized_decomposed_dequantize_per_tensor_default_1202: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_823, 0.0003648563288152218, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_823 = None
2025-03-21T20:31:43.6385132Z             
2025-03-21T20:31:43.6385647Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.6386462Z             aten_unsqueeze_copy_default_56: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1196, -1);  quantized_decomposed_dequantize_per_tensor_default_1196 = None
2025-03-21T20:31:43.6387432Z             quantized_decomposed_quantize_per_tensor_default_824: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_56, 0.000380539771867916, 30682, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_56 = None
2025-03-21T20:31:43.6387536Z             
2025-03-21T20:31:43.6387942Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.6389076Z             quantized_decomposed_dequantize_per_tensor_default_1203: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_824, 0.000380539771867916, 30682, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_824 = None
2025-03-21T20:31:43.6389892Z             aten_permute_copy_default_207: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1203, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1203 = None
2025-03-21T20:31:43.6390836Z             quantized_decomposed_quantize_per_tensor_default_825: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_207, 0.000380539771867916, 30682, 0, 65535, torch.int32);  aten_permute_copy_default_207 = None
2025-03-21T20:31:43.6390924Z             
2025-03-21T20:31:43.6391288Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.6392443Z             quantized_decomposed_dequantize_per_tensor_default_1204: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_825, 0.000380539771867916, 30682, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_825 = None
2025-03-21T20:31:43.6393788Z             aten_convolution_default_36: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_1204, quantized_decomposed_dequantize_per_tensor_default_48, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_1204 = quantized_decomposed_dequantize_per_tensor_default_48 = None
2025-03-21T20:31:43.6394715Z             quantized_decomposed_quantize_per_tensor_default_826: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_36, 0.0004354633274488151, 30890, 0, 65535, torch.int32);  aten_convolution_default_36 = None
2025-03-21T20:31:43.6394822Z             
2025-03-21T20:31:43.6395248Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.6396430Z             quantized_decomposed_dequantize_per_tensor_default_1205: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_826, 0.0004354633274488151, 30890, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_826 = None
2025-03-21T20:31:43.6397233Z             aten_permute_copy_default_208: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1205, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1205 = None
2025-03-21T20:31:43.6398174Z             quantized_decomposed_quantize_per_tensor_default_827: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_208, 0.0004354633274488151, 30890, 0, 65535, torch.int32);  aten_permute_copy_default_208 = None
2025-03-21T20:31:43.6398294Z             
2025-03-21T20:31:43.6398845Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.6399986Z             quantized_decomposed_dequantize_per_tensor_default_1206: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_827, 0.0004354633274488151, 30890, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_827 = None
2025-03-21T20:31:43.6400748Z             aten_squeeze_copy_dims_56: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_1206, [-1]);  quantized_decomposed_dequantize_per_tensor_default_1206 = None
2025-03-21T20:31:43.6401643Z             quantized_decomposed_quantize_per_tensor_default_828: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_56, 0.0004354633274488151, 30890, 0, 65535, torch.int32);  aten_squeeze_copy_dims_56 = None
2025-03-21T20:31:43.6401744Z             
2025-03-21T20:31:43.6402267Z              # File: /pytorch/executorch/examples/models/llama/attention.py:243 in forward, code: k = k.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.6403414Z             quantized_decomposed_dequantize_per_tensor_default_1207: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_828, 0.0004354633274488151, 30890, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_828 = None
2025-03-21T20:31:43.6403501Z             
2025-03-21T20:31:43.6404013Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.6404856Z             aten_unsqueeze_copy_default_57: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1195, -1);  quantized_decomposed_dequantize_per_tensor_default_1195 = None
2025-03-21T20:31:43.6405816Z             quantized_decomposed_quantize_per_tensor_default_829: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_57, 0.000380539771867916, 30682, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_57 = None
2025-03-21T20:31:43.6405917Z             
2025-03-21T20:31:43.6406324Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.6407469Z             quantized_decomposed_dequantize_per_tensor_default_1208: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_829, 0.000380539771867916, 30682, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_829 = None
2025-03-21T20:31:43.6408294Z             aten_permute_copy_default_209: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1208, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1208 = None
2025-03-21T20:31:43.6409231Z             quantized_decomposed_quantize_per_tensor_default_830: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_209, 0.000380539771867916, 30682, 0, 65535, torch.int32);  aten_permute_copy_default_209 = None
2025-03-21T20:31:43.6409392Z             
2025-03-21T20:31:43.6409774Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.6410941Z             quantized_decomposed_dequantize_per_tensor_default_1209: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_830, 0.000380539771867916, 30682, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_830 = None
2025-03-21T20:31:43.6412234Z             aten_convolution_default_37: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_1209, quantized_decomposed_dequantize_per_tensor_default_49, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_1209 = quantized_decomposed_dequantize_per_tensor_default_49 = None
2025-03-21T20:31:43.6413168Z             quantized_decomposed_quantize_per_tensor_default_831: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_37, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_convolution_default_37 = None
2025-03-21T20:31:43.6413260Z             
2025-03-21T20:31:43.6413688Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.6414845Z             quantized_decomposed_dequantize_per_tensor_default_1210: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_831, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_831 = None
2025-03-21T20:31:43.6415638Z             aten_permute_copy_default_210: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1210, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1210 = None
2025-03-21T20:31:43.6416606Z             quantized_decomposed_quantize_per_tensor_default_832: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_210, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_permute_copy_default_210 = None
2025-03-21T20:31:43.6416721Z             
2025-03-21T20:31:43.6417269Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.6418410Z             quantized_decomposed_dequantize_per_tensor_default_1211: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_832, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_832 = None
2025-03-21T20:31:43.6419175Z             aten_squeeze_copy_dims_57: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_1211, [-1]);  quantized_decomposed_dequantize_per_tensor_default_1211 = None
2025-03-21T20:31:43.6420102Z             quantized_decomposed_quantize_per_tensor_default_833: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_57, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_squeeze_copy_dims_57 = None
2025-03-21T20:31:43.6420207Z             
2025-03-21T20:31:43.6420729Z              # File: /pytorch/executorch/examples/models/llama/attention.py:244 in forward, code: v = v.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.6421882Z             quantized_decomposed_dequantize_per_tensor_default_1212: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_833, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_833 = None
2025-03-21T20:31:43.6421998Z             
2025-03-21T20:31:43.6422520Z              # File: /pytorch/executorch/examples/models/llama/attention.py:242 in forward, code: q = q.view(bsz, seqlen, self.n_local_heads, self.head_dim)
2025-03-21T20:31:43.6423291Z             aten_view_copy_default_90: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1202, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_1202 = None
2025-03-21T20:31:43.6424193Z             quantized_decomposed_quantize_per_tensor_default_834: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_90, 0.0003648563288152218, 32914, 0, 65535, torch.int32);  aten_view_copy_default_90 = None
2025-03-21T20:31:43.6424282Z             
2025-03-21T20:31:43.6425218Z              # File: <eval_with_key>.50:3067 in forward, code: dequantize_per_tensor_default_988 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_988, 0.0003648563288152218, 32914, 0, 65535, torch.int32);  quantize_per_tensor_default_988 = None
2025-03-21T20:31:43.6426361Z             quantized_decomposed_dequantize_per_tensor_default_1213: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_834, 0.0003648563288152218, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_834 = None
2025-03-21T20:31:43.6426461Z             
2025-03-21T20:31:43.6426978Z              # File: /pytorch/executorch/examples/models/llama/attention.py:243 in forward, code: k = k.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.6427754Z             aten_view_copy_default_91: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1207, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_1207 = None
2025-03-21T20:31:43.6428679Z             quantized_decomposed_quantize_per_tensor_default_835: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_91, 0.0004354633274488151, 30890, 0, 65535, torch.int32);  aten_view_copy_default_91 = None
2025-03-21T20:31:43.6428812Z             
2025-03-21T20:31:43.6429735Z              # File: <eval_with_key>.50:3070 in forward, code: dequantize_per_tensor_default_989 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_989, 0.0004354633274488151, 30890, 0, 65535, torch.int32);  quantize_per_tensor_default_989 = None
2025-03-21T20:31:43.6430877Z             quantized_decomposed_dequantize_per_tensor_default_1214: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_835, 0.0004354633274488151, 30890, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_835 = None
2025-03-21T20:31:43.6430967Z             
2025-03-21T20:31:43.6431500Z              # File: /pytorch/executorch/examples/models/llama/attention.py:244 in forward, code: v = v.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.6432506Z             aten_view_copy_default_92: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1212, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_1212 = None
2025-03-21T20:31:43.6433426Z             quantized_decomposed_quantize_per_tensor_default_836: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_92, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_view_copy_default_92 = None
2025-03-21T20:31:43.6433517Z             
2025-03-21T20:31:43.6434241Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:346 in update, code: v_out = torch.ops.aten.index_put_(self.past_v_caches, [None, input_pos], v_val)
2025-03-21T20:31:43.6435387Z             quantized_decomposed_dequantize_per_tensor_default_1215: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_836, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_836 = None
2025-03-21T20:31:43.6435492Z             
2025-03-21T20:31:43.6436247Z              # File: <eval_with_key>.50:3075 in forward, code: quantize_per_tensor_default_991 = torch.ops.quantized_decomposed.quantize_per_tensor.default(_to_copy_10, 0.0003648563288152218, 32914, 0, 65535, torch.int32);  _to_copy_10 = None
2025-03-21T20:31:43.6437401Z             quantized_decomposed_quantize_per_tensor_default_837: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_1213, 0.0003648563288152218, 32914, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_1213 = None
2025-03-21T20:31:43.6437495Z             
2025-03-21T20:31:43.6438034Z              # File: /pytorch/executorch/examples/models/llama/rope.py:84 in apply_rotary_emb, code: xq_r, xq_i = xq.float().reshape(xq.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.6439169Z             quantized_decomposed_dequantize_per_tensor_default_1216: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_837, 0.0003648563288152218, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_837 = None
2025-03-21T20:31:43.6439951Z             aten_view_copy_default_93: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1216, [1, 1, 12, -1, 2]);  quantized_decomposed_dequantize_per_tensor_default_1216 = None
2025-03-21T20:31:43.6440991Z             quantized_decomposed_quantize_per_tensor_default_838: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_93, 0.0003648563288152218, 32914, 0, 65535, torch.int32);  aten_view_copy_default_93 = None
2025-03-21T20:31:43.6442182Z             quantized_decomposed_dequantize_per_tensor_default_1217: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_838, 0.0003648563288152218, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_838 = None
2025-03-21T20:31:43.6442716Z             aten_slice_copy_tensor_20: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_1217, 4, 0, 1)
2025-03-21T20:31:43.6443483Z             aten_slice_copy_tensor_21: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_1217, 4, 1, 2);  quantized_decomposed_dequantize_per_tensor_default_1217 = None
2025-03-21T20:31:43.6444031Z             aten_squeeze_copy_dims_58: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_20, [4]);  aten_slice_copy_tensor_20 = None
2025-03-21T20:31:43.6444558Z             aten_squeeze_copy_dims_59: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_21, [4]);  aten_slice_copy_tensor_21 = None
2025-03-21T20:31:43.6445457Z             quantized_decomposed_quantize_per_tensor_default_839: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_58, 0.00027893035439774394, 29335, 0, 65535, torch.int32);  aten_squeeze_copy_dims_58 = None
2025-03-21T20:31:43.6445586Z             
2025-03-21T20:31:43.6446063Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.6446993Z             quantized_decomposed_dequantize_per_tensor_default_1218: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_839, 0.00027893035439774394, 29335, 0, 65535, torch.int32)
2025-03-21T20:31:43.6447080Z             
2025-03-21T20:31:43.6447563Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.6448699Z             quantized_decomposed_dequantize_per_tensor_default_1219: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_839, 0.00027893035439774394, 29335, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_839 = None
2025-03-21T20:31:43.6448800Z             
2025-03-21T20:31:43.6449389Z              # File: /pytorch/executorch/examples/models/llama/rope.py:84 in apply_rotary_emb, code: xq_r, xq_i = xq.float().reshape(xq.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.6450314Z             quantized_decomposed_quantize_per_tensor_default_840: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_59, 0.0003648563288152218, 32914, 0, 65535, torch.int32);  aten_squeeze_copy_dims_59 = None
2025-03-21T20:31:43.6450403Z             
2025-03-21T20:31:43.6450888Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.6452064Z             quantized_decomposed_dequantize_per_tensor_default_1220: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_840, 0.0003648563288152218, 32914, 0, 65535, torch.int32)
2025-03-21T20:31:43.6452165Z             
2025-03-21T20:31:43.6452722Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.6453865Z             quantized_decomposed_dequantize_per_tensor_default_1221: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_840, 0.0003648563288152218, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_840 = None
2025-03-21T20:31:43.6453969Z             
2025-03-21T20:31:43.6454726Z              # File: <eval_with_key>.50:3090 in forward, code: quantize_per_tensor_default_995 = torch.ops.quantized_decomposed.quantize_per_tensor.default(_to_copy_11, 0.0004354633274488151, 30890, 0, 65535, torch.int32);  _to_copy_11 = None
2025-03-21T20:31:43.6455877Z             quantized_decomposed_quantize_per_tensor_default_841: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_1214, 0.0004354633274488151, 30890, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_1214 = None
2025-03-21T20:31:43.6456004Z             
2025-03-21T20:31:43.6456537Z              # File: /pytorch/executorch/examples/models/llama/rope.py:85 in apply_rotary_emb, code: xk_r, xk_i = xk.float().reshape(xk.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.6457673Z             quantized_decomposed_dequantize_per_tensor_default_1222: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_841, 0.0004354633274488151, 30890, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_841 = None
2025-03-21T20:31:43.6458486Z             aten_view_copy_default_94: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1222, [1, 1, 12, -1, 2]);  quantized_decomposed_dequantize_per_tensor_default_1222 = None
2025-03-21T20:31:43.6459382Z             quantized_decomposed_quantize_per_tensor_default_842: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_94, 0.0004354633274488151, 30890, 0, 65535, torch.int32);  aten_view_copy_default_94 = None
2025-03-21T20:31:43.6460529Z             quantized_decomposed_dequantize_per_tensor_default_1223: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_842, 0.0004354633274488151, 30890, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_842 = None
2025-03-21T20:31:43.6461067Z             aten_slice_copy_tensor_22: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_1223, 4, 0, 1)
2025-03-21T20:31:43.6461841Z             aten_slice_copy_tensor_23: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_1223, 4, 1, 2);  quantized_decomposed_dequantize_per_tensor_default_1223 = None
2025-03-21T20:31:43.6462357Z             aten_squeeze_copy_dims_60: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_22, [4]);  aten_slice_copy_tensor_22 = None
2025-03-21T20:31:43.6462883Z             aten_squeeze_copy_dims_61: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_23, [4]);  aten_slice_copy_tensor_23 = None
2025-03-21T20:31:43.6463784Z             quantized_decomposed_quantize_per_tensor_default_843: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_60, 0.00038958649383857846, 30696, 0, 65535, torch.int32);  aten_squeeze_copy_dims_60 = None
2025-03-21T20:31:43.6463914Z             
2025-03-21T20:31:43.6464415Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.6465342Z             quantized_decomposed_dequantize_per_tensor_default_1224: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_843, 0.00038958649383857846, 30696, 0, 65535, torch.int32)
2025-03-21T20:31:43.6465429Z             
2025-03-21T20:31:43.6465913Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.6467055Z             quantized_decomposed_dequantize_per_tensor_default_1225: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_843, 0.00038958649383857846, 30696, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_843 = None
2025-03-21T20:31:43.6467158Z             
2025-03-21T20:31:43.6467702Z              # File: /pytorch/executorch/examples/models/llama/rope.py:85 in apply_rotary_emb, code: xk_r, xk_i = xk.float().reshape(xk.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.6468611Z             quantized_decomposed_quantize_per_tensor_default_844: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_61, 0.0004354633274488151, 30890, 0, 65535, torch.int32);  aten_squeeze_copy_dims_61 = None
2025-03-21T20:31:43.6468701Z             
2025-03-21T20:31:43.6469189Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.6470128Z             quantized_decomposed_dequantize_per_tensor_default_1226: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_844, 0.0004354633274488151, 30890, 0, 65535, torch.int32)
2025-03-21T20:31:43.6470230Z             
2025-03-21T20:31:43.6470701Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.6471852Z             quantized_decomposed_dequantize_per_tensor_default_1227: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_844, 0.0004354633274488151, 30890, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_844 = None
2025-03-21T20:31:43.6471943Z             
2025-03-21T20:31:43.6472382Z              # File: /pytorch/executorch/examples/models/llama/rope.py:78 in reshape_for_broadcast, code: return freqs_cis.view(shape)
2025-03-21T20:31:43.6473149Z             aten_view_copy_default_95: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_157, [1, 1, 1, 32]);  quantized_decomposed_dequantize_per_tensor_default_157 = None
2025-03-21T20:31:43.6474043Z             quantized_decomposed_quantize_per_tensor_default_845: "i32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_95, 3.051804378628731e-05, 32768, 0, 65535, torch.int32);  aten_view_copy_default_95 = None
2025-03-21T20:31:43.6474142Z             
2025-03-21T20:31:43.6474613Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.6475577Z             quantized_decomposed_dequantize_per_tensor_default_1228: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_845, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.6475693Z             
2025-03-21T20:31:43.6476177Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.6477084Z             quantized_decomposed_dequantize_per_tensor_default_1229: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_845, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.6477184Z             
2025-03-21T20:31:43.6477655Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.6478574Z             quantized_decomposed_dequantize_per_tensor_default_1230: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_845, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.6478663Z             
2025-03-21T20:31:43.6479169Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.6480298Z             quantized_decomposed_dequantize_per_tensor_default_1231: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_845, 3.051804378628731e-05, 32768, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_845 = None
2025-03-21T20:31:43.6480398Z             
2025-03-21T20:31:43.6480832Z              # File: /pytorch/executorch/examples/models/llama/rope.py:78 in reshape_for_broadcast, code: return freqs_cis.view(shape)
2025-03-21T20:31:43.6481625Z             aten_view_copy_default_96: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_169, [1, 1, 1, 32]);  quantized_decomposed_dequantize_per_tensor_default_169 = None
2025-03-21T20:31:43.6482515Z             quantized_decomposed_quantize_per_tensor_default_846: "i32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_96, 3.051786916330457e-05, 32767, 0, 65535, torch.int32);  aten_view_copy_default_96 = None
2025-03-21T20:31:43.6482614Z             
2025-03-21T20:31:43.6483086Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.6483995Z             quantized_decomposed_dequantize_per_tensor_default_1232: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_846, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.6484099Z             
2025-03-21T20:31:43.6484569Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.6485491Z             quantized_decomposed_dequantize_per_tensor_default_1233: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_846, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.6485579Z             
2025-03-21T20:31:43.6486062Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.6486969Z             quantized_decomposed_dequantize_per_tensor_default_1234: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_846, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.6487127Z             
2025-03-21T20:31:43.6487596Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.6488738Z             quantized_decomposed_dequantize_per_tensor_default_1235: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_846, 3.051786916330457e-05, 32767, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_846 = None
2025-03-21T20:31:43.6488829Z             
2025-03-21T20:31:43.6489404Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.6490544Z             aten_mul_tensor_77: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1219, quantized_decomposed_dequantize_per_tensor_default_1231);  quantized_decomposed_dequantize_per_tensor_default_1219 = quantized_decomposed_dequantize_per_tensor_default_1231 = None
2025-03-21T20:31:43.6491444Z             quantized_decomposed_quantize_per_tensor_default_847: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_77, 0.0002772713196463883, 29395, 0, 65535, torch.int32);  aten_mul_tensor_77 = None
2025-03-21T20:31:43.6492581Z             quantized_decomposed_dequantize_per_tensor_default_1236: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_847, 0.0002772713196463883, 29395, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_847 = None
2025-03-21T20:31:43.6493743Z             aten_mul_tensor_78: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1220, quantized_decomposed_dequantize_per_tensor_default_1234);  quantized_decomposed_dequantize_per_tensor_default_1220 = quantized_decomposed_dequantize_per_tensor_default_1234 = None
2025-03-21T20:31:43.6494597Z             quantized_decomposed_quantize_per_tensor_default_848: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_78, 0.00015570834511891007, 31919, 0, 65535, torch.int32);  aten_mul_tensor_78 = None
2025-03-21T20:31:43.6495755Z             quantized_decomposed_dequantize_per_tensor_default_1237: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_848, 0.00015570834511891007, 31919, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_848 = None
2025-03-21T20:31:43.6496886Z             aten_sub_tensor_10: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_sub_Tensor(quantized_decomposed_dequantize_per_tensor_default_1236, quantized_decomposed_dequantize_per_tensor_default_1237);  quantized_decomposed_dequantize_per_tensor_default_1236 = quantized_decomposed_dequantize_per_tensor_default_1237 = None
2025-03-21T20:31:43.6497759Z             quantized_decomposed_quantize_per_tensor_default_849: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_sub_tensor_10, 0.00027773523470386863, 29312, 0, 65535, torch.int32);  aten_sub_tensor_10 = None
2025-03-21T20:31:43.6497853Z             
2025-03-21T20:31:43.6498815Z              # File: <eval_with_key>.50:3124 in forward, code: dequantize_per_tensor_default_1003 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1003, 0.00027773523470386863, 29312, 0, 65535, torch.int32);  quantize_per_tensor_default_1003 = None
2025-03-21T20:31:43.6499984Z             quantized_decomposed_dequantize_per_tensor_default_1238: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_849, 0.00027773523470386863, 29312, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_849 = None
2025-03-21T20:31:43.6500119Z             
2025-03-21T20:31:43.6500596Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.6501744Z             aten_mul_tensor_79: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1218, quantized_decomposed_dequantize_per_tensor_default_1235);  quantized_decomposed_dequantize_per_tensor_default_1218 = quantized_decomposed_dequantize_per_tensor_default_1235 = None
2025-03-21T20:31:43.6502601Z             quantized_decomposed_quantize_per_tensor_default_850: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_79, 0.00017529382603242993, 34419, 0, 65535, torch.int32);  aten_mul_tensor_79 = None
2025-03-21T20:31:43.6503773Z             quantized_decomposed_dequantize_per_tensor_default_1239: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_850, 0.00017529382603242993, 34419, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_850 = None
2025-03-21T20:31:43.6504907Z             aten_mul_tensor_80: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1221, quantized_decomposed_dequantize_per_tensor_default_1230);  quantized_decomposed_dequantize_per_tensor_default_1221 = quantized_decomposed_dequantize_per_tensor_default_1230 = None
2025-03-21T20:31:43.6505832Z             quantized_decomposed_quantize_per_tensor_default_851: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_80, 0.0003621247597038746, 32927, 0, 65535, torch.int32);  aten_mul_tensor_80 = None
2025-03-21T20:31:43.6506981Z             quantized_decomposed_dequantize_per_tensor_default_1240: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_851, 0.0003621247597038746, 32927, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_851 = None
2025-03-21T20:31:43.6508100Z             aten_add_tensor_25: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_1239, quantized_decomposed_dequantize_per_tensor_default_1240);  quantized_decomposed_dequantize_per_tensor_default_1239 = quantized_decomposed_dequantize_per_tensor_default_1240 = None
2025-03-21T20:31:43.6508959Z             quantized_decomposed_quantize_per_tensor_default_852: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_25, 0.0003545602085068822, 32712, 0, 65535, torch.int32);  aten_add_tensor_25 = None
2025-03-21T20:31:43.6509048Z             
2025-03-21T20:31:43.6509998Z              # File: <eval_with_key>.50:3133 in forward, code: dequantize_per_tensor_default_1006 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1006, 0.0003545602085068822, 32712, 0, 65535, torch.int32);  quantize_per_tensor_default_1006 = None
2025-03-21T20:31:43.6511132Z             quantized_decomposed_dequantize_per_tensor_default_1241: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_852, 0.0003545602085068822, 32712, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_852 = None
2025-03-21T20:31:43.6511234Z             
2025-03-21T20:31:43.6511735Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.6512903Z             aten_mul_tensor_81: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1225, quantized_decomposed_dequantize_per_tensor_default_1229);  quantized_decomposed_dequantize_per_tensor_default_1225 = quantized_decomposed_dequantize_per_tensor_default_1229 = None
2025-03-21T20:31:43.6513750Z             quantized_decomposed_quantize_per_tensor_default_853: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_81, 0.00038680178113281727, 30861, 0, 65535, torch.int32);  aten_mul_tensor_81 = None
2025-03-21T20:31:43.6514915Z             quantized_decomposed_dequantize_per_tensor_default_1242: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_853, 0.00038680178113281727, 30861, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_853 = None
2025-03-21T20:31:43.6516063Z             aten_mul_tensor_82: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1226, quantized_decomposed_dequantize_per_tensor_default_1232);  quantized_decomposed_dequantize_per_tensor_default_1226 = quantized_decomposed_dequantize_per_tensor_default_1232 = None
2025-03-21T20:31:43.6516920Z             quantized_decomposed_quantize_per_tensor_default_854: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_82, 0.00020304229110479355, 35220, 0, 65535, torch.int32);  aten_mul_tensor_82 = None
2025-03-21T20:31:43.6518090Z             quantized_decomposed_dequantize_per_tensor_default_1243: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_854, 0.00020304229110479355, 35220, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_854 = None
2025-03-21T20:31:43.6519224Z             aten_sub_tensor_11: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_sub_Tensor(quantized_decomposed_dequantize_per_tensor_default_1242, quantized_decomposed_dequantize_per_tensor_default_1243);  quantized_decomposed_dequantize_per_tensor_default_1242 = quantized_decomposed_dequantize_per_tensor_default_1243 = None
2025-03-21T20:31:43.6520077Z             quantized_decomposed_quantize_per_tensor_default_855: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_sub_tensor_11, 0.000387135281926021, 30644, 0, 65535, torch.int32);  aten_sub_tensor_11 = None
2025-03-21T20:31:43.6520167Z             
2025-03-21T20:31:43.6521103Z              # File: <eval_with_key>.50:3142 in forward, code: dequantize_per_tensor_default_1009 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1009, 0.000387135281926021, 30644, 0, 65535, torch.int32);  quantize_per_tensor_default_1009 = None
2025-03-21T20:31:43.6522245Z             quantized_decomposed_dequantize_per_tensor_default_1244: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_855, 0.000387135281926021, 30644, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_855 = None
2025-03-21T20:31:43.6522346Z             
2025-03-21T20:31:43.6522816Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.6523962Z             aten_mul_tensor_83: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1224, quantized_decomposed_dequantize_per_tensor_default_1233);  quantized_decomposed_dequantize_per_tensor_default_1224 = quantized_decomposed_dequantize_per_tensor_default_1233 = None
2025-03-21T20:31:43.6524849Z             quantized_decomposed_quantize_per_tensor_default_856: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_83, 0.00019716918177437037, 32534, 0, 65535, torch.int32);  aten_mul_tensor_83 = None
2025-03-21T20:31:43.6525999Z             quantized_decomposed_dequantize_per_tensor_default_1245: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_856, 0.00019716918177437037, 32534, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_856 = None
2025-03-21T20:31:43.6527119Z             aten_mul_tensor_84: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1227, quantized_decomposed_dequantize_per_tensor_default_1228);  quantized_decomposed_dequantize_per_tensor_default_1227 = quantized_decomposed_dequantize_per_tensor_default_1228 = None
2025-03-21T20:31:43.6528003Z             quantized_decomposed_quantize_per_tensor_default_857: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_84, 0.00042476155795156956, 31446, 0, 65535, torch.int32);  aten_mul_tensor_84 = None
2025-03-21T20:31:43.6529142Z             quantized_decomposed_dequantize_per_tensor_default_1246: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_857, 0.00042476155795156956, 31446, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_857 = None
2025-03-21T20:31:43.6530367Z             aten_add_tensor_26: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_1245, quantized_decomposed_dequantize_per_tensor_default_1246);  quantized_decomposed_dequantize_per_tensor_default_1245 = quantized_decomposed_dequantize_per_tensor_default_1246 = None
2025-03-21T20:31:43.6531223Z             quantized_decomposed_quantize_per_tensor_default_858: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_26, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_add_tensor_26 = None
2025-03-21T20:31:43.6531326Z             
2025-03-21T20:31:43.6532425Z              # File: <eval_with_key>.50:3151 in forward, code: dequantize_per_tensor_default_1012 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1012, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantize_per_tensor_default_1012 = None
2025-03-21T20:31:43.6533588Z             quantized_decomposed_dequantize_per_tensor_default_1247: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_858, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_858 = None
2025-03-21T20:31:43.6533678Z             
2025-03-21T20:31:43.6534218Z              # File: /pytorch/executorch/examples/models/llama/rope.py:95 in apply_rotary_emb, code: xq_out = torch.stack([xq_out_r, xq_out_i], dim=-1).flatten(3)
2025-03-21T20:31:43.6535023Z             aten_unsqueeze_copy_default_58: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1238, 4);  quantized_decomposed_dequantize_per_tensor_default_1238 = None
2025-03-21T20:31:43.6535829Z             aten_unsqueeze_copy_default_59: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1241, 4);  quantized_decomposed_dequantize_per_tensor_default_1241 = None
2025-03-21T20:31:43.6536627Z             aten_cat_default_20: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_cat_default([aten_unsqueeze_copy_default_58, aten_unsqueeze_copy_default_59], -1);  aten_unsqueeze_copy_default_58 = aten_unsqueeze_copy_default_59 = None
2025-03-21T20:31:43.6537530Z             quantized_decomposed_quantize_per_tensor_default_859: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_20, 0.0003545602085068822, 32712, 0, 65535, torch.int32);  aten_cat_default_20 = None
2025-03-21T20:31:43.6538667Z             quantized_decomposed_dequantize_per_tensor_default_1248: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_859, 0.0003545602085068822, 32712, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_859 = None
2025-03-21T20:31:43.6539448Z             aten_view_copy_default_97: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1248, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_1248 = None
2025-03-21T20:31:43.6540379Z             quantized_decomposed_quantize_per_tensor_default_860: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_97, 0.0003545602085068822, 32712, 0, 65535, torch.int32);  aten_view_copy_default_97 = None
2025-03-21T20:31:43.6540483Z             
2025-03-21T20:31:43.6541418Z              # File: <eval_with_key>.50:3157 in forward, code: dequantize_per_tensor_default_1014 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1014, 0.0003545602085068822, 32712, 0, 65535, torch.int32);  quantize_per_tensor_default_1014 = None
2025-03-21T20:31:43.6542609Z             quantized_decomposed_dequantize_per_tensor_default_1249: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_860, 0.0003545602085068822, 32712, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_860 = None
2025-03-21T20:31:43.6542703Z             
2025-03-21T20:31:43.6543238Z              # File: /pytorch/executorch/examples/models/llama/rope.py:96 in apply_rotary_emb, code: xk_out = torch.stack([xk_out_r, xk_out_i], dim=-1).flatten(3)
2025-03-21T20:31:43.6544035Z             aten_unsqueeze_copy_default_60: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1244, 4);  quantized_decomposed_dequantize_per_tensor_default_1244 = None
2025-03-21T20:31:43.6544839Z             aten_unsqueeze_copy_default_61: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1247, 4);  quantized_decomposed_dequantize_per_tensor_default_1247 = None
2025-03-21T20:31:43.6545576Z             aten_cat_default_21: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_cat_default([aten_unsqueeze_copy_default_60, aten_unsqueeze_copy_default_61], -1);  aten_unsqueeze_copy_default_60 = aten_unsqueeze_copy_default_61 = None
2025-03-21T20:31:43.6546445Z             quantized_decomposed_quantize_per_tensor_default_861: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_21, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_cat_default_21 = None
2025-03-21T20:31:43.6547583Z             quantized_decomposed_dequantize_per_tensor_default_1250: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_861, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_861 = None
2025-03-21T20:31:43.6548383Z             aten_view_copy_default_98: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1250, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_1250 = None
2025-03-21T20:31:43.6549316Z             quantized_decomposed_quantize_per_tensor_default_862: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_98, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_view_copy_default_98 = None
2025-03-21T20:31:43.6549405Z             
2025-03-21T20:31:43.6550338Z              # File: <eval_with_key>.50:3163 in forward, code: dequantize_per_tensor_default_1016 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1016, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantize_per_tensor_default_1016 = None
2025-03-21T20:31:43.6551489Z             quantized_decomposed_dequantize_per_tensor_default_1251: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_862, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_862 = None
2025-03-21T20:31:43.6551629Z             
2025-03-21T20:31:43.6552383Z              # File: <eval_with_key>.50:3165 in forward, code: quantize_per_tensor_default_1017 = torch.ops.quantized_decomposed.quantize_per_tensor.default(type_as_10, 0.0003545602085068822, 32712, 0, 65535, torch.int32);  type_as_10 = None
2025-03-21T20:31:43.6553669Z             quantized_decomposed_quantize_per_tensor_default_863: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_1249, 0.0003545602085068822, 32712, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_1249 = None
2025-03-21T20:31:43.6553797Z             
2025-03-21T20:31:43.6554329Z              # File: /pytorch/executorch/examples/models/llama/attention.py:249 in forward, code: q = q.transpose(1, 2)  # (bs, n_local_heads, seqlen, head_dim)
2025-03-21T20:31:43.6555485Z             quantized_decomposed_dequantize_per_tensor_default_1252: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_863, 0.0003545602085068822, 32712, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_863 = None
2025-03-21T20:31:43.6555572Z             
2025-03-21T20:31:43.6556333Z              # File: <eval_with_key>.50:3168 in forward, code: quantize_per_tensor_default_1018 = torch.ops.quantized_decomposed.quantize_per_tensor.default(type_as_11, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  type_as_11 = None
2025-03-21T20:31:43.6557473Z             quantized_decomposed_quantize_per_tensor_default_864: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_1251, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_1251 = None
2025-03-21T20:31:43.6557583Z             
2025-03-21T20:31:43.6558257Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:345 in update, code: k_out = torch.ops.aten.index_put_(self.past_k_caches, [None, input_pos], k_val)
2025-03-21T20:31:43.6559409Z             quantized_decomposed_dequantize_per_tensor_default_1253: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_864, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_864 = None
2025-03-21T20:31:43.6559499Z             
2025-03-21T20:31:43.6560031Z              # File: /pytorch/executorch/examples/models/llama/attention.py:249 in forward, code: q = q.transpose(1, 2)  # (bs, n_local_heads, seqlen, head_dim)
2025-03-21T20:31:43.6560881Z             aten_permute_copy_default_211: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1252, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1252 = None
2025-03-21T20:31:43.6561819Z             quantized_decomposed_quantize_per_tensor_default_865: "i32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_211, 0.0003545602085068822, 32712, 0, 65535, torch.int32);  aten_permute_copy_default_211 = None
2025-03-21T20:31:43.6561905Z             
2025-03-21T20:31:43.6562490Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.6563633Z             quantized_decomposed_dequantize_per_tensor_default_1254: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_865, 0.0003545602085068822, 32712, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_865 = None
2025-03-21T20:31:43.6563772Z             
2025-03-21T20:31:43.6564437Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:345 in update, code: k_out = torch.ops.aten.index_put_(self.past_k_caches, [None, input_pos], k_val)
2025-03-21T20:31:43.6565738Z             aten_index_put_default_10: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_index_put_default(quantized_decomposed_dequantize_per_tensor_default_128, [None, attn_options_input_pos], quantized_decomposed_dequantize_per_tensor_default_1253);  quantized_decomposed_dequantize_per_tensor_default_128 = quantized_decomposed_dequantize_per_tensor_default_1253 = None
2025-03-21T20:31:43.6566668Z             quantized_decomposed_quantize_per_tensor_default_866: "i32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_put_default_10, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_index_put_default_10 = None
2025-03-21T20:31:43.6566768Z             
2025-03-21T20:31:43.6567558Z              # File: <eval_with_key>.50:3175 in forward, code: dequantize_per_tensor_default_1020 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1020, 0.0004216498928144574, 32136, 0, 65535, torch.int32)
2025-03-21T20:31:43.6568492Z             quantized_decomposed_dequantize_per_tensor_default_1255: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_866, 0.0004216498928144574, 32136, 0, 65535, torch.int32)
2025-03-21T20:31:43.6568580Z             
2025-03-21T20:31:43.6569229Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6570223Z             quantized_decomposed_dequantize_per_tensor_default_1256: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_866, 0.0004216498928144574, 32136, 0, 65535, torch.int32)
2025-03-21T20:31:43.6571156Z             quantized_decomposed_dequantize_per_tensor_default_1257: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_866, 0.0004216498928144574, 32136, 0, 65535, torch.int32)
2025-03-21T20:31:43.6572067Z             quantized_decomposed_dequantize_per_tensor_default_1258: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_866, 0.0004216498928144574, 32136, 0, 65535, torch.int32)
2025-03-21T20:31:43.6573060Z             quantized_decomposed_dequantize_per_tensor_default_1259: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_866, 0.0004216498928144574, 32136, 0, 65535, torch.int32)
2025-03-21T20:31:43.6573975Z             quantized_decomposed_dequantize_per_tensor_default_1260: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_866, 0.0004216498928144574, 32136, 0, 65535, torch.int32)
2025-03-21T20:31:43.6574901Z             quantized_decomposed_dequantize_per_tensor_default_1261: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_866, 0.0004216498928144574, 32136, 0, 65535, torch.int32)
2025-03-21T20:31:43.6575817Z             quantized_decomposed_dequantize_per_tensor_default_1262: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_866, 0.0004216498928144574, 32136, 0, 65535, torch.int32)
2025-03-21T20:31:43.6576768Z             quantized_decomposed_dequantize_per_tensor_default_1263: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_866, 0.0004216498928144574, 32136, 0, 65535, torch.int32)
2025-03-21T20:31:43.6577686Z             quantized_decomposed_dequantize_per_tensor_default_1264: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_866, 0.0004216498928144574, 32136, 0, 65535, torch.int32)
2025-03-21T20:31:43.6578639Z             quantized_decomposed_dequantize_per_tensor_default_1265: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_866, 0.0004216498928144574, 32136, 0, 65535, torch.int32)
2025-03-21T20:31:43.6579567Z             quantized_decomposed_dequantize_per_tensor_default_1266: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_866, 0.0004216498928144574, 32136, 0, 65535, torch.int32)
2025-03-21T20:31:43.6580707Z             quantized_decomposed_dequantize_per_tensor_default_1267: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_866, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_866 = None
2025-03-21T20:31:43.6580810Z             
2025-03-21T20:31:43.6581479Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:346 in update, code: v_out = torch.ops.aten.index_put_(self.past_v_caches, [None, input_pos], v_val)
2025-03-21T20:31:43.6582775Z             aten_index_put_default_11: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_index_put_default(quantized_decomposed_dequantize_per_tensor_default_129, [None, attn_options_input_pos], quantized_decomposed_dequantize_per_tensor_default_1215);  quantized_decomposed_dequantize_per_tensor_default_129 = quantized_decomposed_dequantize_per_tensor_default_1215 = None
2025-03-21T20:31:43.6583674Z             quantized_decomposed_quantize_per_tensor_default_867: "i32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_put_default_11, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_index_put_default_11 = None
2025-03-21T20:31:43.6583775Z             
2025-03-21T20:31:43.6584589Z              # File: <eval_with_key>.50:3190 in forward, code: dequantize_per_tensor_default_1021 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1021, 0.0001254916423931718, 28364, 0, 65535, torch.int32)
2025-03-21T20:31:43.6585545Z             quantized_decomposed_dequantize_per_tensor_default_1268: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_867, 0.0001254916423931718, 28364, 0, 65535, torch.int32)
2025-03-21T20:31:43.6585633Z             
2025-03-21T20:31:43.6586276Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6587194Z             quantized_decomposed_dequantize_per_tensor_default_1269: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_867, 0.0001254916423931718, 28364, 0, 65535, torch.int32)
2025-03-21T20:31:43.6588148Z             quantized_decomposed_dequantize_per_tensor_default_1270: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_867, 0.0001254916423931718, 28364, 0, 65535, torch.int32)
2025-03-21T20:31:43.6589058Z             quantized_decomposed_dequantize_per_tensor_default_1271: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_867, 0.0001254916423931718, 28364, 0, 65535, torch.int32)
2025-03-21T20:31:43.6589981Z             quantized_decomposed_dequantize_per_tensor_default_1272: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_867, 0.0001254916423931718, 28364, 0, 65535, torch.int32)
2025-03-21T20:31:43.6590922Z             quantized_decomposed_dequantize_per_tensor_default_1273: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_867, 0.0001254916423931718, 28364, 0, 65535, torch.int32)
2025-03-21T20:31:43.6591848Z             quantized_decomposed_dequantize_per_tensor_default_1274: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_867, 0.0001254916423931718, 28364, 0, 65535, torch.int32)
2025-03-21T20:31:43.6592762Z             quantized_decomposed_dequantize_per_tensor_default_1275: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_867, 0.0001254916423931718, 28364, 0, 65535, torch.int32)
2025-03-21T20:31:43.6593691Z             quantized_decomposed_dequantize_per_tensor_default_1276: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_867, 0.0001254916423931718, 28364, 0, 65535, torch.int32)
2025-03-21T20:31:43.6594605Z             quantized_decomposed_dequantize_per_tensor_default_1277: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_867, 0.0001254916423931718, 28364, 0, 65535, torch.int32)
2025-03-21T20:31:43.6595532Z             quantized_decomposed_dequantize_per_tensor_default_1278: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_867, 0.0001254916423931718, 28364, 0, 65535, torch.int32)
2025-03-21T20:31:43.6596442Z             quantized_decomposed_dequantize_per_tensor_default_1279: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_867, 0.0001254916423931718, 28364, 0, 65535, torch.int32)
2025-03-21T20:31:43.6597656Z             quantized_decomposed_dequantize_per_tensor_default_1280: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_867, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_867 = None
2025-03-21T20:31:43.6597746Z             
2025-03-21T20:31:43.6598400Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6599205Z             aten_permute_copy_default_212: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1267, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1267 = None
2025-03-21T20:31:43.6600178Z             quantized_decomposed_quantize_per_tensor_default_868: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_212, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_permute_copy_default_212 = None
2025-03-21T20:31:43.6601330Z             quantized_decomposed_dequantize_per_tensor_default_1281: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_868, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_868 = None
2025-03-21T20:31:43.6602088Z             aten_select_copy_int_240: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1281, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1281 = None
2025-03-21T20:31:43.6603024Z             quantized_decomposed_quantize_per_tensor_default_869: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_240, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_select_copy_int_240 = None
2025-03-21T20:31:43.6604168Z             quantized_decomposed_dequantize_per_tensor_default_1282: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_869, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_869 = None
2025-03-21T20:31:43.6604924Z             aten_select_copy_int_241: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1282, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1282 = None
2025-03-21T20:31:43.6605816Z             quantized_decomposed_quantize_per_tensor_default_870: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_241, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_select_copy_int_241 = None
2025-03-21T20:31:43.6605920Z             
2025-03-21T20:31:43.6606860Z              # File: <eval_with_key>.50:3211 in forward, code: dequantize_per_tensor_default_1024 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1024, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantize_per_tensor_default_1024 = None
2025-03-21T20:31:43.6608009Z             quantized_decomposed_dequantize_per_tensor_default_1283: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_870, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_870 = None
2025-03-21T20:31:43.6608098Z             
2025-03-21T20:31:43.6608769Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6609710Z             aten_permute_copy_default_213: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1266, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1266 = None
2025-03-21T20:31:43.6610659Z             quantized_decomposed_quantize_per_tensor_default_871: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_213, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_permute_copy_default_213 = None
2025-03-21T20:31:43.6611804Z             quantized_decomposed_dequantize_per_tensor_default_1284: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_871, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_871 = None
2025-03-21T20:31:43.6612595Z             aten_select_copy_int_242: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1284, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1284 = None
2025-03-21T20:31:43.6613497Z             quantized_decomposed_quantize_per_tensor_default_872: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_242, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_select_copy_int_242 = None
2025-03-21T20:31:43.6614657Z             quantized_decomposed_dequantize_per_tensor_default_1285: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_872, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_872 = None
2025-03-21T20:31:43.6615423Z             aten_select_copy_int_243: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1285, 0, 1);  quantized_decomposed_dequantize_per_tensor_default_1285 = None
2025-03-21T20:31:43.6616323Z             quantized_decomposed_quantize_per_tensor_default_873: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_243, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_select_copy_int_243 = None
2025-03-21T20:31:43.6616412Z             
2025-03-21T20:31:43.6617362Z              # File: <eval_with_key>.50:3220 in forward, code: dequantize_per_tensor_default_1027 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1027, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantize_per_tensor_default_1027 = None
2025-03-21T20:31:43.6618505Z             quantized_decomposed_dequantize_per_tensor_default_1286: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_873, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_873 = None
2025-03-21T20:31:43.6618609Z             
2025-03-21T20:31:43.6619248Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6620066Z             aten_permute_copy_default_214: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1265, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1265 = None
2025-03-21T20:31:43.6621033Z             quantized_decomposed_quantize_per_tensor_default_874: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_214, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_permute_copy_default_214 = None
2025-03-21T20:31:43.6622209Z             quantized_decomposed_dequantize_per_tensor_default_1287: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_874, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_874 = None
2025-03-21T20:31:43.6622953Z             aten_select_copy_int_244: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1287, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1287 = None
2025-03-21T20:31:43.6623864Z             quantized_decomposed_quantize_per_tensor_default_875: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_244, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_select_copy_int_244 = None
2025-03-21T20:31:43.6625036Z             quantized_decomposed_dequantize_per_tensor_default_1288: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_875, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_875 = None
2025-03-21T20:31:43.6625792Z             aten_select_copy_int_245: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1288, 0, 2);  quantized_decomposed_dequantize_per_tensor_default_1288 = None
2025-03-21T20:31:43.6626692Z             quantized_decomposed_quantize_per_tensor_default_876: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_245, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_select_copy_int_245 = None
2025-03-21T20:31:43.6626814Z             
2025-03-21T20:31:43.6627756Z              # File: <eval_with_key>.50:3229 in forward, code: dequantize_per_tensor_default_1030 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1030, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantize_per_tensor_default_1030 = None
2025-03-21T20:31:43.6628910Z             quantized_decomposed_dequantize_per_tensor_default_1289: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_876, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_876 = None
2025-03-21T20:31:43.6629000Z             
2025-03-21T20:31:43.6629655Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6630464Z             aten_permute_copy_default_215: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1264, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1264 = None
2025-03-21T20:31:43.6631412Z             quantized_decomposed_quantize_per_tensor_default_877: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_215, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_permute_copy_default_215 = None
2025-03-21T20:31:43.6632775Z             quantized_decomposed_dequantize_per_tensor_default_1290: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_877, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_877 = None
2025-03-21T20:31:43.6633594Z             aten_select_copy_int_246: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1290, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1290 = None
2025-03-21T20:31:43.6634533Z             quantized_decomposed_quantize_per_tensor_default_878: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_246, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_select_copy_int_246 = None
2025-03-21T20:31:43.6635681Z             quantized_decomposed_dequantize_per_tensor_default_1291: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_878, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_878 = None
2025-03-21T20:31:43.6636432Z             aten_select_copy_int_247: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1291, 0, 3);  quantized_decomposed_dequantize_per_tensor_default_1291 = None
2025-03-21T20:31:43.6637367Z             quantized_decomposed_quantize_per_tensor_default_879: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_247, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_select_copy_int_247 = None
2025-03-21T20:31:43.6637473Z             
2025-03-21T20:31:43.6638412Z              # File: <eval_with_key>.50:3238 in forward, code: dequantize_per_tensor_default_1033 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1033, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantize_per_tensor_default_1033 = None
2025-03-21T20:31:43.6639603Z             quantized_decomposed_dequantize_per_tensor_default_1292: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_879, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_879 = None
2025-03-21T20:31:43.6639692Z             
2025-03-21T20:31:43.6640340Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6641143Z             aten_permute_copy_default_216: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1263, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1263 = None
2025-03-21T20:31:43.6642089Z             quantized_decomposed_quantize_per_tensor_default_880: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_216, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_permute_copy_default_216 = None
2025-03-21T20:31:43.6643234Z             quantized_decomposed_dequantize_per_tensor_default_1293: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_880, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_880 = None
2025-03-21T20:31:43.6644090Z             aten_select_copy_int_248: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1293, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1293 = None
2025-03-21T20:31:43.6644981Z             quantized_decomposed_quantize_per_tensor_default_881: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_248, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_select_copy_int_248 = None
2025-03-21T20:31:43.6646166Z             quantized_decomposed_dequantize_per_tensor_default_1294: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_881, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_881 = None
2025-03-21T20:31:43.6646929Z             aten_select_copy_int_249: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1294, 0, 4);  quantized_decomposed_dequantize_per_tensor_default_1294 = None
2025-03-21T20:31:43.6647832Z             quantized_decomposed_quantize_per_tensor_default_882: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_249, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_select_copy_int_249 = None
2025-03-21T20:31:43.6647920Z             
2025-03-21T20:31:43.6648865Z              # File: <eval_with_key>.50:3247 in forward, code: dequantize_per_tensor_default_1036 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1036, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantize_per_tensor_default_1036 = None
2025-03-21T20:31:43.6650102Z             quantized_decomposed_dequantize_per_tensor_default_1295: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_882, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_882 = None
2025-03-21T20:31:43.6650205Z             
2025-03-21T20:31:43.6650841Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6651685Z             aten_permute_copy_default_217: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1262, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1262 = None
2025-03-21T20:31:43.6652621Z             quantized_decomposed_quantize_per_tensor_default_883: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_217, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_permute_copy_default_217 = None
2025-03-21T20:31:43.6653770Z             quantized_decomposed_dequantize_per_tensor_default_1296: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_883, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_883 = None
2025-03-21T20:31:43.6654658Z             aten_select_copy_int_250: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1296, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1296 = None
2025-03-21T20:31:43.6655666Z             quantized_decomposed_quantize_per_tensor_default_884: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_250, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_select_copy_int_250 = None
2025-03-21T20:31:43.6656822Z             quantized_decomposed_dequantize_per_tensor_default_1297: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_884, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_884 = None
2025-03-21T20:31:43.6657558Z             aten_select_copy_int_251: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1297, 0, 5);  quantized_decomposed_dequantize_per_tensor_default_1297 = None
2025-03-21T20:31:43.6658541Z             quantized_decomposed_quantize_per_tensor_default_885: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_251, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_select_copy_int_251 = None
2025-03-21T20:31:43.6658630Z             
2025-03-21T20:31:43.6659579Z              # File: <eval_with_key>.50:3256 in forward, code: dequantize_per_tensor_default_1039 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1039, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantize_per_tensor_default_1039 = None
2025-03-21T20:31:43.6660714Z             quantized_decomposed_dequantize_per_tensor_default_1298: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_885, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_885 = None
2025-03-21T20:31:43.6660823Z             
2025-03-21T20:31:43.6661487Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6662293Z             aten_permute_copy_default_218: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1261, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1261 = None
2025-03-21T20:31:43.6663240Z             quantized_decomposed_quantize_per_tensor_default_886: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_218, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_permute_copy_default_218 = None
2025-03-21T20:31:43.6664422Z             quantized_decomposed_dequantize_per_tensor_default_1299: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_886, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_886 = None
2025-03-21T20:31:43.6665165Z             aten_select_copy_int_252: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1299, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1299 = None
2025-03-21T20:31:43.6666071Z             quantized_decomposed_quantize_per_tensor_default_887: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_252, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_select_copy_int_252 = None
2025-03-21T20:31:43.6667217Z             quantized_decomposed_dequantize_per_tensor_default_1300: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_887, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_887 = None
2025-03-21T20:31:43.6667972Z             aten_select_copy_int_253: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1300, 0, 6);  quantized_decomposed_dequantize_per_tensor_default_1300 = None
2025-03-21T20:31:43.6668860Z             quantized_decomposed_quantize_per_tensor_default_888: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_253, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_select_copy_int_253 = None
2025-03-21T20:31:43.6668967Z             
2025-03-21T20:31:43.6669926Z              # File: <eval_with_key>.50:3265 in forward, code: dequantize_per_tensor_default_1042 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1042, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantize_per_tensor_default_1042 = None
2025-03-21T20:31:43.6671102Z             quantized_decomposed_dequantize_per_tensor_default_1301: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_888, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_888 = None
2025-03-21T20:31:43.6671190Z             
2025-03-21T20:31:43.6671839Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6672640Z             aten_permute_copy_default_219: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1260, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1260 = None
2025-03-21T20:31:43.6673610Z             quantized_decomposed_quantize_per_tensor_default_889: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_219, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_permute_copy_default_219 = None
2025-03-21T20:31:43.6674754Z             quantized_decomposed_dequantize_per_tensor_default_1302: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_889, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_889 = None
2025-03-21T20:31:43.6675503Z             aten_select_copy_int_254: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1302, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1302 = None
2025-03-21T20:31:43.6676427Z             quantized_decomposed_quantize_per_tensor_default_890: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_254, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_select_copy_int_254 = None
2025-03-21T20:31:43.6677578Z             quantized_decomposed_dequantize_per_tensor_default_1303: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_890, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_890 = None
2025-03-21T20:31:43.6678316Z             aten_select_copy_int_255: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1303, 0, 7);  quantized_decomposed_dequantize_per_tensor_default_1303 = None
2025-03-21T20:31:43.6679220Z             quantized_decomposed_quantize_per_tensor_default_891: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_255, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_select_copy_int_255 = None
2025-03-21T20:31:43.6679308Z             
2025-03-21T20:31:43.6680260Z              # File: <eval_with_key>.50:3274 in forward, code: dequantize_per_tensor_default_1045 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1045, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantize_per_tensor_default_1045 = None
2025-03-21T20:31:43.6681393Z             quantized_decomposed_dequantize_per_tensor_default_1304: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_891, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_891 = None
2025-03-21T20:31:43.6681495Z             
2025-03-21T20:31:43.6682156Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6682994Z             aten_permute_copy_default_220: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1259, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1259 = None
2025-03-21T20:31:43.6683926Z             quantized_decomposed_quantize_per_tensor_default_892: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_220, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_permute_copy_default_220 = None
2025-03-21T20:31:43.6685079Z             quantized_decomposed_dequantize_per_tensor_default_1305: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_892, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_892 = None
2025-03-21T20:31:43.6685846Z             aten_select_copy_int_256: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1305, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1305 = None
2025-03-21T20:31:43.6686745Z             quantized_decomposed_quantize_per_tensor_default_893: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_256, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_select_copy_int_256 = None
2025-03-21T20:31:43.6687897Z             quantized_decomposed_dequantize_per_tensor_default_1306: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_893, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_893 = None
2025-03-21T20:31:43.6688661Z             aten_select_copy_int_257: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1306, 0, 8);  quantized_decomposed_dequantize_per_tensor_default_1306 = None
2025-03-21T20:31:43.6689644Z             quantized_decomposed_quantize_per_tensor_default_894: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_257, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_select_copy_int_257 = None
2025-03-21T20:31:43.6689737Z             
2025-03-21T20:31:43.6690686Z              # File: <eval_with_key>.50:3283 in forward, code: dequantize_per_tensor_default_1048 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1048, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantize_per_tensor_default_1048 = None
2025-03-21T20:31:43.6691832Z             quantized_decomposed_dequantize_per_tensor_default_1307: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_894, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_894 = None
2025-03-21T20:31:43.6691938Z             
2025-03-21T20:31:43.6692571Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6693388Z             aten_permute_copy_default_221: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1258, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1258 = None
2025-03-21T20:31:43.6694356Z             quantized_decomposed_quantize_per_tensor_default_895: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_221, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_permute_copy_default_221 = None
2025-03-21T20:31:43.6695535Z             quantized_decomposed_dequantize_per_tensor_default_1308: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_895, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_895 = None
2025-03-21T20:31:43.6696279Z             aten_select_copy_int_258: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1308, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1308 = None
2025-03-21T20:31:43.6697186Z             quantized_decomposed_quantize_per_tensor_default_896: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_258, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_select_copy_int_258 = None
2025-03-21T20:31:43.6698401Z             quantized_decomposed_dequantize_per_tensor_default_1309: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_896, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_896 = None
2025-03-21T20:31:43.6699155Z             aten_select_copy_int_259: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1309, 0, 9);  quantized_decomposed_dequantize_per_tensor_default_1309 = None
2025-03-21T20:31:43.6700079Z             quantized_decomposed_quantize_per_tensor_default_897: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_259, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_select_copy_int_259 = None
2025-03-21T20:31:43.6700185Z             
2025-03-21T20:31:43.6701120Z              # File: <eval_with_key>.50:3292 in forward, code: dequantize_per_tensor_default_1051 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1051, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantize_per_tensor_default_1051 = None
2025-03-21T20:31:43.6702271Z             quantized_decomposed_dequantize_per_tensor_default_1310: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_897, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_897 = None
2025-03-21T20:31:43.6702361Z             
2025-03-21T20:31:43.6703010Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6703817Z             aten_permute_copy_default_222: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1257, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1257 = None
2025-03-21T20:31:43.6704769Z             quantized_decomposed_quantize_per_tensor_default_898: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_222, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_permute_copy_default_222 = None
2025-03-21T20:31:43.6705912Z             quantized_decomposed_dequantize_per_tensor_default_1311: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_898, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_898 = None
2025-03-21T20:31:43.6706724Z             aten_select_copy_int_260: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1311, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1311 = None
2025-03-21T20:31:43.6707620Z             quantized_decomposed_quantize_per_tensor_default_899: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_260, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_select_copy_int_260 = None
2025-03-21T20:31:43.6708775Z             quantized_decomposed_dequantize_per_tensor_default_1312: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_899, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_899 = None
2025-03-21T20:31:43.6709522Z             aten_select_copy_int_261: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1312, 0, 10);  quantized_decomposed_dequantize_per_tensor_default_1312 = None
2025-03-21T20:31:43.6710455Z             quantized_decomposed_quantize_per_tensor_default_900: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_261, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_select_copy_int_261 = None
2025-03-21T20:31:43.6710544Z             
2025-03-21T20:31:43.6711490Z              # File: <eval_with_key>.50:3301 in forward, code: dequantize_per_tensor_default_1054 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1054, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantize_per_tensor_default_1054 = None
2025-03-21T20:31:43.6712649Z             quantized_decomposed_dequantize_per_tensor_default_1313: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_900, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_900 = None
2025-03-21T20:31:43.6712756Z             
2025-03-21T20:31:43.6713392Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6714203Z             aten_permute_copy_default_223: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1256, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1256 = None
2025-03-21T20:31:43.6715138Z             quantized_decomposed_quantize_per_tensor_default_901: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_223, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_permute_copy_default_223 = None
2025-03-21T20:31:43.6716294Z             quantized_decomposed_dequantize_per_tensor_default_1314: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_901, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_901 = None
2025-03-21T20:31:43.6717044Z             aten_select_copy_int_262: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1314, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1314 = None
2025-03-21T20:31:43.6717933Z             quantized_decomposed_quantize_per_tensor_default_902: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_262, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_select_copy_int_262 = None
2025-03-21T20:31:43.6719148Z             quantized_decomposed_dequantize_per_tensor_default_1315: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_902, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_902 = None
2025-03-21T20:31:43.6719886Z             aten_select_copy_int_263: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1315, 0, 11);  quantized_decomposed_dequantize_per_tensor_default_1315 = None
2025-03-21T20:31:43.6720780Z             quantized_decomposed_quantize_per_tensor_default_903: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_263, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_select_copy_int_263 = None
2025-03-21T20:31:43.6720869Z             
2025-03-21T20:31:43.6721848Z              # File: <eval_with_key>.50:3310 in forward, code: dequantize_per_tensor_default_1057 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1057, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantize_per_tensor_default_1057 = None
2025-03-21T20:31:43.6722983Z             quantized_decomposed_dequantize_per_tensor_default_1316: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_903, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_903 = None
2025-03-21T20:31:43.6723083Z             
2025-03-21T20:31:43.6723715Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6729238Z             aten_cat_default_22: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_aten_cat_default([quantized_decomposed_dequantize_per_tensor_default_1283, quantized_decomposed_dequantize_per_tensor_default_1286, quantized_decomposed_dequantize_per_tensor_default_1289, quantized_decomposed_dequantize_per_tensor_default_1292, quantized_decomposed_dequantize_per_tensor_default_1295, quantized_decomposed_dequantize_per_tensor_default_1298, quantized_decomposed_dequantize_per_tensor_default_1301, quantized_decomposed_dequantize_per_tensor_default_1304, quantized_decomposed_dequantize_per_tensor_default_1307, quantized_decomposed_dequantize_per_tensor_default_1310, quantized_decomposed_dequantize_per_tensor_default_1313, quantized_decomposed_dequantize_per_tensor_default_1316]);  quantized_decomposed_dequantize_per_tensor_default_1283 = quantized_decomposed_dequantize_per_tensor_default_1286 = quantized_decomposed_dequantize_per_tensor_default_1289 = quantized_decomposed_dequantize_per_tensor_default_1292 = quantized_decomposed_dequantize_per_tensor_default_1295 = quantized_decomposed_dequantize_per_tensor_default_1298 = quantized_decomposed_dequantize_per_tensor_default_1301 = quantized_decomposed_dequantize_per_tensor_default_1304 = quantized_decomposed_dequantize_per_tensor_default_1307 = quantized_decomposed_dequantize_per_tensor_default_1310 = quantized_decomposed_dequantize_per_tensor_default_1313 = quantized_decomposed_dequantize_per_tensor_default_1316 = None
2025-03-21T20:31:43.6730192Z             quantized_decomposed_quantize_per_tensor_default_904: "i32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_22, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_cat_default_22 = None
2025-03-21T20:31:43.6731371Z             quantized_decomposed_dequantize_per_tensor_default_1317: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_904, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_904 = None
2025-03-21T20:31:43.6732187Z             aten_view_copy_default_99: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1317, [1, 12, 128, 64]);  quantized_decomposed_dequantize_per_tensor_default_1317 = None
2025-03-21T20:31:43.6733288Z             quantized_decomposed_quantize_per_tensor_default_905: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_99, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_view_copy_default_99 = None
2025-03-21T20:31:43.6733393Z             
2025-03-21T20:31:43.6733972Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.6735195Z             quantized_decomposed_dequantize_per_tensor_default_1318: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_905, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_905 = None
2025-03-21T20:31:43.6735287Z             
2025-03-21T20:31:43.6735937Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6736736Z             aten_permute_copy_default_224: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1280, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1280 = None
2025-03-21T20:31:43.6737724Z             quantized_decomposed_quantize_per_tensor_default_906: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_224, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_permute_copy_default_224 = None
2025-03-21T20:31:43.6738872Z             quantized_decomposed_dequantize_per_tensor_default_1319: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_906, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_906 = None
2025-03-21T20:31:43.6739624Z             aten_select_copy_int_264: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1319, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1319 = None
2025-03-21T20:31:43.6740516Z             quantized_decomposed_quantize_per_tensor_default_907: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_264, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_select_copy_int_264 = None
2025-03-21T20:31:43.6741682Z             quantized_decomposed_dequantize_per_tensor_default_1320: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_907, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_907 = None
2025-03-21T20:31:43.6742420Z             aten_select_copy_int_265: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1320, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1320 = None
2025-03-21T20:31:43.6743316Z             quantized_decomposed_quantize_per_tensor_default_908: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_265, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_select_copy_int_265 = None
2025-03-21T20:31:43.6743441Z             
2025-03-21T20:31:43.6744430Z              # File: <eval_with_key>.50:3325 in forward, code: dequantize_per_tensor_default_1062 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1062, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantize_per_tensor_default_1062 = None
2025-03-21T20:31:43.6745570Z             quantized_decomposed_dequantize_per_tensor_default_1321: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_908, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_908 = None
2025-03-21T20:31:43.6745673Z             
2025-03-21T20:31:43.6746310Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6747127Z             aten_permute_copy_default_225: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1279, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1279 = None
2025-03-21T20:31:43.6748110Z             quantized_decomposed_quantize_per_tensor_default_909: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_225, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_permute_copy_default_225 = None
2025-03-21T20:31:43.6749263Z             quantized_decomposed_dequantize_per_tensor_default_1322: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_909, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_909 = None
2025-03-21T20:31:43.6750047Z             aten_select_copy_int_266: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1322, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1322 = None
2025-03-21T20:31:43.6750938Z             quantized_decomposed_quantize_per_tensor_default_910: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_266, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_select_copy_int_266 = None
2025-03-21T20:31:43.6752090Z             quantized_decomposed_dequantize_per_tensor_default_1323: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_910, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_910 = None
2025-03-21T20:31:43.6752831Z             aten_select_copy_int_267: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1323, 0, 1);  quantized_decomposed_dequantize_per_tensor_default_1323 = None
2025-03-21T20:31:43.6753732Z             quantized_decomposed_quantize_per_tensor_default_911: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_267, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_select_copy_int_267 = None
2025-03-21T20:31:43.6753821Z             
2025-03-21T20:31:43.6754772Z              # File: <eval_with_key>.50:3334 in forward, code: dequantize_per_tensor_default_1065 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1065, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantize_per_tensor_default_1065 = None
2025-03-21T20:31:43.6755937Z             quantized_decomposed_dequantize_per_tensor_default_1324: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_911, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_911 = None
2025-03-21T20:31:43.6756076Z             
2025-03-21T20:31:43.6756832Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6757655Z             aten_permute_copy_default_226: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1278, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1278 = None
2025-03-21T20:31:43.6758588Z             quantized_decomposed_quantize_per_tensor_default_912: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_226, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_permute_copy_default_226 = None
2025-03-21T20:31:43.6759782Z             quantized_decomposed_dequantize_per_tensor_default_1325: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_912, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_912 = None
2025-03-21T20:31:43.6760528Z             aten_select_copy_int_268: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1325, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1325 = None
2025-03-21T20:31:43.6761430Z             quantized_decomposed_quantize_per_tensor_default_913: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_268, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_select_copy_int_268 = None
2025-03-21T20:31:43.6762597Z             quantized_decomposed_dequantize_per_tensor_default_1326: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_913, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_913 = None
2025-03-21T20:31:43.6763353Z             aten_select_copy_int_269: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1326, 0, 2);  quantized_decomposed_dequantize_per_tensor_default_1326 = None
2025-03-21T20:31:43.6764239Z             quantized_decomposed_quantize_per_tensor_default_914: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_269, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_select_copy_int_269 = None
2025-03-21T20:31:43.6764349Z             
2025-03-21T20:31:43.6765286Z              # File: <eval_with_key>.50:3343 in forward, code: dequantize_per_tensor_default_1068 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1068, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantize_per_tensor_default_1068 = None
2025-03-21T20:31:43.6766440Z             quantized_decomposed_dequantize_per_tensor_default_1327: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_914, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_914 = None
2025-03-21T20:31:43.6766530Z             
2025-03-21T20:31:43.6767185Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6768016Z             aten_permute_copy_default_227: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1277, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1277 = None
2025-03-21T20:31:43.6768997Z             quantized_decomposed_quantize_per_tensor_default_915: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_227, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_permute_copy_default_227 = None
2025-03-21T20:31:43.6770203Z             quantized_decomposed_dequantize_per_tensor_default_1328: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_915, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_915 = None
2025-03-21T20:31:43.6770971Z             aten_select_copy_int_270: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1328, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1328 = None
2025-03-21T20:31:43.6771896Z             quantized_decomposed_quantize_per_tensor_default_916: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_270, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_select_copy_int_270 = None
2025-03-21T20:31:43.6773050Z             quantized_decomposed_dequantize_per_tensor_default_1329: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_916, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_916 = None
2025-03-21T20:31:43.6773787Z             aten_select_copy_int_271: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1329, 0, 3);  quantized_decomposed_dequantize_per_tensor_default_1329 = None
2025-03-21T20:31:43.6774718Z             quantized_decomposed_quantize_per_tensor_default_917: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_271, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_select_copy_int_271 = None
2025-03-21T20:31:43.6774805Z             
2025-03-21T20:31:43.6775756Z              # File: <eval_with_key>.50:3352 in forward, code: dequantize_per_tensor_default_1071 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1071, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantize_per_tensor_default_1071 = None
2025-03-21T20:31:43.6776892Z             quantized_decomposed_dequantize_per_tensor_default_1330: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_917, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_917 = None
2025-03-21T20:31:43.6777009Z             
2025-03-21T20:31:43.6777648Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6778463Z             aten_permute_copy_default_228: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1276, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1276 = None
2025-03-21T20:31:43.6779396Z             quantized_decomposed_quantize_per_tensor_default_918: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_228, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_permute_copy_default_228 = None
2025-03-21T20:31:43.6780574Z             quantized_decomposed_dequantize_per_tensor_default_1331: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_918, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_918 = None
2025-03-21T20:31:43.6781351Z             aten_select_copy_int_272: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1331, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1331 = None
2025-03-21T20:31:43.6782239Z             quantized_decomposed_quantize_per_tensor_default_919: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_272, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_select_copy_int_272 = None
2025-03-21T20:31:43.6783395Z             quantized_decomposed_dequantize_per_tensor_default_1332: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_919, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_919 = None
2025-03-21T20:31:43.6784156Z             aten_select_copy_int_273: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1332, 0, 4);  quantized_decomposed_dequantize_per_tensor_default_1332 = None
2025-03-21T20:31:43.6785059Z             quantized_decomposed_quantize_per_tensor_default_920: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_273, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_select_copy_int_273 = None
2025-03-21T20:31:43.6785146Z             
2025-03-21T20:31:43.6786145Z              # File: <eval_with_key>.50:3361 in forward, code: dequantize_per_tensor_default_1074 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1074, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantize_per_tensor_default_1074 = None
2025-03-21T20:31:43.6787282Z             quantized_decomposed_dequantize_per_tensor_default_1333: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_920, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_920 = None
2025-03-21T20:31:43.6787381Z             
2025-03-21T20:31:43.6788017Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6788828Z             aten_permute_copy_default_229: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1275, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1275 = None
2025-03-21T20:31:43.6789768Z             quantized_decomposed_quantize_per_tensor_default_921: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_229, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_permute_copy_default_229 = None
2025-03-21T20:31:43.6790917Z             quantized_decomposed_dequantize_per_tensor_default_1334: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_921, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_921 = None
2025-03-21T20:31:43.6791655Z             aten_select_copy_int_274: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1334, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1334 = None
2025-03-21T20:31:43.6792587Z             quantized_decomposed_quantize_per_tensor_default_922: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_274, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_select_copy_int_274 = None
2025-03-21T20:31:43.6793759Z             quantized_decomposed_dequantize_per_tensor_default_1335: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_922, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_922 = None
2025-03-21T20:31:43.6794504Z             aten_select_copy_int_275: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1335, 0, 5);  quantized_decomposed_dequantize_per_tensor_default_1335 = None
2025-03-21T20:31:43.6795390Z             quantized_decomposed_quantize_per_tensor_default_923: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_275, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_select_copy_int_275 = None
2025-03-21T20:31:43.6795492Z             
2025-03-21T20:31:43.6796450Z              # File: <eval_with_key>.50:3370 in forward, code: dequantize_per_tensor_default_1077 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1077, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantize_per_tensor_default_1077 = None
2025-03-21T20:31:43.6797597Z             quantized_decomposed_dequantize_per_tensor_default_1336: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_923, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_923 = None
2025-03-21T20:31:43.6797713Z             
2025-03-21T20:31:43.6798362Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6799167Z             aten_permute_copy_default_230: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1274, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1274 = None
2025-03-21T20:31:43.6800111Z             quantized_decomposed_quantize_per_tensor_default_924: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_230, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_permute_copy_default_230 = None
2025-03-21T20:31:43.6801249Z             quantized_decomposed_dequantize_per_tensor_default_1337: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_924, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_924 = None
2025-03-21T20:31:43.6802009Z             aten_select_copy_int_276: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1337, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1337 = None
2025-03-21T20:31:43.6802900Z             quantized_decomposed_quantize_per_tensor_default_925: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_276, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_select_copy_int_276 = None
2025-03-21T20:31:43.6804075Z             quantized_decomposed_dequantize_per_tensor_default_1338: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_925, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_925 = None
2025-03-21T20:31:43.6804850Z             aten_select_copy_int_277: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1338, 0, 6);  quantized_decomposed_dequantize_per_tensor_default_1338 = None
2025-03-21T20:31:43.6805736Z             quantized_decomposed_quantize_per_tensor_default_926: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_277, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_select_copy_int_277 = None
2025-03-21T20:31:43.6805835Z             
2025-03-21T20:31:43.6806771Z              # File: <eval_with_key>.50:3379 in forward, code: dequantize_per_tensor_default_1080 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1080, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantize_per_tensor_default_1080 = None
2025-03-21T20:31:43.6807951Z             quantized_decomposed_dequantize_per_tensor_default_1339: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_926, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_926 = None
2025-03-21T20:31:43.6808041Z             
2025-03-21T20:31:43.6808679Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6809581Z             aten_permute_copy_default_231: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1273, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1273 = None
2025-03-21T20:31:43.6810580Z             quantized_decomposed_quantize_per_tensor_default_927: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_231, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_permute_copy_default_231 = None
2025-03-21T20:31:43.6811726Z             quantized_decomposed_dequantize_per_tensor_default_1340: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_927, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_927 = None
2025-03-21T20:31:43.6812482Z             aten_select_copy_int_278: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1340, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1340 = None
2025-03-21T20:31:43.6813377Z             quantized_decomposed_quantize_per_tensor_default_928: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_278, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_select_copy_int_278 = None
2025-03-21T20:31:43.6814533Z             quantized_decomposed_dequantize_per_tensor_default_1341: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_928, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_928 = None
2025-03-21T20:31:43.6815273Z             aten_select_copy_int_279: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1341, 0, 7);  quantized_decomposed_dequantize_per_tensor_default_1341 = None
2025-03-21T20:31:43.6816195Z             quantized_decomposed_quantize_per_tensor_default_929: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_279, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_select_copy_int_279 = None
2025-03-21T20:31:43.6816309Z             
2025-03-21T20:31:43.6817261Z              # File: <eval_with_key>.50:3388 in forward, code: dequantize_per_tensor_default_1083 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1083, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantize_per_tensor_default_1083 = None
2025-03-21T20:31:43.6818399Z             quantized_decomposed_dequantize_per_tensor_default_1342: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_929, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_929 = None
2025-03-21T20:31:43.6818500Z             
2025-03-21T20:31:43.6819134Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6819974Z             aten_permute_copy_default_232: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1272, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1272 = None
2025-03-21T20:31:43.6820907Z             quantized_decomposed_quantize_per_tensor_default_930: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_232, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_permute_copy_default_232 = None
2025-03-21T20:31:43.6822059Z             quantized_decomposed_dequantize_per_tensor_default_1343: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_930, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_930 = None
2025-03-21T20:31:43.6822830Z             aten_select_copy_int_280: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1343, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1343 = None
2025-03-21T20:31:43.6823731Z             quantized_decomposed_quantize_per_tensor_default_931: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_280, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_select_copy_int_280 = None
2025-03-21T20:31:43.6824870Z             quantized_decomposed_dequantize_per_tensor_default_1344: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_931, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_931 = None
2025-03-21T20:31:43.6825619Z             aten_select_copy_int_281: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1344, 0, 8);  quantized_decomposed_dequantize_per_tensor_default_1344 = None
2025-03-21T20:31:43.6826506Z             quantized_decomposed_quantize_per_tensor_default_932: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_281, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_select_copy_int_281 = None
2025-03-21T20:31:43.6826607Z             
2025-03-21T20:31:43.6827537Z              # File: <eval_with_key>.50:3397 in forward, code: dequantize_per_tensor_default_1086 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1086, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantize_per_tensor_default_1086 = None
2025-03-21T20:31:43.6828708Z             quantized_decomposed_dequantize_per_tensor_default_1345: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_932, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_932 = None
2025-03-21T20:31:43.6828823Z             
2025-03-21T20:31:43.6829470Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6830269Z             aten_permute_copy_default_233: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1271, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1271 = None
2025-03-21T20:31:43.6831215Z             quantized_decomposed_quantize_per_tensor_default_933: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_233, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_permute_copy_default_233 = None
2025-03-21T20:31:43.6832588Z             quantized_decomposed_dequantize_per_tensor_default_1346: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_933, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_933 = None
2025-03-21T20:31:43.6833351Z             aten_select_copy_int_282: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1346, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1346 = None
2025-03-21T20:31:43.6834238Z             quantized_decomposed_quantize_per_tensor_default_934: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_282, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_select_copy_int_282 = None
2025-03-21T20:31:43.6835434Z             quantized_decomposed_dequantize_per_tensor_default_1347: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_934, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_934 = None
2025-03-21T20:31:43.6836189Z             aten_select_copy_int_283: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1347, 0, 9);  quantized_decomposed_dequantize_per_tensor_default_1347 = None
2025-03-21T20:31:43.6837076Z             quantized_decomposed_quantize_per_tensor_default_935: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_283, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_select_copy_int_283 = None
2025-03-21T20:31:43.6837179Z             
2025-03-21T20:31:43.6838117Z              # File: <eval_with_key>.50:3406 in forward, code: dequantize_per_tensor_default_1089 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1089, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantize_per_tensor_default_1089 = None
2025-03-21T20:31:43.6839264Z             quantized_decomposed_dequantize_per_tensor_default_1348: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_935, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_935 = None
2025-03-21T20:31:43.6839350Z             
2025-03-21T20:31:43.6839996Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6840849Z             aten_permute_copy_default_234: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1270, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1270 = None
2025-03-21T20:31:43.6841831Z             quantized_decomposed_quantize_per_tensor_default_936: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_234, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_permute_copy_default_234 = None
2025-03-21T20:31:43.6842969Z             quantized_decomposed_dequantize_per_tensor_default_1349: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_936, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_936 = None
2025-03-21T20:31:43.6843724Z             aten_select_copy_int_284: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1349, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1349 = None
2025-03-21T20:31:43.6844640Z             quantized_decomposed_quantize_per_tensor_default_937: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_284, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_select_copy_int_284 = None
2025-03-21T20:31:43.6845793Z             quantized_decomposed_dequantize_per_tensor_default_1350: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_937, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_937 = None
2025-03-21T20:31:43.6846562Z             aten_select_copy_int_285: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1350, 0, 10);  quantized_decomposed_dequantize_per_tensor_default_1350 = None
2025-03-21T20:31:43.6847563Z             quantized_decomposed_quantize_per_tensor_default_938: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_285, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_select_copy_int_285 = None
2025-03-21T20:31:43.6847657Z             
2025-03-21T20:31:43.6848604Z              # File: <eval_with_key>.50:3415 in forward, code: dequantize_per_tensor_default_1092 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1092, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantize_per_tensor_default_1092 = None
2025-03-21T20:31:43.6849811Z             quantized_decomposed_dequantize_per_tensor_default_1351: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_938, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_938 = None
2025-03-21T20:31:43.6849921Z             
2025-03-21T20:31:43.6850557Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6851371Z             aten_permute_copy_default_235: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1269, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1269 = None
2025-03-21T20:31:43.6852302Z             quantized_decomposed_quantize_per_tensor_default_939: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_235, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_permute_copy_default_235 = None
2025-03-21T20:31:43.6853494Z             quantized_decomposed_dequantize_per_tensor_default_1352: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_939, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_939 = None
2025-03-21T20:31:43.6854264Z             aten_select_copy_int_286: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1352, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1352 = None
2025-03-21T20:31:43.6855164Z             quantized_decomposed_quantize_per_tensor_default_940: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_286, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_select_copy_int_286 = None
2025-03-21T20:31:43.6856330Z             quantized_decomposed_dequantize_per_tensor_default_1353: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_940, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_940 = None
2025-03-21T20:31:43.6857084Z             aten_select_copy_int_287: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1353, 0, 11);  quantized_decomposed_dequantize_per_tensor_default_1353 = None
2025-03-21T20:31:43.6858231Z             quantized_decomposed_quantize_per_tensor_default_941: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_287, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_select_copy_int_287 = None
2025-03-21T20:31:43.6858386Z             
2025-03-21T20:31:43.6859319Z              # File: <eval_with_key>.50:3424 in forward, code: dequantize_per_tensor_default_1095 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1095, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantize_per_tensor_default_1095 = None
2025-03-21T20:31:43.6860472Z             quantized_decomposed_dequantize_per_tensor_default_1354: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_941, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_941 = None
2025-03-21T20:31:43.6860559Z             
2025-03-21T20:31:43.6861210Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.6866726Z             aten_cat_default_23: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_aten_cat_default([quantized_decomposed_dequantize_per_tensor_default_1321, quantized_decomposed_dequantize_per_tensor_default_1324, quantized_decomposed_dequantize_per_tensor_default_1327, quantized_decomposed_dequantize_per_tensor_default_1330, quantized_decomposed_dequantize_per_tensor_default_1333, quantized_decomposed_dequantize_per_tensor_default_1336, quantized_decomposed_dequantize_per_tensor_default_1339, quantized_decomposed_dequantize_per_tensor_default_1342, quantized_decomposed_dequantize_per_tensor_default_1345, quantized_decomposed_dequantize_per_tensor_default_1348, quantized_decomposed_dequantize_per_tensor_default_1351, quantized_decomposed_dequantize_per_tensor_default_1354]);  quantized_decomposed_dequantize_per_tensor_default_1321 = quantized_decomposed_dequantize_per_tensor_default_1324 = quantized_decomposed_dequantize_per_tensor_default_1327 = quantized_decomposed_dequantize_per_tensor_default_1330 = quantized_decomposed_dequantize_per_tensor_default_1333 = quantized_decomposed_dequantize_per_tensor_default_1336 = quantized_decomposed_dequantize_per_tensor_default_1339 = quantized_decomposed_dequantize_per_tensor_default_1342 = quantized_decomposed_dequantize_per_tensor_default_1345 = quantized_decomposed_dequantize_per_tensor_default_1348 = quantized_decomposed_dequantize_per_tensor_default_1351 = quantized_decomposed_dequantize_per_tensor_default_1354 = None
2025-03-21T20:31:43.6867631Z             quantized_decomposed_quantize_per_tensor_default_942: "i32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_23, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_cat_default_23 = None
2025-03-21T20:31:43.6868768Z             quantized_decomposed_dequantize_per_tensor_default_1355: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_942, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_942 = None
2025-03-21T20:31:43.6869566Z             aten_view_copy_default_100: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1355, [1, 12, 128, 64]);  quantized_decomposed_dequantize_per_tensor_default_1355 = None
2025-03-21T20:31:43.6870501Z             quantized_decomposed_quantize_per_tensor_default_943: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_100, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  aten_view_copy_default_100 = None
2025-03-21T20:31:43.6870605Z             
2025-03-21T20:31:43.6871538Z              # File: <eval_with_key>.50:3430 in forward, code: dequantize_per_tensor_default_1097 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1097, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantize_per_tensor_default_1097 = None
2025-03-21T20:31:43.6872722Z             quantized_decomposed_dequantize_per_tensor_default_1356: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_943, 0.0001254916423931718, 28364, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_943 = None
2025-03-21T20:31:43.6872814Z             
2025-03-21T20:31:43.6873771Z              # File: <eval_with_key>.50:3431 in forward, code: quantize_per_tensor_default_1098 = torch.ops.quantized_decomposed.quantize_per_tensor.default(dequantize_per_tensor_default_1097, 0.00014235699200071394, 0, -32767, 32767, torch.int16);  dequantize_per_tensor_default_1097 = None
2025-03-21T20:31:43.6874933Z             quantized_decomposed_quantize_per_tensor_default_944: "i16[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_1356, 0.00014235699200071394, 0, -32767, 32767, torch.int16);  quantized_decomposed_dequantize_per_tensor_default_1356 = None
2025-03-21T20:31:43.6875040Z             
2025-03-21T20:31:43.6875510Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:163 in forward, code: y = attn_weight @ v
2025-03-21T20:31:43.6876678Z             quantized_decomposed_dequantize_per_tensor_default_1357: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_944, 0.00014235699200071394, 0, -32767, 32767, torch.int16);  quantized_decomposed_quantize_per_tensor_default_944 = None
2025-03-21T20:31:43.6876768Z             
2025-03-21T20:31:43.6877256Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:157 in forward, code: attn_mask = mask[input_pos]
2025-03-21T20:31:43.6878057Z             aten_index_tensor_7: "f32[1, 128]" = executorch_exir_dialects_edge__ops_aten_index_Tensor(quantized_decomposed_dequantize_per_tensor_default_130, [attn_options_input_pos]);  quantized_decomposed_dequantize_per_tensor_default_130 = None
2025-03-21T20:31:43.6878983Z             quantized_decomposed_quantize_per_tensor_default_945: "i32[1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_tensor_7, 0.0038910505827516317, 65535, 0, 65535, torch.int32);  aten_index_tensor_7 = None
2025-03-21T20:31:43.6879073Z             
2025-03-21T20:31:43.6879555Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:161 in forward, code: attn_weight += attn_mask
2025-03-21T20:31:43.6880699Z             quantized_decomposed_dequantize_per_tensor_default_1358: "f32[1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_945, 0.0038910505827516317, 65535, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_945 = None
2025-03-21T20:31:43.6880789Z             
2025-03-21T20:31:43.6881375Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.6882204Z             aten_permute_copy_default_236: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1318, [0, 1, 3, 2]);  quantized_decomposed_dequantize_per_tensor_default_1318 = None
2025-03-21T20:31:43.6883149Z             quantized_decomposed_quantize_per_tensor_default_946: "i32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_236, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  aten_permute_copy_default_236 = None
2025-03-21T20:31:43.6883237Z             
2025-03-21T20:31:43.6884186Z              # File: <eval_with_key>.50:3438 in forward, code: dequantize_per_tensor_default_1100 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1100, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantize_per_tensor_default_1100 = None
2025-03-21T20:31:43.6885374Z             quantized_decomposed_dequantize_per_tensor_default_1359: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_946, 0.0004216498928144574, 32136, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_946 = None
2025-03-21T20:31:43.6885475Z             
2025-03-21T20:31:43.6886413Z              # File: <eval_with_key>.50:3439 in forward, code: quantize_per_tensor_default_1101 = torch.ops.quantized_decomposed.quantize_per_tensor.default(dequantize_per_tensor_default_1100, 0.00042978691635653377, 0, -32767, 32767, torch.int16);  dequantize_per_tensor_default_1100 = None
2025-03-21T20:31:43.6887578Z             quantized_decomposed_quantize_per_tensor_default_947: "i16[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_1359, 0.00042978691635653377, 0, -32767, 32767, torch.int16);  quantized_decomposed_dequantize_per_tensor_default_1359 = None
2025-03-21T20:31:43.6887667Z             
2025-03-21T20:31:43.6888269Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.6889527Z             quantized_decomposed_dequantize_per_tensor_default_1360: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_947, 0.00042978691635653377, 0, -32767, 32767, torch.int16);  quantized_decomposed_quantize_per_tensor_default_947 = None
2025-03-21T20:31:43.6890337Z             aten_expand_copy_default_20: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_1254, [1, 12, 1, 64]);  quantized_decomposed_dequantize_per_tensor_default_1254 = None
2025-03-21T20:31:43.6891007Z             aten_view_copy_default_101: "f32[12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_20, [12, 1, 64]);  aten_expand_copy_default_20 = None
2025-03-21T20:31:43.6891816Z             aten_expand_copy_default_21: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_1360, [1, 12, 64, 128]);  quantized_decomposed_dequantize_per_tensor_default_1360 = None
2025-03-21T20:31:43.6892386Z             aten_view_copy_default_102: "f32[12, 64, 128]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_21, [12, 64, 128]);  aten_expand_copy_default_21 = None
2025-03-21T20:31:43.6893058Z             aten_bmm_default_10: "f32[12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_bmm_default(aten_view_copy_default_101, aten_view_copy_default_102);  aten_view_copy_default_101 = aten_view_copy_default_102 = None
2025-03-21T20:31:43.6893585Z             aten_view_copy_default_103: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_bmm_default_10, [1, 12, 1, 128]);  aten_bmm_default_10 = None
2025-03-21T20:31:43.6894534Z             quantized_decomposed_quantize_per_tensor_default_948: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_103, 0.0038201091811060905, 40308, 0, 65535, torch.int32);  aten_view_copy_default_103 = None
2025-03-21T20:31:43.6895677Z             quantized_decomposed_dequantize_per_tensor_default_1361: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_948, 0.0038201091811060905, 40308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_948 = None
2025-03-21T20:31:43.6896572Z             quantized_decomposed_dequantize_per_tensor_default_1362: "f32[1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param154, 1.9073777366429567e-06, 0, 0, 65535, torch.int32);  b__frozen_param154 = None
2025-03-21T20:31:43.6897715Z             aten_mul_tensor_85: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1361, quantized_decomposed_dequantize_per_tensor_default_1362);  quantized_decomposed_dequantize_per_tensor_default_1361 = quantized_decomposed_dequantize_per_tensor_default_1362 = None
2025-03-21T20:31:43.6898565Z             quantized_decomposed_quantize_per_tensor_default_949: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_85, 0.0004775136476382613, 40308, 0, 65535, torch.int32);  aten_mul_tensor_85 = None
2025-03-21T20:31:43.6898673Z             
2025-03-21T20:31:43.6899163Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:161 in forward, code: attn_weight += attn_mask
2025-03-21T20:31:43.6900323Z             quantized_decomposed_dequantize_per_tensor_default_1363: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_949, 0.0004775136476382613, 40308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_949 = None
2025-03-21T20:31:43.6901454Z             aten_add_tensor_27: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_1363, quantized_decomposed_dequantize_per_tensor_default_1358);  quantized_decomposed_dequantize_per_tensor_default_1363 = quantized_decomposed_dequantize_per_tensor_default_1358 = None
2025-03-21T20:31:43.6902341Z             quantized_decomposed_quantize_per_tensor_default_950: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_27, 0.004275546874850988, 62718, 0, 65535, torch.int32);  aten_add_tensor_27 = None
2025-03-21T20:31:43.6902458Z             
2025-03-21T20:31:43.6903046Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:162 in forward, code: attn_weight = torch.softmax(attn_weight, dim=-1)
2025-03-21T20:31:43.6904184Z             quantized_decomposed_dequantize_per_tensor_default_1364: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_950, 0.004275546874850988, 62718, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_950 = None
2025-03-21T20:31:43.6904976Z             aten__softmax_default_5: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten__softmax_default(quantized_decomposed_dequantize_per_tensor_default_1364, -1, False);  quantized_decomposed_dequantize_per_tensor_default_1364 = None
2025-03-21T20:31:43.6905880Z             quantized_decomposed_quantize_per_tensor_default_951: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten__softmax_default_5, 1.5259021893143654e-05, 0, 0, 65535, torch.int32);  aten__softmax_default_5 = None
2025-03-21T20:31:43.6905987Z             
2025-03-21T20:31:43.6906449Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:163 in forward, code: y = attn_weight @ v
2025-03-21T20:31:43.6907591Z             quantized_decomposed_dequantize_per_tensor_default_1365: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_951, 1.5259021893143654e-05, 0, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_951 = None
2025-03-21T20:31:43.6908409Z             aten_expand_copy_default_22: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_1365, [1, 12, 1, 128]);  quantized_decomposed_dequantize_per_tensor_default_1365 = None
2025-03-21T20:31:43.6908986Z             aten_view_copy_default_104: "f32[12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_22, [12, 1, 128]);  aten_expand_copy_default_22 = None
2025-03-21T20:31:43.6909778Z             aten_expand_copy_default_23: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_1357, [1, 12, 128, 64]);  quantized_decomposed_dequantize_per_tensor_default_1357 = None
2025-03-21T20:31:43.6910357Z             aten_view_copy_default_105: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_23, [12, 128, 64]);  aten_expand_copy_default_23 = None
2025-03-21T20:31:43.6911013Z             aten_bmm_default_11: "f32[12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_bmm_default(aten_view_copy_default_104, aten_view_copy_default_105);  aten_view_copy_default_104 = aten_view_copy_default_105 = None
2025-03-21T20:31:43.6911541Z             aten_view_copy_default_106: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_bmm_default_11, [1, 12, 1, 64]);  aten_bmm_default_11 = None
2025-03-21T20:31:43.6912440Z             quantized_decomposed_quantize_per_tensor_default_952: "i32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_106, 7.123954856069759e-05, 34216, 0, 65535, torch.int32);  aten_view_copy_default_106 = None
2025-03-21T20:31:43.6912541Z             
2025-03-21T20:31:43.6913167Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:165 in forward, code: return y.transpose(1, 2).contiguous().view(bsz, seqlen, self.dim)
2025-03-21T20:31:43.6914344Z             quantized_decomposed_dequantize_per_tensor_default_1366: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_952, 7.123954856069759e-05, 34216, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_952 = None
2025-03-21T20:31:43.6915167Z             aten_permute_copy_default_237: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1366, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1366 = None
2025-03-21T20:31:43.6916102Z             quantized_decomposed_quantize_per_tensor_default_953: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_237, 7.123954856069759e-05, 34216, 0, 65535, torch.int32);  aten_permute_copy_default_237 = None
2025-03-21T20:31:43.6917236Z             quantized_decomposed_dequantize_per_tensor_default_1367: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_953, 7.123954856069759e-05, 34216, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_953 = None
2025-03-21T20:31:43.6918049Z             aten_view_copy_default_107: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1367, [1, 1, 768]);  quantized_decomposed_dequantize_per_tensor_default_1367 = None
2025-03-21T20:31:43.6918950Z             quantized_decomposed_quantize_per_tensor_default_954: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_107, 7.123954856069759e-05, 34216, 0, 65535, torch.int32);  aten_view_copy_default_107 = None
2025-03-21T20:31:43.6919079Z             
2025-03-21T20:31:43.6919603Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.6920749Z             quantized_decomposed_dequantize_per_tensor_default_1368: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_954, 7.123954856069759e-05, 34216, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_954 = None
2025-03-21T20:31:43.6921548Z             aten_unsqueeze_copy_default_62: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1368, -1);  quantized_decomposed_dequantize_per_tensor_default_1368 = None
2025-03-21T20:31:43.6922490Z             quantized_decomposed_quantize_per_tensor_default_955: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_62, 7.123954856069759e-05, 34216, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_62 = None
2025-03-21T20:31:43.6922579Z             
2025-03-21T20:31:43.6923001Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.6924137Z             quantized_decomposed_dequantize_per_tensor_default_1369: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_955, 7.123954856069759e-05, 34216, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_955 = None
2025-03-21T20:31:43.6924945Z             aten_permute_copy_default_238: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1369, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1369 = None
2025-03-21T20:31:43.6925898Z             quantized_decomposed_quantize_per_tensor_default_956: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_238, 7.123954856069759e-05, 34216, 0, 65535, torch.int32);  aten_permute_copy_default_238 = None
2025-03-21T20:31:43.6926024Z             
2025-03-21T20:31:43.6926389Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.6927532Z             quantized_decomposed_dequantize_per_tensor_default_1370: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_956, 7.123954856069759e-05, 34216, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_956 = None
2025-03-21T20:31:43.6928805Z             aten_convolution_default_38: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_1370, quantized_decomposed_dequantize_per_tensor_default_50, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_1370 = quantized_decomposed_dequantize_per_tensor_default_50 = None
2025-03-21T20:31:43.6929846Z             quantized_decomposed_quantize_per_tensor_default_957: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_38, 4.46785670646932e-05, 25383, 0, 65535, torch.int32);  aten_convolution_default_38 = None
2025-03-21T20:31:43.6929940Z             
2025-03-21T20:31:43.6930374Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.6931507Z             quantized_decomposed_dequantize_per_tensor_default_1371: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_957, 4.46785670646932e-05, 25383, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_957 = None
2025-03-21T20:31:43.6932498Z             aten_permute_copy_default_239: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1371, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1371 = None
2025-03-21T20:31:43.6933434Z             quantized_decomposed_quantize_per_tensor_default_958: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_239, 4.46785670646932e-05, 25383, 0, 65535, torch.int32);  aten_permute_copy_default_239 = None
2025-03-21T20:31:43.6933535Z             
2025-03-21T20:31:43.6934073Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.6935223Z             quantized_decomposed_dequantize_per_tensor_default_1372: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_958, 4.46785670646932e-05, 25383, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_958 = None
2025-03-21T20:31:43.6935979Z             aten_squeeze_copy_dims_62: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_1372, [-1]);  quantized_decomposed_dequantize_per_tensor_default_1372 = None
2025-03-21T20:31:43.6936879Z             quantized_decomposed_quantize_per_tensor_default_959: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_62, 4.46785670646932e-05, 25383, 0, 65535, torch.int32);  aten_squeeze_copy_dims_62 = None
2025-03-21T20:31:43.6936969Z             
2025-03-21T20:31:43.6937357Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:111 in forward, code: h = x + h
2025-03-21T20:31:43.6938551Z             quantized_decomposed_dequantize_per_tensor_default_1373: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_959, 4.46785670646932e-05, 25383, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_959 = None
2025-03-21T20:31:43.6939719Z             aten_add_tensor_28: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_1193, quantized_decomposed_dequantize_per_tensor_default_1373);  quantized_decomposed_dequantize_per_tensor_default_1193 = quantized_decomposed_dequantize_per_tensor_default_1373 = None
2025-03-21T20:31:43.6940560Z             quantized_decomposed_quantize_per_tensor_default_960: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_28, 0.0026234339457005262, 6156, 0, 65535, torch.int32);  aten_add_tensor_28 = None
2025-03-21T20:31:43.6940662Z             
2025-03-21T20:31:43.6941171Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:115 in forward, code: out = h + self.feed_forward(self.ffn_norm(h))
2025-03-21T20:31:43.6942141Z             quantized_decomposed_dequantize_per_tensor_default_1374: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_960, 0.0026234339457005262, 6156, 0, 65535, torch.int32)
2025-03-21T20:31:43.6943274Z             quantized_decomposed_dequantize_per_tensor_default_1375: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_960, 0.0026234339457005262, 6156, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_960 = None
2025-03-21T20:31:43.6943833Z             aten_pow_tensor_scalar_11: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_pow_Tensor_Scalar(quantized_decomposed_dequantize_per_tensor_default_1375, 2)
2025-03-21T20:31:43.6944295Z             aten_mean_dim_11: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_mean_dim(aten_pow_tensor_scalar_11, [2], True);  aten_pow_tensor_scalar_11 = None
2025-03-21T20:31:43.6944756Z             aten_add_scalar_11: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_add_Scalar(aten_mean_dim_11, 9.999999747378752e-06);  aten_mean_dim_11 = None
2025-03-21T20:31:43.6945183Z             aten_rsqrt_default_11: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_rsqrt_default(aten_add_scalar_11);  aten_add_scalar_11 = None
2025-03-21T20:31:43.6946048Z             aten_mul_tensor_86: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1375, aten_rsqrt_default_11);  quantized_decomposed_dequantize_per_tensor_default_1375 = aten_rsqrt_default_11 = None
2025-03-21T20:31:43.6946853Z             aten_mul_tensor_87: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(aten_mul_tensor_86, quantized_decomposed_dequantize_per_tensor_default_51);  aten_mul_tensor_86 = quantized_decomposed_dequantize_per_tensor_default_51 = None
2025-03-21T20:31:43.6947713Z             quantized_decomposed_quantize_per_tensor_default_961: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_87, 0.0003379492845851928, 19066, 0, 65535, torch.int32);  aten_mul_tensor_87 = None
2025-03-21T20:31:43.6947805Z             
2025-03-21T20:31:43.6948338Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.6949251Z             quantized_decomposed_dequantize_per_tensor_default_1376: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_961, 0.0003379492845851928, 19066, 0, 65535, torch.int32)
2025-03-21T20:31:43.6950426Z             quantized_decomposed_dequantize_per_tensor_default_1377: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_961, 0.0003379492845851928, 19066, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_961 = None
2025-03-21T20:31:43.6951255Z             aten_unsqueeze_copy_default_63: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1377, -1);  quantized_decomposed_dequantize_per_tensor_default_1377 = None
2025-03-21T20:31:43.6952206Z             quantized_decomposed_quantize_per_tensor_default_962: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_63, 0.0003379492845851928, 19066, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_63 = None
2025-03-21T20:31:43.6952296Z             
2025-03-21T20:31:43.6952719Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.6953885Z             quantized_decomposed_dequantize_per_tensor_default_1378: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_962, 0.0003379492845851928, 19066, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_962 = None
2025-03-21T20:31:43.6954697Z             aten_permute_copy_default_240: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1378, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1378 = None
2025-03-21T20:31:43.6955649Z             quantized_decomposed_quantize_per_tensor_default_963: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_240, 0.0003379492845851928, 19066, 0, 65535, torch.int32);  aten_permute_copy_default_240 = None
2025-03-21T20:31:43.6955752Z             
2025-03-21T20:31:43.6956120Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.6957270Z             quantized_decomposed_dequantize_per_tensor_default_1379: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_963, 0.0003379492845851928, 19066, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_963 = None
2025-03-21T20:31:43.6958546Z             aten_convolution_default_39: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_1379, quantized_decomposed_dequantize_per_tensor_default_52, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_1379 = quantized_decomposed_dequantize_per_tensor_default_52 = None
2025-03-21T20:31:43.6959620Z             quantized_decomposed_quantize_per_tensor_default_964: "i32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_39, 0.00017915855278261006, 28370, 0, 65535, torch.int32);  aten_convolution_default_39 = None
2025-03-21T20:31:43.6959721Z             
2025-03-21T20:31:43.6960157Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.6961305Z             quantized_decomposed_dequantize_per_tensor_default_1380: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_964, 0.00017915855278261006, 28370, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_964 = None
2025-03-21T20:31:43.6962152Z             aten_permute_copy_default_241: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1380, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1380 = None
2025-03-21T20:31:43.6963121Z             quantized_decomposed_quantize_per_tensor_default_965: "i32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_241, 0.00017915855278261006, 28370, 0, 65535, torch.int32);  aten_permute_copy_default_241 = None
2025-03-21T20:31:43.6963223Z             
2025-03-21T20:31:43.6963758Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.6964920Z             quantized_decomposed_dequantize_per_tensor_default_1381: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_965, 0.00017915855278261006, 28370, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_965 = None
2025-03-21T20:31:43.6965704Z             aten_squeeze_copy_dims_63: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_1381, [-1]);  quantized_decomposed_dequantize_per_tensor_default_1381 = None
2025-03-21T20:31:43.6966622Z             quantized_decomposed_quantize_per_tensor_default_966: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_63, 0.00017915855278261006, 28370, 0, 65535, torch.int32);  aten_squeeze_copy_dims_63 = None
2025-03-21T20:31:43.6966712Z             
2025-03-21T20:31:43.6967236Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:36 in forward, code: return self.w2(F.silu(self.w1(x)) * self.w3(x))
2025-03-21T20:31:43.6968181Z             quantized_decomposed_dequantize_per_tensor_default_1382: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_966, 0.00017915855278261006, 28370, 0, 65535, torch.int32)
2025-03-21T20:31:43.6969416Z             quantized_decomposed_dequantize_per_tensor_default_1383: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_966, 0.00017915855278261006, 28370, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_966 = None
2025-03-21T20:31:43.6970161Z             aten_sigmoid_default_5: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_sigmoid_default(quantized_decomposed_dequantize_per_tensor_default_1383);  quantized_decomposed_dequantize_per_tensor_default_1383 = None
2025-03-21T20:31:43.6971028Z             quantized_decomposed_quantize_per_tensor_default_967: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_sigmoid_default_5, 1.52587890625e-05, 0, 0, 65535, torch.int32);  aten_sigmoid_default_5 = None
2025-03-21T20:31:43.6972135Z             quantized_decomposed_dequantize_per_tensor_default_1384: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_967, 1.52587890625e-05, 0, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_967 = None
2025-03-21T20:31:43.6973280Z             aten_mul_tensor_88: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1382, quantized_decomposed_dequantize_per_tensor_default_1384);  quantized_decomposed_dequantize_per_tensor_default_1382 = quantized_decomposed_dequantize_per_tensor_default_1384 = None
2025-03-21T20:31:43.6974161Z             quantized_decomposed_quantize_per_tensor_default_968: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_88, 0.00010571902384981513, 2634, 0, 65535, torch.int32);  aten_mul_tensor_88 = None
2025-03-21T20:31:43.6975354Z             quantized_decomposed_dequantize_per_tensor_default_1385: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_968, 0.00010571902384981513, 2634, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_968 = None
2025-03-21T20:31:43.6975442Z             
2025-03-21T20:31:43.6975978Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.6976781Z             aten_unsqueeze_copy_default_64: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1376, -1);  quantized_decomposed_dequantize_per_tensor_default_1376 = None
2025-03-21T20:31:43.6977761Z             quantized_decomposed_quantize_per_tensor_default_969: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_64, 0.0003379492845851928, 19066, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_64 = None
2025-03-21T20:31:43.6977848Z             
2025-03-21T20:31:43.6978266Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.6979406Z             quantized_decomposed_dequantize_per_tensor_default_1386: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_969, 0.0003379492845851928, 19066, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_969 = None
2025-03-21T20:31:43.6980248Z             aten_permute_copy_default_242: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1386, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1386 = None
2025-03-21T20:31:43.6981181Z             quantized_decomposed_quantize_per_tensor_default_970: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_242, 0.0003379492845851928, 19066, 0, 65535, torch.int32);  aten_permute_copy_default_242 = None
2025-03-21T20:31:43.6981283Z             
2025-03-21T20:31:43.6981646Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.6982791Z             quantized_decomposed_dequantize_per_tensor_default_1387: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_970, 0.0003379492845851928, 19066, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_970 = None
2025-03-21T20:31:43.6984073Z             aten_convolution_default_40: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_1387, quantized_decomposed_dequantize_per_tensor_default_53, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_1387 = quantized_decomposed_dequantize_per_tensor_default_53 = None
2025-03-21T20:31:43.6985014Z             quantized_decomposed_quantize_per_tensor_default_971: "i32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_40, 0.0002466057485435158, 42095, 0, 65535, torch.int32);  aten_convolution_default_40 = None
2025-03-21T20:31:43.6985103Z             
2025-03-21T20:31:43.6985535Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.6986730Z             quantized_decomposed_dequantize_per_tensor_default_1388: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_971, 0.0002466057485435158, 42095, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_971 = None
2025-03-21T20:31:43.6987544Z             aten_permute_copy_default_243: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1388, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1388 = None
2025-03-21T20:31:43.6988473Z             quantized_decomposed_quantize_per_tensor_default_972: "i32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_243, 0.0002466057485435158, 42095, 0, 65535, torch.int32);  aten_permute_copy_default_243 = None
2025-03-21T20:31:43.6988575Z             
2025-03-21T20:31:43.6989112Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.6990291Z             quantized_decomposed_dequantize_per_tensor_default_1389: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_972, 0.0002466057485435158, 42095, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_972 = None
2025-03-21T20:31:43.6991055Z             aten_squeeze_copy_dims_64: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_1389, [-1]);  quantized_decomposed_dequantize_per_tensor_default_1389 = None
2025-03-21T20:31:43.6991992Z             quantized_decomposed_quantize_per_tensor_default_973: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_64, 0.0002466057485435158, 42095, 0, 65535, torch.int32);  aten_squeeze_copy_dims_64 = None
2025-03-21T20:31:43.6992082Z             
2025-03-21T20:31:43.6992606Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:36 in forward, code: return self.w2(F.silu(self.w1(x)) * self.w3(x))
2025-03-21T20:31:43.6993744Z             quantized_decomposed_dequantize_per_tensor_default_1390: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_973, 0.0002466057485435158, 42095, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_973 = None
2025-03-21T20:31:43.6994886Z             aten_mul_tensor_89: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1385, quantized_decomposed_dequantize_per_tensor_default_1390);  quantized_decomposed_dequantize_per_tensor_default_1385 = quantized_decomposed_dequantize_per_tensor_default_1390 = None
2025-03-21T20:31:43.6995753Z             quantized_decomposed_quantize_per_tensor_default_974: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_89, 0.0003100545145571232, 27801, 0, 65535, torch.int32);  aten_mul_tensor_89 = None
2025-03-21T20:31:43.6995841Z             
2025-03-21T20:31:43.6996357Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.6997512Z             quantized_decomposed_dequantize_per_tensor_default_1391: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_974, 0.0003100545145571232, 27801, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_974 = None
2025-03-21T20:31:43.6998353Z             aten_unsqueeze_copy_default_65: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1391, -1);  quantized_decomposed_dequantize_per_tensor_default_1391 = None
2025-03-21T20:31:43.6999342Z             quantized_decomposed_quantize_per_tensor_default_975: "i32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_65, 0.0003100545145571232, 27801, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_65 = None
2025-03-21T20:31:43.6999432Z             
2025-03-21T20:31:43.6999850Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.7000997Z             quantized_decomposed_dequantize_per_tensor_default_1392: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_975, 0.0003100545145571232, 27801, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_975 = None
2025-03-21T20:31:43.7001840Z             aten_permute_copy_default_244: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1392, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1392 = None
2025-03-21T20:31:43.7002790Z             quantized_decomposed_quantize_per_tensor_default_976: "i32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_244, 0.0003100545145571232, 27801, 0, 65535, torch.int32);  aten_permute_copy_default_244 = None
2025-03-21T20:31:43.7002876Z             
2025-03-21T20:31:43.7003239Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.7004424Z             quantized_decomposed_dequantize_per_tensor_default_1393: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_976, 0.0003100545145571232, 27801, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_976 = None
2025-03-21T20:31:43.7005698Z             aten_convolution_default_41: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_1393, quantized_decomposed_dequantize_per_tensor_default_54, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_1393 = quantized_decomposed_dequantize_per_tensor_default_54 = None
2025-03-21T20:31:43.7006639Z             quantized_decomposed_quantize_per_tensor_default_977: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_41, 0.00021493309759534895, 11862, 0, 65535, torch.int32);  aten_convolution_default_41 = None
2025-03-21T20:31:43.7006741Z             
2025-03-21T20:31:43.7007162Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.7008306Z             quantized_decomposed_dequantize_per_tensor_default_1394: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_977, 0.00021493309759534895, 11862, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_977 = None
2025-03-21T20:31:43.7009112Z             aten_permute_copy_default_245: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1394, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1394 = None
2025-03-21T20:31:43.7010177Z             quantized_decomposed_quantize_per_tensor_default_978: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_245, 0.00021493309759534895, 11862, 0, 65535, torch.int32);  aten_permute_copy_default_245 = None
2025-03-21T20:31:43.7010297Z             
2025-03-21T20:31:43.7010836Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.7011995Z             quantized_decomposed_dequantize_per_tensor_default_1395: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_978, 0.00021493309759534895, 11862, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_978 = None
2025-03-21T20:31:43.7012767Z             aten_squeeze_copy_dims_65: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_1395, [-1]);  quantized_decomposed_dequantize_per_tensor_default_1395 = None
2025-03-21T20:31:43.7013692Z             quantized_decomposed_quantize_per_tensor_default_979: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_65, 0.00021493309759534895, 11862, 0, 65535, torch.int32);  aten_squeeze_copy_dims_65 = None
2025-03-21T20:31:43.7013800Z             
2025-03-21T20:31:43.7014308Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:115 in forward, code: out = h + self.feed_forward(self.ffn_norm(h))
2025-03-21T20:31:43.7015450Z             quantized_decomposed_dequantize_per_tensor_default_1396: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_979, 0.00021493309759534895, 11862, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_979 = None
2025-03-21T20:31:43.7016621Z             aten_add_tensor_29: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_1374, quantized_decomposed_dequantize_per_tensor_default_1396);  quantized_decomposed_dequantize_per_tensor_default_1374 = quantized_decomposed_dequantize_per_tensor_default_1396 = None
2025-03-21T20:31:43.7017481Z             quantized_decomposed_quantize_per_tensor_default_980: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_29, 0.002668527187779546, 5953, 0, 65535, torch.int32);  aten_add_tensor_29 = None
2025-03-21T20:31:43.7017571Z             
2025-03-21T20:31:43.7017943Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:111 in forward, code: h = x + h
2025-03-21T20:31:43.7018863Z             quantized_decomposed_dequantize_per_tensor_default_1397: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_980, 0.002668527187779546, 5953, 0, 65535, torch.int32)
2025-03-21T20:31:43.7018958Z             
2025-03-21T20:31:43.7019532Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:108 in forward, code: self.attention_norm(x), freqs_cos, freqs_sin, **attn_options
2025-03-21T20:31:43.7020658Z             quantized_decomposed_dequantize_per_tensor_default_1398: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_980, 0.002668527187779546, 5953, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_980 = None
2025-03-21T20:31:43.7021190Z             aten_pow_tensor_scalar_12: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_pow_Tensor_Scalar(quantized_decomposed_dequantize_per_tensor_default_1398, 2)
2025-03-21T20:31:43.7021651Z             aten_mean_dim_12: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_mean_dim(aten_pow_tensor_scalar_12, [2], True);  aten_pow_tensor_scalar_12 = None
2025-03-21T20:31:43.7022179Z             aten_add_scalar_12: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_add_Scalar(aten_mean_dim_12, 9.999999747378752e-06);  aten_mean_dim_12 = None
2025-03-21T20:31:43.7022609Z             aten_rsqrt_default_12: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_rsqrt_default(aten_add_scalar_12);  aten_add_scalar_12 = None
2025-03-21T20:31:43.7023472Z             aten_mul_tensor_90: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1398, aten_rsqrt_default_12);  quantized_decomposed_dequantize_per_tensor_default_1398 = aten_rsqrt_default_12 = None
2025-03-21T20:31:43.7024273Z             aten_mul_tensor_91: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(aten_mul_tensor_90, quantized_decomposed_dequantize_per_tensor_default_55);  aten_mul_tensor_90 = quantized_decomposed_dequantize_per_tensor_default_55 = None
2025-03-21T20:31:43.7025171Z             quantized_decomposed_quantize_per_tensor_default_981: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_91, 0.0004216353117953986, 31504, 0, 65535, torch.int32);  aten_mul_tensor_91 = None
2025-03-21T20:31:43.7025262Z             
2025-03-21T20:31:43.7025797Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.7026717Z             quantized_decomposed_dequantize_per_tensor_default_1399: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_981, 0.0004216353117953986, 31504, 0, 65535, torch.int32)
2025-03-21T20:31:43.7027664Z             quantized_decomposed_dequantize_per_tensor_default_1400: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_981, 0.0004216353117953986, 31504, 0, 65535, torch.int32)
2025-03-21T20:31:43.7028801Z             quantized_decomposed_dequantize_per_tensor_default_1401: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_981, 0.0004216353117953986, 31504, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_981 = None
2025-03-21T20:31:43.7029618Z             aten_unsqueeze_copy_default_66: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1401, -1);  quantized_decomposed_dequantize_per_tensor_default_1401 = None
2025-03-21T20:31:43.7030560Z             quantized_decomposed_quantize_per_tensor_default_982: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_66, 0.0004216353117953986, 31504, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_66 = None
2025-03-21T20:31:43.7030666Z             
2025-03-21T20:31:43.7031073Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.7032383Z             quantized_decomposed_dequantize_per_tensor_default_1402: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_982, 0.0004216353117953986, 31504, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_982 = None
2025-03-21T20:31:43.7033207Z             aten_permute_copy_default_246: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1402, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1402 = None
2025-03-21T20:31:43.7034216Z             quantized_decomposed_quantize_per_tensor_default_983: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_246, 0.0004216353117953986, 31504, 0, 65535, torch.int32);  aten_permute_copy_default_246 = None
2025-03-21T20:31:43.7034342Z             
2025-03-21T20:31:43.7034725Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.7035864Z             quantized_decomposed_dequantize_per_tensor_default_1403: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_983, 0.0004216353117953986, 31504, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_983 = None
2025-03-21T20:31:43.7037157Z             aten_convolution_default_42: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_1403, quantized_decomposed_dequantize_per_tensor_default_56, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_1403 = quantized_decomposed_dequantize_per_tensor_default_56 = None
2025-03-21T20:31:43.7038132Z             quantized_decomposed_quantize_per_tensor_default_984: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_42, 0.00036033670767210424, 26444, 0, 65535, torch.int32);  aten_convolution_default_42 = None
2025-03-21T20:31:43.7038221Z             
2025-03-21T20:31:43.7038640Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.7039800Z             quantized_decomposed_dequantize_per_tensor_default_1404: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_984, 0.00036033670767210424, 26444, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_984 = None
2025-03-21T20:31:43.7040634Z             aten_permute_copy_default_247: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1404, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1404 = None
2025-03-21T20:31:43.7041582Z             quantized_decomposed_quantize_per_tensor_default_985: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_247, 0.00036033670767210424, 26444, 0, 65535, torch.int32);  aten_permute_copy_default_247 = None
2025-03-21T20:31:43.7041669Z             
2025-03-21T20:31:43.7042215Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.7043362Z             quantized_decomposed_dequantize_per_tensor_default_1405: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_985, 0.00036033670767210424, 26444, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_985 = None
2025-03-21T20:31:43.7044132Z             aten_squeeze_copy_dims_66: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_1405, [-1]);  quantized_decomposed_dequantize_per_tensor_default_1405 = None
2025-03-21T20:31:43.7045028Z             quantized_decomposed_quantize_per_tensor_default_986: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_66, 0.00036033670767210424, 26444, 0, 65535, torch.int32);  aten_squeeze_copy_dims_66 = None
2025-03-21T20:31:43.7045131Z             
2025-03-21T20:31:43.7045674Z              # File: /pytorch/executorch/examples/models/llama/attention.py:242 in forward, code: q = q.view(bsz, seqlen, self.n_local_heads, self.head_dim)
2025-03-21T20:31:43.7046851Z             quantized_decomposed_dequantize_per_tensor_default_1406: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_986, 0.00036033670767210424, 26444, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_986 = None
2025-03-21T20:31:43.7046942Z             
2025-03-21T20:31:43.7047470Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.7048274Z             aten_unsqueeze_copy_default_67: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1400, -1);  quantized_decomposed_dequantize_per_tensor_default_1400 = None
2025-03-21T20:31:43.7049225Z             quantized_decomposed_quantize_per_tensor_default_987: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_67, 0.0004216353117953986, 31504, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_67 = None
2025-03-21T20:31:43.7049406Z             
2025-03-21T20:31:43.7049831Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.7051070Z             quantized_decomposed_dequantize_per_tensor_default_1407: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_987, 0.0004216353117953986, 31504, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_987 = None
2025-03-21T20:31:43.7051924Z             aten_permute_copy_default_248: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1407, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1407 = None
2025-03-21T20:31:43.7052857Z             quantized_decomposed_quantize_per_tensor_default_988: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_248, 0.0004216353117953986, 31504, 0, 65535, torch.int32);  aten_permute_copy_default_248 = None
2025-03-21T20:31:43.7052958Z             
2025-03-21T20:31:43.7053325Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.7054476Z             quantized_decomposed_dequantize_per_tensor_default_1408: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_988, 0.0004216353117953986, 31504, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_988 = None
2025-03-21T20:31:43.7055752Z             aten_convolution_default_43: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_1408, quantized_decomposed_dequantize_per_tensor_default_57, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_1408 = quantized_decomposed_dequantize_per_tensor_default_57 = None
2025-03-21T20:31:43.7056691Z             quantized_decomposed_quantize_per_tensor_default_989: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_43, 0.00046843686141073704, 34413, 0, 65535, torch.int32);  aten_convolution_default_43 = None
2025-03-21T20:31:43.7056780Z             
2025-03-21T20:31:43.7057216Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.7058396Z             quantized_decomposed_dequantize_per_tensor_default_1409: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_989, 0.00046843686141073704, 34413, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_989 = None
2025-03-21T20:31:43.7059227Z             aten_permute_copy_default_249: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1409, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1409 = None
2025-03-21T20:31:43.7060164Z             quantized_decomposed_quantize_per_tensor_default_990: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_249, 0.00046843686141073704, 34413, 0, 65535, torch.int32);  aten_permute_copy_default_249 = None
2025-03-21T20:31:43.7060272Z             
2025-03-21T20:31:43.7060880Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.7062234Z             quantized_decomposed_dequantize_per_tensor_default_1410: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_990, 0.00046843686141073704, 34413, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_990 = None
2025-03-21T20:31:43.7063000Z             aten_squeeze_copy_dims_67: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_1410, [-1]);  quantized_decomposed_dequantize_per_tensor_default_1410 = None
2025-03-21T20:31:43.7063915Z             quantized_decomposed_quantize_per_tensor_default_991: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_67, 0.00046843686141073704, 34413, 0, 65535, torch.int32);  aten_squeeze_copy_dims_67 = None
2025-03-21T20:31:43.7064054Z             
2025-03-21T20:31:43.7064591Z              # File: /pytorch/executorch/examples/models/llama/attention.py:243 in forward, code: k = k.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.7065734Z             quantized_decomposed_dequantize_per_tensor_default_1411: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_991, 0.00046843686141073704, 34413, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_991 = None
2025-03-21T20:31:43.7065835Z             
2025-03-21T20:31:43.7066347Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.7067165Z             aten_unsqueeze_copy_default_68: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1399, -1);  quantized_decomposed_dequantize_per_tensor_default_1399 = None
2025-03-21T20:31:43.7068109Z             quantized_decomposed_quantize_per_tensor_default_992: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_68, 0.0004216353117953986, 31504, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_68 = None
2025-03-21T20:31:43.7068211Z             
2025-03-21T20:31:43.7068618Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.7069769Z             quantized_decomposed_dequantize_per_tensor_default_1412: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_992, 0.0004216353117953986, 31504, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_992 = None
2025-03-21T20:31:43.7070642Z             aten_permute_copy_default_250: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1412, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1412 = None
2025-03-21T20:31:43.7071584Z             quantized_decomposed_quantize_per_tensor_default_993: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_250, 0.0004216353117953986, 31504, 0, 65535, torch.int32);  aten_permute_copy_default_250 = None
2025-03-21T20:31:43.7071675Z             
2025-03-21T20:31:43.7072055Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.7073194Z             quantized_decomposed_dequantize_per_tensor_default_1413: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_993, 0.0004216353117953986, 31504, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_993 = None
2025-03-21T20:31:43.7074503Z             aten_convolution_default_44: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_1413, quantized_decomposed_dequantize_per_tensor_default_58, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_1413 = quantized_decomposed_dequantize_per_tensor_default_58 = None
2025-03-21T20:31:43.7075432Z             quantized_decomposed_quantize_per_tensor_default_994: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_44, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_convolution_default_44 = None
2025-03-21T20:31:43.7075560Z             
2025-03-21T20:31:43.7075984Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.7077152Z             quantized_decomposed_dequantize_per_tensor_default_1414: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_994, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_994 = None
2025-03-21T20:31:43.7077951Z             aten_permute_copy_default_251: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1414, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1414 = None
2025-03-21T20:31:43.7078895Z             quantized_decomposed_quantize_per_tensor_default_995: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_251, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_permute_copy_default_251 = None
2025-03-21T20:31:43.7078990Z             
2025-03-21T20:31:43.7079539Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.7080681Z             quantized_decomposed_dequantize_per_tensor_default_1415: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_995, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_995 = None
2025-03-21T20:31:43.7081445Z             aten_squeeze_copy_dims_68: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_1415, [-1]);  quantized_decomposed_dequantize_per_tensor_default_1415 = None
2025-03-21T20:31:43.7082427Z             quantized_decomposed_quantize_per_tensor_default_996: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_68, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_squeeze_copy_dims_68 = None
2025-03-21T20:31:43.7082560Z             
2025-03-21T20:31:43.7083086Z              # File: /pytorch/executorch/examples/models/llama/attention.py:244 in forward, code: v = v.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.7084243Z             quantized_decomposed_dequantize_per_tensor_default_1416: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_996, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_996 = None
2025-03-21T20:31:43.7084333Z             
2025-03-21T20:31:43.7084856Z              # File: /pytorch/executorch/examples/models/llama/attention.py:242 in forward, code: q = q.view(bsz, seqlen, self.n_local_heads, self.head_dim)
2025-03-21T20:31:43.7085650Z             aten_view_copy_default_108: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1406, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_1406 = None
2025-03-21T20:31:43.7086569Z             quantized_decomposed_quantize_per_tensor_default_997: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_108, 0.00036033670767210424, 26444, 0, 65535, torch.int32);  aten_view_copy_default_108 = None
2025-03-21T20:31:43.7086660Z             
2025-03-21T20:31:43.7087616Z              # File: <eval_with_key>.50:3598 in forward, code: dequantize_per_tensor_default_1152 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1152, 0.00036033670767210424, 26444, 0, 65535, torch.int32);  quantize_per_tensor_default_1152 = None
2025-03-21T20:31:43.7088785Z             quantized_decomposed_dequantize_per_tensor_default_1417: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_997, 0.00036033670767210424, 26444, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_997 = None
2025-03-21T20:31:43.7088887Z             
2025-03-21T20:31:43.7089495Z              # File: /pytorch/executorch/examples/models/llama/attention.py:243 in forward, code: k = k.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.7090276Z             aten_view_copy_default_109: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1411, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_1411 = None
2025-03-21T20:31:43.7091185Z             quantized_decomposed_quantize_per_tensor_default_998: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_109, 0.00046843686141073704, 34413, 0, 65535, torch.int32);  aten_view_copy_default_109 = None
2025-03-21T20:31:43.7091289Z             
2025-03-21T20:31:43.7092233Z              # File: <eval_with_key>.50:3601 in forward, code: dequantize_per_tensor_default_1153 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1153, 0.00046843686141073704, 34413, 0, 65535, torch.int32);  quantize_per_tensor_default_1153 = None
2025-03-21T20:31:43.7093396Z             quantized_decomposed_dequantize_per_tensor_default_1418: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_998, 0.00046843686141073704, 34413, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_998 = None
2025-03-21T20:31:43.7093485Z             
2025-03-21T20:31:43.7094056Z              # File: /pytorch/executorch/examples/models/llama/attention.py:244 in forward, code: v = v.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.7094848Z             aten_view_copy_default_110: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1416, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_1416 = None
2025-03-21T20:31:43.7095764Z             quantized_decomposed_quantize_per_tensor_default_999: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_110, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_view_copy_default_110 = None
2025-03-21T20:31:43.7095852Z             
2025-03-21T20:31:43.7096518Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:346 in update, code: v_out = torch.ops.aten.index_put_(self.past_v_caches, [None, input_pos], v_val)
2025-03-21T20:31:43.7097704Z             quantized_decomposed_dequantize_per_tensor_default_1419: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_999, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_999 = None
2025-03-21T20:31:43.7097793Z             
2025-03-21T20:31:43.7098566Z              # File: <eval_with_key>.50:3606 in forward, code: quantize_per_tensor_default_1155 = torch.ops.quantized_decomposed.quantize_per_tensor.default(_to_copy_12, 0.00036033670767210424, 26444, 0, 65535, torch.int32);  _to_copy_12 = None
2025-03-21T20:31:43.7099707Z             quantized_decomposed_quantize_per_tensor_default_1000: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_1417, 0.00036033670767210424, 26444, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_1417 = None
2025-03-21T20:31:43.7099832Z             
2025-03-21T20:31:43.7100357Z              # File: /pytorch/executorch/examples/models/llama/rope.py:84 in apply_rotary_emb, code: xq_r, xq_i = xq.float().reshape(xq.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.7101541Z             quantized_decomposed_dequantize_per_tensor_default_1420: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1000, 0.00036033670767210424, 26444, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1000 = None
2025-03-21T20:31:43.7102355Z             aten_view_copy_default_111: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1420, [1, 1, 12, -1, 2]);  quantized_decomposed_dequantize_per_tensor_default_1420 = None
2025-03-21T20:31:43.7103286Z             quantized_decomposed_quantize_per_tensor_default_1001: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_111, 0.00036033670767210424, 26444, 0, 65535, torch.int32);  aten_view_copy_default_111 = None
2025-03-21T20:31:43.7104448Z             quantized_decomposed_dequantize_per_tensor_default_1421: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1001, 0.00036033670767210424, 26444, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1001 = None
2025-03-21T20:31:43.7104983Z             aten_slice_copy_tensor_24: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_1421, 4, 0, 1)
2025-03-21T20:31:43.7105782Z             aten_slice_copy_tensor_25: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_1421, 4, 1, 2);  quantized_decomposed_dequantize_per_tensor_default_1421 = None
2025-03-21T20:31:43.7106328Z             aten_squeeze_copy_dims_69: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_24, [4]);  aten_slice_copy_tensor_24 = None
2025-03-21T20:31:43.7106857Z             aten_squeeze_copy_dims_70: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_25, [4]);  aten_slice_copy_tensor_25 = None
2025-03-21T20:31:43.7107758Z             quantized_decomposed_quantize_per_tensor_default_1002: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_69, 0.0002986950858030468, 31901, 0, 65535, torch.int32);  aten_squeeze_copy_dims_69 = None
2025-03-21T20:31:43.7107860Z             
2025-03-21T20:31:43.7108335Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.7109302Z             quantized_decomposed_dequantize_per_tensor_default_1422: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1002, 0.0002986950858030468, 31901, 0, 65535, torch.int32)
2025-03-21T20:31:43.7109392Z             
2025-03-21T20:31:43.7109862Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.7111015Z             quantized_decomposed_dequantize_per_tensor_default_1423: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1002, 0.0002986950858030468, 31901, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1002 = None
2025-03-21T20:31:43.7111134Z             
2025-03-21T20:31:43.7111669Z              # File: /pytorch/executorch/examples/models/llama/rope.py:84 in apply_rotary_emb, code: xq_r, xq_i = xq.float().reshape(xq.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.7112570Z             quantized_decomposed_quantize_per_tensor_default_1003: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_70, 0.0003436956903897226, 24551, 0, 65535, torch.int32);  aten_squeeze_copy_dims_70 = None
2025-03-21T20:31:43.7112674Z             
2025-03-21T20:31:43.7113148Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.7114076Z             quantized_decomposed_dequantize_per_tensor_default_1424: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1003, 0.0003436956903897226, 24551, 0, 65535, torch.int32)
2025-03-21T20:31:43.7114168Z             
2025-03-21T20:31:43.7114662Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.7115811Z             quantized_decomposed_dequantize_per_tensor_default_1425: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1003, 0.0003436956903897226, 24551, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1003 = None
2025-03-21T20:31:43.7115917Z             
2025-03-21T20:31:43.7116682Z              # File: <eval_with_key>.50:3621 in forward, code: quantize_per_tensor_default_1159 = torch.ops.quantized_decomposed.quantize_per_tensor.default(_to_copy_13, 0.00046843686141073704, 34413, 0, 65535, torch.int32);  _to_copy_13 = None
2025-03-21T20:31:43.7117873Z             quantized_decomposed_quantize_per_tensor_default_1004: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_1418, 0.00046843686141073704, 34413, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_1418 = None
2025-03-21T20:31:43.7117991Z             
2025-03-21T20:31:43.7118525Z              # File: /pytorch/executorch/examples/models/llama/rope.py:85 in apply_rotary_emb, code: xk_r, xk_i = xk.float().reshape(xk.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.7119670Z             quantized_decomposed_dequantize_per_tensor_default_1426: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1004, 0.00046843686141073704, 34413, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1004 = None
2025-03-21T20:31:43.7120459Z             aten_view_copy_default_112: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1426, [1, 1, 12, -1, 2]);  quantized_decomposed_dequantize_per_tensor_default_1426 = None
2025-03-21T20:31:43.7121405Z             quantized_decomposed_quantize_per_tensor_default_1005: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_112, 0.00046843686141073704, 34413, 0, 65535, torch.int32);  aten_view_copy_default_112 = None
2025-03-21T20:31:43.7122570Z             quantized_decomposed_dequantize_per_tensor_default_1427: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1005, 0.00046843686141073704, 34413, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1005 = None
2025-03-21T20:31:43.7123135Z             aten_slice_copy_tensor_26: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_1427, 4, 0, 1)
2025-03-21T20:31:43.7123905Z             aten_slice_copy_tensor_27: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_1427, 4, 1, 2);  quantized_decomposed_dequantize_per_tensor_default_1427 = None
2025-03-21T20:31:43.7124424Z             aten_squeeze_copy_dims_71: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_26, [4]);  aten_slice_copy_tensor_26 = None
2025-03-21T20:31:43.7124948Z             aten_squeeze_copy_dims_72: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_27, [4]);  aten_slice_copy_tensor_27 = None
2025-03-21T20:31:43.7125848Z             quantized_decomposed_quantize_per_tensor_default_1006: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_71, 0.0004310147778596729, 31711, 0, 65535, torch.int32);  aten_squeeze_copy_dims_71 = None
2025-03-21T20:31:43.7125952Z             
2025-03-21T20:31:43.7126426Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.7127374Z             quantized_decomposed_dequantize_per_tensor_default_1428: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1006, 0.0004310147778596729, 31711, 0, 65535, torch.int32)
2025-03-21T20:31:43.7127462Z             
2025-03-21T20:31:43.7127947Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.7129119Z             quantized_decomposed_dequantize_per_tensor_default_1429: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1006, 0.0004310147778596729, 31711, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1006 = None
2025-03-21T20:31:43.7129247Z             
2025-03-21T20:31:43.7129843Z              # File: /pytorch/executorch/examples/models/llama/rope.py:85 in apply_rotary_emb, code: xk_r, xk_i = xk.float().reshape(xk.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.7130764Z             quantized_decomposed_quantize_per_tensor_default_1007: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_72, 0.00046482981997542083, 34680, 0, 65535, torch.int32);  aten_squeeze_copy_dims_72 = None
2025-03-21T20:31:43.7130855Z             
2025-03-21T20:31:43.7131329Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.7132420Z             quantized_decomposed_dequantize_per_tensor_default_1430: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1007, 0.00046482981997542083, 34680, 0, 65535, torch.int32)
2025-03-21T20:31:43.7132520Z             
2025-03-21T20:31:43.7133092Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.7134244Z             quantized_decomposed_dequantize_per_tensor_default_1431: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1007, 0.00046482981997542083, 34680, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1007 = None
2025-03-21T20:31:43.7134388Z             
2025-03-21T20:31:43.7134825Z              # File: /pytorch/executorch/examples/models/llama/rope.py:78 in reshape_for_broadcast, code: return freqs_cis.view(shape)
2025-03-21T20:31:43.7135599Z             aten_view_copy_default_113: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_156, [1, 1, 1, 32]);  quantized_decomposed_dequantize_per_tensor_default_156 = None
2025-03-21T20:31:43.7136504Z             quantized_decomposed_quantize_per_tensor_default_1008: "i32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_113, 3.051804378628731e-05, 32768, 0, 65535, torch.int32);  aten_view_copy_default_113 = None
2025-03-21T20:31:43.7136607Z             
2025-03-21T20:31:43.7137084Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.7138021Z             quantized_decomposed_dequantize_per_tensor_default_1432: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1008, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.7138112Z             
2025-03-21T20:31:43.7138600Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.7139512Z             quantized_decomposed_dequantize_per_tensor_default_1433: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1008, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.7139616Z             
2025-03-21T20:31:43.7140085Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.7141053Z             quantized_decomposed_dequantize_per_tensor_default_1434: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1008, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.7141180Z             
2025-03-21T20:31:43.7141647Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.7142797Z             quantized_decomposed_dequantize_per_tensor_default_1435: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1008, 3.051804378628731e-05, 32768, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1008 = None
2025-03-21T20:31:43.7142883Z             
2025-03-21T20:31:43.7143331Z              # File: /pytorch/executorch/examples/models/llama/rope.py:78 in reshape_for_broadcast, code: return freqs_cis.view(shape)
2025-03-21T20:31:43.7144089Z             aten_view_copy_default_114: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_168, [1, 1, 1, 32]);  quantized_decomposed_dequantize_per_tensor_default_168 = None
2025-03-21T20:31:43.7145026Z             quantized_decomposed_quantize_per_tensor_default_1009: "i32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_114, 3.051786916330457e-05, 32767, 0, 65535, torch.int32);  aten_view_copy_default_114 = None
2025-03-21T20:31:43.7145114Z             
2025-03-21T20:31:43.7145599Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.7146517Z             quantized_decomposed_dequantize_per_tensor_default_1436: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1009, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.7146642Z             
2025-03-21T20:31:43.7147108Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.7148033Z             quantized_decomposed_dequantize_per_tensor_default_1437: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1009, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.7148120Z             
2025-03-21T20:31:43.7148600Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.7149506Z             quantized_decomposed_dequantize_per_tensor_default_1438: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1009, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.7149611Z             
2025-03-21T20:31:43.7150078Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.7151231Z             quantized_decomposed_dequantize_per_tensor_default_1439: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1009, 3.051786916330457e-05, 32767, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1009 = None
2025-03-21T20:31:43.7151318Z             
2025-03-21T20:31:43.7151787Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.7152949Z             aten_mul_tensor_92: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1423, quantized_decomposed_dequantize_per_tensor_default_1435);  quantized_decomposed_dequantize_per_tensor_default_1423 = quantized_decomposed_dequantize_per_tensor_default_1435 = None
2025-03-21T20:31:43.7153845Z             quantized_decomposed_quantize_per_tensor_default_1010: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_92, 0.0002917187812272459, 32599, 0, 65535, torch.int32);  aten_mul_tensor_92 = None
2025-03-21T20:31:43.7154995Z             quantized_decomposed_dequantize_per_tensor_default_1440: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1010, 0.0002917187812272459, 32599, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1010 = None
2025-03-21T20:31:43.7156129Z             aten_mul_tensor_93: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1424, quantized_decomposed_dequantize_per_tensor_default_1438);  quantized_decomposed_dequantize_per_tensor_default_1424 = quantized_decomposed_dequantize_per_tensor_default_1438 = None
2025-03-21T20:31:43.7157011Z             quantized_decomposed_quantize_per_tensor_default_1011: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_93, 0.00021490042854566127, 31703, 0, 65535, torch.int32);  aten_mul_tensor_93 = None
2025-03-21T20:31:43.7158169Z             quantized_decomposed_dequantize_per_tensor_default_1441: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1011, 0.00021490042854566127, 31703, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1011 = None
2025-03-21T20:31:43.7159318Z             aten_sub_tensor_12: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_sub_Tensor(quantized_decomposed_dequantize_per_tensor_default_1440, quantized_decomposed_dequantize_per_tensor_default_1441);  quantized_decomposed_dequantize_per_tensor_default_1440 = quantized_decomposed_dequantize_per_tensor_default_1441 = None
2025-03-21T20:31:43.7160184Z             quantized_decomposed_quantize_per_tensor_default_1012: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_sub_tensor_12, 0.0002888002200052142, 33000, 0, 65535, torch.int32);  aten_sub_tensor_12 = None
2025-03-21T20:31:43.7160271Z             
2025-03-21T20:31:43.7161222Z              # File: <eval_with_key>.50:3655 in forward, code: dequantize_per_tensor_default_1167 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1167, 0.0002888002200052142, 33000, 0, 65535, torch.int32);  quantize_per_tensor_default_1167 = None
2025-03-21T20:31:43.7162373Z             quantized_decomposed_dequantize_per_tensor_default_1442: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1012, 0.0002888002200052142, 33000, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1012 = None
2025-03-21T20:31:43.7162475Z             
2025-03-21T20:31:43.7163070Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.7164213Z             aten_mul_tensor_94: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1422, quantized_decomposed_dequantize_per_tensor_default_1439);  quantized_decomposed_dequantize_per_tensor_default_1422 = quantized_decomposed_dequantize_per_tensor_default_1439 = None
2025-03-21T20:31:43.7165102Z             quantized_decomposed_quantize_per_tensor_default_1013: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_94, 0.00015702449309173971, 33148, 0, 65535, torch.int32);  aten_mul_tensor_94 = None
2025-03-21T20:31:43.7166284Z             quantized_decomposed_dequantize_per_tensor_default_1443: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1013, 0.00015702449309173971, 33148, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1013 = None
2025-03-21T20:31:43.7167408Z             aten_mul_tensor_95: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1425, quantized_decomposed_dequantize_per_tensor_default_1434);  quantized_decomposed_dequantize_per_tensor_default_1425 = quantized_decomposed_dequantize_per_tensor_default_1434 = None
2025-03-21T20:31:43.7168277Z             quantized_decomposed_quantize_per_tensor_default_1014: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_95, 0.00033834765781648457, 24827, 0, 65535, torch.int32);  aten_mul_tensor_95 = None
2025-03-21T20:31:43.7169547Z             quantized_decomposed_dequantize_per_tensor_default_1444: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1014, 0.00033834765781648457, 24827, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1014 = None
2025-03-21T20:31:43.7170686Z             aten_add_tensor_30: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_1443, quantized_decomposed_dequantize_per_tensor_default_1444);  quantized_decomposed_dequantize_per_tensor_default_1443 = quantized_decomposed_dequantize_per_tensor_default_1444 = None
2025-03-21T20:31:43.7171587Z             quantized_decomposed_quantize_per_tensor_default_1015: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_30, 0.00033126529888249934, 25134, 0, 65535, torch.int32);  aten_add_tensor_30 = None
2025-03-21T20:31:43.7171677Z             
2025-03-21T20:31:43.7172633Z              # File: <eval_with_key>.50:3664 in forward, code: dequantize_per_tensor_default_1170 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1170, 0.00033126529888249934, 25134, 0, 65535, torch.int32);  quantize_per_tensor_default_1170 = None
2025-03-21T20:31:43.7173779Z             quantized_decomposed_dequantize_per_tensor_default_1445: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1015, 0.00033126529888249934, 25134, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1015 = None
2025-03-21T20:31:43.7173881Z             
2025-03-21T20:31:43.7174362Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.7175502Z             aten_mul_tensor_96: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1429, quantized_decomposed_dequantize_per_tensor_default_1433);  quantized_decomposed_dequantize_per_tensor_default_1429 = quantized_decomposed_dequantize_per_tensor_default_1433 = None
2025-03-21T20:31:43.7176352Z             quantized_decomposed_quantize_per_tensor_default_1016: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_96, 0.00042510710773058236, 32035, 0, 65535, torch.int32);  aten_mul_tensor_96 = None
2025-03-21T20:31:43.7177538Z             quantized_decomposed_dequantize_per_tensor_default_1446: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1016, 0.00042510710773058236, 32035, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1016 = None
2025-03-21T20:31:43.7178681Z             aten_mul_tensor_97: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1430, quantized_decomposed_dequantize_per_tensor_default_1436);  quantized_decomposed_dequantize_per_tensor_default_1430 = quantized_decomposed_dequantize_per_tensor_default_1436 = None
2025-03-21T20:31:43.7179545Z             quantized_decomposed_quantize_per_tensor_default_1017: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_97, 0.00023940755636431277, 32509, 0, 65535, torch.int32);  aten_mul_tensor_97 = None
2025-03-21T20:31:43.7180689Z             quantized_decomposed_dequantize_per_tensor_default_1447: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1017, 0.00023940755636431277, 32509, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1017 = None
2025-03-21T20:31:43.7181846Z             aten_sub_tensor_13: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_sub_Tensor(quantized_decomposed_dequantize_per_tensor_default_1446, quantized_decomposed_dequantize_per_tensor_default_1447);  quantized_decomposed_dequantize_per_tensor_default_1446 = quantized_decomposed_dequantize_per_tensor_default_1447 = None
2025-03-21T20:31:43.7182694Z             quantized_decomposed_quantize_per_tensor_default_1018: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_sub_tensor_13, 0.0004331881063990295, 31428, 0, 65535, torch.int32);  aten_sub_tensor_13 = None
2025-03-21T20:31:43.7182818Z             
2025-03-21T20:31:43.7183760Z              # File: <eval_with_key>.50:3673 in forward, code: dequantize_per_tensor_default_1173 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1173, 0.0004331881063990295, 31428, 0, 65535, torch.int32);  quantize_per_tensor_default_1173 = None
2025-03-21T20:31:43.7184920Z             quantized_decomposed_dequantize_per_tensor_default_1448: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1018, 0.0004331881063990295, 31428, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1018 = None
2025-03-21T20:31:43.7185008Z             
2025-03-21T20:31:43.7185494Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.7186622Z             aten_mul_tensor_98: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1428, quantized_decomposed_dequantize_per_tensor_default_1437);  quantized_decomposed_dequantize_per_tensor_default_1428 = quantized_decomposed_dequantize_per_tensor_default_1437 = None
2025-03-21T20:31:43.7187491Z             quantized_decomposed_quantize_per_tensor_default_1019: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_98, 0.00021039359853602946, 32216, 0, 65535, torch.int32);  aten_mul_tensor_98 = None
2025-03-21T20:31:43.7188634Z             quantized_decomposed_dequantize_per_tensor_default_1449: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1019, 0.00021039359853602946, 32216, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1019 = None
2025-03-21T20:31:43.7189795Z             aten_mul_tensor_99: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1431, quantized_decomposed_dequantize_per_tensor_default_1432);  quantized_decomposed_dequantize_per_tensor_default_1431 = quantized_decomposed_dequantize_per_tensor_default_1432 = None
2025-03-21T20:31:43.7190687Z             quantized_decomposed_quantize_per_tensor_default_1020: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_99, 0.00045264922664500773, 34909, 0, 65535, torch.int32);  aten_mul_tensor_99 = None
2025-03-21T20:31:43.7191835Z             quantized_decomposed_dequantize_per_tensor_default_1450: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1020, 0.00045264922664500773, 34909, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1020 = None
2025-03-21T20:31:43.7192970Z             aten_add_tensor_31: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_1449, quantized_decomposed_dequantize_per_tensor_default_1450);  quantized_decomposed_dequantize_per_tensor_default_1449 = quantized_decomposed_dequantize_per_tensor_default_1450 = None
2025-03-21T20:31:43.7193846Z             quantized_decomposed_quantize_per_tensor_default_1021: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_31, 0.0004520940419752151, 35209, 0, 65535, torch.int32);  aten_add_tensor_31 = None
2025-03-21T20:31:43.7193946Z             
2025-03-21T20:31:43.7194883Z              # File: <eval_with_key>.50:3682 in forward, code: dequantize_per_tensor_default_1176 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1176, 0.0004520940419752151, 35209, 0, 65535, torch.int32);  quantize_per_tensor_default_1176 = None
2025-03-21T20:31:43.7196074Z             quantized_decomposed_dequantize_per_tensor_default_1451: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1021, 0.0004520940419752151, 35209, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1021 = None
2025-03-21T20:31:43.7196165Z             
2025-03-21T20:31:43.7196700Z              # File: /pytorch/executorch/examples/models/llama/rope.py:95 in apply_rotary_emb, code: xq_out = torch.stack([xq_out_r, xq_out_i], dim=-1).flatten(3)
2025-03-21T20:31:43.7197494Z             aten_unsqueeze_copy_default_69: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1442, 4);  quantized_decomposed_dequantize_per_tensor_default_1442 = None
2025-03-21T20:31:43.7198299Z             aten_unsqueeze_copy_default_70: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1445, 4);  quantized_decomposed_dequantize_per_tensor_default_1445 = None
2025-03-21T20:31:43.7199036Z             aten_cat_default_24: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_cat_default([aten_unsqueeze_copy_default_69, aten_unsqueeze_copy_default_70], -1);  aten_unsqueeze_copy_default_69 = aten_unsqueeze_copy_default_70 = None
2025-03-21T20:31:43.7199911Z             quantized_decomposed_quantize_per_tensor_default_1022: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_24, 0.00034964593942277133, 27258, 0, 65535, torch.int32);  aten_cat_default_24 = None
2025-03-21T20:31:43.7201053Z             quantized_decomposed_dequantize_per_tensor_default_1452: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1022, 0.00034964593942277133, 27258, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1022 = None
2025-03-21T20:31:43.7201871Z             aten_view_copy_default_115: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1452, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_1452 = None
2025-03-21T20:31:43.7202806Z             quantized_decomposed_quantize_per_tensor_default_1023: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_115, 0.00034964593942277133, 27258, 0, 65535, torch.int32);  aten_view_copy_default_115 = None
2025-03-21T20:31:43.7202906Z             
2025-03-21T20:31:43.7203842Z              # File: <eval_with_key>.50:3688 in forward, code: dequantize_per_tensor_default_1178 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1178, 0.00034964593942277133, 27258, 0, 65535, torch.int32);  quantize_per_tensor_default_1178 = None
2025-03-21T20:31:43.7205026Z             quantized_decomposed_dequantize_per_tensor_default_1453: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1023, 0.00034964593942277133, 27258, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1023 = None
2025-03-21T20:31:43.7205115Z             
2025-03-21T20:31:43.7205648Z              # File: /pytorch/executorch/examples/models/llama/rope.py:96 in apply_rotary_emb, code: xk_out = torch.stack([xk_out_r, xk_out_i], dim=-1).flatten(3)
2025-03-21T20:31:43.7206442Z             aten_unsqueeze_copy_default_71: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1448, 4);  quantized_decomposed_dequantize_per_tensor_default_1448 = None
2025-03-21T20:31:43.7207271Z             aten_unsqueeze_copy_default_72: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1451, 4);  quantized_decomposed_dequantize_per_tensor_default_1451 = None
2025-03-21T20:31:43.7208006Z             aten_cat_default_25: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_cat_default([aten_unsqueeze_copy_default_71, aten_unsqueeze_copy_default_72], -1);  aten_unsqueeze_copy_default_71 = aten_unsqueeze_copy_default_72 = None
2025-03-21T20:31:43.7208881Z             quantized_decomposed_quantize_per_tensor_default_1024: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_25, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_cat_default_25 = None
2025-03-21T20:31:43.7210112Z             quantized_decomposed_dequantize_per_tensor_default_1454: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1024, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1024 = None
2025-03-21T20:31:43.7210904Z             aten_view_copy_default_116: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1454, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_1454 = None
2025-03-21T20:31:43.7211803Z             quantized_decomposed_quantize_per_tensor_default_1025: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_116, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_view_copy_default_116 = None
2025-03-21T20:31:43.7211906Z             
2025-03-21T20:31:43.7212837Z              # File: <eval_with_key>.50:3694 in forward, code: dequantize_per_tensor_default_1180 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1180, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantize_per_tensor_default_1180 = None
2025-03-21T20:31:43.7214031Z             quantized_decomposed_dequantize_per_tensor_default_1455: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1025, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1025 = None
2025-03-21T20:31:43.7214145Z             
2025-03-21T20:31:43.7214916Z              # File: <eval_with_key>.50:3696 in forward, code: quantize_per_tensor_default_1181 = torch.ops.quantized_decomposed.quantize_per_tensor.default(type_as_12, 0.00034964593942277133, 27258, 0, 65535, torch.int32);  type_as_12 = None
2025-03-21T20:31:43.7216060Z             quantized_decomposed_quantize_per_tensor_default_1026: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_1453, 0.00034964593942277133, 27258, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_1453 = None
2025-03-21T20:31:43.7216163Z             
2025-03-21T20:31:43.7216687Z              # File: /pytorch/executorch/examples/models/llama/attention.py:249 in forward, code: q = q.transpose(1, 2)  # (bs, n_local_heads, seqlen, head_dim)
2025-03-21T20:31:43.7217865Z             quantized_decomposed_dequantize_per_tensor_default_1456: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1026, 0.00034964593942277133, 27258, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1026 = None
2025-03-21T20:31:43.7217954Z             
2025-03-21T20:31:43.7218712Z              # File: <eval_with_key>.50:3699 in forward, code: quantize_per_tensor_default_1182 = torch.ops.quantized_decomposed.quantize_per_tensor.default(type_as_13, 0.000468338665086776, 33988, 0, 65535, torch.int32);  type_as_13 = None
2025-03-21T20:31:43.7219875Z             quantized_decomposed_quantize_per_tensor_default_1027: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_1455, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_1455 = None
2025-03-21T20:31:43.7219980Z             
2025-03-21T20:31:43.7220645Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:345 in update, code: k_out = torch.ops.aten.index_put_(self.past_k_caches, [None, input_pos], k_val)
2025-03-21T20:31:43.7221794Z             quantized_decomposed_dequantize_per_tensor_default_1457: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1027, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1027 = None
2025-03-21T20:31:43.7221883Z             
2025-03-21T20:31:43.7222415Z              # File: /pytorch/executorch/examples/models/llama/attention.py:249 in forward, code: q = q.transpose(1, 2)  # (bs, n_local_heads, seqlen, head_dim)
2025-03-21T20:31:43.7223217Z             aten_permute_copy_default_252: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1456, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1456 = None
2025-03-21T20:31:43.7224164Z             quantized_decomposed_quantize_per_tensor_default_1028: "i32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_252, 0.00034964593942277133, 27258, 0, 65535, torch.int32);  aten_permute_copy_default_252 = None
2025-03-21T20:31:43.7224249Z             
2025-03-21T20:31:43.7231277Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.7232834Z             quantized_decomposed_dequantize_per_tensor_default_1458: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1028, 0.00034964593942277133, 27258, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1028 = None
2025-03-21T20:31:43.7232990Z             
2025-03-21T20:31:43.7233664Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:345 in update, code: k_out = torch.ops.aten.index_put_(self.past_k_caches, [None, input_pos], k_val)
2025-03-21T20:31:43.7234963Z             aten_index_put_default_12: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_index_put_default(quantized_decomposed_dequantize_per_tensor_default_131, [None, attn_options_input_pos], quantized_decomposed_dequantize_per_tensor_default_1457);  quantized_decomposed_dequantize_per_tensor_default_131 = quantized_decomposed_dequantize_per_tensor_default_1457 = None
2025-03-21T20:31:43.7235933Z             quantized_decomposed_quantize_per_tensor_default_1029: "i32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_put_default_12, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_index_put_default_12 = None
2025-03-21T20:31:43.7236040Z             
2025-03-21T20:31:43.7236831Z              # File: <eval_with_key>.50:3706 in forward, code: dequantize_per_tensor_default_1184 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1184, 0.000468338665086776, 33988, 0, 65535, torch.int32)
2025-03-21T20:31:43.7237765Z             quantized_decomposed_dequantize_per_tensor_default_1459: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1029, 0.000468338665086776, 33988, 0, 65535, torch.int32)
2025-03-21T20:31:43.7237893Z             
2025-03-21T20:31:43.7238543Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.7239467Z             quantized_decomposed_dequantize_per_tensor_default_1460: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1029, 0.000468338665086776, 33988, 0, 65535, torch.int32)
2025-03-21T20:31:43.7240396Z             quantized_decomposed_dequantize_per_tensor_default_1461: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1029, 0.000468338665086776, 33988, 0, 65535, torch.int32)
2025-03-21T20:31:43.7241313Z             quantized_decomposed_dequantize_per_tensor_default_1462: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1029, 0.000468338665086776, 33988, 0, 65535, torch.int32)
2025-03-21T20:31:43.7242245Z             quantized_decomposed_dequantize_per_tensor_default_1463: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1029, 0.000468338665086776, 33988, 0, 65535, torch.int32)
2025-03-21T20:31:43.7243158Z             quantized_decomposed_dequantize_per_tensor_default_1464: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1029, 0.000468338665086776, 33988, 0, 65535, torch.int32)
2025-03-21T20:31:43.7244086Z             quantized_decomposed_dequantize_per_tensor_default_1465: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1029, 0.000468338665086776, 33988, 0, 65535, torch.int32)
2025-03-21T20:31:43.7245064Z             quantized_decomposed_dequantize_per_tensor_default_1466: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1029, 0.000468338665086776, 33988, 0, 65535, torch.int32)
2025-03-21T20:31:43.7245994Z             quantized_decomposed_dequantize_per_tensor_default_1467: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1029, 0.000468338665086776, 33988, 0, 65535, torch.int32)
2025-03-21T20:31:43.7246924Z             quantized_decomposed_dequantize_per_tensor_default_1468: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1029, 0.000468338665086776, 33988, 0, 65535, torch.int32)
2025-03-21T20:31:43.7247845Z             quantized_decomposed_dequantize_per_tensor_default_1469: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1029, 0.000468338665086776, 33988, 0, 65535, torch.int32)
2025-03-21T20:31:43.7248802Z             quantized_decomposed_dequantize_per_tensor_default_1470: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1029, 0.000468338665086776, 33988, 0, 65535, torch.int32)
2025-03-21T20:31:43.7250024Z             quantized_decomposed_dequantize_per_tensor_default_1471: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1029, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1029 = None
2025-03-21T20:31:43.7250185Z             
2025-03-21T20:31:43.7250856Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:346 in update, code: v_out = torch.ops.aten.index_put_(self.past_v_caches, [None, input_pos], v_val)
2025-03-21T20:31:43.7252154Z             aten_index_put_default_13: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_index_put_default(quantized_decomposed_dequantize_per_tensor_default_132, [None, attn_options_input_pos], quantized_decomposed_dequantize_per_tensor_default_1419);  quantized_decomposed_dequantize_per_tensor_default_132 = quantized_decomposed_dequantize_per_tensor_default_1419 = None
2025-03-21T20:31:43.7253068Z             quantized_decomposed_quantize_per_tensor_default_1030: "i32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_put_default_13, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_index_put_default_13 = None
2025-03-21T20:31:43.7253174Z             
2025-03-21T20:31:43.7254081Z              # File: <eval_with_key>.50:3721 in forward, code: dequantize_per_tensor_default_1185 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1185, 0.00011607543274294585, 32773, 0, 65535, torch.int32)
2025-03-21T20:31:43.7255031Z             quantized_decomposed_dequantize_per_tensor_default_1472: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1030, 0.00011607543274294585, 32773, 0, 65535, torch.int32)
2025-03-21T20:31:43.7255119Z             
2025-03-21T20:31:43.7255764Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.7256719Z             quantized_decomposed_dequantize_per_tensor_default_1473: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1030, 0.00011607543274294585, 32773, 0, 65535, torch.int32)
2025-03-21T20:31:43.7257675Z             quantized_decomposed_dequantize_per_tensor_default_1474: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1030, 0.00011607543274294585, 32773, 0, 65535, torch.int32)
2025-03-21T20:31:43.7258592Z             quantized_decomposed_dequantize_per_tensor_default_1475: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1030, 0.00011607543274294585, 32773, 0, 65535, torch.int32)
2025-03-21T20:31:43.7259519Z             quantized_decomposed_dequantize_per_tensor_default_1476: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1030, 0.00011607543274294585, 32773, 0, 65535, torch.int32)
2025-03-21T20:31:43.7260464Z             quantized_decomposed_dequantize_per_tensor_default_1477: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1030, 0.00011607543274294585, 32773, 0, 65535, torch.int32)
2025-03-21T20:31:43.7261390Z             quantized_decomposed_dequantize_per_tensor_default_1478: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1030, 0.00011607543274294585, 32773, 0, 65535, torch.int32)
2025-03-21T20:31:43.7262309Z             quantized_decomposed_dequantize_per_tensor_default_1479: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1030, 0.00011607543274294585, 32773, 0, 65535, torch.int32)
2025-03-21T20:31:43.7263267Z             quantized_decomposed_dequantize_per_tensor_default_1480: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1030, 0.00011607543274294585, 32773, 0, 65535, torch.int32)
2025-03-21T20:31:43.7264197Z             quantized_decomposed_dequantize_per_tensor_default_1481: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1030, 0.00011607543274294585, 32773, 0, 65535, torch.int32)
2025-03-21T20:31:43.7265420Z             quantized_decomposed_dequantize_per_tensor_default_1482: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1030, 0.00011607543274294585, 32773, 0, 65535, torch.int32)
2025-03-21T20:31:43.7266352Z             quantized_decomposed_dequantize_per_tensor_default_1483: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1030, 0.00011607543274294585, 32773, 0, 65535, torch.int32)
2025-03-21T20:31:43.7267519Z             quantized_decomposed_dequantize_per_tensor_default_1484: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1030, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1030 = None
2025-03-21T20:31:43.7267619Z             
2025-03-21T20:31:43.7268251Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.7269099Z             aten_permute_copy_default_253: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1471, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1471 = None
2025-03-21T20:31:43.7270071Z             quantized_decomposed_quantize_per_tensor_default_1031: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_253, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_permute_copy_default_253 = None
2025-03-21T20:31:43.7271224Z             quantized_decomposed_dequantize_per_tensor_default_1485: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1031, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1031 = None
2025-03-21T20:31:43.7271966Z             aten_select_copy_int_288: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1485, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1485 = None
2025-03-21T20:31:43.7272902Z             quantized_decomposed_quantize_per_tensor_default_1032: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_288, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_select_copy_int_288 = None
2025-03-21T20:31:43.7274046Z             quantized_decomposed_dequantize_per_tensor_default_1486: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1032, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1032 = None
2025-03-21T20:31:43.7274795Z             aten_select_copy_int_289: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1486, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1486 = None
2025-03-21T20:31:43.7275770Z             quantized_decomposed_quantize_per_tensor_default_1033: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_289, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_select_copy_int_289 = None
2025-03-21T20:31:43.7275873Z             
2025-03-21T20:31:43.7276805Z              # File: <eval_with_key>.50:3742 in forward, code: dequantize_per_tensor_default_1188 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1188, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantize_per_tensor_default_1188 = None
2025-03-21T20:31:43.7277956Z             quantized_decomposed_dequantize_per_tensor_default_1487: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1033, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1033 = None
2025-03-21T20:31:43.7278050Z             
2025-03-21T20:31:43.7278701Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.7279505Z             aten_permute_copy_default_254: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1470, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1470 = None
2025-03-21T20:31:43.7280456Z             quantized_decomposed_quantize_per_tensor_default_1034: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_254, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_permute_copy_default_254 = None
2025-03-21T20:31:43.7281627Z             quantized_decomposed_dequantize_per_tensor_default_1488: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1034, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1034 = None
2025-03-21T20:31:43.7282409Z             aten_select_copy_int_290: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1488, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1488 = None
2025-03-21T20:31:43.7283301Z             quantized_decomposed_quantize_per_tensor_default_1035: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_290, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_select_copy_int_290 = None
2025-03-21T20:31:43.7284457Z             quantized_decomposed_dequantize_per_tensor_default_1489: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1035, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1035 = None
2025-03-21T20:31:43.7285222Z             aten_select_copy_int_291: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1489, 0, 1);  quantized_decomposed_dequantize_per_tensor_default_1489 = None
2025-03-21T20:31:43.7286123Z             quantized_decomposed_quantize_per_tensor_default_1036: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_291, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_select_copy_int_291 = None
2025-03-21T20:31:43.7286209Z             
2025-03-21T20:31:43.7287151Z              # File: <eval_with_key>.50:3751 in forward, code: dequantize_per_tensor_default_1191 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1191, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantize_per_tensor_default_1191 = None
2025-03-21T20:31:43.7288318Z             quantized_decomposed_dequantize_per_tensor_default_1490: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1036, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1036 = None
2025-03-21T20:31:43.7288418Z             
2025-03-21T20:31:43.7289055Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.7289942Z             aten_permute_copy_default_255: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1469, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1469 = None
2025-03-21T20:31:43.7290883Z             quantized_decomposed_quantize_per_tensor_default_1037: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_255, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_permute_copy_default_255 = None
2025-03-21T20:31:43.7292044Z             quantized_decomposed_dequantize_per_tensor_default_1491: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1037, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1037 = None
2025-03-21T20:31:43.7292782Z             aten_select_copy_int_292: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1491, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1491 = None
2025-03-21T20:31:43.7293722Z             quantized_decomposed_quantize_per_tensor_default_1038: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_292, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_select_copy_int_292 = None
2025-03-21T20:31:43.7294908Z             quantized_decomposed_dequantize_per_tensor_default_1492: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1038, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1038 = None
2025-03-21T20:31:43.7295641Z             aten_select_copy_int_293: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1492, 0, 2);  quantized_decomposed_dequantize_per_tensor_default_1492 = None
2025-03-21T20:31:43.7296541Z             quantized_decomposed_quantize_per_tensor_default_1039: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_293, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_select_copy_int_293 = None
2025-03-21T20:31:43.7296633Z             
2025-03-21T20:31:43.7297610Z              # File: <eval_with_key>.50:3760 in forward, code: dequantize_per_tensor_default_1194 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1194, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantize_per_tensor_default_1194 = None
2025-03-21T20:31:43.7298752Z             quantized_decomposed_dequantize_per_tensor_default_1493: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1039, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1039 = None
2025-03-21T20:31:43.7298877Z             
2025-03-21T20:31:43.7299512Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.7300326Z             aten_permute_copy_default_256: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1468, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1468 = None
2025-03-21T20:31:43.7301260Z             quantized_decomposed_quantize_per_tensor_default_1040: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_256, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_permute_copy_default_256 = None
2025-03-21T20:31:43.7302417Z             quantized_decomposed_dequantize_per_tensor_default_1494: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1040, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1040 = None
2025-03-21T20:31:43.7303158Z             aten_select_copy_int_294: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1494, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1494 = None
2025-03-21T20:31:43.7304061Z             quantized_decomposed_quantize_per_tensor_default_1041: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_294, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_select_copy_int_294 = None
2025-03-21T20:31:43.7305202Z             quantized_decomposed_dequantize_per_tensor_default_1495: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1041, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1041 = None
2025-03-21T20:31:43.7306000Z             aten_select_copy_int_295: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1495, 0, 3);  quantized_decomposed_dequantize_per_tensor_default_1495 = None
2025-03-21T20:31:43.7306889Z             quantized_decomposed_quantize_per_tensor_default_1042: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_295, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_select_copy_int_295 = None
2025-03-21T20:31:43.7306988Z             
2025-03-21T20:31:43.7307916Z              # File: <eval_with_key>.50:3769 in forward, code: dequantize_per_tensor_default_1197 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1197, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantize_per_tensor_default_1197 = None
2025-03-21T20:31:43.7309097Z             quantized_decomposed_dequantize_per_tensor_default_1496: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1042, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1042 = None
2025-03-21T20:31:43.7309187Z             
2025-03-21T20:31:43.7309833Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.7310632Z             aten_permute_copy_default_257: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1467, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1467 = None
2025-03-21T20:31:43.7311601Z             quantized_decomposed_quantize_per_tensor_default_1043: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_257, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_permute_copy_default_257 = None
2025-03-21T20:31:43.7312748Z             quantized_decomposed_dequantize_per_tensor_default_1497: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1043, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1043 = None
2025-03-21T20:31:43.7313495Z             aten_select_copy_int_296: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1497, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1497 = None
2025-03-21T20:31:43.7314388Z             quantized_decomposed_quantize_per_tensor_default_1044: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_296, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_select_copy_int_296 = None
2025-03-21T20:31:43.7315543Z             quantized_decomposed_dequantize_per_tensor_default_1498: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1044, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1044 = None
2025-03-21T20:31:43.7316274Z             aten_select_copy_int_297: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1498, 0, 4);  quantized_decomposed_dequantize_per_tensor_default_1498 = None
2025-03-21T20:31:43.7317172Z             quantized_decomposed_quantize_per_tensor_default_1045: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_297, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_select_copy_int_297 = None
2025-03-21T20:31:43.7317321Z             
2025-03-21T20:31:43.7318265Z              # File: <eval_with_key>.50:3778 in forward, code: dequantize_per_tensor_default_1200 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1200, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantize_per_tensor_default_1200 = None
2025-03-21T20:31:43.7319402Z             quantized_decomposed_dequantize_per_tensor_default_1499: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1045, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1045 = None
2025-03-21T20:31:43.7319500Z             
2025-03-21T20:31:43.7320133Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.7320975Z             aten_permute_copy_default_258: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1466, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1466 = None
2025-03-21T20:31:43.7321907Z             quantized_decomposed_quantize_per_tensor_default_1046: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_258, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_permute_copy_default_258 = None
2025-03-21T20:31:43.7323065Z             quantized_decomposed_dequantize_per_tensor_default_1500: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1046, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1046 = None
2025-03-21T20:31:43.7323842Z             aten_select_copy_int_298: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1500, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1500 = None
2025-03-21T20:31:43.7324734Z             quantized_decomposed_quantize_per_tensor_default_1047: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_298, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_select_copy_int_298 = None
2025-03-21T20:31:43.7325883Z             quantized_decomposed_dequantize_per_tensor_default_1501: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1047, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1047 = None
2025-03-21T20:31:43.7326622Z             aten_select_copy_int_299: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1501, 0, 5);  quantized_decomposed_dequantize_per_tensor_default_1501 = None
2025-03-21T20:31:43.7327518Z             quantized_decomposed_quantize_per_tensor_default_1048: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_299, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_select_copy_int_299 = None
2025-03-21T20:31:43.7327606Z             
2025-03-21T20:31:43.7328545Z              # File: <eval_with_key>.50:3787 in forward, code: dequantize_per_tensor_default_1203 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1203, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantize_per_tensor_default_1203 = None
2025-03-21T20:31:43.7329782Z             quantized_decomposed_dequantize_per_tensor_default_1502: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1048, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1048 = None
2025-03-21T20:31:43.7329911Z             
2025-03-21T20:31:43.7330548Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.7331358Z             aten_permute_copy_default_259: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1465, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1465 = None
2025-03-21T20:31:43.7332461Z             quantized_decomposed_quantize_per_tensor_default_1049: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_259, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_permute_copy_default_259 = None
2025-03-21T20:31:43.7333705Z             quantized_decomposed_dequantize_per_tensor_default_1503: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1049, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1049 = None
2025-03-21T20:31:43.7334447Z             aten_select_copy_int_300: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1503, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1503 = None
2025-03-21T20:31:43.7335347Z             quantized_decomposed_quantize_per_tensor_default_1050: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_300, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_select_copy_int_300 = None
2025-03-21T20:31:43.7336531Z             quantized_decomposed_dequantize_per_tensor_default_1504: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1050, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1050 = None
2025-03-21T20:31:43.7337281Z             aten_select_copy_int_301: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1504, 0, 6);  quantized_decomposed_dequantize_per_tensor_default_1504 = None
2025-03-21T20:31:43.7338170Z             quantized_decomposed_quantize_per_tensor_default_1051: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_301, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_select_copy_int_301 = None
2025-03-21T20:31:43.7338274Z             
2025-03-21T20:31:43.7339207Z              # File: <eval_with_key>.50:3796 in forward, code: dequantize_per_tensor_default_1206 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1206, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantize_per_tensor_default_1206 = None
2025-03-21T20:31:43.7340361Z             quantized_decomposed_dequantize_per_tensor_default_1505: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1051, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1051 = None
2025-03-21T20:31:43.7340453Z             
2025-03-21T20:31:43.7341104Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.7341945Z             aten_permute_copy_default_260: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1464, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1464 = None
2025-03-21T20:31:43.7342940Z             quantized_decomposed_quantize_per_tensor_default_1052: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_260, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_permute_copy_default_260 = None
2025-03-21T20:31:43.7344084Z             quantized_decomposed_dequantize_per_tensor_default_1506: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1052, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1052 = None
2025-03-21T20:31:43.7344845Z             aten_select_copy_int_302: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1506, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1506 = None
2025-03-21T20:31:43.7345760Z             quantized_decomposed_quantize_per_tensor_default_1053: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_302, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_select_copy_int_302 = None
2025-03-21T20:31:43.7346913Z             quantized_decomposed_dequantize_per_tensor_default_1507: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1053, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1053 = None
2025-03-21T20:31:43.7347674Z             aten_select_copy_int_303: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1507, 0, 7);  quantized_decomposed_dequantize_per_tensor_default_1507 = None
2025-03-21T20:31:43.7348583Z             quantized_decomposed_quantize_per_tensor_default_1054: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_303, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_select_copy_int_303 = None
2025-03-21T20:31:43.7348672Z             
2025-03-21T20:31:43.7349608Z              # File: <eval_with_key>.50:3805 in forward, code: dequantize_per_tensor_default_1209 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1209, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantize_per_tensor_default_1209 = None
2025-03-21T20:31:43.7350749Z             quantized_decomposed_dequantize_per_tensor_default_1508: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1054, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1054 = None
2025-03-21T20:31:43.7350852Z             
2025-03-21T20:31:43.7351489Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.7352303Z             aten_permute_copy_default_261: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1463, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1463 = None
2025-03-21T20:31:43.7353234Z             quantized_decomposed_quantize_per_tensor_default_1055: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_261, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_permute_copy_default_261 = None
2025-03-21T20:31:43.7354417Z             quantized_decomposed_dequantize_per_tensor_default_1509: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1055, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1055 = None
2025-03-21T20:31:43.7355197Z             aten_select_copy_int_304: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1509, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1509 = None
2025-03-21T20:31:43.7356087Z             quantized_decomposed_quantize_per_tensor_default_1056: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_304, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_select_copy_int_304 = None
2025-03-21T20:31:43.7357243Z             quantized_decomposed_dequantize_per_tensor_default_1510: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1056, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1056 = None
2025-03-21T20:31:43.7358004Z             aten_select_copy_int_305: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1510, 0, 8);  quantized_decomposed_dequantize_per_tensor_default_1510 = None
2025-03-21T20:31:43.7358900Z             quantized_decomposed_quantize_per_tensor_default_1057: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_305, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_select_copy_int_305 = None
2025-03-21T20:31:43.7359013Z             
2025-03-21T20:31:43.7359955Z              # File: <eval_with_key>.50:3814 in forward, code: dequantize_per_tensor_default_1212 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1212, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantize_per_tensor_default_1212 = None
2025-03-21T20:31:43.7361101Z             quantized_decomposed_dequantize_per_tensor_default_1511: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1057, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1057 = None
2025-03-21T20:31:43.7361197Z             
2025-03-21T20:31:43.7361829Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.7362644Z             aten_permute_copy_default_262: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1462, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1462 = None
2025-03-21T20:31:43.7363583Z             quantized_decomposed_quantize_per_tensor_default_1058: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_262, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_permute_copy_default_262 = None
2025-03-21T20:31:43.7364736Z             quantized_decomposed_dequantize_per_tensor_default_1512: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1058, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1058 = None
2025-03-21T20:31:43.7365478Z             aten_select_copy_int_306: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1512, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1512 = None
2025-03-21T20:31:43.7366527Z             quantized_decomposed_quantize_per_tensor_default_1059: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_306, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_select_copy_int_306 = None
2025-03-21T20:31:43.7367750Z             quantized_decomposed_dequantize_per_tensor_default_1513: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1059, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1059 = None
2025-03-21T20:31:43.7368506Z             aten_select_copy_int_307: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1513, 0, 9);  quantized_decomposed_dequantize_per_tensor_default_1513 = None
2025-03-21T20:31:43.7369473Z             quantized_decomposed_quantize_per_tensor_default_1060: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_307, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_select_copy_int_307 = None
2025-03-21T20:31:43.7369618Z             
2025-03-21T20:31:43.7370550Z              # File: <eval_with_key>.50:3823 in forward, code: dequantize_per_tensor_default_1215 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1215, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantize_per_tensor_default_1215 = None
2025-03-21T20:31:43.7371708Z             quantized_decomposed_dequantize_per_tensor_default_1514: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1060, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1060 = None
2025-03-21T20:31:43.7371834Z             
2025-03-21T20:31:43.7372494Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.7373297Z             aten_permute_copy_default_263: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1461, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1461 = None
2025-03-21T20:31:43.7374240Z             quantized_decomposed_quantize_per_tensor_default_1061: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_263, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_permute_copy_default_263 = None
2025-03-21T20:31:43.7375388Z             quantized_decomposed_dequantize_per_tensor_default_1515: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1061, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1061 = None
2025-03-21T20:31:43.7376143Z             aten_select_copy_int_308: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1515, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1515 = None
2025-03-21T20:31:43.7377032Z             quantized_decomposed_quantize_per_tensor_default_1062: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_308, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_select_copy_int_308 = None
2025-03-21T20:31:43.7378214Z             quantized_decomposed_dequantize_per_tensor_default_1516: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1062, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1062 = None
2025-03-21T20:31:43.7378998Z             aten_select_copy_int_309: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1516, 0, 10);  quantized_decomposed_dequantize_per_tensor_default_1516 = None
2025-03-21T20:31:43.7379883Z             quantized_decomposed_quantize_per_tensor_default_1063: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_309, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_select_copy_int_309 = None
2025-03-21T20:31:43.7379984Z             
2025-03-21T20:31:43.7380918Z              # File: <eval_with_key>.50:3832 in forward, code: dequantize_per_tensor_default_1218 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1218, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantize_per_tensor_default_1218 = None
2025-03-21T20:31:43.7382101Z             quantized_decomposed_dequantize_per_tensor_default_1517: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1063, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1063 = None
2025-03-21T20:31:43.7382191Z             
2025-03-21T20:31:43.7382827Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.7383644Z             aten_permute_copy_default_264: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1460, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1460 = None
2025-03-21T20:31:43.7384618Z             quantized_decomposed_quantize_per_tensor_default_1064: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_264, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_permute_copy_default_264 = None
2025-03-21T20:31:43.7385764Z             quantized_decomposed_dequantize_per_tensor_default_1518: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1064, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1064 = None
2025-03-21T20:31:43.7386518Z             aten_select_copy_int_310: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1518, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1518 = None
2025-03-21T20:31:43.7387411Z             quantized_decomposed_quantize_per_tensor_default_1065: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_310, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_select_copy_int_310 = None
2025-03-21T20:31:43.7388575Z             quantized_decomposed_dequantize_per_tensor_default_1519: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1065, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1065 = None
2025-03-21T20:31:43.7389313Z             aten_select_copy_int_311: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1519, 0, 11);  quantized_decomposed_dequantize_per_tensor_default_1519 = None
2025-03-21T20:31:43.7390247Z             quantized_decomposed_quantize_per_tensor_default_1066: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_311, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_select_copy_int_311 = None
2025-03-21T20:31:43.7390363Z             
2025-03-21T20:31:43.7391302Z              # File: <eval_with_key>.50:3841 in forward, code: dequantize_per_tensor_default_1221 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1221, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantize_per_tensor_default_1221 = None
2025-03-21T20:31:43.7392440Z             quantized_decomposed_dequantize_per_tensor_default_1520: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1066, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1066 = None
2025-03-21T20:31:43.7392544Z             
2025-03-21T20:31:43.7393181Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.7398685Z             aten_cat_default_26: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_aten_cat_default([quantized_decomposed_dequantize_per_tensor_default_1487, quantized_decomposed_dequantize_per_tensor_default_1490, quantized_decomposed_dequantize_per_tensor_default_1493, quantized_decomposed_dequantize_per_tensor_default_1496, quantized_decomposed_dequantize_per_tensor_default_1499, quantized_decomposed_dequantize_per_tensor_default_1502, quantized_decomposed_dequantize_per_tensor_default_1505, quantized_decomposed_dequantize_per_tensor_default_1508, quantized_decomposed_dequantize_per_tensor_default_1511, quantized_decomposed_dequantize_per_tensor_default_1514, quantized_decomposed_dequantize_per_tensor_default_1517, quantized_decomposed_dequantize_per_tensor_default_1520]);  quantized_decomposed_dequantize_per_tensor_default_1487 = quantized_decomposed_dequantize_per_tensor_default_1490 = quantized_decomposed_dequantize_per_tensor_default_1493 = quantized_decomposed_dequantize_per_tensor_default_1496 = quantized_decomposed_dequantize_per_tensor_default_1499 = quantized_decomposed_dequantize_per_tensor_default_1502 = quantized_decomposed_dequantize_per_tensor_default_1505 = quantized_decomposed_dequantize_per_tensor_default_1508 = quantized_decomposed_dequantize_per_tensor_default_1511 = quantized_decomposed_dequantize_per_tensor_default_1514 = quantized_decomposed_dequantize_per_tensor_default_1517 = quantized_decomposed_dequantize_per_tensor_default_1520 = None
2025-03-21T20:31:43.7399590Z             quantized_decomposed_quantize_per_tensor_default_1067: "i32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_26, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_cat_default_26 = None
2025-03-21T20:31:43.7400734Z             quantized_decomposed_dequantize_per_tensor_default_1521: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1067, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1067 = None
2025-03-21T20:31:43.7401536Z             aten_view_copy_default_117: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1521, [1, 12, 128, 64]);  quantized_decomposed_dequantize_per_tensor_default_1521 = None
2025-03-21T20:31:43.7402447Z             quantized_decomposed_quantize_per_tensor_default_1068: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_117, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_view_copy_default_117 = None
2025-03-21T20:31:43.7402550Z             
2025-03-21T20:31:43.7403130Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.7404340Z             quantized_decomposed_dequantize_per_tensor_default_1522: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1068, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1068 = None
2025-03-21T20:31:43.7404431Z             
2025-03-21T20:31:43.7405071Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.7405872Z             aten_permute_copy_default_265: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1484, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1484 = None
2025-03-21T20:31:43.7406852Z             quantized_decomposed_quantize_per_tensor_default_1069: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_265, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_permute_copy_default_265 = None
2025-03-21T20:31:43.7408008Z             quantized_decomposed_dequantize_per_tensor_default_1523: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1069, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1069 = None
2025-03-21T20:31:43.7408761Z             aten_select_copy_int_312: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1523, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1523 = None
2025-03-21T20:31:43.7409752Z             quantized_decomposed_quantize_per_tensor_default_1070: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_312, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_select_copy_int_312 = None
2025-03-21T20:31:43.7410921Z             quantized_decomposed_dequantize_per_tensor_default_1524: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1070, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1070 = None
2025-03-21T20:31:43.7411673Z             aten_select_copy_int_313: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1524, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1524 = None
2025-03-21T20:31:43.7412574Z             quantized_decomposed_quantize_per_tensor_default_1071: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_313, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_select_copy_int_313 = None
2025-03-21T20:31:43.7412681Z             
2025-03-21T20:31:43.7413625Z              # File: <eval_with_key>.50:3856 in forward, code: dequantize_per_tensor_default_1226 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1226, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantize_per_tensor_default_1226 = None
2025-03-21T20:31:43.7414788Z             quantized_decomposed_dequantize_per_tensor_default_1525: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1071, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1071 = None
2025-03-21T20:31:43.7414880Z             
2025-03-21T20:31:43.7415554Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.7416400Z             aten_permute_copy_default_266: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1483, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1483 = None
2025-03-21T20:31:43.7417356Z             quantized_decomposed_quantize_per_tensor_default_1072: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_266, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_permute_copy_default_266 = None
2025-03-21T20:31:43.7418504Z             quantized_decomposed_dequantize_per_tensor_default_1526: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1072, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1072 = None
2025-03-21T20:31:43.7419279Z             aten_select_copy_int_314: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1526, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1526 = None
2025-03-21T20:31:43.7420179Z             quantized_decomposed_quantize_per_tensor_default_1073: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_314, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_select_copy_int_314 = None
2025-03-21T20:31:43.7421340Z             quantized_decomposed_dequantize_per_tensor_default_1527: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1073, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1073 = None
2025-03-21T20:31:43.7422105Z             aten_select_copy_int_315: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1527, 0, 1);  quantized_decomposed_dequantize_per_tensor_default_1527 = None
2025-03-21T20:31:43.7423013Z             quantized_decomposed_quantize_per_tensor_default_1074: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_315, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_select_copy_int_315 = None
2025-03-21T20:31:43.7423100Z             
2025-03-21T20:31:43.7424046Z              # File: <eval_with_key>.50:3865 in forward, code: dequantize_per_tensor_default_1229 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1229, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantize_per_tensor_default_1229 = None
2025-03-21T20:31:43.7425201Z             quantized_decomposed_dequantize_per_tensor_default_1528: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1074, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1074 = None
2025-03-21T20:31:43.7425305Z             
2025-03-21T20:31:43.7425938Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.7426746Z             aten_permute_copy_default_267: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1482, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1482 = None
2025-03-21T20:31:43.7427722Z             quantized_decomposed_quantize_per_tensor_default_1075: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_267, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_permute_copy_default_267 = None
2025-03-21T20:31:43.7428910Z             quantized_decomposed_dequantize_per_tensor_default_1529: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1075, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1075 = None
2025-03-21T20:31:43.7429647Z             aten_select_copy_int_316: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1529, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1529 = None
2025-03-21T20:31:43.7430555Z             quantized_decomposed_quantize_per_tensor_default_1076: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_316, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_select_copy_int_316 = None
2025-03-21T20:31:43.7431728Z             quantized_decomposed_dequantize_per_tensor_default_1530: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1076, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1076 = None
2025-03-21T20:31:43.7432664Z             aten_select_copy_int_317: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1530, 0, 2);  quantized_decomposed_dequantize_per_tensor_default_1530 = None
2025-03-21T20:31:43.7433643Z             quantized_decomposed_quantize_per_tensor_default_1077: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_317, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_select_copy_int_317 = None
2025-03-21T20:31:43.7433746Z             
2025-03-21T20:31:43.7434684Z              # File: <eval_with_key>.50:3874 in forward, code: dequantize_per_tensor_default_1232 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1232, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantize_per_tensor_default_1232 = None
2025-03-21T20:31:43.7435847Z             quantized_decomposed_dequantize_per_tensor_default_1531: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1077, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1077 = None
2025-03-21T20:31:43.7435937Z             
2025-03-21T20:31:43.7436585Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.7437388Z             aten_permute_copy_default_268: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1481, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1481 = None
2025-03-21T20:31:43.7438343Z             quantized_decomposed_quantize_per_tensor_default_1078: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_268, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_permute_copy_default_268 = None
2025-03-21T20:31:43.7439495Z             quantized_decomposed_dequantize_per_tensor_default_1532: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1078, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1078 = None
2025-03-21T20:31:43.7440325Z             aten_select_copy_int_318: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1532, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1532 = None
2025-03-21T20:31:43.7441234Z             quantized_decomposed_quantize_per_tensor_default_1079: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_318, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_select_copy_int_318 = None
2025-03-21T20:31:43.7442385Z             quantized_decomposed_dequantize_per_tensor_default_1533: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1079, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1079 = None
2025-03-21T20:31:43.7443135Z             aten_select_copy_int_319: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1533, 0, 3);  quantized_decomposed_dequantize_per_tensor_default_1533 = None
2025-03-21T20:31:43.7444065Z             quantized_decomposed_quantize_per_tensor_default_1080: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_319, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_select_copy_int_319 = None
2025-03-21T20:31:43.7444169Z             
2025-03-21T20:31:43.7445109Z              # File: <eval_with_key>.50:3883 in forward, code: dequantize_per_tensor_default_1235 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1235, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantize_per_tensor_default_1235 = None
2025-03-21T20:31:43.7446302Z             quantized_decomposed_dequantize_per_tensor_default_1534: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1080, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1080 = None
2025-03-21T20:31:43.7446392Z             
2025-03-21T20:31:43.7447037Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.7447838Z             aten_permute_copy_default_269: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1480, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1480 = None
2025-03-21T20:31:43.7448796Z             quantized_decomposed_quantize_per_tensor_default_1081: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_269, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_permute_copy_default_269 = None
2025-03-21T20:31:43.7450053Z             quantized_decomposed_dequantize_per_tensor_default_1535: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1081, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1081 = None
2025-03-21T20:31:43.7450809Z             aten_select_copy_int_320: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1535, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1535 = None
2025-03-21T20:31:43.7451706Z             quantized_decomposed_quantize_per_tensor_default_1082: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_320, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_select_copy_int_320 = None
2025-03-21T20:31:43.7452940Z             quantized_decomposed_dequantize_per_tensor_default_1536: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1082, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1082 = None
2025-03-21T20:31:43.7453676Z             aten_select_copy_int_321: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1536, 0, 4);  quantized_decomposed_dequantize_per_tensor_default_1536 = None
2025-03-21T20:31:43.7454582Z             quantized_decomposed_quantize_per_tensor_default_1083: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_321, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_select_copy_int_321 = None
2025-03-21T20:31:43.7454673Z             
2025-03-21T20:31:43.7455650Z              # File: <eval_with_key>.50:3892 in forward, code: dequantize_per_tensor_default_1238 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1238, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantize_per_tensor_default_1238 = None
2025-03-21T20:31:43.7456796Z             quantized_decomposed_dequantize_per_tensor_default_1537: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1083, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1083 = None
2025-03-21T20:31:43.7456893Z             
2025-03-21T20:31:43.7457631Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.7458484Z             aten_permute_copy_default_270: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1479, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1479 = None
2025-03-21T20:31:43.7459430Z             quantized_decomposed_quantize_per_tensor_default_1084: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_270, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_permute_copy_default_270 = None
2025-03-21T20:31:43.7460587Z             quantized_decomposed_dequantize_per_tensor_default_1538: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1084, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1084 = None
2025-03-21T20:31:43.7461332Z             aten_select_copy_int_322: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1538, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1538 = None
2025-03-21T20:31:43.7462243Z             quantized_decomposed_quantize_per_tensor_default_1085: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_322, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_select_copy_int_322 = None
2025-03-21T20:31:43.7463389Z             quantized_decomposed_dequantize_per_tensor_default_1539: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1085, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1085 = None
2025-03-21T20:31:43.7464160Z             aten_select_copy_int_323: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1539, 0, 5);  quantized_decomposed_dequantize_per_tensor_default_1539 = None
2025-03-21T20:31:43.7465092Z             quantized_decomposed_quantize_per_tensor_default_1086: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_323, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_select_copy_int_323 = None
2025-03-21T20:31:43.7465185Z             
2025-03-21T20:31:43.7466126Z              # File: <eval_with_key>.50:3901 in forward, code: dequantize_per_tensor_default_1241 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1241, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantize_per_tensor_default_1241 = None
2025-03-21T20:31:43.7467286Z             quantized_decomposed_dequantize_per_tensor_default_1540: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1086, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1086 = None
2025-03-21T20:31:43.7467387Z             
2025-03-21T20:31:43.7468219Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.7469163Z             aten_permute_copy_default_271: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1478, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1478 = None
2025-03-21T20:31:43.7470135Z             quantized_decomposed_quantize_per_tensor_default_1087: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_271, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_permute_copy_default_271 = None
2025-03-21T20:31:43.7471348Z             quantized_decomposed_dequantize_per_tensor_default_1541: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1087, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1087 = None
2025-03-21T20:31:43.7472086Z             aten_select_copy_int_324: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1541, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1541 = None
2025-03-21T20:31:43.7472993Z             quantized_decomposed_quantize_per_tensor_default_1088: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_324, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_select_copy_int_324 = None
2025-03-21T20:31:43.7474145Z             quantized_decomposed_dequantize_per_tensor_default_1542: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1088, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1088 = None
2025-03-21T20:31:43.7474894Z             aten_select_copy_int_325: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1542, 0, 6);  quantized_decomposed_dequantize_per_tensor_default_1542 = None
2025-03-21T20:31:43.7475783Z             quantized_decomposed_quantize_per_tensor_default_1089: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_325, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_select_copy_int_325 = None
2025-03-21T20:31:43.7475885Z             
2025-03-21T20:31:43.7476846Z              # File: <eval_with_key>.50:3910 in forward, code: dequantize_per_tensor_default_1244 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1244, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantize_per_tensor_default_1244 = None
2025-03-21T20:31:43.7478028Z             quantized_decomposed_dequantize_per_tensor_default_1543: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1089, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1089 = None
2025-03-21T20:31:43.7478116Z             
2025-03-21T20:31:43.7478763Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.7479563Z             aten_permute_copy_default_272: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1477, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1477 = None
2025-03-21T20:31:43.7480557Z             quantized_decomposed_quantize_per_tensor_default_1090: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_272, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_permute_copy_default_272 = None
2025-03-21T20:31:43.7481707Z             quantized_decomposed_dequantize_per_tensor_default_1544: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1090, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1090 = None
2025-03-21T20:31:43.7482482Z             aten_select_copy_int_326: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1544, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1544 = None
2025-03-21T20:31:43.7483381Z             quantized_decomposed_quantize_per_tensor_default_1091: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_326, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_select_copy_int_326 = None
2025-03-21T20:31:43.7484538Z             quantized_decomposed_dequantize_per_tensor_default_1545: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1091, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1091 = None
2025-03-21T20:31:43.7485275Z             aten_select_copy_int_327: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1545, 0, 7);  quantized_decomposed_dequantize_per_tensor_default_1545 = None
2025-03-21T20:31:43.7486184Z             quantized_decomposed_quantize_per_tensor_default_1092: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_327, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_select_copy_int_327 = None
2025-03-21T20:31:43.7486272Z             
2025-03-21T20:31:43.7487221Z              # File: <eval_with_key>.50:3919 in forward, code: dequantize_per_tensor_default_1247 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1247, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantize_per_tensor_default_1247 = None
2025-03-21T20:31:43.7488366Z             quantized_decomposed_dequantize_per_tensor_default_1546: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1092, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1092 = None
2025-03-21T20:31:43.7488518Z             
2025-03-21T20:31:43.7489156Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.7490050Z             aten_permute_copy_default_273: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1476, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1476 = None
2025-03-21T20:31:43.7490998Z             quantized_decomposed_quantize_per_tensor_default_1093: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_273, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_permute_copy_default_273 = None
2025-03-21T20:31:43.7492202Z             quantized_decomposed_dequantize_per_tensor_default_1547: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1093, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1093 = None
2025-03-21T20:31:43.7492944Z             aten_select_copy_int_328: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1547, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1547 = None
2025-03-21T20:31:43.7493857Z             quantized_decomposed_quantize_per_tensor_default_1094: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_328, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_select_copy_int_328 = None
2025-03-21T20:31:43.7495046Z             quantized_decomposed_dequantize_per_tensor_default_1548: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1094, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1094 = None
2025-03-21T20:31:43.7495786Z             aten_select_copy_int_329: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1548, 0, 8);  quantized_decomposed_dequantize_per_tensor_default_1548 = None
2025-03-21T20:31:43.7496693Z             quantized_decomposed_quantize_per_tensor_default_1095: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_329, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_select_copy_int_329 = None
2025-03-21T20:31:43.7496782Z             
2025-03-21T20:31:43.7497736Z              # File: <eval_with_key>.50:3928 in forward, code: dequantize_per_tensor_default_1250 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1250, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantize_per_tensor_default_1250 = None
2025-03-21T20:31:43.7498886Z             quantized_decomposed_dequantize_per_tensor_default_1549: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1095, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1095 = None
2025-03-21T20:31:43.7498987Z             
2025-03-21T20:31:43.7499622Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.7500432Z             aten_permute_copy_default_274: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1475, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1475 = None
2025-03-21T20:31:43.7501440Z             quantized_decomposed_quantize_per_tensor_default_1096: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_274, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_permute_copy_default_274 = None
2025-03-21T20:31:43.7502596Z             quantized_decomposed_dequantize_per_tensor_default_1550: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1096, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1096 = None
2025-03-21T20:31:43.7503336Z             aten_select_copy_int_330: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1550, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1550 = None
2025-03-21T20:31:43.7504271Z             quantized_decomposed_quantize_per_tensor_default_1097: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_330, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_select_copy_int_330 = None
2025-03-21T20:31:43.7505423Z             quantized_decomposed_dequantize_per_tensor_default_1551: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1097, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1097 = None
2025-03-21T20:31:43.7506166Z             aten_select_copy_int_331: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1551, 0, 9);  quantized_decomposed_dequantize_per_tensor_default_1551 = None
2025-03-21T20:31:43.7507096Z             quantized_decomposed_quantize_per_tensor_default_1098: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_331, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_select_copy_int_331 = None
2025-03-21T20:31:43.7507200Z             
2025-03-21T20:31:43.7508137Z              # File: <eval_with_key>.50:3937 in forward, code: dequantize_per_tensor_default_1253 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1253, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantize_per_tensor_default_1253 = None
2025-03-21T20:31:43.7509308Z             quantized_decomposed_dequantize_per_tensor_default_1552: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1098, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1098 = None
2025-03-21T20:31:43.7509400Z             
2025-03-21T20:31:43.7510053Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.7510861Z             aten_permute_copy_default_275: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1474, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1474 = None
2025-03-21T20:31:43.7511819Z             quantized_decomposed_quantize_per_tensor_default_1099: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_275, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_permute_copy_default_275 = None
2025-03-21T20:31:43.7513248Z             quantized_decomposed_dequantize_per_tensor_default_1553: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1099, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1099 = None
2025-03-21T20:31:43.7514038Z             aten_select_copy_int_332: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1553, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1553 = None
2025-03-21T20:31:43.7514936Z             quantized_decomposed_quantize_per_tensor_default_1100: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_332, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_select_copy_int_332 = None
2025-03-21T20:31:43.7516108Z             quantized_decomposed_dequantize_per_tensor_default_1554: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1100, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1100 = None
2025-03-21T20:31:43.7516873Z             aten_select_copy_int_333: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1554, 0, 10);  quantized_decomposed_dequantize_per_tensor_default_1554 = None
2025-03-21T20:31:43.7517785Z             quantized_decomposed_quantize_per_tensor_default_1101: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_333, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_select_copy_int_333 = None
2025-03-21T20:31:43.7517877Z             
2025-03-21T20:31:43.7518832Z              # File: <eval_with_key>.50:3946 in forward, code: dequantize_per_tensor_default_1256 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1256, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantize_per_tensor_default_1256 = None
2025-03-21T20:31:43.7520011Z             quantized_decomposed_dequantize_per_tensor_default_1555: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1101, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1101 = None
2025-03-21T20:31:43.7520113Z             
2025-03-21T20:31:43.7520753Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.7521570Z             aten_permute_copy_default_276: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1473, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1473 = None
2025-03-21T20:31:43.7522519Z             quantized_decomposed_quantize_per_tensor_default_1102: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_276, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_permute_copy_default_276 = None
2025-03-21T20:31:43.7523689Z             quantized_decomposed_dequantize_per_tensor_default_1556: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1102, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1102 = None
2025-03-21T20:31:43.7524445Z             aten_select_copy_int_334: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1556, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1556 = None
2025-03-21T20:31:43.7525369Z             quantized_decomposed_quantize_per_tensor_default_1103: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_334, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_select_copy_int_334 = None
2025-03-21T20:31:43.7526569Z             quantized_decomposed_dequantize_per_tensor_default_1557: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1103, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1103 = None
2025-03-21T20:31:43.7527306Z             aten_select_copy_int_335: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1557, 0, 11);  quantized_decomposed_dequantize_per_tensor_default_1557 = None
2025-03-21T20:31:43.7528214Z             quantized_decomposed_quantize_per_tensor_default_1104: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_335, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_select_copy_int_335 = None
2025-03-21T20:31:43.7528305Z             
2025-03-21T20:31:43.7529359Z              # File: <eval_with_key>.50:3955 in forward, code: dequantize_per_tensor_default_1259 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1259, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantize_per_tensor_default_1259 = None
2025-03-21T20:31:43.7530521Z             quantized_decomposed_dequantize_per_tensor_default_1558: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1104, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1104 = None
2025-03-21T20:31:43.7530653Z             
2025-03-21T20:31:43.7531290Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.7536949Z             aten_cat_default_27: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_aten_cat_default([quantized_decomposed_dequantize_per_tensor_default_1525, quantized_decomposed_dequantize_per_tensor_default_1528, quantized_decomposed_dequantize_per_tensor_default_1531, quantized_decomposed_dequantize_per_tensor_default_1534, quantized_decomposed_dequantize_per_tensor_default_1537, quantized_decomposed_dequantize_per_tensor_default_1540, quantized_decomposed_dequantize_per_tensor_default_1543, quantized_decomposed_dequantize_per_tensor_default_1546, quantized_decomposed_dequantize_per_tensor_default_1549, quantized_decomposed_dequantize_per_tensor_default_1552, quantized_decomposed_dequantize_per_tensor_default_1555, quantized_decomposed_dequantize_per_tensor_default_1558]);  quantized_decomposed_dequantize_per_tensor_default_1525 = quantized_decomposed_dequantize_per_tensor_default_1528 = quantized_decomposed_dequantize_per_tensor_default_1531 = quantized_decomposed_dequantize_per_tensor_default_1534 = quantized_decomposed_dequantize_per_tensor_default_1537 = quantized_decomposed_dequantize_per_tensor_default_1540 = quantized_decomposed_dequantize_per_tensor_default_1543 = quantized_decomposed_dequantize_per_tensor_default_1546 = quantized_decomposed_dequantize_per_tensor_default_1549 = quantized_decomposed_dequantize_per_tensor_default_1552 = quantized_decomposed_dequantize_per_tensor_default_1555 = quantized_decomposed_dequantize_per_tensor_default_1558 = None
2025-03-21T20:31:43.7537847Z             quantized_decomposed_quantize_per_tensor_default_1105: "i32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_27, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_cat_default_27 = None
2025-03-21T20:31:43.7539073Z             quantized_decomposed_dequantize_per_tensor_default_1559: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1105, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1105 = None
2025-03-21T20:31:43.7539900Z             aten_view_copy_default_118: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1559, [1, 12, 128, 64]);  quantized_decomposed_dequantize_per_tensor_default_1559 = None
2025-03-21T20:31:43.7540823Z             quantized_decomposed_quantize_per_tensor_default_1106: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_118, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  aten_view_copy_default_118 = None
2025-03-21T20:31:43.7540927Z             
2025-03-21T20:31:43.7541868Z              # File: <eval_with_key>.50:3961 in forward, code: dequantize_per_tensor_default_1261 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1261, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantize_per_tensor_default_1261 = None
2025-03-21T20:31:43.7543072Z             quantized_decomposed_dequantize_per_tensor_default_1560: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1106, 0.00011607543274294585, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1106 = None
2025-03-21T20:31:43.7543162Z             
2025-03-21T20:31:43.7544116Z              # File: <eval_with_key>.50:3962 in forward, code: quantize_per_tensor_default_1262 = torch.ops.quantized_decomposed.quantize_per_tensor.default(dequantize_per_tensor_default_1261, 0.00011609794455580413, 0, -32767, 32767, torch.int16);  dequantize_per_tensor_default_1261 = None
2025-03-21T20:31:43.7545308Z             quantized_decomposed_quantize_per_tensor_default_1107: "i16[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_1560, 0.00011609794455580413, 0, -32767, 32767, torch.int16);  quantized_decomposed_dequantize_per_tensor_default_1560 = None
2025-03-21T20:31:43.7545406Z             
2025-03-21T20:31:43.7545870Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:163 in forward, code: y = attn_weight @ v
2025-03-21T20:31:43.7547040Z             quantized_decomposed_dequantize_per_tensor_default_1561: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1107, 0.00011609794455580413, 0, -32767, 32767, torch.int16);  quantized_decomposed_quantize_per_tensor_default_1107 = None
2025-03-21T20:31:43.7547129Z             
2025-03-21T20:31:43.7547633Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:157 in forward, code: attn_mask = mask[input_pos]
2025-03-21T20:31:43.7548425Z             aten_index_tensor_8: "f32[1, 128]" = executorch_exir_dialects_edge__ops_aten_index_Tensor(quantized_decomposed_dequantize_per_tensor_default_133, [attn_options_input_pos]);  quantized_decomposed_dequantize_per_tensor_default_133 = None
2025-03-21T20:31:43.7549297Z             quantized_decomposed_quantize_per_tensor_default_1108: "i32[1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_tensor_8, 0.0038910505827516317, 65535, 0, 65535, torch.int32);  aten_index_tensor_8 = None
2025-03-21T20:31:43.7549387Z             
2025-03-21T20:31:43.7549879Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:161 in forward, code: attn_weight += attn_mask
2025-03-21T20:31:43.7551052Z             quantized_decomposed_dequantize_per_tensor_default_1562: "f32[1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1108, 0.0038910505827516317, 65535, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1108 = None
2025-03-21T20:31:43.7551178Z             
2025-03-21T20:31:43.7551750Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.7552565Z             aten_permute_copy_default_277: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1522, [0, 1, 3, 2]);  quantized_decomposed_dequantize_per_tensor_default_1522 = None
2025-03-21T20:31:43.7553503Z             quantized_decomposed_quantize_per_tensor_default_1109: "i32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_277, 0.000468338665086776, 33988, 0, 65535, torch.int32);  aten_permute_copy_default_277 = None
2025-03-21T20:31:43.7553608Z             
2025-03-21T20:31:43.7554561Z              # File: <eval_with_key>.50:3969 in forward, code: dequantize_per_tensor_default_1264 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1264, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantize_per_tensor_default_1264 = None
2025-03-21T20:31:43.7555718Z             quantized_decomposed_dequantize_per_tensor_default_1563: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1109, 0.000468338665086776, 33988, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1109 = None
2025-03-21T20:31:43.7555833Z             
2025-03-21T20:31:43.7556783Z              # File: <eval_with_key>.50:3970 in forward, code: quantize_per_tensor_default_1265 = torch.ops.quantized_decomposed.quantize_per_tensor.default(dequantize_per_tensor_default_1264, 0.0004857908934354782, 0, -32767, 32767, torch.int16);  dequantize_per_tensor_default_1264 = None
2025-03-21T20:31:43.7557933Z             quantized_decomposed_quantize_per_tensor_default_1110: "i16[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_1563, 0.0004857908934354782, 0, -32767, 32767, torch.int16);  quantized_decomposed_dequantize_per_tensor_default_1563 = None
2025-03-21T20:31:43.7558039Z             
2025-03-21T20:31:43.7558612Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.7559786Z             quantized_decomposed_dequantize_per_tensor_default_1564: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1110, 0.0004857908934354782, 0, -32767, 32767, torch.int16);  quantized_decomposed_quantize_per_tensor_default_1110 = None
2025-03-21T20:31:43.7560574Z             aten_expand_copy_default_24: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_1458, [1, 12, 1, 64]);  quantized_decomposed_dequantize_per_tensor_default_1458 = None
2025-03-21T20:31:43.7561140Z             aten_view_copy_default_119: "f32[12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_24, [12, 1, 64]);  aten_expand_copy_default_24 = None
2025-03-21T20:31:43.7561932Z             aten_expand_copy_default_25: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_1564, [1, 12, 64, 128]);  quantized_decomposed_dequantize_per_tensor_default_1564 = None
2025-03-21T20:31:43.7562539Z             aten_view_copy_default_120: "f32[12, 64, 128]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_25, [12, 64, 128]);  aten_expand_copy_default_25 = None
2025-03-21T20:31:43.7563217Z             aten_bmm_default_12: "f32[12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_bmm_default(aten_view_copy_default_119, aten_view_copy_default_120);  aten_view_copy_default_119 = aten_view_copy_default_120 = None
2025-03-21T20:31:43.7563743Z             aten_view_copy_default_121: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_bmm_default_12, [1, 12, 1, 128]);  aten_bmm_default_12 = None
2025-03-21T20:31:43.7564652Z             quantized_decomposed_quantize_per_tensor_default_1111: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_121, 0.004839103203266859, 45381, 0, 65535, torch.int32);  aten_view_copy_default_121 = None
2025-03-21T20:31:43.7565836Z             quantized_decomposed_dequantize_per_tensor_default_1565: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1111, 0.004839103203266859, 45381, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1111 = None
2025-03-21T20:31:43.7566692Z             quantized_decomposed_dequantize_per_tensor_default_1566: "f32[1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param155, 1.9073777366429567e-06, 0, 0, 65535, torch.int32);  b__frozen_param155 = None
2025-03-21T20:31:43.7567840Z             aten_mul_tensor_100: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1565, quantized_decomposed_dequantize_per_tensor_default_1566);  quantized_decomposed_dequantize_per_tensor_default_1565 = quantized_decomposed_dequantize_per_tensor_default_1566 = None
2025-03-21T20:31:43.7568752Z             quantized_decomposed_quantize_per_tensor_default_1112: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_100, 0.0006048879004083574, 45381, 0, 65535, torch.int32);  aten_mul_tensor_100 = None
2025-03-21T20:31:43.7568854Z             
2025-03-21T20:31:43.7569396Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:161 in forward, code: attn_weight += attn_mask
2025-03-21T20:31:43.7570698Z             quantized_decomposed_dequantize_per_tensor_default_1567: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1112, 0.0006048879004083574, 45381, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1112 = None
2025-03-21T20:31:43.7571839Z             aten_add_tensor_32: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_1567, quantized_decomposed_dequantize_per_tensor_default_1562);  quantized_decomposed_dequantize_per_tensor_default_1567 = quantized_decomposed_dequantize_per_tensor_default_1562 = None
2025-03-21T20:31:43.7572710Z             quantized_decomposed_quantize_per_tensor_default_1113: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_32, 0.004426939878612757, 62781, 0, 65535, torch.int32);  aten_add_tensor_32 = None
2025-03-21T20:31:43.7572805Z             
2025-03-21T20:31:43.7573385Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:162 in forward, code: attn_weight = torch.softmax(attn_weight, dim=-1)
2025-03-21T20:31:43.7574581Z             quantized_decomposed_dequantize_per_tensor_default_1568: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1113, 0.004426939878612757, 62781, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1113 = None
2025-03-21T20:31:43.7575403Z             aten__softmax_default_6: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten__softmax_default(quantized_decomposed_dequantize_per_tensor_default_1568, -1, False);  quantized_decomposed_dequantize_per_tensor_default_1568 = None
2025-03-21T20:31:43.7576287Z             quantized_decomposed_quantize_per_tensor_default_1114: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten__softmax_default_6, 1.5259021893143654e-05, 0, 0, 65535, torch.int32);  aten__softmax_default_6 = None
2025-03-21T20:31:43.7576390Z             
2025-03-21T20:31:43.7576849Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:163 in forward, code: y = attn_weight @ v
2025-03-21T20:31:43.7577997Z             quantized_decomposed_dequantize_per_tensor_default_1569: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1114, 1.5259021893143654e-05, 0, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1114 = None
2025-03-21T20:31:43.7578817Z             aten_expand_copy_default_26: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_1569, [1, 12, 1, 128]);  quantized_decomposed_dequantize_per_tensor_default_1569 = None
2025-03-21T20:31:43.7579397Z             aten_view_copy_default_122: "f32[12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_26, [12, 1, 128]);  aten_expand_copy_default_26 = None
2025-03-21T20:31:43.7580194Z             aten_expand_copy_default_27: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_1561, [1, 12, 128, 64]);  quantized_decomposed_dequantize_per_tensor_default_1561 = None
2025-03-21T20:31:43.7580807Z             aten_view_copy_default_123: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_27, [12, 128, 64]);  aten_expand_copy_default_27 = None
2025-03-21T20:31:43.7581457Z             aten_bmm_default_13: "f32[12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_bmm_default(aten_view_copy_default_122, aten_view_copy_default_123);  aten_view_copy_default_122 = aten_view_copy_default_123 = None
2025-03-21T20:31:43.7581979Z             aten_view_copy_default_124: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_bmm_default_13, [1, 12, 1, 64]);  aten_bmm_default_13 = None
2025-03-21T20:31:43.7582881Z             quantized_decomposed_quantize_per_tensor_default_1115: "i32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_124, 8.035911014303565e-05, 31531, 0, 65535, torch.int32);  aten_view_copy_default_124 = None
2025-03-21T20:31:43.7582986Z             
2025-03-21T20:31:43.7583614Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:165 in forward, code: return y.transpose(1, 2).contiguous().view(bsz, seqlen, self.dim)
2025-03-21T20:31:43.7584767Z             quantized_decomposed_dequantize_per_tensor_default_1570: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1115, 8.035911014303565e-05, 31531, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1115 = None
2025-03-21T20:31:43.7585560Z             aten_permute_copy_default_278: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1570, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1570 = None
2025-03-21T20:31:43.7586530Z             quantized_decomposed_quantize_per_tensor_default_1116: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_278, 8.035911014303565e-05, 31531, 0, 65535, torch.int32);  aten_permute_copy_default_278 = None
2025-03-21T20:31:43.7587690Z             quantized_decomposed_dequantize_per_tensor_default_1571: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1116, 8.035911014303565e-05, 31531, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1116 = None
2025-03-21T20:31:43.7588476Z             aten_view_copy_default_125: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1571, [1, 1, 768]);  quantized_decomposed_dequantize_per_tensor_default_1571 = None
2025-03-21T20:31:43.7589382Z             quantized_decomposed_quantize_per_tensor_default_1117: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_125, 8.035911014303565e-05, 31531, 0, 65535, torch.int32);  aten_view_copy_default_125 = None
2025-03-21T20:31:43.7589482Z             
2025-03-21T20:31:43.7590029Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.7591182Z             quantized_decomposed_dequantize_per_tensor_default_1572: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1117, 8.035911014303565e-05, 31531, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1117 = None
2025-03-21T20:31:43.7591984Z             aten_unsqueeze_copy_default_73: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1572, -1);  quantized_decomposed_dequantize_per_tensor_default_1572 = None
2025-03-21T20:31:43.7592968Z             quantized_decomposed_quantize_per_tensor_default_1118: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_73, 8.035911014303565e-05, 31531, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_73 = None
2025-03-21T20:31:43.7593056Z             
2025-03-21T20:31:43.7593473Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.7594613Z             quantized_decomposed_dequantize_per_tensor_default_1573: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1118, 8.035911014303565e-05, 31531, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1118 = None
2025-03-21T20:31:43.7595430Z             aten_permute_copy_default_279: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1573, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1573 = None
2025-03-21T20:31:43.7596361Z             quantized_decomposed_quantize_per_tensor_default_1119: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_279, 8.035911014303565e-05, 31531, 0, 65535, torch.int32);  aten_permute_copy_default_279 = None
2025-03-21T20:31:43.7596463Z             
2025-03-21T20:31:43.7596831Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.7597989Z             quantized_decomposed_dequantize_per_tensor_default_1574: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1119, 8.035911014303565e-05, 31531, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1119 = None
2025-03-21T20:31:43.7599324Z             aten_convolution_default_45: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_1574, quantized_decomposed_dequantize_per_tensor_default_59, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_1574 = quantized_decomposed_dequantize_per_tensor_default_59 = None
2025-03-21T20:31:43.7600264Z             quantized_decomposed_quantize_per_tensor_default_1120: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_45, 4.686550164478831e-05, 25382, 0, 65535, torch.int32);  aten_convolution_default_45 = None
2025-03-21T20:31:43.7600366Z             
2025-03-21T20:31:43.7600788Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.7601956Z             quantized_decomposed_dequantize_per_tensor_default_1575: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1120, 4.686550164478831e-05, 25382, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1120 = None
2025-03-21T20:31:43.7602766Z             aten_permute_copy_default_280: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1575, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1575 = None
2025-03-21T20:31:43.7603709Z             quantized_decomposed_quantize_per_tensor_default_1121: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_280, 4.686550164478831e-05, 25382, 0, 65535, torch.int32);  aten_permute_copy_default_280 = None
2025-03-21T20:31:43.7603820Z             
2025-03-21T20:31:43.7604361Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.7605515Z             quantized_decomposed_dequantize_per_tensor_default_1576: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1121, 4.686550164478831e-05, 25382, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1121 = None
2025-03-21T20:31:43.7606268Z             aten_squeeze_copy_dims_73: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_1576, [-1]);  quantized_decomposed_dequantize_per_tensor_default_1576 = None
2025-03-21T20:31:43.7607178Z             quantized_decomposed_quantize_per_tensor_default_1122: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_73, 4.686550164478831e-05, 25382, 0, 65535, torch.int32);  aten_squeeze_copy_dims_73 = None
2025-03-21T20:31:43.7607266Z             
2025-03-21T20:31:43.7607649Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:111 in forward, code: h = x + h
2025-03-21T20:31:43.7608784Z             quantized_decomposed_dequantize_per_tensor_default_1577: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1122, 4.686550164478831e-05, 25382, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1122 = None
2025-03-21T20:31:43.7610010Z             aten_add_tensor_33: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_1397, quantized_decomposed_dequantize_per_tensor_default_1577);  quantized_decomposed_dequantize_per_tensor_default_1397 = quantized_decomposed_dequantize_per_tensor_default_1577 = None
2025-03-21T20:31:43.7610930Z             quantized_decomposed_quantize_per_tensor_default_1123: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_33, 0.00266623985953629, 5970, 0, 65535, torch.int32);  aten_add_tensor_33 = None
2025-03-21T20:31:43.7611023Z             
2025-03-21T20:31:43.7611533Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:115 in forward, code: out = h + self.feed_forward(self.ffn_norm(h))
2025-03-21T20:31:43.7612454Z             quantized_decomposed_dequantize_per_tensor_default_1578: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1123, 0.00266623985953629, 5970, 0, 65535, torch.int32)
2025-03-21T20:31:43.7613586Z             quantized_decomposed_dequantize_per_tensor_default_1579: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1123, 0.00266623985953629, 5970, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1123 = None
2025-03-21T20:31:43.7614139Z             aten_pow_tensor_scalar_13: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_pow_Tensor_Scalar(quantized_decomposed_dequantize_per_tensor_default_1579, 2)
2025-03-21T20:31:43.7614600Z             aten_mean_dim_13: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_mean_dim(aten_pow_tensor_scalar_13, [2], True);  aten_pow_tensor_scalar_13 = None
2025-03-21T20:31:43.7615058Z             aten_add_scalar_13: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_add_Scalar(aten_mean_dim_13, 9.999999747378752e-06);  aten_mean_dim_13 = None
2025-03-21T20:31:43.7615519Z             aten_rsqrt_default_13: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_rsqrt_default(aten_add_scalar_13);  aten_add_scalar_13 = None
2025-03-21T20:31:43.7616391Z             aten_mul_tensor_101: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1579, aten_rsqrt_default_13);  quantized_decomposed_dequantize_per_tensor_default_1579 = aten_rsqrt_default_13 = None
2025-03-21T20:31:43.7617203Z             aten_mul_tensor_102: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(aten_mul_tensor_101, quantized_decomposed_dequantize_per_tensor_default_60);  aten_mul_tensor_101 = quantized_decomposed_dequantize_per_tensor_default_60 = None
2025-03-21T20:31:43.7618072Z             quantized_decomposed_quantize_per_tensor_default_1124: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_102, 0.0003203543310519308, 20731, 0, 65535, torch.int32);  aten_mul_tensor_102 = None
2025-03-21T20:31:43.7618162Z             
2025-03-21T20:31:43.7618697Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.7619620Z             quantized_decomposed_dequantize_per_tensor_default_1580: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1124, 0.0003203543310519308, 20731, 0, 65535, torch.int32)
2025-03-21T20:31:43.7620772Z             quantized_decomposed_dequantize_per_tensor_default_1581: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1124, 0.0003203543310519308, 20731, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1124 = None
2025-03-21T20:31:43.7621573Z             aten_unsqueeze_copy_default_74: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1581, -1);  quantized_decomposed_dequantize_per_tensor_default_1581 = None
2025-03-21T20:31:43.7622593Z             quantized_decomposed_quantize_per_tensor_default_1125: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_74, 0.0003203543310519308, 20731, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_74 = None
2025-03-21T20:31:43.7622684Z             
2025-03-21T20:31:43.7623107Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.7624256Z             quantized_decomposed_dequantize_per_tensor_default_1582: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1125, 0.0003203543310519308, 20731, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1125 = None
2025-03-21T20:31:43.7625069Z             aten_permute_copy_default_281: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1582, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1582 = None
2025-03-21T20:31:43.7626042Z             quantized_decomposed_quantize_per_tensor_default_1126: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_281, 0.0003203543310519308, 20731, 0, 65535, torch.int32);  aten_permute_copy_default_281 = None
2025-03-21T20:31:43.7626133Z             
2025-03-21T20:31:43.7626495Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.7627653Z             quantized_decomposed_dequantize_per_tensor_default_1583: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1126, 0.0003203543310519308, 20731, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1126 = None
2025-03-21T20:31:43.7628976Z             aten_convolution_default_46: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_1583, quantized_decomposed_dequantize_per_tensor_default_61, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_1583 = quantized_decomposed_dequantize_per_tensor_default_61 = None
2025-03-21T20:31:43.7629914Z             quantized_decomposed_quantize_per_tensor_default_1127: "i32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_46, 0.00019273435464128852, 30017, 0, 65535, torch.int32);  aten_convolution_default_46 = None
2025-03-21T20:31:43.7630016Z             
2025-03-21T20:31:43.7630434Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.7631597Z             quantized_decomposed_dequantize_per_tensor_default_1584: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1127, 0.00019273435464128852, 30017, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1127 = None
2025-03-21T20:31:43.7632598Z             aten_permute_copy_default_282: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1584, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1584 = None
2025-03-21T20:31:43.7633560Z             quantized_decomposed_quantize_per_tensor_default_1128: "i32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_282, 0.00019273435464128852, 30017, 0, 65535, torch.int32);  aten_permute_copy_default_282 = None
2025-03-21T20:31:43.7633653Z             
2025-03-21T20:31:43.7634290Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.7635471Z             quantized_decomposed_dequantize_per_tensor_default_1585: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1128, 0.00019273435464128852, 30017, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1128 = None
2025-03-21T20:31:43.7636245Z             aten_squeeze_copy_dims_74: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_1585, [-1]);  quantized_decomposed_dequantize_per_tensor_default_1585 = None
2025-03-21T20:31:43.7637159Z             quantized_decomposed_quantize_per_tensor_default_1129: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_74, 0.00019273435464128852, 30017, 0, 65535, torch.int32);  aten_squeeze_copy_dims_74 = None
2025-03-21T20:31:43.7637266Z             
2025-03-21T20:31:43.7637812Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:36 in forward, code: return self.w2(F.silu(self.w1(x)) * self.w3(x))
2025-03-21T20:31:43.7638738Z             quantized_decomposed_dequantize_per_tensor_default_1586: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1129, 0.00019273435464128852, 30017, 0, 65535, torch.int32)
2025-03-21T20:31:43.7639900Z             quantized_decomposed_dequantize_per_tensor_default_1587: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1129, 0.00019273435464128852, 30017, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1129 = None
2025-03-21T20:31:43.7640694Z             aten_sigmoid_default_6: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_sigmoid_default(quantized_decomposed_dequantize_per_tensor_default_1587);  quantized_decomposed_dequantize_per_tensor_default_1587 = None
2025-03-21T20:31:43.7641553Z             quantized_decomposed_quantize_per_tensor_default_1130: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_sigmoid_default_6, 1.52587890625e-05, 0, 0, 65535, torch.int32);  aten_sigmoid_default_6 = None
2025-03-21T20:31:43.7642678Z             quantized_decomposed_dequantize_per_tensor_default_1588: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1130, 1.52587890625e-05, 0, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1130 = None
2025-03-21T20:31:43.7643819Z             aten_mul_tensor_103: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1586, quantized_decomposed_dequantize_per_tensor_default_1588);  quantized_decomposed_dequantize_per_tensor_default_1586 = quantized_decomposed_dequantize_per_tensor_default_1588 = None
2025-03-21T20:31:43.7644698Z             quantized_decomposed_quantize_per_tensor_default_1131: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_103, 0.00010859330359380692, 2564, 0, 65535, torch.int32);  aten_mul_tensor_103 = None
2025-03-21T20:31:43.7645842Z             quantized_decomposed_dequantize_per_tensor_default_1589: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1131, 0.00010859330359380692, 2564, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1131 = None
2025-03-21T20:31:43.7645948Z             
2025-03-21T20:31:43.7646519Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.7647339Z             aten_unsqueeze_copy_default_75: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1580, -1);  quantized_decomposed_dequantize_per_tensor_default_1580 = None
2025-03-21T20:31:43.7648289Z             quantized_decomposed_quantize_per_tensor_default_1132: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_75, 0.0003203543310519308, 20731, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_75 = None
2025-03-21T20:31:43.7648394Z             
2025-03-21T20:31:43.7648801Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.7650056Z             quantized_decomposed_dequantize_per_tensor_default_1590: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1132, 0.0003203543310519308, 20731, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1132 = None
2025-03-21T20:31:43.7650858Z             aten_permute_copy_default_283: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1590, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1590 = None
2025-03-21T20:31:43.7651802Z             quantized_decomposed_quantize_per_tensor_default_1133: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_283, 0.0003203543310519308, 20731, 0, 65535, torch.int32);  aten_permute_copy_default_283 = None
2025-03-21T20:31:43.7651918Z             
2025-03-21T20:31:43.7652297Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.7653446Z             quantized_decomposed_dequantize_per_tensor_default_1591: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1133, 0.0003203543310519308, 20731, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1133 = None
2025-03-21T20:31:43.7654739Z             aten_convolution_default_47: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_1591, quantized_decomposed_dequantize_per_tensor_default_62, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_1591 = quantized_decomposed_dequantize_per_tensor_default_62 = None
2025-03-21T20:31:43.7655678Z             quantized_decomposed_quantize_per_tensor_default_1134: "i32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_47, 0.00018771942995954305, 34569, 0, 65535, torch.int32);  aten_convolution_default_47 = None
2025-03-21T20:31:43.7655787Z             
2025-03-21T20:31:43.7656208Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.7657376Z             quantized_decomposed_dequantize_per_tensor_default_1592: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1134, 0.00018771942995954305, 34569, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1134 = None
2025-03-21T20:31:43.7658201Z             aten_permute_copy_default_284: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1592, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1592 = None
2025-03-21T20:31:43.7659220Z             quantized_decomposed_quantize_per_tensor_default_1135: "i32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_284, 0.00018771942995954305, 34569, 0, 65535, torch.int32);  aten_permute_copy_default_284 = None
2025-03-21T20:31:43.7659308Z             
2025-03-21T20:31:43.7659855Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.7661111Z             quantized_decomposed_dequantize_per_tensor_default_1593: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1135, 0.00018771942995954305, 34569, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1135 = None
2025-03-21T20:31:43.7661938Z             aten_squeeze_copy_dims_75: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_1593, [-1]);  quantized_decomposed_dequantize_per_tensor_default_1593 = None
2025-03-21T20:31:43.7662855Z             quantized_decomposed_quantize_per_tensor_default_1136: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_75, 0.00018771942995954305, 34569, 0, 65535, torch.int32);  aten_squeeze_copy_dims_75 = None
2025-03-21T20:31:43.7662957Z             
2025-03-21T20:31:43.7663471Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:36 in forward, code: return self.w2(F.silu(self.w1(x)) * self.w3(x))
2025-03-21T20:31:43.7664664Z             quantized_decomposed_dequantize_per_tensor_default_1594: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1136, 0.00018771942995954305, 34569, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1136 = None
2025-03-21T20:31:43.7665802Z             aten_mul_tensor_104: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1589, quantized_decomposed_dequantize_per_tensor_default_1594);  quantized_decomposed_dequantize_per_tensor_default_1589 = quantized_decomposed_dequantize_per_tensor_default_1594 = None
2025-03-21T20:31:43.7666675Z             quantized_decomposed_quantize_per_tensor_default_1137: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_104, 0.00036516462569124997, 41930, 0, 65535, torch.int32);  aten_mul_tensor_104 = None
2025-03-21T20:31:43.7666762Z             
2025-03-21T20:31:43.7667290Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.7668446Z             quantized_decomposed_dequantize_per_tensor_default_1595: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1137, 0.00036516462569124997, 41930, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1137 = None
2025-03-21T20:31:43.7669266Z             aten_unsqueeze_copy_default_76: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1595, -1);  quantized_decomposed_dequantize_per_tensor_default_1595 = None
2025-03-21T20:31:43.7670218Z             quantized_decomposed_quantize_per_tensor_default_1138: "i32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_76, 0.00036516462569124997, 41930, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_76 = None
2025-03-21T20:31:43.7670343Z             
2025-03-21T20:31:43.7670770Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.7672211Z             quantized_decomposed_dequantize_per_tensor_default_1596: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1138, 0.00036516462569124997, 41930, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1138 = None
2025-03-21T20:31:43.7673022Z             aten_permute_copy_default_285: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1596, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1596 = None
2025-03-21T20:31:43.7673978Z             quantized_decomposed_quantize_per_tensor_default_1139: "i32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_285, 0.00036516462569124997, 41930, 0, 65535, torch.int32);  aten_permute_copy_default_285 = None
2025-03-21T20:31:43.7674067Z             
2025-03-21T20:31:43.7674483Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.7675635Z             quantized_decomposed_dequantize_per_tensor_default_1597: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1139, 0.00036516462569124997, 41930, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1139 = None
2025-03-21T20:31:43.7676919Z             aten_convolution_default_48: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_1597, quantized_decomposed_dequantize_per_tensor_default_63, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_1597 = quantized_decomposed_dequantize_per_tensor_default_63 = None
2025-03-21T20:31:43.7677885Z             quantized_decomposed_quantize_per_tensor_default_1140: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_48, 0.0002038518141489476, 13251, 0, 65535, torch.int32);  aten_convolution_default_48 = None
2025-03-21T20:31:43.7677985Z             
2025-03-21T20:31:43.7678405Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.7679567Z             quantized_decomposed_dequantize_per_tensor_default_1598: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1140, 0.0002038518141489476, 13251, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1140 = None
2025-03-21T20:31:43.7680367Z             aten_permute_copy_default_286: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1598, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1598 = None
2025-03-21T20:31:43.7681311Z             quantized_decomposed_quantize_per_tensor_default_1141: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_286, 0.0002038518141489476, 13251, 0, 65535, torch.int32);  aten_permute_copy_default_286 = None
2025-03-21T20:31:43.7681400Z             
2025-03-21T20:31:43.7681947Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.7683127Z             quantized_decomposed_dequantize_per_tensor_default_1599: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1141, 0.0002038518141489476, 13251, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1141 = None
2025-03-21T20:31:43.7683922Z             aten_squeeze_copy_dims_76: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_1599, [-1]);  quantized_decomposed_dequantize_per_tensor_default_1599 = None
2025-03-21T20:31:43.7684822Z             quantized_decomposed_quantize_per_tensor_default_1142: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_76, 0.0002038518141489476, 13251, 0, 65535, torch.int32);  aten_squeeze_copy_dims_76 = None
2025-03-21T20:31:43.7684925Z             
2025-03-21T20:31:43.7685433Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:115 in forward, code: out = h + self.feed_forward(self.ffn_norm(h))
2025-03-21T20:31:43.7686612Z             quantized_decomposed_dequantize_per_tensor_default_1600: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1142, 0.0002038518141489476, 13251, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1142 = None
2025-03-21T20:31:43.7687737Z             aten_add_tensor_34: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_1578, quantized_decomposed_dequantize_per_tensor_default_1600);  quantized_decomposed_dequantize_per_tensor_default_1578 = quantized_decomposed_dequantize_per_tensor_default_1600 = None
2025-03-21T20:31:43.7688590Z             quantized_decomposed_quantize_per_tensor_default_1143: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_34, 0.002665344625711441, 5896, 0, 65535, torch.int32);  aten_add_tensor_34 = None
2025-03-21T20:31:43.7688711Z             
2025-03-21T20:31:43.7689091Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:111 in forward, code: h = x + h
2025-03-21T20:31:43.7690090Z             quantized_decomposed_dequantize_per_tensor_default_1601: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1143, 0.002665344625711441, 5896, 0, 65535, torch.int32)
2025-03-21T20:31:43.7690192Z             
2025-03-21T20:31:43.7690754Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:108 in forward, code: self.attention_norm(x), freqs_cos, freqs_sin, **attn_options
2025-03-21T20:31:43.7691905Z             quantized_decomposed_dequantize_per_tensor_default_1602: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1143, 0.002665344625711441, 5896, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1143 = None
2025-03-21T20:31:43.7692424Z             aten_pow_tensor_scalar_14: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_pow_Tensor_Scalar(quantized_decomposed_dequantize_per_tensor_default_1602, 2)
2025-03-21T20:31:43.7692896Z             aten_mean_dim_14: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_mean_dim(aten_pow_tensor_scalar_14, [2], True);  aten_pow_tensor_scalar_14 = None
2025-03-21T20:31:43.7693341Z             aten_add_scalar_14: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_add_Scalar(aten_mean_dim_14, 9.999999747378752e-06);  aten_mean_dim_14 = None
2025-03-21T20:31:43.7693777Z             aten_rsqrt_default_14: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_rsqrt_default(aten_add_scalar_14);  aten_add_scalar_14 = None
2025-03-21T20:31:43.7694665Z             aten_mul_tensor_105: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1602, aten_rsqrt_default_14);  quantized_decomposed_dequantize_per_tensor_default_1602 = aten_rsqrt_default_14 = None
2025-03-21T20:31:43.7695519Z             aten_mul_tensor_106: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(aten_mul_tensor_105, quantized_decomposed_dequantize_per_tensor_default_64);  aten_mul_tensor_105 = quantized_decomposed_dequantize_per_tensor_default_64 = None
2025-03-21T20:31:43.7696371Z             quantized_decomposed_quantize_per_tensor_default_1144: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_106, 0.0004271493526175618, 31257, 0, 65535, torch.int32);  aten_mul_tensor_106 = None
2025-03-21T20:31:43.7696472Z             
2025-03-21T20:31:43.7696991Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.7697948Z             quantized_decomposed_dequantize_per_tensor_default_1603: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1144, 0.0004271493526175618, 31257, 0, 65535, torch.int32)
2025-03-21T20:31:43.7698864Z             quantized_decomposed_dequantize_per_tensor_default_1604: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1144, 0.0004271493526175618, 31257, 0, 65535, torch.int32)
2025-03-21T20:31:43.7700019Z             quantized_decomposed_dequantize_per_tensor_default_1605: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1144, 0.0004271493526175618, 31257, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1144 = None
2025-03-21T20:31:43.7700849Z             aten_unsqueeze_copy_default_77: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1605, -1);  quantized_decomposed_dequantize_per_tensor_default_1605 = None
2025-03-21T20:31:43.7701807Z             quantized_decomposed_quantize_per_tensor_default_1145: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_77, 0.0004271493526175618, 31257, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_77 = None
2025-03-21T20:31:43.7701896Z             
2025-03-21T20:31:43.7702314Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.7703458Z             quantized_decomposed_dequantize_per_tensor_default_1606: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1145, 0.0004271493526175618, 31257, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1145 = None
2025-03-21T20:31:43.7704272Z             aten_permute_copy_default_287: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1606, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1606 = None
2025-03-21T20:31:43.7705204Z             quantized_decomposed_quantize_per_tensor_default_1146: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_287, 0.0004271493526175618, 31257, 0, 65535, torch.int32);  aten_permute_copy_default_287 = None
2025-03-21T20:31:43.7705304Z             
2025-03-21T20:31:43.7705668Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.7706853Z             quantized_decomposed_dequantize_per_tensor_default_1607: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1146, 0.0004271493526175618, 31257, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1146 = None
2025-03-21T20:31:43.7708169Z             aten_convolution_default_49: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_1607, quantized_decomposed_dequantize_per_tensor_default_65, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_1607 = quantized_decomposed_dequantize_per_tensor_default_65 = None
2025-03-21T20:31:43.7709113Z             quantized_decomposed_quantize_per_tensor_default_1147: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_49, 0.00033543823519721627, 30157, 0, 65535, torch.int32);  aten_convolution_default_49 = None
2025-03-21T20:31:43.7709202Z             
2025-03-21T20:31:43.7709636Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.7710811Z             quantized_decomposed_dequantize_per_tensor_default_1608: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1147, 0.00033543823519721627, 30157, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1147 = None
2025-03-21T20:31:43.7711620Z             aten_permute_copy_default_288: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1608, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1608 = None
2025-03-21T20:31:43.7712583Z             quantized_decomposed_quantize_per_tensor_default_1148: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_288, 0.00033543823519721627, 30157, 0, 65535, torch.int32);  aten_permute_copy_default_288 = None
2025-03-21T20:31:43.7712688Z             
2025-03-21T20:31:43.7713225Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.7714391Z             quantized_decomposed_dequantize_per_tensor_default_1609: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1148, 0.00033543823519721627, 30157, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1148 = None
2025-03-21T20:31:43.7715146Z             aten_squeeze_copy_dims_77: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_1609, [-1]);  quantized_decomposed_dequantize_per_tensor_default_1609 = None
2025-03-21T20:31:43.7716065Z             quantized_decomposed_quantize_per_tensor_default_1149: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_77, 0.00033543823519721627, 30157, 0, 65535, torch.int32);  aten_squeeze_copy_dims_77 = None
2025-03-21T20:31:43.7716151Z             
2025-03-21T20:31:43.7716677Z              # File: /pytorch/executorch/examples/models/llama/attention.py:242 in forward, code: q = q.view(bsz, seqlen, self.n_local_heads, self.head_dim)
2025-03-21T20:31:43.7717837Z             quantized_decomposed_dequantize_per_tensor_default_1610: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1149, 0.00033543823519721627, 30157, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1149 = None
2025-03-21T20:31:43.7717941Z             
2025-03-21T20:31:43.7718478Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.7719320Z             aten_unsqueeze_copy_default_78: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1604, -1);  quantized_decomposed_dequantize_per_tensor_default_1604 = None
2025-03-21T20:31:43.7720265Z             quantized_decomposed_quantize_per_tensor_default_1150: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_78, 0.0004271493526175618, 31257, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_78 = None
2025-03-21T20:31:43.7720368Z             
2025-03-21T20:31:43.7720774Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.7721968Z             quantized_decomposed_dequantize_per_tensor_default_1611: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1150, 0.0004271493526175618, 31257, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1150 = None
2025-03-21T20:31:43.7722767Z             aten_permute_copy_default_289: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1611, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1611 = None
2025-03-21T20:31:43.7723711Z             quantized_decomposed_quantize_per_tensor_default_1151: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_289, 0.0004271493526175618, 31257, 0, 65535, torch.int32);  aten_permute_copy_default_289 = None
2025-03-21T20:31:43.7723823Z             
2025-03-21T20:31:43.7724198Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.7725346Z             quantized_decomposed_dequantize_per_tensor_default_1612: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1151, 0.0004271493526175618, 31257, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1151 = None
2025-03-21T20:31:43.7726624Z             aten_convolution_default_50: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_1612, quantized_decomposed_dequantize_per_tensor_default_66, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_1612 = quantized_decomposed_dequantize_per_tensor_default_66 = None
2025-03-21T20:31:43.7727556Z             quantized_decomposed_quantize_per_tensor_default_1152: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_50, 0.00040363334119319916, 34283, 0, 65535, torch.int32);  aten_convolution_default_50 = None
2025-03-21T20:31:43.7727658Z             
2025-03-21T20:31:43.7728078Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.7729241Z             quantized_decomposed_dequantize_per_tensor_default_1613: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1152, 0.00040363334119319916, 34283, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1152 = None
2025-03-21T20:31:43.7730101Z             aten_permute_copy_default_290: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1613, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1613 = None
2025-03-21T20:31:43.7731110Z             quantized_decomposed_quantize_per_tensor_default_1153: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_290, 0.00040363334119319916, 34283, 0, 65535, torch.int32);  aten_permute_copy_default_290 = None
2025-03-21T20:31:43.7731202Z             
2025-03-21T20:31:43.7731750Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.7733079Z             quantized_decomposed_dequantize_per_tensor_default_1614: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1153, 0.00040363334119319916, 34283, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1153 = None
2025-03-21T20:31:43.7733856Z             aten_squeeze_copy_dims_78: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_1614, [-1]);  quantized_decomposed_dequantize_per_tensor_default_1614 = None
2025-03-21T20:31:43.7734818Z             quantized_decomposed_quantize_per_tensor_default_1154: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_78, 0.00040363334119319916, 34283, 0, 65535, torch.int32);  aten_squeeze_copy_dims_78 = None
2025-03-21T20:31:43.7734919Z             
2025-03-21T20:31:43.7735441Z              # File: /pytorch/executorch/examples/models/llama/attention.py:243 in forward, code: k = k.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.7736641Z             quantized_decomposed_dequantize_per_tensor_default_1615: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1154, 0.00040363334119319916, 34283, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1154 = None
2025-03-21T20:31:43.7736730Z             
2025-03-21T20:31:43.7737259Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.7738061Z             aten_unsqueeze_copy_default_79: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1603, -1);  quantized_decomposed_dequantize_per_tensor_default_1603 = None
2025-03-21T20:31:43.7739017Z             quantized_decomposed_quantize_per_tensor_default_1155: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_79, 0.0004271493526175618, 31257, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_79 = None
2025-03-21T20:31:43.7739109Z             
2025-03-21T20:31:43.7739518Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.7740677Z             quantized_decomposed_dequantize_per_tensor_default_1616: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1155, 0.0004271493526175618, 31257, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1155 = None
2025-03-21T20:31:43.7741486Z             aten_permute_copy_default_291: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1616, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1616 = None
2025-03-21T20:31:43.7742462Z             quantized_decomposed_quantize_per_tensor_default_1156: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_291, 0.0004271493526175618, 31257, 0, 65535, torch.int32);  aten_permute_copy_default_291 = None
2025-03-21T20:31:43.7742596Z             
2025-03-21T20:31:43.7742964Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.7744112Z             quantized_decomposed_dequantize_per_tensor_default_1617: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1156, 0.0004271493526175618, 31257, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1156 = None
2025-03-21T20:31:43.7745392Z             aten_convolution_default_51: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_1617, quantized_decomposed_dequantize_per_tensor_default_67, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_1617 = quantized_decomposed_dequantize_per_tensor_default_67 = None
2025-03-21T20:31:43.7746356Z             quantized_decomposed_quantize_per_tensor_default_1157: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_51, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_convolution_default_51 = None
2025-03-21T20:31:43.7746444Z             
2025-03-21T20:31:43.7746880Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.7748025Z             quantized_decomposed_dequantize_per_tensor_default_1618: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1157, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1157 = None
2025-03-21T20:31:43.7748864Z             aten_permute_copy_default_292: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1618, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1618 = None
2025-03-21T20:31:43.7749799Z             quantized_decomposed_quantize_per_tensor_default_1158: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_292, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_permute_copy_default_292 = None
2025-03-21T20:31:43.7749901Z             
2025-03-21T20:31:43.7750436Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.7751597Z             quantized_decomposed_dequantize_per_tensor_default_1619: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1158, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1158 = None
2025-03-21T20:31:43.7752350Z             aten_squeeze_copy_dims_79: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_1619, [-1]);  quantized_decomposed_dequantize_per_tensor_default_1619 = None
2025-03-21T20:31:43.7753258Z             quantized_decomposed_quantize_per_tensor_default_1159: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_79, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_squeeze_copy_dims_79 = None
2025-03-21T20:31:43.7753346Z             
2025-03-21T20:31:43.7753886Z              # File: /pytorch/executorch/examples/models/llama/attention.py:244 in forward, code: v = v.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.7755064Z             quantized_decomposed_dequantize_per_tensor_default_1620: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1159, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1159 = None
2025-03-21T20:31:43.7755185Z             
2025-03-21T20:31:43.7755706Z              # File: /pytorch/executorch/examples/models/llama/attention.py:242 in forward, code: q = q.view(bsz, seqlen, self.n_local_heads, self.head_dim)
2025-03-21T20:31:43.7756474Z             aten_view_copy_default_126: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1610, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_1610 = None
2025-03-21T20:31:43.7757401Z             quantized_decomposed_quantize_per_tensor_default_1160: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_126, 0.00033543823519721627, 30157, 0, 65535, torch.int32);  aten_view_copy_default_126 = None
2025-03-21T20:31:43.7757494Z             
2025-03-21T20:31:43.7758468Z              # File: <eval_with_key>.50:4129 in forward, code: dequantize_per_tensor_default_1316 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1316, 0.00033543823519721627, 30157, 0, 65535, torch.int32);  quantize_per_tensor_default_1316 = None
2025-03-21T20:31:43.7759623Z             quantized_decomposed_dequantize_per_tensor_default_1621: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1160, 0.00033543823519721627, 30157, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1160 = None
2025-03-21T20:31:43.7761054Z             
2025-03-21T20:31:43.7761724Z              # File: /pytorch/executorch/examples/models/llama/attention.py:243 in forward, code: k = k.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.7763230Z             aten_view_copy_default_127: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1615, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_1615 = None
2025-03-21T20:31:43.7765210Z             quantized_decomposed_quantize_per_tensor_default_1161: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_127, 0.00040363334119319916, 34283, 0, 65535, torch.int32);  aten_view_copy_default_127 = None
2025-03-21T20:31:43.7766415Z             
2025-03-21T20:31:43.7767499Z              # File: <eval_with_key>.50:4132 in forward, code: dequantize_per_tensor_default_1317 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1317, 0.00040363334119319916, 34283, 0, 65535, torch.int32);  quantize_per_tensor_default_1317 = None
2025-03-21T20:31:43.7769813Z             quantized_decomposed_dequantize_per_tensor_default_1622: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1161, 0.00040363334119319916, 34283, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1161 = None
2025-03-21T20:31:43.7771178Z             
2025-03-21T20:31:43.7771837Z              # File: /pytorch/executorch/examples/models/llama/attention.py:244 in forward, code: v = v.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.7774267Z             aten_view_copy_default_128: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1620, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_1620 = None
2025-03-21T20:31:43.7776561Z             quantized_decomposed_quantize_per_tensor_default_1162: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_128, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_view_copy_default_128 = None
2025-03-21T20:31:43.7777722Z             
2025-03-21T20:31:43.7778536Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:346 in update, code: v_out = torch.ops.aten.index_put_(self.past_v_caches, [None, input_pos], v_val)
2025-03-21T20:31:43.7780474Z             quantized_decomposed_dequantize_per_tensor_default_1623: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1162, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1162 = None
2025-03-21T20:31:43.7781831Z             
2025-03-21T20:31:43.7782738Z              # File: <eval_with_key>.50:4137 in forward, code: quantize_per_tensor_default_1319 = torch.ops.quantized_decomposed.quantize_per_tensor.default(_to_copy_14, 0.00033543823519721627, 30157, 0, 65535, torch.int32);  _to_copy_14 = None
2025-03-21T20:31:43.7785471Z             quantized_decomposed_quantize_per_tensor_default_1163: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_1621, 0.00033543823519721627, 30157, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_1621 = None
2025-03-21T20:31:43.7786900Z             
2025-03-21T20:31:43.7787572Z              # File: /pytorch/executorch/examples/models/llama/rope.py:84 in apply_rotary_emb, code: xq_r, xq_i = xq.float().reshape(xq.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.7789405Z             quantized_decomposed_dequantize_per_tensor_default_1624: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1163, 0.00033543823519721627, 30157, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1163 = None
2025-03-21T20:31:43.7791456Z             aten_view_copy_default_129: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1624, [1, 1, 12, -1, 2]);  quantized_decomposed_dequantize_per_tensor_default_1624 = None
2025-03-21T20:31:43.7793258Z             quantized_decomposed_quantize_per_tensor_default_1164: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_129, 0.00033543823519721627, 30157, 0, 65535, torch.int32);  aten_view_copy_default_129 = None
2025-03-21T20:31:43.7795866Z             quantized_decomposed_dequantize_per_tensor_default_1625: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1164, 0.00033543823519721627, 30157, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1164 = None
2025-03-21T20:31:43.7797675Z             aten_slice_copy_tensor_28: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_1625, 4, 0, 1)
2025-03-21T20:31:43.7799085Z             aten_slice_copy_tensor_29: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_1625, 4, 1, 2);  quantized_decomposed_dequantize_per_tensor_default_1625 = None
2025-03-21T20:31:43.7800474Z             aten_squeeze_copy_dims_80: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_28, [4]);  aten_slice_copy_tensor_28 = None
2025-03-21T20:31:43.7801612Z             aten_squeeze_copy_dims_81: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_29, [4]);  aten_slice_copy_tensor_29 = None
2025-03-21T20:31:43.7803210Z             quantized_decomposed_quantize_per_tensor_default_1165: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_80, 0.00033543823519721627, 30157, 0, 65535, torch.int32);  aten_squeeze_copy_dims_80 = None
2025-03-21T20:31:43.7804316Z             
2025-03-21T20:31:43.7804931Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.7806446Z             quantized_decomposed_dequantize_per_tensor_default_1626: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1165, 0.00033543823519721627, 30157, 0, 65535, torch.int32)
2025-03-21T20:31:43.7807567Z             
2025-03-21T20:31:43.7808176Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.7810048Z             quantized_decomposed_dequantize_per_tensor_default_1627: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1165, 0.00033543823519721627, 30157, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1165 = None
2025-03-21T20:31:43.7811411Z             
2025-03-21T20:31:43.7812062Z              # File: /pytorch/executorch/examples/models/llama/rope.py:84 in apply_rotary_emb, code: xq_r, xq_i = xq.float().reshape(xq.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.7813601Z             quantized_decomposed_quantize_per_tensor_default_1166: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_81, 0.00027173387934453785, 36672, 0, 65535, torch.int32);  aten_squeeze_copy_dims_81 = None
2025-03-21T20:31:43.7814733Z             
2025-03-21T20:31:43.7815348Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.7816859Z             quantized_decomposed_dequantize_per_tensor_default_1628: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1166, 0.00027173387934453785, 36672, 0, 65535, torch.int32)
2025-03-21T20:31:43.7817982Z             
2025-03-21T20:31:43.7818583Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.7820319Z             quantized_decomposed_dequantize_per_tensor_default_1629: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1166, 0.00027173387934453785, 36672, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1166 = None
2025-03-21T20:31:43.7821671Z             
2025-03-21T20:31:43.7822558Z              # File: <eval_with_key>.50:4152 in forward, code: quantize_per_tensor_default_1323 = torch.ops.quantized_decomposed.quantize_per_tensor.default(_to_copy_15, 0.00040363334119319916, 34283, 0, 65535, torch.int32);  _to_copy_15 = None
2025-03-21T20:31:43.7824580Z             quantized_decomposed_quantize_per_tensor_default_1167: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_1622, 0.00040363334119319916, 34283, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_1622 = None
2025-03-21T20:31:43.7825928Z             
2025-03-21T20:31:43.7826592Z              # File: /pytorch/executorch/examples/models/llama/rope.py:85 in apply_rotary_emb, code: xk_r, xk_i = xk.float().reshape(xk.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.7828442Z             quantized_decomposed_dequantize_per_tensor_default_1630: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1167, 0.00040363334119319916, 34283, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1167 = None
2025-03-21T20:31:43.7830479Z             aten_view_copy_default_130: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1630, [1, 1, 12, -1, 2]);  quantized_decomposed_dequantize_per_tensor_default_1630 = None
2025-03-21T20:31:43.7832465Z             quantized_decomposed_quantize_per_tensor_default_1168: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_130, 0.00040363334119319916, 34283, 0, 65535, torch.int32);  aten_view_copy_default_130 = None
2025-03-21T20:31:43.7834726Z             quantized_decomposed_dequantize_per_tensor_default_1631: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1168, 0.00040363334119319916, 34283, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1168 = None
2025-03-21T20:31:43.7836526Z             aten_slice_copy_tensor_30: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_1631, 4, 0, 1)
2025-03-21T20:31:43.7837933Z             aten_slice_copy_tensor_31: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_1631, 4, 1, 2);  quantized_decomposed_dequantize_per_tensor_default_1631 = None
2025-03-21T20:31:43.7839374Z             aten_squeeze_copy_dims_82: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_30, [4]);  aten_slice_copy_tensor_30 = None
2025-03-21T20:31:43.7840533Z             aten_squeeze_copy_dims_83: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_31, [4]);  aten_slice_copy_tensor_31 = None
2025-03-21T20:31:43.7842076Z             quantized_decomposed_quantize_per_tensor_default_1169: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_82, 0.00040363334119319916, 34283, 0, 65535, torch.int32);  aten_squeeze_copy_dims_82 = None
2025-03-21T20:31:43.7843191Z             
2025-03-21T20:31:43.7843809Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.7845319Z             quantized_decomposed_dequantize_per_tensor_default_1632: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1169, 0.00040363334119319916, 34283, 0, 65535, torch.int32)
2025-03-21T20:31:43.7846444Z             
2025-03-21T20:31:43.7847055Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.7848798Z             quantized_decomposed_dequantize_per_tensor_default_1633: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1169, 0.00040363334119319916, 34283, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1169 = None
2025-03-21T20:31:43.7850218Z             
2025-03-21T20:31:43.7850876Z              # File: /pytorch/executorch/examples/models/llama/rope.py:85 in apply_rotary_emb, code: xk_r, xk_i = xk.float().reshape(xk.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.7852469Z             quantized_decomposed_quantize_per_tensor_default_1170: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_83, 0.00034802465233951807, 38786, 0, 65535, torch.int32);  aten_squeeze_copy_dims_83 = None
2025-03-21T20:31:43.7853608Z             
2025-03-21T20:31:43.7854222Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.7855723Z             quantized_decomposed_dequantize_per_tensor_default_1634: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1170, 0.00034802465233951807, 38786, 0, 65535, torch.int32)
2025-03-21T20:31:43.7856844Z             
2025-03-21T20:31:43.7857452Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.7859211Z             quantized_decomposed_dequantize_per_tensor_default_1635: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1170, 0.00034802465233951807, 38786, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1170 = None
2025-03-21T20:31:43.7860560Z             
2025-03-21T20:31:43.7861136Z              # File: /pytorch/executorch/examples/models/llama/rope.py:78 in reshape_for_broadcast, code: return freqs_cis.view(shape)
2025-03-21T20:31:43.7862448Z             aten_view_copy_default_131: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_155, [1, 1, 1, 32]);  quantized_decomposed_dequantize_per_tensor_default_155 = None
2025-03-21T20:31:43.7864356Z             quantized_decomposed_quantize_per_tensor_default_1171: "i32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_131, 3.051804378628731e-05, 32768, 0, 65535, torch.int32);  aten_view_copy_default_131 = None
2025-03-21T20:31:43.7865472Z             
2025-03-21T20:31:43.7866071Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.7867578Z             quantized_decomposed_dequantize_per_tensor_default_1636: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1171, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.7868700Z             
2025-03-21T20:31:43.7869307Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.7870810Z             quantized_decomposed_dequantize_per_tensor_default_1637: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1171, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.7871925Z             
2025-03-21T20:31:43.7872530Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.7874031Z             quantized_decomposed_dequantize_per_tensor_default_1638: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1171, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.7875404Z             
2025-03-21T20:31:43.7876004Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.7877791Z             quantized_decomposed_dequantize_per_tensor_default_1639: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1171, 3.051804378628731e-05, 32768, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1171 = None
2025-03-21T20:31:43.7879167Z             
2025-03-21T20:31:43.7879742Z              # File: /pytorch/executorch/examples/models/llama/rope.py:78 in reshape_for_broadcast, code: return freqs_cis.view(shape)
2025-03-21T20:31:43.7881052Z             aten_view_copy_default_132: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_167, [1, 1, 1, 32]);  quantized_decomposed_dequantize_per_tensor_default_167 = None
2025-03-21T20:31:43.7882825Z             quantized_decomposed_quantize_per_tensor_default_1172: "i32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_132, 3.051786916330457e-05, 32767, 0, 65535, torch.int32);  aten_view_copy_default_132 = None
2025-03-21T20:31:43.7883935Z             
2025-03-21T20:31:43.7884549Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.7886085Z             quantized_decomposed_dequantize_per_tensor_default_1640: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1172, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.7887193Z             
2025-03-21T20:31:43.7887795Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.7889378Z             quantized_decomposed_dequantize_per_tensor_default_1641: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1172, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.7890536Z             
2025-03-21T20:31:43.7891145Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.7892647Z             quantized_decomposed_dequantize_per_tensor_default_1642: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1172, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.7893770Z             
2025-03-21T20:31:43.7894379Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.7896098Z             quantized_decomposed_dequantize_per_tensor_default_1643: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1172, 3.051786916330457e-05, 32767, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1172 = None
2025-03-21T20:31:43.7897438Z             
2025-03-21T20:31:43.7898049Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.7899772Z             aten_mul_tensor_107: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1627, quantized_decomposed_dequantize_per_tensor_default_1639);  quantized_decomposed_dequantize_per_tensor_default_1627 = quantized_decomposed_dequantize_per_tensor_default_1639 = None
2025-03-21T20:31:43.7901867Z             quantized_decomposed_quantize_per_tensor_default_1173: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_107, 0.0003348104073666036, 30213, 0, 65535, torch.int32);  aten_mul_tensor_107 = None
2025-03-21T20:31:43.7904039Z             quantized_decomposed_dequantize_per_tensor_default_1644: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1173, 0.0003348104073666036, 30213, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1173 = None
2025-03-21T20:31:43.7906418Z             aten_mul_tensor_108: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1628, quantized_decomposed_dequantize_per_tensor_default_1642);  quantized_decomposed_dequantize_per_tensor_default_1628 = quantized_decomposed_dequantize_per_tensor_default_1642 = None
2025-03-21T20:31:43.7908511Z             quantized_decomposed_quantize_per_tensor_default_1174: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_108, 0.0001602927513886243, 36040, 0, 65535, torch.int32);  aten_mul_tensor_108 = None
2025-03-21T20:31:43.7910653Z             quantized_decomposed_dequantize_per_tensor_default_1645: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1174, 0.0001602927513886243, 36040, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1174 = None
2025-03-21T20:31:43.7913033Z             aten_sub_tensor_14: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_sub_Tensor(quantized_decomposed_dequantize_per_tensor_default_1644, quantized_decomposed_dequantize_per_tensor_default_1645);  quantized_decomposed_dequantize_per_tensor_default_1644 = quantized_decomposed_dequantize_per_tensor_default_1645 = None
2025-03-21T20:31:43.7915140Z             quantized_decomposed_quantize_per_tensor_default_1175: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_sub_tensor_14, 0.0003344771103002131, 30259, 0, 65535, torch.int32);  aten_sub_tensor_14 = None
2025-03-21T20:31:43.7916194Z             
2025-03-21T20:31:43.7917266Z              # File: <eval_with_key>.50:4186 in forward, code: dequantize_per_tensor_default_1331 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1331, 0.0003344771103002131, 30259, 0, 65535, torch.int32);  quantize_per_tensor_default_1331 = None
2025-03-21T20:31:43.7919456Z             quantized_decomposed_dequantize_per_tensor_default_1646: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1175, 0.0003344771103002131, 30259, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1175 = None
2025-03-21T20:31:43.7920801Z             
2025-03-21T20:31:43.7921410Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.7923135Z             aten_mul_tensor_109: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1626, quantized_decomposed_dequantize_per_tensor_default_1643);  quantized_decomposed_dequantize_per_tensor_default_1626 = quantized_decomposed_dequantize_per_tensor_default_1643 = None
2025-03-21T20:31:43.7925239Z             quantized_decomposed_quantize_per_tensor_default_1176: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_109, 0.00014775632007513195, 30678, 0, 65535, torch.int32);  aten_mul_tensor_109 = None
2025-03-21T20:31:43.7927379Z             quantized_decomposed_dequantize_per_tensor_default_1647: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1176, 0.00014775632007513195, 30678, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1176 = None
2025-03-21T20:31:43.7929850Z             aten_mul_tensor_110: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1629, quantized_decomposed_dequantize_per_tensor_default_1638);  quantized_decomposed_dequantize_per_tensor_default_1629 = quantized_decomposed_dequantize_per_tensor_default_1638 = None
2025-03-21T20:31:43.7931942Z             quantized_decomposed_quantize_per_tensor_default_1177: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_110, 0.000265473616309464, 35993, 0, 65535, torch.int32);  aten_mul_tensor_110 = None
2025-03-21T20:31:43.7934233Z             quantized_decomposed_dequantize_per_tensor_default_1648: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1177, 0.000265473616309464, 35993, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1177 = None
2025-03-21T20:31:43.7936690Z             aten_add_tensor_35: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_1647, quantized_decomposed_dequantize_per_tensor_default_1648);  quantized_decomposed_dequantize_per_tensor_default_1647 = quantized_decomposed_dequantize_per_tensor_default_1648 = None
2025-03-21T20:31:43.7938777Z             quantized_decomposed_quantize_per_tensor_default_1178: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_35, 0.0002655599091667682, 35943, 0, 65535, torch.int32);  aten_add_tensor_35 = None
2025-03-21T20:31:43.7939830Z             
2025-03-21T20:31:43.7940936Z              # File: <eval_with_key>.50:4195 in forward, code: dequantize_per_tensor_default_1334 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1334, 0.0002655599091667682, 35943, 0, 65535, torch.int32);  quantize_per_tensor_default_1334 = None
2025-03-21T20:31:43.7943134Z             quantized_decomposed_dequantize_per_tensor_default_1649: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1178, 0.0002655599091667682, 35943, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1178 = None
2025-03-21T20:31:43.7944475Z             
2025-03-21T20:31:43.7945088Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.7946807Z             aten_mul_tensor_111: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1633, quantized_decomposed_dequantize_per_tensor_default_1637);  quantized_decomposed_dequantize_per_tensor_default_1633 = quantized_decomposed_dequantize_per_tensor_default_1637 = None
2025-03-21T20:31:43.7948916Z             quantized_decomposed_quantize_per_tensor_default_1179: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_111, 0.0004010801203548908, 34212, 0, 65535, torch.int32);  aten_mul_tensor_111 = None
2025-03-21T20:31:43.7951031Z             quantized_decomposed_dequantize_per_tensor_default_1650: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1179, 0.0004010801203548908, 34212, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1179 = None
2025-03-21T20:31:43.7953512Z             aten_mul_tensor_112: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1634, quantized_decomposed_dequantize_per_tensor_default_1640);  quantized_decomposed_dequantize_per_tensor_default_1634 = quantized_decomposed_dequantize_per_tensor_default_1640 = None
2025-03-21T20:31:43.7955656Z             quantized_decomposed_quantize_per_tensor_default_1180: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_112, 0.0001895799214253202, 36365, 0, 65535, torch.int32);  aten_mul_tensor_112 = None
2025-03-21T20:31:43.7957764Z             quantized_decomposed_dequantize_per_tensor_default_1651: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1180, 0.0001895799214253202, 36365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1180 = None
2025-03-21T20:31:43.7960139Z             aten_sub_tensor_15: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_sub_Tensor(quantized_decomposed_dequantize_per_tensor_default_1650, quantized_decomposed_dequantize_per_tensor_default_1651);  quantized_decomposed_dequantize_per_tensor_default_1650 = quantized_decomposed_dequantize_per_tensor_default_1651 = None
2025-03-21T20:31:43.7962255Z             quantized_decomposed_quantize_per_tensor_default_1181: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_sub_tensor_15, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_sub_tensor_15 = None
2025-03-21T20:31:43.7963327Z             
2025-03-21T20:31:43.7964395Z              # File: <eval_with_key>.50:4204 in forward, code: dequantize_per_tensor_default_1337 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1337, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantize_per_tensor_default_1337 = None
2025-03-21T20:31:43.7966605Z             quantized_decomposed_dequantize_per_tensor_default_1652: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1181, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1181 = None
2025-03-21T20:31:43.7967984Z             
2025-03-21T20:31:43.7968601Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.7970390Z             aten_mul_tensor_113: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1632, quantized_decomposed_dequantize_per_tensor_default_1641);  quantized_decomposed_dequantize_per_tensor_default_1632 = quantized_decomposed_dequantize_per_tensor_default_1641 = None
2025-03-21T20:31:43.7972502Z             quantized_decomposed_quantize_per_tensor_default_1182: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_113, 0.00017923355335369706, 34002, 0, 65535, torch.int32);  aten_mul_tensor_113 = None
2025-03-21T20:31:43.7974639Z             quantized_decomposed_dequantize_per_tensor_default_1653: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1182, 0.00017923355335369706, 34002, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1182 = None
2025-03-21T20:31:43.7977157Z             aten_mul_tensor_114: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1635, quantized_decomposed_dequantize_per_tensor_default_1636);  quantized_decomposed_dequantize_per_tensor_default_1635 = quantized_decomposed_dequantize_per_tensor_default_1636 = None
2025-03-21T20:31:43.7979264Z             quantized_decomposed_quantize_per_tensor_default_1183: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_114, 0.00034465600037947297, 38891, 0, 65535, torch.int32);  aten_mul_tensor_114 = None
2025-03-21T20:31:43.7981450Z             quantized_decomposed_dequantize_per_tensor_default_1654: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1183, 0.00034465600037947297, 38891, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1183 = None
2025-03-21T20:31:43.7983832Z             aten_add_tensor_36: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_1653, quantized_decomposed_dequantize_per_tensor_default_1654);  quantized_decomposed_dequantize_per_tensor_default_1653 = quantized_decomposed_dequantize_per_tensor_default_1654 = None
2025-03-21T20:31:43.7985914Z             quantized_decomposed_quantize_per_tensor_default_1184: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_36, 0.0003462613676674664, 38962, 0, 65535, torch.int32);  aten_add_tensor_36 = None
2025-03-21T20:31:43.7986974Z             
2025-03-21T20:31:43.7988077Z              # File: <eval_with_key>.50:4213 in forward, code: dequantize_per_tensor_default_1340 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1340, 0.0003462613676674664, 38962, 0, 65535, torch.int32);  quantize_per_tensor_default_1340 = None
2025-03-21T20:31:43.7990283Z             quantized_decomposed_dequantize_per_tensor_default_1655: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1184, 0.0003462613676674664, 38962, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1184 = None
2025-03-21T20:31:43.7991658Z             
2025-03-21T20:31:43.7992312Z              # File: /pytorch/executorch/examples/models/llama/rope.py:95 in apply_rotary_emb, code: xq_out = torch.stack([xq_out_r, xq_out_i], dim=-1).flatten(3)
2025-03-21T20:31:43.7993752Z             aten_unsqueeze_copy_default_80: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1646, 4);  quantized_decomposed_dequantize_per_tensor_default_1646 = None
2025-03-21T20:31:43.7995450Z             aten_unsqueeze_copy_default_81: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1649, 4);  quantized_decomposed_dequantize_per_tensor_default_1649 = None
2025-03-21T20:31:43.7997100Z             aten_cat_default_28: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_cat_default([aten_unsqueeze_copy_default_80, aten_unsqueeze_copy_default_81], -1);  aten_unsqueeze_copy_default_80 = aten_unsqueeze_copy_default_81 = None
2025-03-21T20:31:43.7998794Z             quantized_decomposed_quantize_per_tensor_default_1185: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_28, 0.0003344771103002131, 30259, 0, 65535, torch.int32);  aten_cat_default_28 = None
2025-03-21T20:31:43.8000910Z             quantized_decomposed_dequantize_per_tensor_default_1656: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1185, 0.0003344771103002131, 30259, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1185 = None
2025-03-21T20:31:43.8002928Z             aten_view_copy_default_133: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1656, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_1656 = None
2025-03-21T20:31:43.8004736Z             quantized_decomposed_quantize_per_tensor_default_1186: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_133, 0.0003344771103002131, 30259, 0, 65535, torch.int32);  aten_view_copy_default_133 = None
2025-03-21T20:31:43.8005870Z             
2025-03-21T20:31:43.8006944Z              # File: <eval_with_key>.50:4219 in forward, code: dequantize_per_tensor_default_1342 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1342, 0.0003344771103002131, 30259, 0, 65535, torch.int32);  quantize_per_tensor_default_1342 = None
2025-03-21T20:31:43.8009144Z             quantized_decomposed_dequantize_per_tensor_default_1657: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1186, 0.0003344771103002131, 30259, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1186 = None
2025-03-21T20:31:43.8010588Z             
2025-03-21T20:31:43.8011251Z              # File: /pytorch/executorch/examples/models/llama/rope.py:96 in apply_rotary_emb, code: xk_out = torch.stack([xk_out_r, xk_out_i], dim=-1).flatten(3)
2025-03-21T20:31:43.8012725Z             aten_unsqueeze_copy_default_82: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1652, 4);  quantized_decomposed_dequantize_per_tensor_default_1652 = None
2025-03-21T20:31:43.8014432Z             aten_unsqueeze_copy_default_83: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1655, 4);  quantized_decomposed_dequantize_per_tensor_default_1655 = None
2025-03-21T20:31:43.8016076Z             aten_cat_default_29: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_cat_default([aten_unsqueeze_copy_default_82, aten_unsqueeze_copy_default_83], -1);  aten_unsqueeze_copy_default_82 = aten_unsqueeze_copy_default_83 = None
2025-03-21T20:31:43.8017821Z             quantized_decomposed_quantize_per_tensor_default_1187: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_29, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_cat_default_29 = None
2025-03-21T20:31:43.8019967Z             quantized_decomposed_dequantize_per_tensor_default_1658: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1187, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1187 = None
2025-03-21T20:31:43.8021999Z             aten_view_copy_default_134: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1658, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_1658 = None
2025-03-21T20:31:43.8023791Z             quantized_decomposed_quantize_per_tensor_default_1188: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_134, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_view_copy_default_134 = None
2025-03-21T20:31:43.8024903Z             
2025-03-21T20:31:43.8025964Z              # File: <eval_with_key>.50:4225 in forward, code: dequantize_per_tensor_default_1344 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1344, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantize_per_tensor_default_1344 = None
2025-03-21T20:31:43.8028173Z             quantized_decomposed_dequantize_per_tensor_default_1659: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1188, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1188 = None
2025-03-21T20:31:43.8029522Z             
2025-03-21T20:31:43.8030434Z              # File: <eval_with_key>.50:4227 in forward, code: quantize_per_tensor_default_1345 = torch.ops.quantized_decomposed.quantize_per_tensor.default(type_as_14, 0.0003344771103002131, 30259, 0, 65535, torch.int32);  type_as_14 = None
2025-03-21T20:31:43.8032670Z             quantized_decomposed_quantize_per_tensor_default_1189: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_1657, 0.0003344771103002131, 30259, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_1657 = None
2025-03-21T20:31:43.8034032Z             
2025-03-21T20:31:43.8034702Z              # File: /pytorch/executorch/examples/models/llama/attention.py:249 in forward, code: q = q.transpose(1, 2)  # (bs, n_local_heads, seqlen, head_dim)
2025-03-21T20:31:43.8036499Z             quantized_decomposed_dequantize_per_tensor_default_1660: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1189, 0.0003344771103002131, 30259, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1189 = None
2025-03-21T20:31:43.8037857Z             
2025-03-21T20:31:43.8038813Z              # File: <eval_with_key>.50:4230 in forward, code: quantize_per_tensor_default_1346 = torch.ops.quantized_decomposed.quantize_per_tensor.default(type_as_15, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  type_as_15 = None
2025-03-21T20:31:43.8040836Z             quantized_decomposed_quantize_per_tensor_default_1190: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_1659, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_1659 = None
2025-03-21T20:31:43.8042220Z             
2025-03-21T20:31:43.8043019Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:345 in update, code: k_out = torch.ops.aten.index_put_(self.past_k_caches, [None, input_pos], k_val)
2025-03-21T20:31:43.8044955Z             quantized_decomposed_dequantize_per_tensor_default_1661: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1190, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1190 = None
2025-03-21T20:31:43.8046299Z             
2025-03-21T20:31:43.8046955Z              # File: /pytorch/executorch/examples/models/llama/attention.py:249 in forward, code: q = q.transpose(1, 2)  # (bs, n_local_heads, seqlen, head_dim)
2025-03-21T20:31:43.8048386Z             aten_permute_copy_default_293: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1660, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1660 = None
2025-03-21T20:31:43.8050289Z             quantized_decomposed_quantize_per_tensor_default_1191: "i32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_293, 0.0003344771103002131, 30259, 0, 65535, torch.int32);  aten_permute_copy_default_293 = None
2025-03-21T20:31:43.8051431Z             
2025-03-21T20:31:43.8052141Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.8053982Z             quantized_decomposed_dequantize_per_tensor_default_1662: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1191, 0.0003344771103002131, 30259, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1191 = None
2025-03-21T20:31:43.8055329Z             
2025-03-21T20:31:43.8056171Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:345 in update, code: k_out = torch.ops.aten.index_put_(self.past_k_caches, [None, input_pos], k_val)
2025-03-21T20:31:43.8058255Z             aten_index_put_default_14: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_index_put_default(quantized_decomposed_dequantize_per_tensor_default_134, [None, attn_options_input_pos], quantized_decomposed_dequantize_per_tensor_default_1661);  quantized_decomposed_dequantize_per_tensor_default_134 = quantized_decomposed_dequantize_per_tensor_default_1661 = None
2025-03-21T20:31:43.8060578Z             quantized_decomposed_quantize_per_tensor_default_1192: "i32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_put_default_14, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_index_put_default_14 = None
2025-03-21T20:31:43.8061680Z             
2025-03-21T20:31:43.8062613Z              # File: <eval_with_key>.50:4237 in forward, code: dequantize_per_tensor_default_1348 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1348, 0.00039715005550533533, 34049, 0, 65535, torch.int32)
2025-03-21T20:31:43.8064476Z             quantized_decomposed_dequantize_per_tensor_default_1663: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1192, 0.00039715005550533533, 34049, 0, 65535, torch.int32)
2025-03-21T20:31:43.8065601Z             
2025-03-21T20:31:43.8066370Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.8068145Z             quantized_decomposed_dequantize_per_tensor_default_1664: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1192, 0.00039715005550533533, 34049, 0, 65535, torch.int32)
2025-03-21T20:31:43.8070147Z             quantized_decomposed_dequantize_per_tensor_default_1665: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1192, 0.00039715005550533533, 34049, 0, 65535, torch.int32)
2025-03-21T20:31:43.8072103Z             quantized_decomposed_dequantize_per_tensor_default_1666: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1192, 0.00039715005550533533, 34049, 0, 65535, torch.int32)
2025-03-21T20:31:43.8074056Z             quantized_decomposed_dequantize_per_tensor_default_1667: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1192, 0.00039715005550533533, 34049, 0, 65535, torch.int32)
2025-03-21T20:31:43.8076021Z             quantized_decomposed_dequantize_per_tensor_default_1668: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1192, 0.00039715005550533533, 34049, 0, 65535, torch.int32)
2025-03-21T20:31:43.8078000Z             quantized_decomposed_dequantize_per_tensor_default_1669: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1192, 0.00039715005550533533, 34049, 0, 65535, torch.int32)
2025-03-21T20:31:43.8080188Z             quantized_decomposed_dequantize_per_tensor_default_1670: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1192, 0.00039715005550533533, 34049, 0, 65535, torch.int32)
2025-03-21T20:31:43.8082198Z             quantized_decomposed_dequantize_per_tensor_default_1671: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1192, 0.00039715005550533533, 34049, 0, 65535, torch.int32)
2025-03-21T20:31:43.8084191Z             quantized_decomposed_dequantize_per_tensor_default_1672: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1192, 0.00039715005550533533, 34049, 0, 65535, torch.int32)
2025-03-21T20:31:43.8086157Z             quantized_decomposed_dequantize_per_tensor_default_1673: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1192, 0.00039715005550533533, 34049, 0, 65535, torch.int32)
2025-03-21T20:31:43.8088119Z             quantized_decomposed_dequantize_per_tensor_default_1674: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1192, 0.00039715005550533533, 34049, 0, 65535, torch.int32)
2025-03-21T20:31:43.8090446Z             quantized_decomposed_dequantize_per_tensor_default_1675: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1192, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1192 = None
2025-03-21T20:31:43.8091813Z             
2025-03-21T20:31:43.8092607Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:346 in update, code: v_out = torch.ops.aten.index_put_(self.past_v_caches, [None, input_pos], v_val)
2025-03-21T20:31:43.8094704Z             aten_index_put_default_15: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_index_put_default(quantized_decomposed_dequantize_per_tensor_default_135, [None, attn_options_input_pos], quantized_decomposed_dequantize_per_tensor_default_1623);  quantized_decomposed_dequantize_per_tensor_default_135 = quantized_decomposed_dequantize_per_tensor_default_1623 = None
2025-03-21T20:31:43.8097010Z             quantized_decomposed_quantize_per_tensor_default_1193: "i32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_put_default_15, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_index_put_default_15 = None
2025-03-21T20:31:43.8098121Z             
2025-03-21T20:31:43.8099047Z              # File: <eval_with_key>.50:4252 in forward, code: dequantize_per_tensor_default_1349 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1349, 0.0001613850035937503, 35011, 0, 65535, torch.int32)
2025-03-21T20:31:43.8100880Z             quantized_decomposed_dequantize_per_tensor_default_1676: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1193, 0.0001613850035937503, 35011, 0, 65535, torch.int32)
2025-03-21T20:31:43.8102009Z             
2025-03-21T20:31:43.8102785Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.8104460Z             quantized_decomposed_dequantize_per_tensor_default_1677: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1193, 0.0001613850035937503, 35011, 0, 65535, torch.int32)
2025-03-21T20:31:43.8106423Z             quantized_decomposed_dequantize_per_tensor_default_1678: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1193, 0.0001613850035937503, 35011, 0, 65535, torch.int32)
2025-03-21T20:31:43.8108411Z             quantized_decomposed_dequantize_per_tensor_default_1679: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1193, 0.0001613850035937503, 35011, 0, 65535, torch.int32)
2025-03-21T20:31:43.8110386Z             quantized_decomposed_dequantize_per_tensor_default_1680: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1193, 0.0001613850035937503, 35011, 0, 65535, torch.int32)
2025-03-21T20:31:43.8112345Z             quantized_decomposed_dequantize_per_tensor_default_1681: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1193, 0.0001613850035937503, 35011, 0, 65535, torch.int32)
2025-03-21T20:31:43.8114303Z             quantized_decomposed_dequantize_per_tensor_default_1682: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1193, 0.0001613850035937503, 35011, 0, 65535, torch.int32)
2025-03-21T20:31:43.8116282Z             quantized_decomposed_dequantize_per_tensor_default_1683: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1193, 0.0001613850035937503, 35011, 0, 65535, torch.int32)
2025-03-21T20:31:43.8118242Z             quantized_decomposed_dequantize_per_tensor_default_1684: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1193, 0.0001613850035937503, 35011, 0, 65535, torch.int32)
2025-03-21T20:31:43.8120226Z             quantized_decomposed_dequantize_per_tensor_default_1685: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1193, 0.0001613850035937503, 35011, 0, 65535, torch.int32)
2025-03-21T20:31:43.8122184Z             quantized_decomposed_dequantize_per_tensor_default_1686: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1193, 0.0001613850035937503, 35011, 0, 65535, torch.int32)
2025-03-21T20:31:43.8124143Z             quantized_decomposed_dequantize_per_tensor_default_1687: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1193, 0.0001613850035937503, 35011, 0, 65535, torch.int32)
2025-03-21T20:31:43.8126332Z             quantized_decomposed_dequantize_per_tensor_default_1688: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1193, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1193 = None
2025-03-21T20:31:43.8127699Z             
2025-03-21T20:31:43.8128456Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.8130061Z             aten_permute_copy_default_294: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1675, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1675 = None
2025-03-21T20:31:43.8131924Z             quantized_decomposed_quantize_per_tensor_default_1194: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_294, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_permute_copy_default_294 = None
2025-03-21T20:31:43.8134387Z             quantized_decomposed_dequantize_per_tensor_default_1689: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1194, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1194 = None
2025-03-21T20:31:43.8136433Z             aten_select_copy_int_336: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1689, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1689 = None
2025-03-21T20:31:43.8138189Z             quantized_decomposed_quantize_per_tensor_default_1195: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_336, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_select_copy_int_336 = None
2025-03-21T20:31:43.8140388Z             quantized_decomposed_dequantize_per_tensor_default_1690: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1195, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1195 = None
2025-03-21T20:31:43.8142389Z             aten_select_copy_int_337: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1690, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1690 = None
2025-03-21T20:31:43.8144133Z             quantized_decomposed_quantize_per_tensor_default_1196: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_337, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_select_copy_int_337 = None
2025-03-21T20:31:43.8145260Z             
2025-03-21T20:31:43.8146339Z              # File: <eval_with_key>.50:4273 in forward, code: dequantize_per_tensor_default_1352 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1352, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantize_per_tensor_default_1352 = None
2025-03-21T20:31:43.8148547Z             quantized_decomposed_dequantize_per_tensor_default_1691: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1196, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1196 = None
2025-03-21T20:31:43.8149894Z             
2025-03-21T20:31:43.8150671Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.8152226Z             aten_permute_copy_default_295: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1674, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1674 = None
2025-03-21T20:31:43.8154090Z             quantized_decomposed_quantize_per_tensor_default_1197: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_295, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_permute_copy_default_295 = None
2025-03-21T20:31:43.8156308Z             quantized_decomposed_dequantize_per_tensor_default_1692: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1197, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1197 = None
2025-03-21T20:31:43.8158348Z             aten_select_copy_int_338: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1692, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1692 = None
2025-03-21T20:31:43.8160130Z             quantized_decomposed_quantize_per_tensor_default_1198: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_338, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_select_copy_int_338 = None
2025-03-21T20:31:43.8162297Z             quantized_decomposed_dequantize_per_tensor_default_1693: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1198, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1198 = None
2025-03-21T20:31:43.8164302Z             aten_select_copy_int_339: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1693, 0, 1);  quantized_decomposed_dequantize_per_tensor_default_1693 = None
2025-03-21T20:31:43.8166076Z             quantized_decomposed_quantize_per_tensor_default_1199: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_339, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_select_copy_int_339 = None
2025-03-21T20:31:43.8167176Z             
2025-03-21T20:31:43.8168239Z              # File: <eval_with_key>.50:4282 in forward, code: dequantize_per_tensor_default_1355 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1355, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantize_per_tensor_default_1355 = None
2025-03-21T20:31:43.8170518Z             quantized_decomposed_dequantize_per_tensor_default_1694: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1199, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1199 = None
2025-03-21T20:31:43.8171906Z             
2025-03-21T20:31:43.8172686Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.8174238Z             aten_permute_copy_default_296: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1673, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1673 = None
2025-03-21T20:31:43.8176092Z             quantized_decomposed_quantize_per_tensor_default_1200: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_296, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_permute_copy_default_296 = None
2025-03-21T20:31:43.8178309Z             quantized_decomposed_dequantize_per_tensor_default_1695: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1200, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1200 = None
2025-03-21T20:31:43.8180454Z             aten_select_copy_int_340: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1695, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1695 = None
2025-03-21T20:31:43.8182215Z             quantized_decomposed_quantize_per_tensor_default_1201: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_340, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_select_copy_int_340 = None
2025-03-21T20:31:43.8184427Z             quantized_decomposed_dequantize_per_tensor_default_1696: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1201, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1201 = None
2025-03-21T20:31:43.8186449Z             aten_select_copy_int_341: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1696, 0, 2);  quantized_decomposed_dequantize_per_tensor_default_1696 = None
2025-03-21T20:31:43.8188195Z             quantized_decomposed_quantize_per_tensor_default_1202: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_341, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_select_copy_int_341 = None
2025-03-21T20:31:43.8189291Z             
2025-03-21T20:31:43.8190366Z              # File: <eval_with_key>.50:4291 in forward, code: dequantize_per_tensor_default_1358 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1358, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantize_per_tensor_default_1358 = None
2025-03-21T20:31:43.8192606Z             quantized_decomposed_dequantize_per_tensor_default_1697: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1202, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1202 = None
2025-03-21T20:31:43.8193953Z             
2025-03-21T20:31:43.8194723Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.8196258Z             aten_permute_copy_default_297: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1672, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1672 = None
2025-03-21T20:31:43.8198142Z             quantized_decomposed_quantize_per_tensor_default_1203: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_297, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_permute_copy_default_297 = None
2025-03-21T20:31:43.8200350Z             quantized_decomposed_dequantize_per_tensor_default_1698: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1203, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1203 = None
2025-03-21T20:31:43.8202359Z             aten_select_copy_int_342: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1698, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1698 = None
2025-03-21T20:31:43.8204120Z             quantized_decomposed_quantize_per_tensor_default_1204: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_342, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_select_copy_int_342 = None
2025-03-21T20:31:43.8206283Z             quantized_decomposed_dequantize_per_tensor_default_1699: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1204, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1204 = None
2025-03-21T20:31:43.8208279Z             aten_select_copy_int_343: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1699, 0, 3);  quantized_decomposed_dequantize_per_tensor_default_1699 = None
2025-03-21T20:31:43.8210136Z             quantized_decomposed_quantize_per_tensor_default_1205: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_343, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_select_copy_int_343 = None
2025-03-21T20:31:43.8211266Z             
2025-03-21T20:31:43.8212349Z              # File: <eval_with_key>.50:4300 in forward, code: dequantize_per_tensor_default_1361 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1361, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantize_per_tensor_default_1361 = None
2025-03-21T20:31:43.8214553Z             quantized_decomposed_dequantize_per_tensor_default_1700: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1205, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1205 = None
2025-03-21T20:31:43.8215912Z             
2025-03-21T20:31:43.8216687Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.8218262Z             aten_permute_copy_default_298: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1671, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1671 = None
2025-03-21T20:31:43.8220118Z             quantized_decomposed_quantize_per_tensor_default_1206: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_298, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_permute_copy_default_298 = None
2025-03-21T20:31:43.8222366Z             quantized_decomposed_dequantize_per_tensor_default_1701: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1206, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1206 = None
2025-03-21T20:31:43.8224370Z             aten_select_copy_int_344: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1701, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1701 = None
2025-03-21T20:31:43.8226122Z             quantized_decomposed_quantize_per_tensor_default_1207: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_344, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_select_copy_int_344 = None
2025-03-21T20:31:43.8228287Z             quantized_decomposed_dequantize_per_tensor_default_1702: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1207, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1207 = None
2025-03-21T20:31:43.8230294Z             aten_select_copy_int_345: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1702, 0, 4);  quantized_decomposed_dequantize_per_tensor_default_1702 = None
2025-03-21T20:31:43.8232040Z             quantized_decomposed_quantize_per_tensor_default_1208: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_345, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_select_copy_int_345 = None
2025-03-21T20:31:43.8233333Z             
2025-03-21T20:31:43.8234401Z              # File: <eval_with_key>.50:4309 in forward, code: dequantize_per_tensor_default_1364 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1364, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantize_per_tensor_default_1364 = None
2025-03-21T20:31:43.8236714Z             quantized_decomposed_dequantize_per_tensor_default_1703: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1208, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1208 = None
2025-03-21T20:31:43.8238072Z             
2025-03-21T20:31:43.8238848Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.8240395Z             aten_permute_copy_default_299: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1670, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1670 = None
2025-03-21T20:31:43.8242263Z             quantized_decomposed_quantize_per_tensor_default_1209: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_299, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_permute_copy_default_299 = None
2025-03-21T20:31:43.8244511Z             quantized_decomposed_dequantize_per_tensor_default_1704: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1209, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1209 = None
2025-03-21T20:31:43.8246520Z             aten_select_copy_int_346: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1704, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1704 = None
2025-03-21T20:31:43.8248309Z             quantized_decomposed_quantize_per_tensor_default_1210: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_346, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_select_copy_int_346 = None
2025-03-21T20:31:43.8250672Z             quantized_decomposed_dequantize_per_tensor_default_1705: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1210, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1210 = None
2025-03-21T20:31:43.8252686Z             aten_select_copy_int_347: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1705, 0, 5);  quantized_decomposed_dequantize_per_tensor_default_1705 = None
2025-03-21T20:31:43.8254447Z             quantized_decomposed_quantize_per_tensor_default_1211: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_347, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_select_copy_int_347 = None
2025-03-21T20:31:43.8255548Z             
2025-03-21T20:31:43.8256633Z              # File: <eval_with_key>.50:4318 in forward, code: dequantize_per_tensor_default_1367 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1367, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantize_per_tensor_default_1367 = None
2025-03-21T20:31:43.8258851Z             quantized_decomposed_dequantize_per_tensor_default_1706: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1211, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1211 = None
2025-03-21T20:31:43.8260208Z             
2025-03-21T20:31:43.8261021Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.8262590Z             aten_permute_copy_default_300: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1669, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1669 = None
2025-03-21T20:31:43.8264450Z             quantized_decomposed_quantize_per_tensor_default_1212: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_300, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_permute_copy_default_300 = None
2025-03-21T20:31:43.8266661Z             quantized_decomposed_dequantize_per_tensor_default_1707: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1212, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1212 = None
2025-03-21T20:31:43.8268805Z             aten_select_copy_int_348: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1707, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1707 = None
2025-03-21T20:31:43.8270598Z             quantized_decomposed_quantize_per_tensor_default_1213: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_348, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_select_copy_int_348 = None
2025-03-21T20:31:43.8272826Z             quantized_decomposed_dequantize_per_tensor_default_1708: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1213, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1213 = None
2025-03-21T20:31:43.8274873Z             aten_select_copy_int_349: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1708, 0, 6);  quantized_decomposed_dequantize_per_tensor_default_1708 = None
2025-03-21T20:31:43.8276620Z             quantized_decomposed_quantize_per_tensor_default_1214: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_349, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_select_copy_int_349 = None
2025-03-21T20:31:43.8277721Z             
2025-03-21T20:31:43.8278794Z              # File: <eval_with_key>.50:4327 in forward, code: dequantize_per_tensor_default_1370 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1370, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantize_per_tensor_default_1370 = None
2025-03-21T20:31:43.8281006Z             quantized_decomposed_dequantize_per_tensor_default_1709: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1214, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1214 = None
2025-03-21T20:31:43.8282624Z             
2025-03-21T20:31:43.8283400Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.8284953Z             aten_permute_copy_default_301: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1668, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1668 = None
2025-03-21T20:31:43.8286853Z             quantized_decomposed_quantize_per_tensor_default_1215: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_301, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_permute_copy_default_301 = None
2025-03-21T20:31:43.8289093Z             quantized_decomposed_dequantize_per_tensor_default_1710: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1215, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1215 = None
2025-03-21T20:31:43.8291194Z             aten_select_copy_int_350: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1710, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1710 = None
2025-03-21T20:31:43.8292948Z             quantized_decomposed_quantize_per_tensor_default_1216: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_350, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_select_copy_int_350 = None
2025-03-21T20:31:43.8295148Z             quantized_decomposed_dequantize_per_tensor_default_1711: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1216, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1216 = None
2025-03-21T20:31:43.8297150Z             aten_select_copy_int_351: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1711, 0, 7);  quantized_decomposed_dequantize_per_tensor_default_1711 = None
2025-03-21T20:31:43.8298889Z             quantized_decomposed_quantize_per_tensor_default_1217: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_351, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_select_copy_int_351 = None
2025-03-21T20:31:43.8300019Z             
2025-03-21T20:31:43.8301082Z              # File: <eval_with_key>.50:4336 in forward, code: dequantize_per_tensor_default_1373 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1373, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantize_per_tensor_default_1373 = None
2025-03-21T20:31:43.8303293Z             quantized_decomposed_dequantize_per_tensor_default_1712: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1217, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1217 = None
2025-03-21T20:31:43.8304642Z             
2025-03-21T20:31:43.8305419Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.8306977Z             aten_permute_copy_default_302: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1667, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1667 = None
2025-03-21T20:31:43.8308831Z             quantized_decomposed_quantize_per_tensor_default_1218: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_302, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_permute_copy_default_302 = None
2025-03-21T20:31:43.8311037Z             quantized_decomposed_dequantize_per_tensor_default_1713: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1218, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1218 = None
2025-03-21T20:31:43.8313065Z             aten_select_copy_int_352: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1713, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1713 = None
2025-03-21T20:31:43.8314842Z             quantized_decomposed_quantize_per_tensor_default_1219: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_352, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_select_copy_int_352 = None
2025-03-21T20:31:43.8317007Z             quantized_decomposed_dequantize_per_tensor_default_1714: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1219, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1219 = None
2025-03-21T20:31:43.8319011Z             aten_select_copy_int_353: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1714, 0, 8);  quantized_decomposed_dequantize_per_tensor_default_1714 = None
2025-03-21T20:31:43.8320804Z             quantized_decomposed_quantize_per_tensor_default_1220: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_353, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_select_copy_int_353 = None
2025-03-21T20:31:43.8321901Z             
2025-03-21T20:31:43.8322981Z              # File: <eval_with_key>.50:4345 in forward, code: dequantize_per_tensor_default_1376 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1376, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantize_per_tensor_default_1376 = None
2025-03-21T20:31:43.8325326Z             quantized_decomposed_dequantize_per_tensor_default_1715: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1220, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1220 = None
2025-03-21T20:31:43.8326693Z             
2025-03-21T20:31:43.8327472Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.8329031Z             aten_permute_copy_default_303: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1666, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1666 = None
2025-03-21T20:31:43.8330967Z             quantized_decomposed_quantize_per_tensor_default_1221: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_303, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_permute_copy_default_303 = None
2025-03-21T20:31:43.8333350Z             quantized_decomposed_dequantize_per_tensor_default_1716: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1221, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1221 = None
2025-03-21T20:31:43.8335377Z             aten_select_copy_int_354: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1716, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1716 = None
2025-03-21T20:31:43.8337120Z             quantized_decomposed_quantize_per_tensor_default_1222: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_354, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_select_copy_int_354 = None
2025-03-21T20:31:43.8339401Z             quantized_decomposed_dequantize_per_tensor_default_1717: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1222, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1222 = None
2025-03-21T20:31:43.8341412Z             aten_select_copy_int_355: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1717, 0, 9);  quantized_decomposed_dequantize_per_tensor_default_1717 = None
2025-03-21T20:31:43.8343159Z             quantized_decomposed_quantize_per_tensor_default_1223: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_355, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_select_copy_int_355 = None
2025-03-21T20:31:43.8344259Z             
2025-03-21T20:31:43.8345368Z              # File: <eval_with_key>.50:4354 in forward, code: dequantize_per_tensor_default_1379 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1379, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantize_per_tensor_default_1379 = None
2025-03-21T20:31:43.8347583Z             quantized_decomposed_dequantize_per_tensor_default_1718: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1223, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1223 = None
2025-03-21T20:31:43.8348936Z             
2025-03-21T20:31:43.8349706Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.8351327Z             aten_permute_copy_default_304: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1665, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1665 = None
2025-03-21T20:31:43.8353182Z             quantized_decomposed_quantize_per_tensor_default_1224: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_304, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_permute_copy_default_304 = None
2025-03-21T20:31:43.8355390Z             quantized_decomposed_dequantize_per_tensor_default_1719: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1224, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1224 = None
2025-03-21T20:31:43.8357400Z             aten_select_copy_int_356: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1719, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1719 = None
2025-03-21T20:31:43.8359154Z             quantized_decomposed_quantize_per_tensor_default_1225: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_356, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_select_copy_int_356 = None
2025-03-21T20:31:43.8361311Z             quantized_decomposed_dequantize_per_tensor_default_1720: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1225, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1225 = None
2025-03-21T20:31:43.8363341Z             aten_select_copy_int_357: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1720, 0, 10);  quantized_decomposed_dequantize_per_tensor_default_1720 = None
2025-03-21T20:31:43.8365113Z             quantized_decomposed_quantize_per_tensor_default_1226: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_357, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_select_copy_int_357 = None
2025-03-21T20:31:43.8366217Z             
2025-03-21T20:31:43.8367289Z              # File: <eval_with_key>.50:4363 in forward, code: dequantize_per_tensor_default_1382 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1382, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantize_per_tensor_default_1382 = None
2025-03-21T20:31:43.8369572Z             quantized_decomposed_dequantize_per_tensor_default_1721: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1226, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1226 = None
2025-03-21T20:31:43.8370924Z             
2025-03-21T20:31:43.8371733Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.8373294Z             aten_permute_copy_default_305: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1664, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1664 = None
2025-03-21T20:31:43.8375156Z             quantized_decomposed_quantize_per_tensor_default_1227: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_305, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_permute_copy_default_305 = None
2025-03-21T20:31:43.8377404Z             quantized_decomposed_dequantize_per_tensor_default_1722: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1227, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1227 = None
2025-03-21T20:31:43.8379429Z             aten_select_copy_int_358: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1722, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1722 = None
2025-03-21T20:31:43.8381187Z             quantized_decomposed_quantize_per_tensor_default_1228: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_358, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_select_copy_int_358 = None
2025-03-21T20:31:43.8383503Z             quantized_decomposed_dequantize_per_tensor_default_1723: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1228, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1228 = None
2025-03-21T20:31:43.8385515Z             aten_select_copy_int_359: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1723, 0, 11);  quantized_decomposed_dequantize_per_tensor_default_1723 = None
2025-03-21T20:31:43.8387263Z             quantized_decomposed_quantize_per_tensor_default_1229: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_359, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_select_copy_int_359 = None
2025-03-21T20:31:43.8394403Z             
2025-03-21T20:31:43.8395626Z              # File: <eval_with_key>.50:4372 in forward, code: dequantize_per_tensor_default_1385 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1385, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantize_per_tensor_default_1385 = None
2025-03-21T20:31:43.8397904Z             quantized_decomposed_dequantize_per_tensor_default_1724: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1229, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1229 = None
2025-03-21T20:31:43.8399268Z             
2025-03-21T20:31:43.8400038Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.8406325Z             aten_cat_default_30: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_aten_cat_default([quantized_decomposed_dequantize_per_tensor_default_1691, quantized_decomposed_dequantize_per_tensor_default_1694, quantized_decomposed_dequantize_per_tensor_default_1697, quantized_decomposed_dequantize_per_tensor_default_1700, quantized_decomposed_dequantize_per_tensor_default_1703, quantized_decomposed_dequantize_per_tensor_default_1706, quantized_decomposed_dequantize_per_tensor_default_1709, quantized_decomposed_dequantize_per_tensor_default_1712, quantized_decomposed_dequantize_per_tensor_default_1715, quantized_decomposed_dequantize_per_tensor_default_1718, quantized_decomposed_dequantize_per_tensor_default_1721, quantized_decomposed_dequantize_per_tensor_default_1724]);  quantized_decomposed_dequantize_per_tensor_default_1691 = quantized_decomposed_dequantize_per_tensor_default_1694 = quantized_decomposed_dequantize_per_tensor_default_1697 = quantized_decomposed_dequantize_per_tensor_default_1700 = quantized_decomposed_dequantize_per_tensor_default_1703 = quantized_decomposed_dequantize_per_tensor_default_1706 = quantized_decomposed_dequantize_per_tensor_default_1709 = quantized_decomposed_dequantize_per_tensor_default_1712 = quantized_decomposed_dequantize_per_tensor_default_1715 = quantized_decomposed_dequantize_per_tensor_default_1718 = quantized_decomposed_dequantize_per_tensor_default_1721 = quantized_decomposed_dequantize_per_tensor_default_1724 = None
2025-03-21T20:31:43.8413147Z             quantized_decomposed_quantize_per_tensor_default_1230: "i32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_30, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_cat_default_30 = None
2025-03-21T20:31:43.8415416Z             quantized_decomposed_dequantize_per_tensor_default_1725: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1230, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1230 = None
2025-03-21T20:31:43.8417469Z             aten_view_copy_default_135: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1725, [1, 12, 128, 64]);  quantized_decomposed_dequantize_per_tensor_default_1725 = None
2025-03-21T20:31:43.8419294Z             quantized_decomposed_quantize_per_tensor_default_1231: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_135, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_view_copy_default_135 = None
2025-03-21T20:31:43.8420413Z             
2025-03-21T20:31:43.8421134Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.8423021Z             quantized_decomposed_dequantize_per_tensor_default_1726: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1231, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1231 = None
2025-03-21T20:31:43.8424417Z             
2025-03-21T20:31:43.8425187Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.8426731Z             aten_permute_copy_default_306: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1688, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1688 = None
2025-03-21T20:31:43.8428580Z             quantized_decomposed_quantize_per_tensor_default_1232: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_306, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_permute_copy_default_306 = None
2025-03-21T20:31:43.8430808Z             quantized_decomposed_dequantize_per_tensor_default_1727: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1232, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1232 = None
2025-03-21T20:31:43.8433008Z             aten_select_copy_int_360: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1727, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1727 = None
2025-03-21T20:31:43.8434767Z             quantized_decomposed_quantize_per_tensor_default_1233: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_360, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_select_copy_int_360 = None
2025-03-21T20:31:43.8436989Z             quantized_decomposed_dequantize_per_tensor_default_1728: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1233, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1233 = None
2025-03-21T20:31:43.8438986Z             aten_select_copy_int_361: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1728, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1728 = None
2025-03-21T20:31:43.8440730Z             quantized_decomposed_quantize_per_tensor_default_1234: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_361, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_select_copy_int_361 = None
2025-03-21T20:31:43.8441829Z             
2025-03-21T20:31:43.8442903Z              # File: <eval_with_key>.50:4387 in forward, code: dequantize_per_tensor_default_1390 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1390, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantize_per_tensor_default_1390 = None
2025-03-21T20:31:43.8445109Z             quantized_decomposed_dequantize_per_tensor_default_1729: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1234, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1234 = None
2025-03-21T20:31:43.8446458Z             
2025-03-21T20:31:43.8447229Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.8448827Z             aten_permute_copy_default_307: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1687, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1687 = None
2025-03-21T20:31:43.8450793Z             quantized_decomposed_quantize_per_tensor_default_1235: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_307, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_permute_copy_default_307 = None
2025-03-21T20:31:43.8452992Z             quantized_decomposed_dequantize_per_tensor_default_1730: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1235, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1235 = None
2025-03-21T20:31:43.8455001Z             aten_select_copy_int_362: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1730, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1730 = None
2025-03-21T20:31:43.8456792Z             quantized_decomposed_quantize_per_tensor_default_1236: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_362, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_select_copy_int_362 = None
2025-03-21T20:31:43.8458951Z             quantized_decomposed_dequantize_per_tensor_default_1731: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1236, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1236 = None
2025-03-21T20:31:43.8460974Z             aten_select_copy_int_363: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1731, 0, 1);  quantized_decomposed_dequantize_per_tensor_default_1731 = None
2025-03-21T20:31:43.8462717Z             quantized_decomposed_quantize_per_tensor_default_1237: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_363, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_select_copy_int_363 = None
2025-03-21T20:31:43.8463816Z             
2025-03-21T20:31:43.8464878Z              # File: <eval_with_key>.50:4396 in forward, code: dequantize_per_tensor_default_1393 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1393, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantize_per_tensor_default_1393 = None
2025-03-21T20:31:43.8467079Z             quantized_decomposed_dequantize_per_tensor_default_1732: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1237, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1237 = None
2025-03-21T20:31:43.8468428Z             
2025-03-21T20:31:43.8469201Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.8470750Z             aten_permute_copy_default_308: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1686, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1686 = None
2025-03-21T20:31:43.8472603Z             quantized_decomposed_quantize_per_tensor_default_1238: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_308, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_permute_copy_default_308 = None
2025-03-21T20:31:43.8474966Z             quantized_decomposed_dequantize_per_tensor_default_1733: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1238, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1238 = None
2025-03-21T20:31:43.8476997Z             aten_select_copy_int_364: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1733, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1733 = None
2025-03-21T20:31:43.8478739Z             quantized_decomposed_quantize_per_tensor_default_1239: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_364, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_select_copy_int_364 = None
2025-03-21T20:31:43.8480893Z             quantized_decomposed_dequantize_per_tensor_default_1734: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1239, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1239 = None
2025-03-21T20:31:43.8482924Z             aten_select_copy_int_365: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1734, 0, 2);  quantized_decomposed_dequantize_per_tensor_default_1734 = None
2025-03-21T20:31:43.8484816Z             quantized_decomposed_quantize_per_tensor_default_1240: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_365, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_select_copy_int_365 = None
2025-03-21T20:31:43.8486073Z             
2025-03-21T20:31:43.8487156Z              # File: <eval_with_key>.50:4405 in forward, code: dequantize_per_tensor_default_1396 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1396, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantize_per_tensor_default_1396 = None
2025-03-21T20:31:43.8489443Z             quantized_decomposed_dequantize_per_tensor_default_1735: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1240, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1240 = None
2025-03-21T20:31:43.8490790Z             
2025-03-21T20:31:43.8491568Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.8493128Z             aten_permute_copy_default_309: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1685, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1685 = None
2025-03-21T20:31:43.8494973Z             quantized_decomposed_quantize_per_tensor_default_1241: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_309, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_permute_copy_default_309 = None
2025-03-21T20:31:43.8497170Z             quantized_decomposed_dequantize_per_tensor_default_1736: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1241, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1241 = None
2025-03-21T20:31:43.8499163Z             aten_select_copy_int_366: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1736, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1736 = None
2025-03-21T20:31:43.8500983Z             quantized_decomposed_quantize_per_tensor_default_1242: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_366, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_select_copy_int_366 = None
2025-03-21T20:31:43.8503137Z             quantized_decomposed_dequantize_per_tensor_default_1737: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1242, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1242 = None
2025-03-21T20:31:43.8505128Z             aten_select_copy_int_367: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1737, 0, 3);  quantized_decomposed_dequantize_per_tensor_default_1737 = None
2025-03-21T20:31:43.8506872Z             quantized_decomposed_quantize_per_tensor_default_1243: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_367, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_select_copy_int_367 = None
2025-03-21T20:31:43.8507984Z             
2025-03-21T20:31:43.8509059Z              # File: <eval_with_key>.50:4414 in forward, code: dequantize_per_tensor_default_1399 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1399, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantize_per_tensor_default_1399 = None
2025-03-21T20:31:43.8511258Z             quantized_decomposed_dequantize_per_tensor_default_1738: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1243, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1243 = None
2025-03-21T20:31:43.8512629Z             
2025-03-21T20:31:43.8513404Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.8514956Z             aten_permute_copy_default_310: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1684, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1684 = None
2025-03-21T20:31:43.8516801Z             quantized_decomposed_quantize_per_tensor_default_1244: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_310, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_permute_copy_default_310 = None
2025-03-21T20:31:43.8519005Z             quantized_decomposed_dequantize_per_tensor_default_1739: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1244, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1244 = None
2025-03-21T20:31:43.8521002Z             aten_select_copy_int_368: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1739, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1739 = None
2025-03-21T20:31:43.8522751Z             quantized_decomposed_quantize_per_tensor_default_1245: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_368, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_select_copy_int_368 = None
2025-03-21T20:31:43.8524948Z             quantized_decomposed_dequantize_per_tensor_default_1740: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1245, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1245 = None
2025-03-21T20:31:43.8526972Z             aten_select_copy_int_369: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1740, 0, 4);  quantized_decomposed_dequantize_per_tensor_default_1740 = None
2025-03-21T20:31:43.8528721Z             quantized_decomposed_quantize_per_tensor_default_1246: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_369, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_select_copy_int_369 = None
2025-03-21T20:31:43.8529885Z             
2025-03-21T20:31:43.8530956Z              # File: <eval_with_key>.50:4423 in forward, code: dequantize_per_tensor_default_1402 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1402, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantize_per_tensor_default_1402 = None
2025-03-21T20:31:43.8533572Z             quantized_decomposed_dequantize_per_tensor_default_1741: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1246, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1246 = None
2025-03-21T20:31:43.8534920Z             
2025-03-21T20:31:43.8535697Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.8537250Z             aten_permute_copy_default_311: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1683, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1683 = None
2025-03-21T20:31:43.8539143Z             quantized_decomposed_quantize_per_tensor_default_1247: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_311, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_permute_copy_default_311 = None
2025-03-21T20:31:43.8541356Z             quantized_decomposed_dequantize_per_tensor_default_1742: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1247, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1247 = None
2025-03-21T20:31:43.8543360Z             aten_select_copy_int_370: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1742, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1742 = None
2025-03-21T20:31:43.8545108Z             quantized_decomposed_quantize_per_tensor_default_1248: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_370, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_select_copy_int_370 = None
2025-03-21T20:31:43.8547274Z             quantized_decomposed_dequantize_per_tensor_default_1743: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1248, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1248 = None
2025-03-21T20:31:43.8549265Z             aten_select_copy_int_371: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1743, 0, 5);  quantized_decomposed_dequantize_per_tensor_default_1743 = None
2025-03-21T20:31:43.8551044Z             quantized_decomposed_quantize_per_tensor_default_1249: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_371, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_select_copy_int_371 = None
2025-03-21T20:31:43.8552169Z             
2025-03-21T20:31:43.8553245Z              # File: <eval_with_key>.50:4432 in forward, code: dequantize_per_tensor_default_1405 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1405, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantize_per_tensor_default_1405 = None
2025-03-21T20:31:43.8555444Z             quantized_decomposed_dequantize_per_tensor_default_1744: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1249, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1249 = None
2025-03-21T20:31:43.8556793Z             
2025-03-21T20:31:43.8557561Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.8559143Z             aten_permute_copy_default_312: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1682, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1682 = None
2025-03-21T20:31:43.8560999Z             quantized_decomposed_quantize_per_tensor_default_1250: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_312, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_permute_copy_default_312 = None
2025-03-21T20:31:43.8563202Z             quantized_decomposed_dequantize_per_tensor_default_1745: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1250, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1250 = None
2025-03-21T20:31:43.8565238Z             aten_select_copy_int_372: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1745, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1745 = None
2025-03-21T20:31:43.8566971Z             quantized_decomposed_quantize_per_tensor_default_1251: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_372, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_select_copy_int_372 = None
2025-03-21T20:31:43.8569126Z             quantized_decomposed_dequantize_per_tensor_default_1746: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1251, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1251 = None
2025-03-21T20:31:43.8571223Z             aten_select_copy_int_373: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1746, 0, 6);  quantized_decomposed_dequantize_per_tensor_default_1746 = None
2025-03-21T20:31:43.8572970Z             quantized_decomposed_quantize_per_tensor_default_1252: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_373, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_select_copy_int_373 = None
2025-03-21T20:31:43.8574066Z             
2025-03-21T20:31:43.8575141Z              # File: <eval_with_key>.50:4441 in forward, code: dequantize_per_tensor_default_1408 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1408, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantize_per_tensor_default_1408 = None
2025-03-21T20:31:43.8577371Z             quantized_decomposed_dequantize_per_tensor_default_1747: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1252, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1252 = None
2025-03-21T20:31:43.8578740Z             
2025-03-21T20:31:43.8579507Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.8581058Z             aten_permute_copy_default_313: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1681, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1681 = None
2025-03-21T20:31:43.8581998Z             quantized_decomposed_quantize_per_tensor_default_1253: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_313, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_permute_copy_default_313 = None
2025-03-21T20:31:43.8583186Z             quantized_decomposed_dequantize_per_tensor_default_1748: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1253, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1253 = None
2025-03-21T20:31:43.8583935Z             aten_select_copy_int_374: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1748, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1748 = None
2025-03-21T20:31:43.8584852Z             quantized_decomposed_quantize_per_tensor_default_1254: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_374, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_select_copy_int_374 = None
2025-03-21T20:31:43.8586012Z             quantized_decomposed_dequantize_per_tensor_default_1749: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1254, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1254 = None
2025-03-21T20:31:43.8586881Z             aten_select_copy_int_375: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1749, 0, 7);  quantized_decomposed_dequantize_per_tensor_default_1749 = None
2025-03-21T20:31:43.8587785Z             quantized_decomposed_quantize_per_tensor_default_1255: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_375, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_select_copy_int_375 = None
2025-03-21T20:31:43.8587882Z             
2025-03-21T20:31:43.8588831Z              # File: <eval_with_key>.50:4450 in forward, code: dequantize_per_tensor_default_1411 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1411, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantize_per_tensor_default_1411 = None
2025-03-21T20:31:43.8589971Z             quantized_decomposed_dequantize_per_tensor_default_1750: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1255, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1255 = None
2025-03-21T20:31:43.8590076Z             
2025-03-21T20:31:43.8590711Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.8591585Z             aten_permute_copy_default_314: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1680, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1680 = None
2025-03-21T20:31:43.8592527Z             quantized_decomposed_quantize_per_tensor_default_1256: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_314, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_permute_copy_default_314 = None
2025-03-21T20:31:43.8593682Z             quantized_decomposed_dequantize_per_tensor_default_1751: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1256, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1256 = None
2025-03-21T20:31:43.8594427Z             aten_select_copy_int_376: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1751, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1751 = None
2025-03-21T20:31:43.8595363Z             quantized_decomposed_quantize_per_tensor_default_1257: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_376, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_select_copy_int_376 = None
2025-03-21T20:31:43.8596508Z             quantized_decomposed_dequantize_per_tensor_default_1752: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1257, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1257 = None
2025-03-21T20:31:43.8597289Z             aten_select_copy_int_377: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1752, 0, 8);  quantized_decomposed_dequantize_per_tensor_default_1752 = None
2025-03-21T20:31:43.8598179Z             quantized_decomposed_quantize_per_tensor_default_1258: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_377, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_select_copy_int_377 = None
2025-03-21T20:31:43.8598280Z             
2025-03-21T20:31:43.8599215Z              # File: <eval_with_key>.50:4459 in forward, code: dequantize_per_tensor_default_1414 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1414, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantize_per_tensor_default_1414 = None
2025-03-21T20:31:43.8600369Z             quantized_decomposed_dequantize_per_tensor_default_1753: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1258, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1258 = None
2025-03-21T20:31:43.8600457Z             
2025-03-21T20:31:43.8601102Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.8601904Z             aten_permute_copy_default_315: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1679, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1679 = None
2025-03-21T20:31:43.8602850Z             quantized_decomposed_quantize_per_tensor_default_1259: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_315, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_permute_copy_default_315 = None
2025-03-21T20:31:43.8604048Z             quantized_decomposed_dequantize_per_tensor_default_1754: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1259, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1259 = None
2025-03-21T20:31:43.8604797Z             aten_select_copy_int_378: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1754, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1754 = None
2025-03-21T20:31:43.8605690Z             quantized_decomposed_quantize_per_tensor_default_1260: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_378, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_select_copy_int_378 = None
2025-03-21T20:31:43.8606874Z             quantized_decomposed_dequantize_per_tensor_default_1755: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1260, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1260 = None
2025-03-21T20:31:43.8607619Z             aten_select_copy_int_379: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1755, 0, 9);  quantized_decomposed_dequantize_per_tensor_default_1755 = None
2025-03-21T20:31:43.8608509Z             quantized_decomposed_quantize_per_tensor_default_1261: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_379, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_select_copy_int_379 = None
2025-03-21T20:31:43.8608618Z             
2025-03-21T20:31:43.8609637Z              # File: <eval_with_key>.50:4468 in forward, code: dequantize_per_tensor_default_1417 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1417, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantize_per_tensor_default_1417 = None
2025-03-21T20:31:43.8610799Z             quantized_decomposed_dequantize_per_tensor_default_1756: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1261, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1261 = None
2025-03-21T20:31:43.8610890Z             
2025-03-21T20:31:43.8611525Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.8612348Z             aten_permute_copy_default_316: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1678, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1678 = None
2025-03-21T20:31:43.8613290Z             quantized_decomposed_quantize_per_tensor_default_1262: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_316, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_permute_copy_default_316 = None
2025-03-21T20:31:43.8614450Z             quantized_decomposed_dequantize_per_tensor_default_1757: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1262, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1262 = None
2025-03-21T20:31:43.8615239Z             aten_select_copy_int_380: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1757, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1757 = None
2025-03-21T20:31:43.8616173Z             quantized_decomposed_quantize_per_tensor_default_1263: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_380, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_select_copy_int_380 = None
2025-03-21T20:31:43.8617336Z             quantized_decomposed_dequantize_per_tensor_default_1758: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1263, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1263 = None
2025-03-21T20:31:43.8618078Z             aten_select_copy_int_381: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1758, 0, 10);  quantized_decomposed_dequantize_per_tensor_default_1758 = None
2025-03-21T20:31:43.8619001Z             quantized_decomposed_quantize_per_tensor_default_1264: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_381, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_select_copy_int_381 = None
2025-03-21T20:31:43.8619088Z             
2025-03-21T20:31:43.8620034Z              # File: <eval_with_key>.50:4477 in forward, code: dequantize_per_tensor_default_1420 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1420, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantize_per_tensor_default_1420 = None
2025-03-21T20:31:43.8621177Z             quantized_decomposed_dequantize_per_tensor_default_1759: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1264, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1264 = None
2025-03-21T20:31:43.8621301Z             
2025-03-21T20:31:43.8621934Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.8622746Z             aten_permute_copy_default_317: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1677, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1677 = None
2025-03-21T20:31:43.8623684Z             quantized_decomposed_quantize_per_tensor_default_1265: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_317, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_permute_copy_default_317 = None
2025-03-21T20:31:43.8624847Z             quantized_decomposed_dequantize_per_tensor_default_1760: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1265, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1265 = None
2025-03-21T20:31:43.8625586Z             aten_select_copy_int_382: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1760, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1760 = None
2025-03-21T20:31:43.8626488Z             quantized_decomposed_quantize_per_tensor_default_1266: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_382, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_select_copy_int_382 = None
2025-03-21T20:31:43.8627659Z             quantized_decomposed_dequantize_per_tensor_default_1761: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1266, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1266 = None
2025-03-21T20:31:43.8628431Z             aten_select_copy_int_383: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1761, 0, 11);  quantized_decomposed_dequantize_per_tensor_default_1761 = None
2025-03-21T20:31:43.8629321Z             quantized_decomposed_quantize_per_tensor_default_1267: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_383, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_select_copy_int_383 = None
2025-03-21T20:31:43.8629420Z             
2025-03-21T20:31:43.8630352Z              # File: <eval_with_key>.50:4486 in forward, code: dequantize_per_tensor_default_1423 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1423, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantize_per_tensor_default_1423 = None
2025-03-21T20:31:43.8631529Z             quantized_decomposed_dequantize_per_tensor_default_1762: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1267, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1267 = None
2025-03-21T20:31:43.8631616Z             
2025-03-21T20:31:43.8632424Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.8637974Z             aten_cat_default_31: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_aten_cat_default([quantized_decomposed_dequantize_per_tensor_default_1729, quantized_decomposed_dequantize_per_tensor_default_1732, quantized_decomposed_dequantize_per_tensor_default_1735, quantized_decomposed_dequantize_per_tensor_default_1738, quantized_decomposed_dequantize_per_tensor_default_1741, quantized_decomposed_dequantize_per_tensor_default_1744, quantized_decomposed_dequantize_per_tensor_default_1747, quantized_decomposed_dequantize_per_tensor_default_1750, quantized_decomposed_dequantize_per_tensor_default_1753, quantized_decomposed_dequantize_per_tensor_default_1756, quantized_decomposed_dequantize_per_tensor_default_1759, quantized_decomposed_dequantize_per_tensor_default_1762]);  quantized_decomposed_dequantize_per_tensor_default_1729 = quantized_decomposed_dequantize_per_tensor_default_1732 = quantized_decomposed_dequantize_per_tensor_default_1735 = quantized_decomposed_dequantize_per_tensor_default_1738 = quantized_decomposed_dequantize_per_tensor_default_1741 = quantized_decomposed_dequantize_per_tensor_default_1744 = quantized_decomposed_dequantize_per_tensor_default_1747 = quantized_decomposed_dequantize_per_tensor_default_1750 = quantized_decomposed_dequantize_per_tensor_default_1753 = quantized_decomposed_dequantize_per_tensor_default_1756 = quantized_decomposed_dequantize_per_tensor_default_1759 = quantized_decomposed_dequantize_per_tensor_default_1762 = None
2025-03-21T20:31:43.8638847Z             quantized_decomposed_quantize_per_tensor_default_1268: "i32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_31, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_cat_default_31 = None
2025-03-21T20:31:43.8640003Z             quantized_decomposed_dequantize_per_tensor_default_1763: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1268, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1268 = None
2025-03-21T20:31:43.8640836Z             aten_view_copy_default_136: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1763, [1, 12, 128, 64]);  quantized_decomposed_dequantize_per_tensor_default_1763 = None
2025-03-21T20:31:43.8641786Z             quantized_decomposed_quantize_per_tensor_default_1269: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_136, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  aten_view_copy_default_136 = None
2025-03-21T20:31:43.8641883Z             
2025-03-21T20:31:43.8642819Z              # File: <eval_with_key>.50:4492 in forward, code: dequantize_per_tensor_default_1425 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1425, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantize_per_tensor_default_1425 = None
2025-03-21T20:31:43.8643980Z             quantized_decomposed_dequantize_per_tensor_default_1764: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1269, 0.0001613850035937503, 35011, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1269 = None
2025-03-21T20:31:43.8644112Z             
2025-03-21T20:31:43.8645065Z              # File: <eval_with_key>.50:4493 in forward, code: quantize_per_tensor_default_1426 = torch.ops.quantized_decomposed.quantize_per_tensor.default(dequantize_per_tensor_default_1425, 0.0001724382018437609, 0, -32767, 32767, torch.int16);  dequantize_per_tensor_default_1425 = None
2025-03-21T20:31:43.8646214Z             quantized_decomposed_quantize_per_tensor_default_1270: "i16[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_1764, 0.0001724382018437609, 0, -32767, 32767, torch.int16);  quantized_decomposed_dequantize_per_tensor_default_1764 = None
2025-03-21T20:31:43.8646336Z             
2025-03-21T20:31:43.8646802Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:163 in forward, code: y = attn_weight @ v
2025-03-21T20:31:43.8647968Z             quantized_decomposed_dequantize_per_tensor_default_1765: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1270, 0.0001724382018437609, 0, -32767, 32767, torch.int16);  quantized_decomposed_quantize_per_tensor_default_1270 = None
2025-03-21T20:31:43.8648056Z             
2025-03-21T20:31:43.8648544Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:157 in forward, code: attn_mask = mask[input_pos]
2025-03-21T20:31:43.8649402Z             aten_index_tensor_9: "f32[1, 128]" = executorch_exir_dialects_edge__ops_aten_index_Tensor(quantized_decomposed_dequantize_per_tensor_default_136, [attn_options_input_pos]);  quantized_decomposed_dequantize_per_tensor_default_136 = None
2025-03-21T20:31:43.8650275Z             quantized_decomposed_quantize_per_tensor_default_1271: "i32[1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_tensor_9, 0.0038910505827516317, 65535, 0, 65535, torch.int32);  aten_index_tensor_9 = None
2025-03-21T20:31:43.8650373Z             
2025-03-21T20:31:43.8650853Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:161 in forward, code: attn_weight += attn_mask
2025-03-21T20:31:43.8652004Z             quantized_decomposed_dequantize_per_tensor_default_1766: "f32[1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1271, 0.0038910505827516317, 65535, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1271 = None
2025-03-21T20:31:43.8652091Z             
2025-03-21T20:31:43.8652708Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.8653537Z             aten_permute_copy_default_318: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1726, [0, 1, 3, 2]);  quantized_decomposed_dequantize_per_tensor_default_1726 = None
2025-03-21T20:31:43.8654489Z             quantized_decomposed_quantize_per_tensor_default_1272: "i32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_318, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  aten_permute_copy_default_318 = None
2025-03-21T20:31:43.8654579Z             
2025-03-21T20:31:43.8655532Z              # File: <eval_with_key>.50:4500 in forward, code: dequantize_per_tensor_default_1428 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1428, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantize_per_tensor_default_1428 = None
2025-03-21T20:31:43.8656718Z             quantized_decomposed_dequantize_per_tensor_default_1767: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1272, 0.00039715005550533533, 34049, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1272 = None
2025-03-21T20:31:43.8656816Z             
2025-03-21T20:31:43.8657748Z              # File: <eval_with_key>.50:4501 in forward, code: quantize_per_tensor_default_1429 = torch.ops.quantized_decomposed.quantize_per_tensor.default(dequantize_per_tensor_default_1428, 0.0004126892308704555, 0, -32767, 32767, torch.int16);  dequantize_per_tensor_default_1428 = None
2025-03-21T20:31:43.8658938Z             quantized_decomposed_quantize_per_tensor_default_1273: "i16[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_1767, 0.0004126892308704555, 0, -32767, 32767, torch.int16);  quantized_decomposed_dequantize_per_tensor_default_1767 = None
2025-03-21T20:31:43.8659025Z             
2025-03-21T20:31:43.8659614Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.8660763Z             quantized_decomposed_dequantize_per_tensor_default_1768: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1273, 0.0004126892308704555, 0, -32767, 32767, torch.int16);  quantized_decomposed_quantize_per_tensor_default_1273 = None
2025-03-21T20:31:43.8661561Z             aten_expand_copy_default_28: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_1662, [1, 12, 1, 64]);  quantized_decomposed_dequantize_per_tensor_default_1662 = None
2025-03-21T20:31:43.8662119Z             aten_view_copy_default_137: "f32[12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_28, [12, 1, 64]);  aten_expand_copy_default_28 = None
2025-03-21T20:31:43.8662926Z             aten_expand_copy_default_29: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_1768, [1, 12, 64, 128]);  quantized_decomposed_dequantize_per_tensor_default_1768 = None
2025-03-21T20:31:43.8663489Z             aten_view_copy_default_138: "f32[12, 64, 128]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_29, [12, 64, 128]);  aten_expand_copy_default_29 = None
2025-03-21T20:31:43.8664154Z             aten_bmm_default_14: "f32[12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_bmm_default(aten_view_copy_default_137, aten_view_copy_default_138);  aten_view_copy_default_137 = aten_view_copy_default_138 = None
2025-03-21T20:31:43.8664721Z             aten_view_copy_default_139: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_bmm_default_14, [1, 12, 1, 128]);  aten_bmm_default_14 = None
2025-03-21T20:31:43.8665643Z             quantized_decomposed_quantize_per_tensor_default_1274: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_139, 0.0034391621593385935, 32661, 0, 65535, torch.int32);  aten_view_copy_default_139 = None
2025-03-21T20:31:43.8666792Z             quantized_decomposed_dequantize_per_tensor_default_1769: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1274, 0.0034391621593385935, 32661, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1274 = None
2025-03-21T20:31:43.8667659Z             quantized_decomposed_dequantize_per_tensor_default_1770: "f32[1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param156, 1.9073777366429567e-06, 0, 0, 65535, torch.int32);  b__frozen_param156 = None
2025-03-21T20:31:43.8668842Z             aten_mul_tensor_115: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1769, quantized_decomposed_dequantize_per_tensor_default_1770);  quantized_decomposed_dequantize_per_tensor_default_1769 = quantized_decomposed_dequantize_per_tensor_default_1770 = None
2025-03-21T20:31:43.8669713Z             quantized_decomposed_quantize_per_tensor_default_1275: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_115, 0.0004298952699173242, 32661, 0, 65535, torch.int32);  aten_mul_tensor_115 = None
2025-03-21T20:31:43.8669836Z             
2025-03-21T20:31:43.8670319Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:161 in forward, code: attn_weight += attn_mask
2025-03-21T20:31:43.8671466Z             quantized_decomposed_dequantize_per_tensor_default_1771: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1275, 0.0004298952699173242, 32661, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1275 = None
2025-03-21T20:31:43.8672608Z             aten_add_tensor_37: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_1771, quantized_decomposed_dequantize_per_tensor_default_1766);  quantized_decomposed_dequantize_per_tensor_default_1771 = quantized_decomposed_dequantize_per_tensor_default_1766 = None
2025-03-21T20:31:43.8673476Z             quantized_decomposed_quantize_per_tensor_default_1276: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_37, 0.004289415664970875, 62271, 0, 65535, torch.int32);  aten_add_tensor_37 = None
2025-03-21T20:31:43.8673569Z             
2025-03-21T20:31:43.8674138Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:162 in forward, code: attn_weight = torch.softmax(attn_weight, dim=-1)
2025-03-21T20:31:43.8675296Z             quantized_decomposed_dequantize_per_tensor_default_1772: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1276, 0.004289415664970875, 62271, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1276 = None
2025-03-21T20:31:43.8676086Z             aten__softmax_default_7: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten__softmax_default(quantized_decomposed_dequantize_per_tensor_default_1772, -1, False);  quantized_decomposed_dequantize_per_tensor_default_1772 = None
2025-03-21T20:31:43.8677020Z             quantized_decomposed_quantize_per_tensor_default_1277: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten__softmax_default_7, 1.5259021893143654e-05, 0, 0, 65535, torch.int32);  aten__softmax_default_7 = None
2025-03-21T20:31:43.8677168Z             
2025-03-21T20:31:43.8677681Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:163 in forward, code: y = attn_weight @ v
2025-03-21T20:31:43.8678814Z             quantized_decomposed_dequantize_per_tensor_default_1773: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1277, 1.5259021893143654e-05, 0, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1277 = None
2025-03-21T20:31:43.8679618Z             aten_expand_copy_default_30: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_1773, [1, 12, 1, 128]);  quantized_decomposed_dequantize_per_tensor_default_1773 = None
2025-03-21T20:31:43.8680224Z             aten_view_copy_default_140: "f32[12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_30, [12, 1, 128]);  aten_expand_copy_default_30 = None
2025-03-21T20:31:43.8681022Z             aten_expand_copy_default_31: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_1765, [1, 12, 128, 64]);  quantized_decomposed_dequantize_per_tensor_default_1765 = None
2025-03-21T20:31:43.8681583Z             aten_view_copy_default_141: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_31, [12, 128, 64]);  aten_expand_copy_default_31 = None
2025-03-21T20:31:43.8682269Z             aten_bmm_default_15: "f32[12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_bmm_default(aten_view_copy_default_140, aten_view_copy_default_141);  aten_view_copy_default_140 = aten_view_copy_default_141 = None
2025-03-21T20:31:43.8682785Z             aten_view_copy_default_142: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_bmm_default_15, [1, 12, 1, 64]);  aten_bmm_default_15 = None
2025-03-21T20:31:43.8683702Z             quantized_decomposed_quantize_per_tensor_default_1278: "i32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_142, 0.00010833422857103869, 34577, 0, 65535, torch.int32);  aten_view_copy_default_142 = None
2025-03-21T20:31:43.8683788Z             
2025-03-21T20:31:43.8684410Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:165 in forward, code: return y.transpose(1, 2).contiguous().view(bsz, seqlen, self.dim)
2025-03-21T20:31:43.8685572Z             quantized_decomposed_dequantize_per_tensor_default_1774: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1278, 0.00010833422857103869, 34577, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1278 = None
2025-03-21T20:31:43.8686381Z             aten_permute_copy_default_319: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1774, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1774 = None
2025-03-21T20:31:43.8687317Z             quantized_decomposed_quantize_per_tensor_default_1279: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_319, 0.00010833422857103869, 34577, 0, 65535, torch.int32);  aten_permute_copy_default_319 = None
2025-03-21T20:31:43.8688775Z             quantized_decomposed_dequantize_per_tensor_default_1775: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1279, 0.00010833422857103869, 34577, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1279 = None
2025-03-21T20:31:43.8689685Z             aten_view_copy_default_143: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1775, [1, 1, 768]);  quantized_decomposed_dequantize_per_tensor_default_1775 = None
2025-03-21T20:31:43.8690604Z             quantized_decomposed_quantize_per_tensor_default_1280: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_143, 0.00010833422857103869, 34577, 0, 65535, torch.int32);  aten_view_copy_default_143 = None
2025-03-21T20:31:43.8690691Z             
2025-03-21T20:31:43.8691224Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.8692398Z             quantized_decomposed_dequantize_per_tensor_default_1776: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1280, 0.00010833422857103869, 34577, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1280 = None
2025-03-21T20:31:43.8693214Z             aten_unsqueeze_copy_default_84: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1776, -1);  quantized_decomposed_dequantize_per_tensor_default_1776 = None
2025-03-21T20:31:43.8694166Z             quantized_decomposed_quantize_per_tensor_default_1281: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_84, 0.00010833422857103869, 34577, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_84 = None
2025-03-21T20:31:43.8694297Z             
2025-03-21T20:31:43.8694702Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.8695880Z             quantized_decomposed_dequantize_per_tensor_default_1777: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1281, 0.00010833422857103869, 34577, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1281 = None
2025-03-21T20:31:43.8696681Z             aten_permute_copy_default_320: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1777, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1777 = None
2025-03-21T20:31:43.8697640Z             quantized_decomposed_quantize_per_tensor_default_1282: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_320, 0.00010833422857103869, 34577, 0, 65535, torch.int32);  aten_permute_copy_default_320 = None
2025-03-21T20:31:43.8697729Z             
2025-03-21T20:31:43.8698109Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.8699259Z             quantized_decomposed_dequantize_per_tensor_default_1778: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1282, 0.00010833422857103869, 34577, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1282 = None
2025-03-21T20:31:43.8700584Z             aten_convolution_default_52: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_1778, quantized_decomposed_dequantize_per_tensor_default_68, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_1778 = quantized_decomposed_dequantize_per_tensor_default_68 = None
2025-03-21T20:31:43.8701542Z             quantized_decomposed_quantize_per_tensor_default_1283: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_52, 6.415071402443573e-05, 32880, 0, 65535, torch.int32);  aten_convolution_default_52 = None
2025-03-21T20:31:43.8701638Z             
2025-03-21T20:31:43.8702061Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.8703219Z             quantized_decomposed_dequantize_per_tensor_default_1779: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1283, 6.415071402443573e-05, 32880, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1283 = None
2025-03-21T20:31:43.8704041Z             aten_permute_copy_default_321: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1779, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1779 = None
2025-03-21T20:31:43.8704981Z             quantized_decomposed_quantize_per_tensor_default_1284: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_321, 6.415071402443573e-05, 32880, 0, 65535, torch.int32);  aten_permute_copy_default_321 = None
2025-03-21T20:31:43.8705065Z             
2025-03-21T20:31:43.8705608Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.8706778Z             quantized_decomposed_dequantize_per_tensor_default_1780: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1284, 6.415071402443573e-05, 32880, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1284 = None
2025-03-21T20:31:43.8707541Z             aten_squeeze_copy_dims_84: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_1780, [-1]);  quantized_decomposed_dequantize_per_tensor_default_1780 = None
2025-03-21T20:31:43.8708437Z             quantized_decomposed_quantize_per_tensor_default_1285: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_84, 6.415071402443573e-05, 32880, 0, 65535, torch.int32);  aten_squeeze_copy_dims_84 = None
2025-03-21T20:31:43.8708530Z             
2025-03-21T20:31:43.8708901Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:111 in forward, code: h = x + h
2025-03-21T20:31:43.8710051Z             quantized_decomposed_dequantize_per_tensor_default_1781: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1285, 6.415071402443573e-05, 32880, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1285 = None
2025-03-21T20:31:43.8711176Z             aten_add_tensor_38: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_1601, quantized_decomposed_dequantize_per_tensor_default_1781);  quantized_decomposed_dequantize_per_tensor_default_1601 = quantized_decomposed_dequantize_per_tensor_default_1781 = None
2025-03-21T20:31:43.8712025Z             quantized_decomposed_quantize_per_tensor_default_1286: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_38, 0.0026616528630256653, 5869, 0, 65535, torch.int32);  aten_add_tensor_38 = None
2025-03-21T20:31:43.8712146Z             
2025-03-21T20:31:43.8712682Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:115 in forward, code: out = h + self.feed_forward(self.ffn_norm(h))
2025-03-21T20:31:43.8713593Z             quantized_decomposed_dequantize_per_tensor_default_1782: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1286, 0.0026616528630256653, 5869, 0, 65535, torch.int32)
2025-03-21T20:31:43.8714737Z             quantized_decomposed_dequantize_per_tensor_default_1783: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1286, 0.0026616528630256653, 5869, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1286 = None
2025-03-21T20:31:43.8715253Z             aten_pow_tensor_scalar_15: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_pow_Tensor_Scalar(quantized_decomposed_dequantize_per_tensor_default_1783, 2)
2025-03-21T20:31:43.8715742Z             aten_mean_dim_15: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_mean_dim(aten_pow_tensor_scalar_15, [2], True);  aten_pow_tensor_scalar_15 = None
2025-03-21T20:31:43.8716187Z             aten_add_scalar_15: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_add_Scalar(aten_mean_dim_15, 9.999999747378752e-06);  aten_mean_dim_15 = None
2025-03-21T20:31:43.8716615Z             aten_rsqrt_default_15: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_rsqrt_default(aten_add_scalar_15);  aten_add_scalar_15 = None
2025-03-21T20:31:43.8717475Z             aten_mul_tensor_116: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1783, aten_rsqrt_default_15);  quantized_decomposed_dequantize_per_tensor_default_1783 = aten_rsqrt_default_15 = None
2025-03-21T20:31:43.8718321Z             aten_mul_tensor_117: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(aten_mul_tensor_116, quantized_decomposed_dequantize_per_tensor_default_69);  aten_mul_tensor_116 = quantized_decomposed_dequantize_per_tensor_default_69 = None
2025-03-21T20:31:43.8719176Z             quantized_decomposed_quantize_per_tensor_default_1287: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_117, 0.0003230620641261339, 20283, 0, 65535, torch.int32);  aten_mul_tensor_117 = None
2025-03-21T20:31:43.8719269Z             
2025-03-21T20:31:43.8719789Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.8720713Z             quantized_decomposed_dequantize_per_tensor_default_1784: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1287, 0.0003230620641261339, 20283, 0, 65535, torch.int32)
2025-03-21T20:31:43.8721862Z             quantized_decomposed_dequantize_per_tensor_default_1785: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1287, 0.0003230620641261339, 20283, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1287 = None
2025-03-21T20:31:43.8722674Z             aten_unsqueeze_copy_default_85: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1785, -1);  quantized_decomposed_dequantize_per_tensor_default_1785 = None
2025-03-21T20:31:43.8723614Z             quantized_decomposed_quantize_per_tensor_default_1288: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_85, 0.0003230620641261339, 20283, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_85 = None
2025-03-21T20:31:43.8723738Z             
2025-03-21T20:31:43.8724167Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.8725330Z             quantized_decomposed_dequantize_per_tensor_default_1786: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1288, 0.0003230620641261339, 20283, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1288 = None
2025-03-21T20:31:43.8726122Z             aten_permute_copy_default_322: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1786, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1786 = None
2025-03-21T20:31:43.8727071Z             quantized_decomposed_quantize_per_tensor_default_1289: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_322, 0.0003230620641261339, 20283, 0, 65535, torch.int32);  aten_permute_copy_default_322 = None
2025-03-21T20:31:43.8727160Z             
2025-03-21T20:31:43.8727558Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.8728702Z             quantized_decomposed_dequantize_per_tensor_default_1787: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1289, 0.0003230620641261339, 20283, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1289 = None
2025-03-21T20:31:43.8730064Z             aten_convolution_default_53: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_1787, quantized_decomposed_dequantize_per_tensor_default_70, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_1787 = quantized_decomposed_dequantize_per_tensor_default_70 = None
2025-03-21T20:31:43.8731037Z             quantized_decomposed_quantize_per_tensor_default_1290: "i32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_53, 0.0002114040544256568, 29834, 0, 65535, torch.int32);  aten_convolution_default_53 = None
2025-03-21T20:31:43.8731133Z             
2025-03-21T20:31:43.8731551Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.8732871Z             quantized_decomposed_dequantize_per_tensor_default_1788: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1290, 0.0002114040544256568, 29834, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1290 = None
2025-03-21T20:31:43.8733679Z             aten_permute_copy_default_323: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1788, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1788 = None
2025-03-21T20:31:43.8734628Z             quantized_decomposed_quantize_per_tensor_default_1291: "i32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_323, 0.0002114040544256568, 29834, 0, 65535, torch.int32);  aten_permute_copy_default_323 = None
2025-03-21T20:31:43.8734711Z             
2025-03-21T20:31:43.8735256Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.8736477Z             quantized_decomposed_dequantize_per_tensor_default_1789: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1291, 0.0002114040544256568, 29834, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1291 = None
2025-03-21T20:31:43.8737282Z             aten_squeeze_copy_dims_85: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_1789, [-1]);  quantized_decomposed_dequantize_per_tensor_default_1789 = None
2025-03-21T20:31:43.8738185Z             quantized_decomposed_quantize_per_tensor_default_1292: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_85, 0.0002114040544256568, 29834, 0, 65535, torch.int32);  aten_squeeze_copy_dims_85 = None
2025-03-21T20:31:43.8738285Z             
2025-03-21T20:31:43.8738796Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:36 in forward, code: return self.w2(F.silu(self.w1(x)) * self.w3(x))
2025-03-21T20:31:43.8739768Z             quantized_decomposed_dequantize_per_tensor_default_1790: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1292, 0.0002114040544256568, 29834, 0, 65535, torch.int32)
2025-03-21T20:31:43.8740916Z             quantized_decomposed_dequantize_per_tensor_default_1791: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1292, 0.0002114040544256568, 29834, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1292 = None
2025-03-21T20:31:43.8741665Z             aten_sigmoid_default_7: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_sigmoid_default(quantized_decomposed_dequantize_per_tensor_default_1791);  quantized_decomposed_dequantize_per_tensor_default_1791 = None
2025-03-21T20:31:43.8742551Z             quantized_decomposed_quantize_per_tensor_default_1293: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_sigmoid_default_7, 1.52587890625e-05, 0, 0, 65535, torch.int32);  aten_sigmoid_default_7 = None
2025-03-21T20:31:43.8743665Z             quantized_decomposed_dequantize_per_tensor_default_1792: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1293, 1.52587890625e-05, 0, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1293 = None
2025-03-21T20:31:43.8744799Z             aten_mul_tensor_118: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1790, quantized_decomposed_dequantize_per_tensor_default_1792);  quantized_decomposed_dequantize_per_tensor_default_1790 = quantized_decomposed_dequantize_per_tensor_default_1792 = None
2025-03-21T20:31:43.8745670Z             quantized_decomposed_quantize_per_tensor_default_1294: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_118, 0.00011935368820559233, 2333, 0, 65535, torch.int32);  aten_mul_tensor_118 = None
2025-03-21T20:31:43.8746828Z             quantized_decomposed_dequantize_per_tensor_default_1793: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1294, 0.00011935368820559233, 2333, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1294 = None
2025-03-21T20:31:43.8746914Z             
2025-03-21T20:31:43.8747428Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.8748273Z             aten_unsqueeze_copy_default_86: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1784, -1);  quantized_decomposed_dequantize_per_tensor_default_1784 = None
2025-03-21T20:31:43.8749246Z             quantized_decomposed_quantize_per_tensor_default_1295: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_86, 0.0003230620641261339, 20283, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_86 = None
2025-03-21T20:31:43.8749343Z             
2025-03-21T20:31:43.8749747Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.8750900Z             quantized_decomposed_dequantize_per_tensor_default_1794: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1295, 0.0003230620641261339, 20283, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1295 = None
2025-03-21T20:31:43.8751723Z             aten_permute_copy_default_324: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1794, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1794 = None
2025-03-21T20:31:43.8752661Z             quantized_decomposed_quantize_per_tensor_default_1296: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_324, 0.0003230620641261339, 20283, 0, 65535, torch.int32);  aten_permute_copy_default_324 = None
2025-03-21T20:31:43.8752744Z             
2025-03-21T20:31:43.8753114Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.8754285Z             quantized_decomposed_dequantize_per_tensor_default_1795: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1296, 0.0003230620641261339, 20283, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1296 = None
2025-03-21T20:31:43.8755572Z             aten_convolution_default_54: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_1795, quantized_decomposed_dequantize_per_tensor_default_71, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_1795 = quantized_decomposed_dequantize_per_tensor_default_71 = None
2025-03-21T20:31:43.8756518Z             quantized_decomposed_quantize_per_tensor_default_1297: "i32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_54, 0.00024151173420250416, 31646, 0, 65535, torch.int32);  aten_convolution_default_54 = None
2025-03-21T20:31:43.8756605Z             
2025-03-21T20:31:43.8757023Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.8758194Z             quantized_decomposed_dequantize_per_tensor_default_1796: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1297, 0.00024151173420250416, 31646, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1297 = None
2025-03-21T20:31:43.8758989Z             aten_permute_copy_default_325: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1796, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1796 = None
2025-03-21T20:31:43.8759965Z             quantized_decomposed_quantize_per_tensor_default_1298: "i32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_325, 0.00024151173420250416, 31646, 0, 65535, torch.int32);  aten_permute_copy_default_325 = None
2025-03-21T20:31:43.8760073Z             
2025-03-21T20:31:43.8760616Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.8761768Z             quantized_decomposed_dequantize_per_tensor_default_1797: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1298, 0.00024151173420250416, 31646, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1298 = None
2025-03-21T20:31:43.8762533Z             aten_squeeze_copy_dims_86: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_1797, [-1]);  quantized_decomposed_dequantize_per_tensor_default_1797 = None
2025-03-21T20:31:43.8763445Z             quantized_decomposed_quantize_per_tensor_default_1299: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_86, 0.00024151173420250416, 31646, 0, 65535, torch.int32);  aten_squeeze_copy_dims_86 = None
2025-03-21T20:31:43.8763567Z             
2025-03-21T20:31:43.8764079Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:36 in forward, code: return self.w2(F.silu(self.w1(x)) * self.w3(x))
2025-03-21T20:31:43.8765235Z             quantized_decomposed_dequantize_per_tensor_default_1798: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1299, 0.00024151173420250416, 31646, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1299 = None
2025-03-21T20:31:43.8766392Z             aten_mul_tensor_119: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1793, quantized_decomposed_dequantize_per_tensor_default_1798);  quantized_decomposed_dequantize_per_tensor_default_1793 = quantized_decomposed_dequantize_per_tensor_default_1798 = None
2025-03-21T20:31:43.8767264Z             quantized_decomposed_quantize_per_tensor_default_1300: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_119, 0.00026427191914990544, 35887, 0, 65535, torch.int32);  aten_mul_tensor_119 = None
2025-03-21T20:31:43.8767349Z             
2025-03-21T20:31:43.8767872Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.8769025Z             quantized_decomposed_dequantize_per_tensor_default_1799: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1300, 0.00026427191914990544, 35887, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1300 = None
2025-03-21T20:31:43.8769910Z             aten_unsqueeze_copy_default_87: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1799, -1);  quantized_decomposed_dequantize_per_tensor_default_1799 = None
2025-03-21T20:31:43.8770875Z             quantized_decomposed_quantize_per_tensor_default_1301: "i32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_87, 0.00026427191914990544, 35887, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_87 = None
2025-03-21T20:31:43.8770961Z             
2025-03-21T20:31:43.8771364Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.8772566Z             quantized_decomposed_dequantize_per_tensor_default_1800: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1301, 0.00026427191914990544, 35887, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1301 = None
2025-03-21T20:31:43.8773389Z             aten_permute_copy_default_326: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1800, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1800 = None
2025-03-21T20:31:43.8774341Z             quantized_decomposed_quantize_per_tensor_default_1302: "i32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_326, 0.00026427191914990544, 35887, 0, 65535, torch.int32);  aten_permute_copy_default_326 = None
2025-03-21T20:31:43.8774430Z             
2025-03-21T20:31:43.8774798Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.8775973Z             quantized_decomposed_dequantize_per_tensor_default_1801: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1302, 0.00026427191914990544, 35887, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1302 = None
2025-03-21T20:31:43.8777252Z             aten_convolution_default_55: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_1801, quantized_decomposed_dequantize_per_tensor_default_72, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_1801 = quantized_decomposed_dequantize_per_tensor_default_72 = None
2025-03-21T20:31:43.8778237Z             quantized_decomposed_quantize_per_tensor_default_1303: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_55, 0.00013502163346856833, 26548, 0, 65535, torch.int32);  aten_convolution_default_55 = None
2025-03-21T20:31:43.8778325Z             
2025-03-21T20:31:43.8778751Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.8779918Z             quantized_decomposed_dequantize_per_tensor_default_1802: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1303, 0.00013502163346856833, 26548, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1303 = None
2025-03-21T20:31:43.8780728Z             aten_permute_copy_default_327: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1802, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1802 = None
2025-03-21T20:31:43.8781672Z             quantized_decomposed_quantize_per_tensor_default_1304: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_327, 0.00013502163346856833, 26548, 0, 65535, torch.int32);  aten_permute_copy_default_327 = None
2025-03-21T20:31:43.8781773Z             
2025-03-21T20:31:43.8782312Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.8783481Z             quantized_decomposed_dequantize_per_tensor_default_1803: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1304, 0.00013502163346856833, 26548, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1304 = None
2025-03-21T20:31:43.8784266Z             aten_squeeze_copy_dims_87: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_1803, [-1]);  quantized_decomposed_dequantize_per_tensor_default_1803 = None
2025-03-21T20:31:43.8785210Z             quantized_decomposed_quantize_per_tensor_default_1305: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_87, 0.00013502163346856833, 26548, 0, 65535, torch.int32);  aten_squeeze_copy_dims_87 = None
2025-03-21T20:31:43.8785297Z             
2025-03-21T20:31:43.8785802Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:115 in forward, code: out = h + self.feed_forward(self.ffn_norm(h))
2025-03-21T20:31:43.8786970Z             quantized_decomposed_dequantize_per_tensor_default_1804: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1305, 0.00013502163346856833, 26548, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1305 = None
2025-03-21T20:31:43.8788139Z             aten_add_tensor_39: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_1782, quantized_decomposed_dequantize_per_tensor_default_1804);  quantized_decomposed_dequantize_per_tensor_default_1782 = quantized_decomposed_dequantize_per_tensor_default_1804 = None
2025-03-21T20:31:43.8788986Z             quantized_decomposed_quantize_per_tensor_default_1306: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_39, 0.0026549873873591423, 5846, 0, 65535, torch.int32);  aten_add_tensor_39 = None
2025-03-21T20:31:43.8789082Z             
2025-03-21T20:31:43.8789461Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:111 in forward, code: h = x + h
2025-03-21T20:31:43.8790538Z             quantized_decomposed_dequantize_per_tensor_default_1805: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1306, 0.0026549873873591423, 5846, 0, 65535, torch.int32)
2025-03-21T20:31:43.8790638Z             
2025-03-21T20:31:43.8791197Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:108 in forward, code: self.attention_norm(x), freqs_cos, freqs_sin, **attn_options
2025-03-21T20:31:43.8792346Z             quantized_decomposed_dequantize_per_tensor_default_1806: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1306, 0.0026549873873591423, 5846, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1306 = None
2025-03-21T20:31:43.8792859Z             aten_pow_tensor_scalar_16: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_pow_Tensor_Scalar(quantized_decomposed_dequantize_per_tensor_default_1806, 2)
2025-03-21T20:31:43.8793335Z             aten_mean_dim_16: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_mean_dim(aten_pow_tensor_scalar_16, [2], True);  aten_pow_tensor_scalar_16 = None
2025-03-21T20:31:43.8793776Z             aten_add_scalar_16: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_add_Scalar(aten_mean_dim_16, 9.999999747378752e-06);  aten_mean_dim_16 = None
2025-03-21T20:31:43.8794209Z             aten_rsqrt_default_16: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_rsqrt_default(aten_add_scalar_16);  aten_add_scalar_16 = None
2025-03-21T20:31:43.8795062Z             aten_mul_tensor_120: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1806, aten_rsqrt_default_16);  quantized_decomposed_dequantize_per_tensor_default_1806 = aten_rsqrt_default_16 = None
2025-03-21T20:31:43.8795922Z             aten_mul_tensor_121: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(aten_mul_tensor_120, quantized_decomposed_dequantize_per_tensor_default_73);  aten_mul_tensor_120 = quantized_decomposed_dequantize_per_tensor_default_73 = None
2025-03-21T20:31:43.8796803Z             quantized_decomposed_quantize_per_tensor_default_1307: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_121, 0.0004401287587825209, 30665, 0, 65535, torch.int32);  aten_mul_tensor_121 = None
2025-03-21T20:31:43.8796902Z             
2025-03-21T20:31:43.8797422Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.8798349Z             quantized_decomposed_dequantize_per_tensor_default_1807: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1307, 0.0004401287587825209, 30665, 0, 65535, torch.int32)
2025-03-21T20:31:43.8799292Z             quantized_decomposed_dequantize_per_tensor_default_1808: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1307, 0.0004401287587825209, 30665, 0, 65535, torch.int32)
2025-03-21T20:31:43.8800449Z             quantized_decomposed_dequantize_per_tensor_default_1809: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1307, 0.0004401287587825209, 30665, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1307 = None
2025-03-21T20:31:43.8801252Z             aten_unsqueeze_copy_default_88: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1809, -1);  quantized_decomposed_dequantize_per_tensor_default_1809 = None
2025-03-21T20:31:43.8802238Z             quantized_decomposed_quantize_per_tensor_default_1308: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_88, 0.0004401287587825209, 30665, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_88 = None
2025-03-21T20:31:43.8802328Z             
2025-03-21T20:31:43.8802745Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.8803895Z             quantized_decomposed_dequantize_per_tensor_default_1810: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1308, 0.0004401287587825209, 30665, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1308 = None
2025-03-21T20:31:43.8804704Z             aten_permute_copy_default_328: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1810, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1810 = None
2025-03-21T20:31:43.8805639Z             quantized_decomposed_quantize_per_tensor_default_1309: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_328, 0.0004401287587825209, 30665, 0, 65535, torch.int32);  aten_permute_copy_default_328 = None
2025-03-21T20:31:43.8805735Z             
2025-03-21T20:31:43.8806096Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.8807252Z             quantized_decomposed_dequantize_per_tensor_default_1811: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1309, 0.0004401287587825209, 30665, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1309 = None
2025-03-21T20:31:43.8808558Z             aten_convolution_default_56: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_1811, quantized_decomposed_dequantize_per_tensor_default_74, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_1811 = quantized_decomposed_dequantize_per_tensor_default_74 = None
2025-03-21T20:31:43.8809609Z             quantized_decomposed_quantize_per_tensor_default_1310: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_56, 0.00033537388662807643, 31155, 0, 65535, torch.int32);  aten_convolution_default_56 = None
2025-03-21T20:31:43.8809712Z             
2025-03-21T20:31:43.8810132Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.8811293Z             quantized_decomposed_dequantize_per_tensor_default_1812: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1310, 0.00033537388662807643, 31155, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1310 = None
2025-03-21T20:31:43.8812137Z             aten_permute_copy_default_329: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1812, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1812 = None
2025-03-21T20:31:43.8813088Z             quantized_decomposed_quantize_per_tensor_default_1311: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_329, 0.00033537388662807643, 31155, 0, 65535, torch.int32);  aten_permute_copy_default_329 = None
2025-03-21T20:31:43.8813200Z             
2025-03-21T20:31:43.8813735Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.8814901Z             quantized_decomposed_dequantize_per_tensor_default_1813: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1311, 0.00033537388662807643, 31155, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1311 = None
2025-03-21T20:31:43.8815656Z             aten_squeeze_copy_dims_88: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_1813, [-1]);  quantized_decomposed_dequantize_per_tensor_default_1813 = None
2025-03-21T20:31:43.8816569Z             quantized_decomposed_quantize_per_tensor_default_1312: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_88, 0.00033537388662807643, 31155, 0, 65535, torch.int32);  aten_squeeze_copy_dims_88 = None
2025-03-21T20:31:43.8816663Z             
2025-03-21T20:31:43.8817192Z              # File: /pytorch/executorch/examples/models/llama/attention.py:242 in forward, code: q = q.view(bsz, seqlen, self.n_local_heads, self.head_dim)
2025-03-21T20:31:43.8818342Z             quantized_decomposed_dequantize_per_tensor_default_1814: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1312, 0.00033537388662807643, 31155, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1312 = None
2025-03-21T20:31:43.8818443Z             
2025-03-21T20:31:43.8818957Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.8819801Z             aten_unsqueeze_copy_default_89: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1808, -1);  quantized_decomposed_dequantize_per_tensor_default_1808 = None
2025-03-21T20:31:43.8820769Z             quantized_decomposed_quantize_per_tensor_default_1313: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_89, 0.0004401287587825209, 30665, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_89 = None
2025-03-21T20:31:43.8820865Z             
2025-03-21T20:31:43.8821271Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.8822429Z             quantized_decomposed_dequantize_per_tensor_default_1815: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1313, 0.0004401287587825209, 30665, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1313 = None
2025-03-21T20:31:43.8823259Z             aten_permute_copy_default_330: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1815, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1815 = None
2025-03-21T20:31:43.8824199Z             quantized_decomposed_quantize_per_tensor_default_1314: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_330, 0.0004401287587825209, 30665, 0, 65535, torch.int32);  aten_permute_copy_default_330 = None
2025-03-21T20:31:43.8824286Z             
2025-03-21T20:31:43.8824655Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.8825828Z             quantized_decomposed_dequantize_per_tensor_default_1816: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1314, 0.0004401287587825209, 30665, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1314 = None
2025-03-21T20:31:43.8827105Z             aten_convolution_default_57: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_1816, quantized_decomposed_dequantize_per_tensor_default_75, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_1816 = quantized_decomposed_dequantize_per_tensor_default_75 = None
2025-03-21T20:31:43.8828020Z             quantized_decomposed_quantize_per_tensor_default_1315: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_57, 0.00042168446816504, 35651, 0, 65535, torch.int32);  aten_convolution_default_57 = None
2025-03-21T20:31:43.8828123Z             
2025-03-21T20:31:43.8828540Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.8829688Z             quantized_decomposed_dequantize_per_tensor_default_1817: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1315, 0.00042168446816504, 35651, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1315 = None
2025-03-21T20:31:43.8830486Z             aten_permute_copy_default_331: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1817, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1817 = None
2025-03-21T20:31:43.8831413Z             quantized_decomposed_quantize_per_tensor_default_1316: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_331, 0.00042168446816504, 35651, 0, 65535, torch.int32);  aten_permute_copy_default_331 = None
2025-03-21T20:31:43.8831551Z             
2025-03-21T20:31:43.8832093Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.8833399Z             quantized_decomposed_dequantize_per_tensor_default_1818: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1316, 0.00042168446816504, 35651, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1316 = None
2025-03-21T20:31:43.8834166Z             aten_squeeze_copy_dims_89: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_1818, [-1]);  quantized_decomposed_dequantize_per_tensor_default_1818 = None
2025-03-21T20:31:43.8835060Z             quantized_decomposed_quantize_per_tensor_default_1317: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_89, 0.00042168446816504, 35651, 0, 65535, torch.int32);  aten_squeeze_copy_dims_89 = None
2025-03-21T20:31:43.8835161Z             
2025-03-21T20:31:43.8835744Z              # File: /pytorch/executorch/examples/models/llama/attention.py:243 in forward, code: k = k.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.8836891Z             quantized_decomposed_dequantize_per_tensor_default_1819: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1317, 0.00042168446816504, 35651, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1317 = None
2025-03-21T20:31:43.8837006Z             
2025-03-21T20:31:43.8837534Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.8838339Z             aten_unsqueeze_copy_default_90: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1807, -1);  quantized_decomposed_dequantize_per_tensor_default_1807 = None
2025-03-21T20:31:43.8839293Z             quantized_decomposed_quantize_per_tensor_default_1318: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_90, 0.0004401287587825209, 30665, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_90 = None
2025-03-21T20:31:43.8839380Z             
2025-03-21T20:31:43.8839794Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.8840944Z             quantized_decomposed_dequantize_per_tensor_default_1820: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1318, 0.0004401287587825209, 30665, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1318 = None
2025-03-21T20:31:43.8841753Z             aten_permute_copy_default_332: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1820, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1820 = None
2025-03-21T20:31:43.8842683Z             quantized_decomposed_quantize_per_tensor_default_1319: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_332, 0.0004401287587825209, 30665, 0, 65535, torch.int32);  aten_permute_copy_default_332 = None
2025-03-21T20:31:43.8842783Z             
2025-03-21T20:31:43.8843143Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.8844338Z             quantized_decomposed_dequantize_per_tensor_default_1821: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1319, 0.0004401287587825209, 30665, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1319 = None
2025-03-21T20:31:43.8845639Z             aten_convolution_default_58: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_1821, quantized_decomposed_dequantize_per_tensor_default_76, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_1821 = quantized_decomposed_dequantize_per_tensor_default_76 = None
2025-03-21T20:31:43.8846576Z             quantized_decomposed_quantize_per_tensor_default_1320: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_58, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_convolution_default_58 = None
2025-03-21T20:31:43.8846668Z             
2025-03-21T20:31:43.8847125Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.8848275Z             quantized_decomposed_dequantize_per_tensor_default_1822: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1320, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1320 = None
2025-03-21T20:31:43.8849079Z             aten_permute_copy_default_333: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1822, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1822 = None
2025-03-21T20:31:43.8850101Z             quantized_decomposed_quantize_per_tensor_default_1321: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_333, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_permute_copy_default_333 = None
2025-03-21T20:31:43.8850206Z             
2025-03-21T20:31:43.8850743Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.8851894Z             quantized_decomposed_dequantize_per_tensor_default_1823: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1321, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1321 = None
2025-03-21T20:31:43.8852654Z             aten_squeeze_copy_dims_90: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_1823, [-1]);  quantized_decomposed_dequantize_per_tensor_default_1823 = None
2025-03-21T20:31:43.8853561Z             quantized_decomposed_quantize_per_tensor_default_1322: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_90, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_squeeze_copy_dims_90 = None
2025-03-21T20:31:43.8853648Z             
2025-03-21T20:31:43.8854181Z              # File: /pytorch/executorch/examples/models/llama/attention.py:244 in forward, code: v = v.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.8855330Z             quantized_decomposed_dequantize_per_tensor_default_1824: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1322, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1322 = None
2025-03-21T20:31:43.8855460Z             
2025-03-21T20:31:43.8856023Z              # File: /pytorch/executorch/examples/models/llama/attention.py:242 in forward, code: q = q.view(bsz, seqlen, self.n_local_heads, self.head_dim)
2025-03-21T20:31:43.8856797Z             aten_view_copy_default_144: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1814, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_1814 = None
2025-03-21T20:31:43.8857704Z             quantized_decomposed_quantize_per_tensor_default_1323: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_144, 0.00033537388662807643, 31155, 0, 65535, torch.int32);  aten_view_copy_default_144 = None
2025-03-21T20:31:43.8857800Z             
2025-03-21T20:31:43.8858740Z              # File: <eval_with_key>.50:4660 in forward, code: dequantize_per_tensor_default_1480 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1480, 0.00033537388662807643, 31155, 0, 65535, torch.int32);  quantize_per_tensor_default_1480 = None
2025-03-21T20:31:43.8859924Z             quantized_decomposed_dequantize_per_tensor_default_1825: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1323, 0.00033537388662807643, 31155, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1323 = None
2025-03-21T20:31:43.8860012Z             
2025-03-21T20:31:43.8860541Z              # File: /pytorch/executorch/examples/models/llama/attention.py:243 in forward, code: k = k.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.8861305Z             aten_view_copy_default_145: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1819, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_1819 = None
2025-03-21T20:31:43.8862244Z             quantized_decomposed_quantize_per_tensor_default_1324: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_145, 0.00042168446816504, 35651, 0, 65535, torch.int32);  aten_view_copy_default_145 = None
2025-03-21T20:31:43.8862334Z             
2025-03-21T20:31:43.8863273Z              # File: <eval_with_key>.50:4663 in forward, code: dequantize_per_tensor_default_1481 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1481, 0.00042168446816504, 35651, 0, 65535, torch.int32);  quantize_per_tensor_default_1481 = None
2025-03-21T20:31:43.8864412Z             quantized_decomposed_dequantize_per_tensor_default_1826: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1324, 0.00042168446816504, 35651, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1324 = None
2025-03-21T20:31:43.8864511Z             
2025-03-21T20:31:43.8865032Z              # File: /pytorch/executorch/examples/models/llama/attention.py:244 in forward, code: v = v.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.8865809Z             aten_view_copy_default_146: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1824, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_1824 = None
2025-03-21T20:31:43.8866710Z             quantized_decomposed_quantize_per_tensor_default_1325: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_146, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_view_copy_default_146 = None
2025-03-21T20:31:43.8866808Z             
2025-03-21T20:31:43.8867506Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:346 in update, code: v_out = torch.ops.aten.index_put_(self.past_v_caches, [None, input_pos], v_val)
2025-03-21T20:31:43.8868703Z             quantized_decomposed_dequantize_per_tensor_default_1827: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1325, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1325 = None
2025-03-21T20:31:43.8868791Z             
2025-03-21T20:31:43.8869552Z              # File: <eval_with_key>.50:4668 in forward, code: quantize_per_tensor_default_1483 = torch.ops.quantized_decomposed.quantize_per_tensor.default(_to_copy_16, 0.00033537388662807643, 31155, 0, 65535, torch.int32);  _to_copy_16 = None
2025-03-21T20:31:43.8870710Z             quantized_decomposed_quantize_per_tensor_default_1326: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_1825, 0.00033537388662807643, 31155, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_1825 = None
2025-03-21T20:31:43.8870809Z             
2025-03-21T20:31:43.8871360Z              # File: /pytorch/executorch/examples/models/llama/rope.py:84 in apply_rotary_emb, code: xq_r, xq_i = xq.float().reshape(xq.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.8872508Z             quantized_decomposed_dequantize_per_tensor_default_1828: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1326, 0.00033537388662807643, 31155, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1326 = None
2025-03-21T20:31:43.8873331Z             aten_view_copy_default_147: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1828, [1, 1, 12, -1, 2]);  quantized_decomposed_dequantize_per_tensor_default_1828 = None
2025-03-21T20:31:43.8874264Z             quantized_decomposed_quantize_per_tensor_default_1327: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_147, 0.00033537388662807643, 31155, 0, 65535, torch.int32);  aten_view_copy_default_147 = None
2025-03-21T20:31:43.8875407Z             quantized_decomposed_dequantize_per_tensor_default_1829: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1327, 0.00033537388662807643, 31155, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1327 = None
2025-03-21T20:31:43.8875958Z             aten_slice_copy_tensor_32: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_1829, 4, 0, 1)
2025-03-21T20:31:43.8876709Z             aten_slice_copy_tensor_33: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_1829, 4, 1, 2);  quantized_decomposed_dequantize_per_tensor_default_1829 = None
2025-03-21T20:31:43.8877237Z             aten_squeeze_copy_dims_91: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_32, [4]);  aten_slice_copy_tensor_32 = None
2025-03-21T20:31:43.8877752Z             aten_squeeze_copy_dims_92: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_33, [4]);  aten_slice_copy_tensor_33 = None
2025-03-21T20:31:43.8878671Z             quantized_decomposed_quantize_per_tensor_default_1328: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_91, 0.0003121877380181104, 28601, 0, 65535, torch.int32);  aten_squeeze_copy_dims_91 = None
2025-03-21T20:31:43.8878760Z             
2025-03-21T20:31:43.8879314Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.8880239Z             quantized_decomposed_dequantize_per_tensor_default_1830: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1328, 0.0003121877380181104, 28601, 0, 65535, torch.int32)
2025-03-21T20:31:43.8880384Z             
2025-03-21T20:31:43.8880907Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.8882059Z             quantized_decomposed_dequantize_per_tensor_default_1831: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1328, 0.0003121877380181104, 28601, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1328 = None
2025-03-21T20:31:43.8882161Z             
2025-03-21T20:31:43.8882719Z              # File: /pytorch/executorch/examples/models/llama/rope.py:84 in apply_rotary_emb, code: xq_r, xq_i = xq.float().reshape(xq.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.8883640Z             quantized_decomposed_quantize_per_tensor_default_1329: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_92, 0.0003160475753247738, 33060, 0, 65535, torch.int32);  aten_squeeze_copy_dims_92 = None
2025-03-21T20:31:43.8883728Z             
2025-03-21T20:31:43.8884213Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.8885166Z             quantized_decomposed_dequantize_per_tensor_default_1832: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1329, 0.0003160475753247738, 33060, 0, 65535, torch.int32)
2025-03-21T20:31:43.8885262Z             
2025-03-21T20:31:43.8885734Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.8886891Z             quantized_decomposed_dequantize_per_tensor_default_1833: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1329, 0.0003160475753247738, 33060, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1329 = None
2025-03-21T20:31:43.8886976Z             
2025-03-21T20:31:43.8887745Z              # File: <eval_with_key>.50:4683 in forward, code: quantize_per_tensor_default_1487 = torch.ops.quantized_decomposed.quantize_per_tensor.default(_to_copy_17, 0.00042168446816504, 35651, 0, 65535, torch.int32);  _to_copy_17 = None
2025-03-21T20:31:43.8888879Z             quantized_decomposed_quantize_per_tensor_default_1330: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_1826, 0.00042168446816504, 35651, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_1826 = None
2025-03-21T20:31:43.8888977Z             
2025-03-21T20:31:43.8889558Z              # File: /pytorch/executorch/examples/models/llama/rope.py:85 in apply_rotary_emb, code: xk_r, xk_i = xk.float().reshape(xk.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.8890704Z             quantized_decomposed_dequantize_per_tensor_default_1834: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1330, 0.00042168446816504, 35651, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1330 = None
2025-03-21T20:31:43.8891838Z             aten_view_copy_default_148: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1834, [1, 1, 12, -1, 2]);  quantized_decomposed_dequantize_per_tensor_default_1834 = None
2025-03-21T20:31:43.8892761Z             quantized_decomposed_quantize_per_tensor_default_1331: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_148, 0.00042168446816504, 35651, 0, 65535, torch.int32);  aten_view_copy_default_148 = None
2025-03-21T20:31:43.8893893Z             quantized_decomposed_dequantize_per_tensor_default_1835: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1331, 0.00042168446816504, 35651, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1331 = None
2025-03-21T20:31:43.8894442Z             aten_slice_copy_tensor_34: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_1835, 4, 0, 1)
2025-03-21T20:31:43.8895228Z             aten_slice_copy_tensor_35: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_1835, 4, 1, 2);  quantized_decomposed_dequantize_per_tensor_default_1835 = None
2025-03-21T20:31:43.8895755Z             aten_squeeze_copy_dims_93: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_34, [4]);  aten_slice_copy_tensor_34 = None
2025-03-21T20:31:43.8896270Z             aten_squeeze_copy_dims_94: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_35, [4]);  aten_slice_copy_tensor_35 = None
2025-03-21T20:31:43.8897215Z             quantized_decomposed_quantize_per_tensor_default_1332: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_93, 0.0003787923196796328, 32268, 0, 65535, torch.int32);  aten_squeeze_copy_dims_93 = None
2025-03-21T20:31:43.8897307Z             
2025-03-21T20:31:43.8897794Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.8898705Z             quantized_decomposed_dequantize_per_tensor_default_1836: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1332, 0.0003787923196796328, 32268, 0, 65535, torch.int32)
2025-03-21T20:31:43.8898803Z             
2025-03-21T20:31:43.8899276Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.8900430Z             quantized_decomposed_dequantize_per_tensor_default_1837: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1332, 0.0003787923196796328, 32268, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1332 = None
2025-03-21T20:31:43.8900519Z             
2025-03-21T20:31:43.8901047Z              # File: /pytorch/executorch/examples/models/llama/rope.py:85 in apply_rotary_emb, code: xk_r, xk_i = xk.float().reshape(xk.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.8901953Z             quantized_decomposed_quantize_per_tensor_default_1333: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_94, 0.00038380088517442346, 39170, 0, 65535, torch.int32);  aten_squeeze_copy_dims_94 = None
2025-03-21T20:31:43.8902055Z             
2025-03-21T20:31:43.8902524Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.8903489Z             quantized_decomposed_dequantize_per_tensor_default_1838: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1333, 0.00038380088517442346, 39170, 0, 65535, torch.int32)
2025-03-21T20:31:43.8903594Z             
2025-03-21T20:31:43.8904057Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.8905217Z             quantized_decomposed_dequantize_per_tensor_default_1839: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1333, 0.00038380088517442346, 39170, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1333 = None
2025-03-21T20:31:43.8905304Z             
2025-03-21T20:31:43.8905754Z              # File: /pytorch/executorch/examples/models/llama/rope.py:78 in reshape_for_broadcast, code: return freqs_cis.view(shape)
2025-03-21T20:31:43.8906534Z             aten_view_copy_default_149: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_154, [1, 1, 1, 32]);  quantized_decomposed_dequantize_per_tensor_default_154 = None
2025-03-21T20:31:43.8907443Z             quantized_decomposed_quantize_per_tensor_default_1334: "i32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_149, 3.051804378628731e-05, 32768, 0, 65535, torch.int32);  aten_view_copy_default_149 = None
2025-03-21T20:31:43.8907528Z             
2025-03-21T20:31:43.8908030Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.8908943Z             quantized_decomposed_dequantize_per_tensor_default_1840: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1334, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.8909048Z             
2025-03-21T20:31:43.8909517Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.8910438Z             quantized_decomposed_dequantize_per_tensor_default_1841: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1334, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.8910527Z             
2025-03-21T20:31:43.8911004Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.8911917Z             quantized_decomposed_dequantize_per_tensor_default_1842: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1334, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.8912015Z             
2025-03-21T20:31:43.8912481Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.8913628Z             quantized_decomposed_dequantize_per_tensor_default_1843: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1334, 3.051804378628731e-05, 32768, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1334 = None
2025-03-21T20:31:43.8913730Z             
2025-03-21T20:31:43.8914208Z              # File: /pytorch/executorch/examples/models/llama/rope.py:78 in reshape_for_broadcast, code: return freqs_cis.view(shape)
2025-03-21T20:31:43.8915008Z             aten_view_copy_default_150: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_166, [1, 1, 1, 32]);  quantized_decomposed_dequantize_per_tensor_default_166 = None
2025-03-21T20:31:43.8915910Z             quantized_decomposed_quantize_per_tensor_default_1335: "i32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_150, 3.051786916330457e-05, 32767, 0, 65535, torch.int32);  aten_view_copy_default_150 = None
2025-03-21T20:31:43.8916007Z             
2025-03-21T20:31:43.8916476Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.8917402Z             quantized_decomposed_dequantize_per_tensor_default_1844: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1335, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.8917493Z             
2025-03-21T20:31:43.8918001Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.8918915Z             quantized_decomposed_dequantize_per_tensor_default_1845: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1335, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.8919016Z             
2025-03-21T20:31:43.8919487Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.8920438Z             quantized_decomposed_dequantize_per_tensor_default_1846: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1335, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.8920529Z             
2025-03-21T20:31:43.8921011Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.8922146Z             quantized_decomposed_dequantize_per_tensor_default_1847: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1335, 3.051786916330457e-05, 32767, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1335 = None
2025-03-21T20:31:43.8922250Z             
2025-03-21T20:31:43.8922717Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.8923857Z             aten_mul_tensor_122: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1831, quantized_decomposed_dequantize_per_tensor_default_1843);  quantized_decomposed_dequantize_per_tensor_default_1831 = quantized_decomposed_dequantize_per_tensor_default_1843 = None
2025-03-21T20:31:43.8924728Z             quantized_decomposed_quantize_per_tensor_default_1336: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_122, 0.00030949688516557217, 28792, 0, 65535, torch.int32);  aten_mul_tensor_122 = None
2025-03-21T20:31:43.8925887Z             quantized_decomposed_dequantize_per_tensor_default_1848: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1336, 0.00030949688516557217, 28792, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1336 = None
2025-03-21T20:31:43.8927065Z             aten_mul_tensor_123: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1832, quantized_decomposed_dequantize_per_tensor_default_1846);  quantized_decomposed_dequantize_per_tensor_default_1832 = quantized_decomposed_dequantize_per_tensor_default_1846 = None
2025-03-21T20:31:43.8927936Z             quantized_decomposed_quantize_per_tensor_default_1337: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_123, 0.00016250982298515737, 35603, 0, 65535, torch.int32);  aten_mul_tensor_123 = None
2025-03-21T20:31:43.8929076Z             quantized_decomposed_dequantize_per_tensor_default_1849: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1337, 0.00016250982298515737, 35603, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1337 = None
2025-03-21T20:31:43.8930357Z             aten_sub_tensor_16: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_sub_Tensor(quantized_decomposed_dequantize_per_tensor_default_1848, quantized_decomposed_dequantize_per_tensor_default_1849);  quantized_decomposed_dequantize_per_tensor_default_1848 = quantized_decomposed_dequantize_per_tensor_default_1849 = None
2025-03-21T20:31:43.8931207Z             quantized_decomposed_quantize_per_tensor_default_1338: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_sub_tensor_16, 0.0003078577865380794, 28618, 0, 65535, torch.int32);  aten_sub_tensor_16 = None
2025-03-21T20:31:43.8931307Z             
2025-03-21T20:31:43.8932439Z              # File: <eval_with_key>.50:4717 in forward, code: dequantize_per_tensor_default_1495 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1495, 0.0003078577865380794, 28618, 0, 65535, torch.int32);  quantize_per_tensor_default_1495 = None
2025-03-21T20:31:43.8933607Z             quantized_decomposed_dequantize_per_tensor_default_1850: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1338, 0.0003078577865380794, 28618, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1338 = None
2025-03-21T20:31:43.8933694Z             
2025-03-21T20:31:43.8934176Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.8935313Z             aten_mul_tensor_124: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1830, quantized_decomposed_dequantize_per_tensor_default_1847);  quantized_decomposed_dequantize_per_tensor_default_1830 = quantized_decomposed_dequantize_per_tensor_default_1847 = None
2025-03-21T20:31:43.8936188Z             quantized_decomposed_quantize_per_tensor_default_1339: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_124, 0.00012979988241568208, 32122, 0, 65535, torch.int32);  aten_mul_tensor_124 = None
2025-03-21T20:31:43.8937336Z             quantized_decomposed_dequantize_per_tensor_default_1851: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1339, 0.00012979988241568208, 32122, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1339 = None
2025-03-21T20:31:43.8938473Z             aten_mul_tensor_125: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1833, quantized_decomposed_dequantize_per_tensor_default_1842);  quantized_decomposed_dequantize_per_tensor_default_1833 = quantized_decomposed_dequantize_per_tensor_default_1842 = None
2025-03-21T20:31:43.8939432Z             quantized_decomposed_quantize_per_tensor_default_1340: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_125, 0.0003096680738963187, 32788, 0, 65535, torch.int32);  aten_mul_tensor_125 = None
2025-03-21T20:31:43.8940587Z             quantized_decomposed_dequantize_per_tensor_default_1852: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1340, 0.0003096680738963187, 32788, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1340 = None
2025-03-21T20:31:43.8941730Z             aten_add_tensor_40: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_1851, quantized_decomposed_dequantize_per_tensor_default_1852);  quantized_decomposed_dequantize_per_tensor_default_1851 = quantized_decomposed_dequantize_per_tensor_default_1852 = None
2025-03-21T20:31:43.8942615Z             quantized_decomposed_quantize_per_tensor_default_1341: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_40, 0.00031102492357604206, 32893, 0, 65535, torch.int32);  aten_add_tensor_40 = None
2025-03-21T20:31:43.8942719Z             
2025-03-21T20:31:43.8943659Z              # File: <eval_with_key>.50:4726 in forward, code: dequantize_per_tensor_default_1498 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1498, 0.00031102492357604206, 32893, 0, 65535, torch.int32);  quantize_per_tensor_default_1498 = None
2025-03-21T20:31:43.8944818Z             quantized_decomposed_dequantize_per_tensor_default_1853: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1341, 0.00031102492357604206, 32893, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1341 = None
2025-03-21T20:31:43.8944940Z             
2025-03-21T20:31:43.8945425Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.8946553Z             aten_mul_tensor_126: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1837, quantized_decomposed_dequantize_per_tensor_default_1841);  quantized_decomposed_dequantize_per_tensor_default_1837 = quantized_decomposed_dequantize_per_tensor_default_1841 = None
2025-03-21T20:31:43.8947419Z             quantized_decomposed_quantize_per_tensor_default_1342: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_126, 0.00037348963087424636, 32361, 0, 65535, torch.int32);  aten_mul_tensor_126 = None
2025-03-21T20:31:43.8948565Z             quantized_decomposed_dequantize_per_tensor_default_1854: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1342, 0.00037348963087424636, 32361, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1342 = None
2025-03-21T20:31:43.8949702Z             aten_mul_tensor_127: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1838, quantized_decomposed_dequantize_per_tensor_default_1844);  quantized_decomposed_dequantize_per_tensor_default_1838 = quantized_decomposed_dequantize_per_tensor_default_1844 = None
2025-03-21T20:31:43.8950555Z             quantized_decomposed_quantize_per_tensor_default_1343: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_127, 0.00014117307728156447, 32406, 0, 65535, torch.int32);  aten_mul_tensor_127 = None
2025-03-21T20:31:43.8951759Z             quantized_decomposed_dequantize_per_tensor_default_1855: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1343, 0.00014117307728156447, 32406, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1343 = None
2025-03-21T20:31:43.8952880Z             aten_sub_tensor_17: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_sub_Tensor(quantized_decomposed_dequantize_per_tensor_default_1854, quantized_decomposed_dequantize_per_tensor_default_1855);  quantized_decomposed_dequantize_per_tensor_default_1854 = quantized_decomposed_dequantize_per_tensor_default_1855 = None
2025-03-21T20:31:43.8953734Z             quantized_decomposed_quantize_per_tensor_default_1344: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_sub_tensor_17, 0.0003733103221748024, 32559, 0, 65535, torch.int32);  aten_sub_tensor_17 = None
2025-03-21T20:31:43.8953825Z             
2025-03-21T20:31:43.8954797Z              # File: <eval_with_key>.50:4735 in forward, code: dequantize_per_tensor_default_1501 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1501, 0.0003733103221748024, 32559, 0, 65535, torch.int32);  quantize_per_tensor_default_1501 = None
2025-03-21T20:31:43.8955936Z             quantized_decomposed_dequantize_per_tensor_default_1856: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1344, 0.0003733103221748024, 32559, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1344 = None
2025-03-21T20:31:43.8956034Z             
2025-03-21T20:31:43.8956542Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.8957682Z             aten_mul_tensor_128: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1836, quantized_decomposed_dequantize_per_tensor_default_1845);  quantized_decomposed_dequantize_per_tensor_default_1836 = quantized_decomposed_dequantize_per_tensor_default_1845 = None
2025-03-21T20:31:43.8958543Z             quantized_decomposed_quantize_per_tensor_default_1345: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_128, 0.00018785295833367854, 29230, 0, 65535, torch.int32);  aten_mul_tensor_128 = None
2025-03-21T20:31:43.8959700Z             quantized_decomposed_dequantize_per_tensor_default_1857: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1345, 0.00018785295833367854, 29230, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1345 = None
2025-03-21T20:31:43.8960846Z             aten_mul_tensor_129: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1839, quantized_decomposed_dequantize_per_tensor_default_1840);  quantized_decomposed_dequantize_per_tensor_default_1839 = quantized_decomposed_dequantize_per_tensor_default_1840 = None
2025-03-21T20:31:43.8961703Z             quantized_decomposed_quantize_per_tensor_default_1346: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_129, 0.00037025712663307786, 38747, 0, 65535, torch.int32);  aten_mul_tensor_129 = None
2025-03-21T20:31:43.8962856Z             quantized_decomposed_dequantize_per_tensor_default_1858: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1346, 0.00037025712663307786, 38747, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1346 = None
2025-03-21T20:31:43.8964027Z             aten_add_tensor_41: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_1857, quantized_decomposed_dequantize_per_tensor_default_1858);  quantized_decomposed_dequantize_per_tensor_default_1857 = quantized_decomposed_dequantize_per_tensor_default_1858 = None
2025-03-21T20:31:43.8964880Z             quantized_decomposed_quantize_per_tensor_default_1347: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_41, 0.0003686967247631401, 39138, 0, 65535, torch.int32);  aten_add_tensor_41 = None
2025-03-21T20:31:43.8964970Z             
2025-03-21T20:31:43.8965918Z              # File: <eval_with_key>.50:4744 in forward, code: dequantize_per_tensor_default_1504 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1504, 0.0003686967247631401, 39138, 0, 65535, torch.int32);  quantize_per_tensor_default_1504 = None
2025-03-21T20:31:43.8967092Z             quantized_decomposed_dequantize_per_tensor_default_1859: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1347, 0.0003686967247631401, 39138, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1347 = None
2025-03-21T20:31:43.8967191Z             
2025-03-21T20:31:43.8967713Z              # File: /pytorch/executorch/examples/models/llama/rope.py:95 in apply_rotary_emb, code: xq_out = torch.stack([xq_out_r, xq_out_i], dim=-1).flatten(3)
2025-03-21T20:31:43.8968521Z             aten_unsqueeze_copy_default_91: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1850, 4);  quantized_decomposed_dequantize_per_tensor_default_1850 = None
2025-03-21T20:31:43.8969405Z             aten_unsqueeze_copy_default_92: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1853, 4);  quantized_decomposed_dequantize_per_tensor_default_1853 = None
2025-03-21T20:31:43.8970159Z             aten_cat_default_32: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_cat_default([aten_unsqueeze_copy_default_91, aten_unsqueeze_copy_default_92], -1);  aten_unsqueeze_copy_default_91 = aten_unsqueeze_copy_default_92 = None
2025-03-21T20:31:43.8971016Z             quantized_decomposed_quantize_per_tensor_default_1348: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_32, 0.0003295276255812496, 31046, 0, 65535, torch.int32);  aten_cat_default_32 = None
2025-03-21T20:31:43.8972174Z             quantized_decomposed_dequantize_per_tensor_default_1860: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1348, 0.0003295276255812496, 31046, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1348 = None
2025-03-21T20:31:43.8972940Z             aten_view_copy_default_151: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1860, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_1860 = None
2025-03-21T20:31:43.8973853Z             quantized_decomposed_quantize_per_tensor_default_1349: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_151, 0.0003295276255812496, 31046, 0, 65535, torch.int32);  aten_view_copy_default_151 = None
2025-03-21T20:31:43.8973938Z             
2025-03-21T20:31:43.8974911Z              # File: <eval_with_key>.50:4750 in forward, code: dequantize_per_tensor_default_1506 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1506, 0.0003295276255812496, 31046, 0, 65535, torch.int32);  quantize_per_tensor_default_1506 = None
2025-03-21T20:31:43.8976080Z             quantized_decomposed_dequantize_per_tensor_default_1861: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1349, 0.0003295276255812496, 31046, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1349 = None
2025-03-21T20:31:43.8976175Z             
2025-03-21T20:31:43.8976692Z              # File: /pytorch/executorch/examples/models/llama/rope.py:96 in apply_rotary_emb, code: xk_out = torch.stack([xk_out_r, xk_out_i], dim=-1).flatten(3)
2025-03-21T20:31:43.8977497Z             aten_unsqueeze_copy_default_93: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1856, 4);  quantized_decomposed_dequantize_per_tensor_default_1856 = None
2025-03-21T20:31:43.8978291Z             aten_unsqueeze_copy_default_94: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1859, 4);  quantized_decomposed_dequantize_per_tensor_default_1859 = None
2025-03-21T20:31:43.8979060Z             aten_cat_default_33: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_cat_default([aten_unsqueeze_copy_default_93, aten_unsqueeze_copy_default_94], -1);  aten_unsqueeze_copy_default_93 = aten_unsqueeze_copy_default_94 = None
2025-03-21T20:31:43.8979915Z             quantized_decomposed_quantize_per_tensor_default_1350: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_33, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_cat_default_33 = None
2025-03-21T20:31:43.8981093Z             quantized_decomposed_dequantize_per_tensor_default_1862: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1350, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1350 = None
2025-03-21T20:31:43.8981867Z             aten_view_copy_default_152: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1862, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_1862 = None
2025-03-21T20:31:43.8982784Z             quantized_decomposed_quantize_per_tensor_default_1351: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_152, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_view_copy_default_152 = None
2025-03-21T20:31:43.8982878Z             
2025-03-21T20:31:43.8983823Z              # File: <eval_with_key>.50:4756 in forward, code: dequantize_per_tensor_default_1508 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1508, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantize_per_tensor_default_1508 = None
2025-03-21T20:31:43.8984966Z             quantized_decomposed_dequantize_per_tensor_default_1863: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1351, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1351 = None
2025-03-21T20:31:43.8985068Z             
2025-03-21T20:31:43.8985825Z              # File: <eval_with_key>.50:4758 in forward, code: quantize_per_tensor_default_1509 = torch.ops.quantized_decomposed.quantize_per_tensor.default(type_as_16, 0.0003295276255812496, 31046, 0, 65535, torch.int32);  type_as_16 = None
2025-03-21T20:31:43.8987017Z             quantized_decomposed_quantize_per_tensor_default_1352: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_1861, 0.0003295276255812496, 31046, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_1861 = None
2025-03-21T20:31:43.8987133Z             
2025-03-21T20:31:43.8987674Z              # File: /pytorch/executorch/examples/models/llama/attention.py:249 in forward, code: q = q.transpose(1, 2)  # (bs, n_local_heads, seqlen, head_dim)
2025-03-21T20:31:43.8988819Z             quantized_decomposed_dequantize_per_tensor_default_1864: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1352, 0.0003295276255812496, 31046, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1352 = None
2025-03-21T20:31:43.8988918Z             
2025-03-21T20:31:43.8989669Z              # File: <eval_with_key>.50:4761 in forward, code: quantize_per_tensor_default_1510 = torch.ops.quantized_decomposed.quantize_per_tensor.default(type_as_17, 0.000408027321100235, 35365, 0, 65535, torch.int32);  type_as_17 = None
2025-03-21T20:31:43.8990849Z             quantized_decomposed_quantize_per_tensor_default_1353: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_1863, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_1863 = None
2025-03-21T20:31:43.8990936Z             
2025-03-21T20:31:43.8991615Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:345 in update, code: k_out = torch.ops.aten.index_put_(self.past_k_caches, [None, input_pos], k_val)
2025-03-21T20:31:43.8992754Z             quantized_decomposed_dequantize_per_tensor_default_1865: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1353, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1353 = None
2025-03-21T20:31:43.8992927Z             
2025-03-21T20:31:43.8993531Z              # File: /pytorch/executorch/examples/models/llama/attention.py:249 in forward, code: q = q.transpose(1, 2)  # (bs, n_local_heads, seqlen, head_dim)
2025-03-21T20:31:43.8994344Z             aten_permute_copy_default_334: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1864, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1864 = None
2025-03-21T20:31:43.8995280Z             quantized_decomposed_quantize_per_tensor_default_1354: "i32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_334, 0.0003295276255812496, 31046, 0, 65535, torch.int32);  aten_permute_copy_default_334 = None
2025-03-21T20:31:43.8995385Z             
2025-03-21T20:31:43.8995960Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.8997120Z             quantized_decomposed_dequantize_per_tensor_default_1866: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1354, 0.0003295276255812496, 31046, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1354 = None
2025-03-21T20:31:43.8997210Z             
2025-03-21T20:31:43.8997892Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:345 in update, code: k_out = torch.ops.aten.index_put_(self.past_k_caches, [None, input_pos], k_val)
2025-03-21T20:31:43.8999217Z             aten_index_put_default_16: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_index_put_default(quantized_decomposed_dequantize_per_tensor_default_137, [None, attn_options_input_pos], quantized_decomposed_dequantize_per_tensor_default_1865);  quantized_decomposed_dequantize_per_tensor_default_137 = quantized_decomposed_dequantize_per_tensor_default_1865 = None
2025-03-21T20:31:43.9000164Z             quantized_decomposed_quantize_per_tensor_default_1355: "i32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_put_default_16, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_index_put_default_16 = None
2025-03-21T20:31:43.9000251Z             
2025-03-21T20:31:43.9001052Z              # File: <eval_with_key>.50:4768 in forward, code: dequantize_per_tensor_default_1512 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1512, 0.000408027321100235, 35365, 0, 65535, torch.int32)
2025-03-21T20:31:43.9001978Z             quantized_decomposed_dequantize_per_tensor_default_1867: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1355, 0.000408027321100235, 35365, 0, 65535, torch.int32)
2025-03-21T20:31:43.9002080Z             
2025-03-21T20:31:43.9002751Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9003682Z             quantized_decomposed_dequantize_per_tensor_default_1868: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1355, 0.000408027321100235, 35365, 0, 65535, torch.int32)
2025-03-21T20:31:43.9004598Z             quantized_decomposed_dequantize_per_tensor_default_1869: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1355, 0.000408027321100235, 35365, 0, 65535, torch.int32)
2025-03-21T20:31:43.9005554Z             quantized_decomposed_dequantize_per_tensor_default_1870: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1355, 0.000408027321100235, 35365, 0, 65535, torch.int32)
2025-03-21T20:31:43.9006465Z             quantized_decomposed_dequantize_per_tensor_default_1871: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1355, 0.000408027321100235, 35365, 0, 65535, torch.int32)
2025-03-21T20:31:43.9007393Z             quantized_decomposed_dequantize_per_tensor_default_1872: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1355, 0.000408027321100235, 35365, 0, 65535, torch.int32)
2025-03-21T20:31:43.9008310Z             quantized_decomposed_dequantize_per_tensor_default_1873: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1355, 0.000408027321100235, 35365, 0, 65535, torch.int32)
2025-03-21T20:31:43.9009238Z             quantized_decomposed_dequantize_per_tensor_default_1874: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1355, 0.000408027321100235, 35365, 0, 65535, torch.int32)
2025-03-21T20:31:43.9010247Z             quantized_decomposed_dequantize_per_tensor_default_1875: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1355, 0.000408027321100235, 35365, 0, 65535, torch.int32)
2025-03-21T20:31:43.9011210Z             quantized_decomposed_dequantize_per_tensor_default_1876: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1355, 0.000408027321100235, 35365, 0, 65535, torch.int32)
2025-03-21T20:31:43.9012148Z             quantized_decomposed_dequantize_per_tensor_default_1877: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1355, 0.000408027321100235, 35365, 0, 65535, torch.int32)
2025-03-21T20:31:43.9013075Z             quantized_decomposed_dequantize_per_tensor_default_1878: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1355, 0.000408027321100235, 35365, 0, 65535, torch.int32)
2025-03-21T20:31:43.9014233Z             quantized_decomposed_dequantize_per_tensor_default_1879: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1355, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1355 = None
2025-03-21T20:31:43.9014323Z             
2025-03-21T20:31:43.9015015Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:346 in update, code: v_out = torch.ops.aten.index_put_(self.past_v_caches, [None, input_pos], v_val)
2025-03-21T20:31:43.9016314Z             aten_index_put_default_17: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_index_put_default(quantized_decomposed_dequantize_per_tensor_default_138, [None, attn_options_input_pos], quantized_decomposed_dequantize_per_tensor_default_1827);  quantized_decomposed_dequantize_per_tensor_default_138 = quantized_decomposed_dequantize_per_tensor_default_1827 = None
2025-03-21T20:31:43.9017260Z             quantized_decomposed_quantize_per_tensor_default_1356: "i32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_put_default_17, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_index_put_default_17 = None
2025-03-21T20:31:43.9017350Z             
2025-03-21T20:31:43.9018140Z              # File: <eval_with_key>.50:4783 in forward, code: dequantize_per_tensor_default_1513 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1513, 0.0001714634709060192, 32914, 0, 65535, torch.int32)
2025-03-21T20:31:43.9019072Z             quantized_decomposed_dequantize_per_tensor_default_1880: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1356, 0.0001714634709060192, 32914, 0, 65535, torch.int32)
2025-03-21T20:31:43.9019159Z             
2025-03-21T20:31:43.9019810Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9020733Z             quantized_decomposed_dequantize_per_tensor_default_1881: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1356, 0.0001714634709060192, 32914, 0, 65535, torch.int32)
2025-03-21T20:31:43.9021665Z             quantized_decomposed_dequantize_per_tensor_default_1882: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1356, 0.0001714634709060192, 32914, 0, 65535, torch.int32)
2025-03-21T20:31:43.9022578Z             quantized_decomposed_dequantize_per_tensor_default_1883: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1356, 0.0001714634709060192, 32914, 0, 65535, torch.int32)
2025-03-21T20:31:43.9023530Z             quantized_decomposed_dequantize_per_tensor_default_1884: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1356, 0.0001714634709060192, 32914, 0, 65535, torch.int32)
2025-03-21T20:31:43.9024488Z             quantized_decomposed_dequantize_per_tensor_default_1885: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1356, 0.0001714634709060192, 32914, 0, 65535, torch.int32)
2025-03-21T20:31:43.9025400Z             quantized_decomposed_dequantize_per_tensor_default_1886: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1356, 0.0001714634709060192, 32914, 0, 65535, torch.int32)
2025-03-21T20:31:43.9026334Z             quantized_decomposed_dequantize_per_tensor_default_1887: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1356, 0.0001714634709060192, 32914, 0, 65535, torch.int32)
2025-03-21T20:31:43.9027279Z             quantized_decomposed_dequantize_per_tensor_default_1888: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1356, 0.0001714634709060192, 32914, 0, 65535, torch.int32)
2025-03-21T20:31:43.9028209Z             quantized_decomposed_dequantize_per_tensor_default_1889: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1356, 0.0001714634709060192, 32914, 0, 65535, torch.int32)
2025-03-21T20:31:43.9029127Z             quantized_decomposed_dequantize_per_tensor_default_1890: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1356, 0.0001714634709060192, 32914, 0, 65535, torch.int32)
2025-03-21T20:31:43.9030089Z             quantized_decomposed_dequantize_per_tensor_default_1891: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1356, 0.0001714634709060192, 32914, 0, 65535, torch.int32)
2025-03-21T20:31:43.9031234Z             quantized_decomposed_dequantize_per_tensor_default_1892: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1356, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1356 = None
2025-03-21T20:31:43.9031335Z             
2025-03-21T20:31:43.9031968Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9032994Z             aten_permute_copy_default_335: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1879, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1879 = None
2025-03-21T20:31:43.9033941Z             quantized_decomposed_quantize_per_tensor_default_1357: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_335, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_permute_copy_default_335 = None
2025-03-21T20:31:43.9035098Z             quantized_decomposed_dequantize_per_tensor_default_1893: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1357, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1357 = None
2025-03-21T20:31:43.9035904Z             aten_select_copy_int_384: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1893, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1893 = None
2025-03-21T20:31:43.9036846Z             quantized_decomposed_quantize_per_tensor_default_1358: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_384, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_select_copy_int_384 = None
2025-03-21T20:31:43.9037988Z             quantized_decomposed_dequantize_per_tensor_default_1894: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1358, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1358 = None
2025-03-21T20:31:43.9038740Z             aten_select_copy_int_385: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1894, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1894 = None
2025-03-21T20:31:43.9039691Z             quantized_decomposed_quantize_per_tensor_default_1359: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_385, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_select_copy_int_385 = None
2025-03-21T20:31:43.9039778Z             
2025-03-21T20:31:43.9040710Z              # File: <eval_with_key>.50:4804 in forward, code: dequantize_per_tensor_default_1516 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1516, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantize_per_tensor_default_1516 = None
2025-03-21T20:31:43.9041899Z             quantized_decomposed_dequantize_per_tensor_default_1895: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1359, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1359 = None
2025-03-21T20:31:43.9042002Z             
2025-03-21T20:31:43.9042643Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9043443Z             aten_permute_copy_default_336: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1878, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1878 = None
2025-03-21T20:31:43.9044395Z             quantized_decomposed_quantize_per_tensor_default_1360: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_336, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_permute_copy_default_336 = None
2025-03-21T20:31:43.9045565Z             quantized_decomposed_dequantize_per_tensor_default_1896: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1360, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1360 = None
2025-03-21T20:31:43.9046306Z             aten_select_copy_int_386: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1896, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1896 = None
2025-03-21T20:31:43.9047210Z             quantized_decomposed_quantize_per_tensor_default_1361: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_386, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_select_copy_int_386 = None
2025-03-21T20:31:43.9048413Z             quantized_decomposed_dequantize_per_tensor_default_1897: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1361, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1361 = None
2025-03-21T20:31:43.9049199Z             aten_select_copy_int_387: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1897, 0, 1);  quantized_decomposed_dequantize_per_tensor_default_1897 = None
2025-03-21T20:31:43.9050145Z             quantized_decomposed_quantize_per_tensor_default_1362: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_387, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_select_copy_int_387 = None
2025-03-21T20:31:43.9050257Z             
2025-03-21T20:31:43.9051192Z              # File: <eval_with_key>.50:4813 in forward, code: dequantize_per_tensor_default_1519 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1519, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantize_per_tensor_default_1519 = None
2025-03-21T20:31:43.9052380Z             quantized_decomposed_dequantize_per_tensor_default_1898: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1362, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1362 = None
2025-03-21T20:31:43.9052470Z             
2025-03-21T20:31:43.9053120Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9053950Z             aten_permute_copy_default_337: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1877, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1877 = None
2025-03-21T20:31:43.9054904Z             quantized_decomposed_quantize_per_tensor_default_1363: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_337, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_permute_copy_default_337 = None
2025-03-21T20:31:43.9056050Z             quantized_decomposed_dequantize_per_tensor_default_1899: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1363, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1363 = None
2025-03-21T20:31:43.9056809Z             aten_select_copy_int_388: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1899, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1899 = None
2025-03-21T20:31:43.9057706Z             quantized_decomposed_quantize_per_tensor_default_1364: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_388, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_select_copy_int_388 = None
2025-03-21T20:31:43.9058865Z             quantized_decomposed_dequantize_per_tensor_default_1900: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1364, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1364 = None
2025-03-21T20:31:43.9059600Z             aten_select_copy_int_389: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1900, 0, 2);  quantized_decomposed_dequantize_per_tensor_default_1900 = None
2025-03-21T20:31:43.9060562Z             quantized_decomposed_quantize_per_tensor_default_1365: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_389, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_select_copy_int_389 = None
2025-03-21T20:31:43.9060654Z             
2025-03-21T20:31:43.9061603Z              # File: <eval_with_key>.50:4822 in forward, code: dequantize_per_tensor_default_1522 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1522, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantize_per_tensor_default_1522 = None
2025-03-21T20:31:43.9062741Z             quantized_decomposed_dequantize_per_tensor_default_1901: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1365, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1365 = None
2025-03-21T20:31:43.9062853Z             
2025-03-21T20:31:43.9063513Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9064328Z             aten_permute_copy_default_338: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1876, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1876 = None
2025-03-21T20:31:43.9065263Z             quantized_decomposed_quantize_per_tensor_default_1366: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_338, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_permute_copy_default_338 = None
2025-03-21T20:31:43.9066450Z             quantized_decomposed_dequantize_per_tensor_default_1902: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1366, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1366 = None
2025-03-21T20:31:43.9067193Z             aten_select_copy_int_390: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1902, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1902 = None
2025-03-21T20:31:43.9068093Z             quantized_decomposed_quantize_per_tensor_default_1367: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_390, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_select_copy_int_390 = None
2025-03-21T20:31:43.9069250Z             quantized_decomposed_dequantize_per_tensor_default_1903: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1367, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1367 = None
2025-03-21T20:31:43.9069985Z             aten_select_copy_int_391: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1903, 0, 3);  quantized_decomposed_dequantize_per_tensor_default_1903 = None
2025-03-21T20:31:43.9070883Z             quantized_decomposed_quantize_per_tensor_default_1368: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_391, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_select_copy_int_391 = None
2025-03-21T20:31:43.9070977Z             
2025-03-21T20:31:43.9071945Z              # File: <eval_with_key>.50:4831 in forward, code: dequantize_per_tensor_default_1525 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1525, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantize_per_tensor_default_1525 = None
2025-03-21T20:31:43.9073112Z             quantized_decomposed_dequantize_per_tensor_default_1904: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1368, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1368 = None
2025-03-21T20:31:43.9073211Z             
2025-03-21T20:31:43.9073843Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9074654Z             aten_permute_copy_default_339: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1875, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1875 = None
2025-03-21T20:31:43.9075613Z             quantized_decomposed_quantize_per_tensor_default_1369: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_339, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_permute_copy_default_339 = None
2025-03-21T20:31:43.9076769Z             quantized_decomposed_dequantize_per_tensor_default_1905: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1369, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1369 = None
2025-03-21T20:31:43.9077511Z             aten_select_copy_int_392: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1905, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1905 = None
2025-03-21T20:31:43.9078442Z             quantized_decomposed_quantize_per_tensor_default_1370: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_392, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_select_copy_int_392 = None
2025-03-21T20:31:43.9079586Z             quantized_decomposed_dequantize_per_tensor_default_1906: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1370, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1370 = None
2025-03-21T20:31:43.9080331Z             aten_select_copy_int_393: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1906, 0, 4);  quantized_decomposed_dequantize_per_tensor_default_1906 = None
2025-03-21T20:31:43.9081220Z             quantized_decomposed_quantize_per_tensor_default_1371: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_393, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_select_copy_int_393 = None
2025-03-21T20:31:43.9081320Z             
2025-03-21T20:31:43.9082253Z              # File: <eval_with_key>.50:4840 in forward, code: dequantize_per_tensor_default_1528 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1528, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantize_per_tensor_default_1528 = None
2025-03-21T20:31:43.9083404Z             quantized_decomposed_dequantize_per_tensor_default_1907: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1371, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1371 = None
2025-03-21T20:31:43.9083496Z             
2025-03-21T20:31:43.9084274Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9085108Z             aten_permute_copy_default_340: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1874, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1874 = None
2025-03-21T20:31:43.9086060Z             quantized_decomposed_quantize_per_tensor_default_1372: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_340, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_permute_copy_default_340 = None
2025-03-21T20:31:43.9087209Z             quantized_decomposed_dequantize_per_tensor_default_1908: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1372, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1372 = None
2025-03-21T20:31:43.9087994Z             aten_select_copy_int_394: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1908, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1908 = None
2025-03-21T20:31:43.9088888Z             quantized_decomposed_quantize_per_tensor_default_1373: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_394, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_select_copy_int_394 = None
2025-03-21T20:31:43.9090109Z             quantized_decomposed_dequantize_per_tensor_default_1909: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1373, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1373 = None
2025-03-21T20:31:43.9090883Z             aten_select_copy_int_395: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1909, 0, 5);  quantized_decomposed_dequantize_per_tensor_default_1909 = None
2025-03-21T20:31:43.9091790Z             quantized_decomposed_quantize_per_tensor_default_1374: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_395, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_select_copy_int_395 = None
2025-03-21T20:31:43.9091878Z             
2025-03-21T20:31:43.9092824Z              # File: <eval_with_key>.50:4849 in forward, code: dequantize_per_tensor_default_1531 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1531, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantize_per_tensor_default_1531 = None
2025-03-21T20:31:43.9093976Z             quantized_decomposed_dequantize_per_tensor_default_1910: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1374, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1374 = None
2025-03-21T20:31:43.9094076Z             
2025-03-21T20:31:43.9094954Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9095783Z             aten_permute_copy_default_341: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1873, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1873 = None
2025-03-21T20:31:43.9096780Z             quantized_decomposed_quantize_per_tensor_default_1375: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_341, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_permute_copy_default_341 = None
2025-03-21T20:31:43.9097967Z             quantized_decomposed_dequantize_per_tensor_default_1911: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1375, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1375 = None
2025-03-21T20:31:43.9098720Z             aten_select_copy_int_396: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1911, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1911 = None
2025-03-21T20:31:43.9099615Z             quantized_decomposed_quantize_per_tensor_default_1376: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_396, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_select_copy_int_396 = None
2025-03-21T20:31:43.9100796Z             quantized_decomposed_dequantize_per_tensor_default_1912: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1376, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1376 = None
2025-03-21T20:31:43.9101536Z             aten_select_copy_int_397: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1912, 0, 6);  quantized_decomposed_dequantize_per_tensor_default_1912 = None
2025-03-21T20:31:43.9102463Z             quantized_decomposed_quantize_per_tensor_default_1377: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_397, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_select_copy_int_397 = None
2025-03-21T20:31:43.9102553Z             
2025-03-21T20:31:43.9103494Z              # File: <eval_with_key>.50:4858 in forward, code: dequantize_per_tensor_default_1534 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1534, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantize_per_tensor_default_1534 = None
2025-03-21T20:31:43.9104634Z             quantized_decomposed_dequantize_per_tensor_default_1913: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1377, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1377 = None
2025-03-21T20:31:43.9104738Z             
2025-03-21T20:31:43.9105375Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9106193Z             aten_permute_copy_default_342: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1872, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1872 = None
2025-03-21T20:31:43.9107130Z             quantized_decomposed_quantize_per_tensor_default_1378: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_342, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_permute_copy_default_342 = None
2025-03-21T20:31:43.9108283Z             quantized_decomposed_dequantize_per_tensor_default_1914: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1378, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1378 = None
2025-03-21T20:31:43.9109078Z             aten_select_copy_int_398: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1914, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1914 = None
2025-03-21T20:31:43.9109984Z             quantized_decomposed_quantize_per_tensor_default_1379: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_398, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_select_copy_int_398 = None
2025-03-21T20:31:43.9111124Z             quantized_decomposed_dequantize_per_tensor_default_1915: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1379, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1379 = None
2025-03-21T20:31:43.9111872Z             aten_select_copy_int_399: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1915, 0, 7);  quantized_decomposed_dequantize_per_tensor_default_1915 = None
2025-03-21T20:31:43.9112788Z             quantized_decomposed_quantize_per_tensor_default_1380: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_399, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_select_copy_int_399 = None
2025-03-21T20:31:43.9112890Z             
2025-03-21T20:31:43.9113822Z              # File: <eval_with_key>.50:4867 in forward, code: dequantize_per_tensor_default_1537 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1537, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantize_per_tensor_default_1537 = None
2025-03-21T20:31:43.9114997Z             quantized_decomposed_dequantize_per_tensor_default_1916: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1380, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1380 = None
2025-03-21T20:31:43.9115087Z             
2025-03-21T20:31:43.9115735Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9116533Z             aten_permute_copy_default_343: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1871, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1871 = None
2025-03-21T20:31:43.9117479Z             quantized_decomposed_quantize_per_tensor_default_1381: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_343, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_permute_copy_default_343 = None
2025-03-21T20:31:43.9118620Z             quantized_decomposed_dequantize_per_tensor_default_1917: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1381, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1381 = None
2025-03-21T20:31:43.9119373Z             aten_select_copy_int_400: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1917, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1917 = None
2025-03-21T20:31:43.9120259Z             quantized_decomposed_quantize_per_tensor_default_1382: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_400, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_select_copy_int_400 = None
2025-03-21T20:31:43.9121469Z             quantized_decomposed_dequantize_per_tensor_default_1918: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1382, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1382 = None
2025-03-21T20:31:43.9122220Z             aten_select_copy_int_401: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1918, 0, 8);  quantized_decomposed_dequantize_per_tensor_default_1918 = None
2025-03-21T20:31:43.9123104Z             quantized_decomposed_quantize_per_tensor_default_1383: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_401, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_select_copy_int_401 = None
2025-03-21T20:31:43.9123194Z             
2025-03-21T20:31:43.9124171Z              # File: <eval_with_key>.50:4876 in forward, code: dequantize_per_tensor_default_1540 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1540, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantize_per_tensor_default_1540 = None
2025-03-21T20:31:43.9125325Z             quantized_decomposed_dequantize_per_tensor_default_1919: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1383, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1383 = None
2025-03-21T20:31:43.9125416Z             
2025-03-21T20:31:43.9126052Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9126891Z             aten_permute_copy_default_344: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1870, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1870 = None
2025-03-21T20:31:43.9127827Z             quantized_decomposed_quantize_per_tensor_default_1384: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_344, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_permute_copy_default_344 = None
2025-03-21T20:31:43.9128983Z             quantized_decomposed_dequantize_per_tensor_default_1920: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1384, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1384 = None
2025-03-21T20:31:43.9129810Z             aten_select_copy_int_402: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1920, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1920 = None
2025-03-21T20:31:43.9130710Z             quantized_decomposed_quantize_per_tensor_default_1385: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_402, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_select_copy_int_402 = None
2025-03-21T20:31:43.9131865Z             quantized_decomposed_dequantize_per_tensor_default_1921: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1385, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1385 = None
2025-03-21T20:31:43.9132844Z             aten_select_copy_int_403: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1921, 0, 9);  quantized_decomposed_dequantize_per_tensor_default_1921 = None
2025-03-21T20:31:43.9133784Z             quantized_decomposed_quantize_per_tensor_default_1386: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_403, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_select_copy_int_403 = None
2025-03-21T20:31:43.9133872Z             
2025-03-21T20:31:43.9134817Z              # File: <eval_with_key>.50:4885 in forward, code: dequantize_per_tensor_default_1543 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1543, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantize_per_tensor_default_1543 = None
2025-03-21T20:31:43.9135955Z             quantized_decomposed_dequantize_per_tensor_default_1922: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1386, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1386 = None
2025-03-21T20:31:43.9136062Z             
2025-03-21T20:31:43.9136739Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9137551Z             aten_permute_copy_default_345: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1869, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1869 = None
2025-03-21T20:31:43.9138487Z             quantized_decomposed_quantize_per_tensor_default_1387: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_345, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_permute_copy_default_345 = None
2025-03-21T20:31:43.9139699Z             quantized_decomposed_dequantize_per_tensor_default_1923: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1387, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1387 = None
2025-03-21T20:31:43.9140438Z             aten_select_copy_int_404: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1923, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1923 = None
2025-03-21T20:31:43.9141339Z             quantized_decomposed_quantize_per_tensor_default_1388: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_404, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_select_copy_int_404 = None
2025-03-21T20:31:43.9142486Z             quantized_decomposed_dequantize_per_tensor_default_1924: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1388, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1388 = None
2025-03-21T20:31:43.9143238Z             aten_select_copy_int_405: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1924, 0, 10);  quantized_decomposed_dequantize_per_tensor_default_1924 = None
2025-03-21T20:31:43.9144124Z             quantized_decomposed_quantize_per_tensor_default_1389: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_405, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_select_copy_int_405 = None
2025-03-21T20:31:43.9144223Z             
2025-03-21T20:31:43.9145178Z              # File: <eval_with_key>.50:4894 in forward, code: dequantize_per_tensor_default_1546 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1546, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantize_per_tensor_default_1546 = None
2025-03-21T20:31:43.9146352Z             quantized_decomposed_dequantize_per_tensor_default_1925: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1389, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1389 = None
2025-03-21T20:31:43.9146441Z             
2025-03-21T20:31:43.9147095Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9147900Z             aten_permute_copy_default_346: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1868, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1868 = None
2025-03-21T20:31:43.9148866Z             quantized_decomposed_quantize_per_tensor_default_1390: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_346, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_permute_copy_default_346 = None
2025-03-21T20:31:43.9150012Z             quantized_decomposed_dequantize_per_tensor_default_1926: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1390, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1390 = None
2025-03-21T20:31:43.9150789Z             aten_select_copy_int_406: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1926, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1926 = None
2025-03-21T20:31:43.9151684Z             quantized_decomposed_quantize_per_tensor_default_1391: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_406, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_select_copy_int_406 = None
2025-03-21T20:31:43.9152841Z             quantized_decomposed_dequantize_per_tensor_default_1927: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1391, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1391 = None
2025-03-21T20:31:43.9153590Z             aten_select_copy_int_407: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1927, 0, 11);  quantized_decomposed_dequantize_per_tensor_default_1927 = None
2025-03-21T20:31:43.9154481Z             quantized_decomposed_quantize_per_tensor_default_1392: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_407, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_select_copy_int_407 = None
2025-03-21T20:31:43.9154579Z             
2025-03-21T20:31:43.9155512Z              # File: <eval_with_key>.50:4903 in forward, code: dequantize_per_tensor_default_1549 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1549, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantize_per_tensor_default_1549 = None
2025-03-21T20:31:43.9156659Z             quantized_decomposed_dequantize_per_tensor_default_1928: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1392, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1392 = None
2025-03-21T20:31:43.9156781Z             
2025-03-21T20:31:43.9157441Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9162952Z             aten_cat_default_34: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_aten_cat_default([quantized_decomposed_dequantize_per_tensor_default_1895, quantized_decomposed_dequantize_per_tensor_default_1898, quantized_decomposed_dequantize_per_tensor_default_1901, quantized_decomposed_dequantize_per_tensor_default_1904, quantized_decomposed_dequantize_per_tensor_default_1907, quantized_decomposed_dequantize_per_tensor_default_1910, quantized_decomposed_dequantize_per_tensor_default_1913, quantized_decomposed_dequantize_per_tensor_default_1916, quantized_decomposed_dequantize_per_tensor_default_1919, quantized_decomposed_dequantize_per_tensor_default_1922, quantized_decomposed_dequantize_per_tensor_default_1925, quantized_decomposed_dequantize_per_tensor_default_1928]);  quantized_decomposed_dequantize_per_tensor_default_1895 = quantized_decomposed_dequantize_per_tensor_default_1898 = quantized_decomposed_dequantize_per_tensor_default_1901 = quantized_decomposed_dequantize_per_tensor_default_1904 = quantized_decomposed_dequantize_per_tensor_default_1907 = quantized_decomposed_dequantize_per_tensor_default_1910 = quantized_decomposed_dequantize_per_tensor_default_1913 = quantized_decomposed_dequantize_per_tensor_default_1916 = quantized_decomposed_dequantize_per_tensor_default_1919 = quantized_decomposed_dequantize_per_tensor_default_1922 = quantized_decomposed_dequantize_per_tensor_default_1925 = quantized_decomposed_dequantize_per_tensor_default_1928 = None
2025-03-21T20:31:43.9163834Z             quantized_decomposed_quantize_per_tensor_default_1393: "i32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_34, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_cat_default_34 = None
2025-03-21T20:31:43.9165022Z             quantized_decomposed_dequantize_per_tensor_default_1929: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1393, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1393 = None
2025-03-21T20:31:43.9165806Z             aten_view_copy_default_153: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1929, [1, 12, 128, 64]);  quantized_decomposed_dequantize_per_tensor_default_1929 = None
2025-03-21T20:31:43.9166724Z             quantized_decomposed_quantize_per_tensor_default_1394: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_153, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_view_copy_default_153 = None
2025-03-21T20:31:43.9166817Z             
2025-03-21T20:31:43.9167413Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.9168561Z             quantized_decomposed_dequantize_per_tensor_default_1930: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1394, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1394 = None
2025-03-21T20:31:43.9168661Z             
2025-03-21T20:31:43.9169353Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9170208Z             aten_permute_copy_default_347: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1892, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1892 = None
2025-03-21T20:31:43.9171179Z             quantized_decomposed_quantize_per_tensor_default_1395: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_347, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_permute_copy_default_347 = None
2025-03-21T20:31:43.9172345Z             quantized_decomposed_dequantize_per_tensor_default_1931: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1395, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1395 = None
2025-03-21T20:31:43.9173084Z             aten_select_copy_int_408: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1931, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1931 = None
2025-03-21T20:31:43.9174017Z             quantized_decomposed_quantize_per_tensor_default_1396: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_408, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_select_copy_int_408 = None
2025-03-21T20:31:43.9175162Z             quantized_decomposed_dequantize_per_tensor_default_1932: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1396, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1396 = None
2025-03-21T20:31:43.9175913Z             aten_select_copy_int_409: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1932, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1932 = None
2025-03-21T20:31:43.9176836Z             quantized_decomposed_quantize_per_tensor_default_1397: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_409, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_select_copy_int_409 = None
2025-03-21T20:31:43.9176939Z             
2025-03-21T20:31:43.9177875Z              # File: <eval_with_key>.50:4918 in forward, code: dequantize_per_tensor_default_1554 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1554, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantize_per_tensor_default_1554 = None
2025-03-21T20:31:43.9179030Z             quantized_decomposed_dequantize_per_tensor_default_1933: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1397, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1397 = None
2025-03-21T20:31:43.9179124Z             
2025-03-21T20:31:43.9179774Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9180577Z             aten_permute_copy_default_348: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1891, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1891 = None
2025-03-21T20:31:43.9181526Z             quantized_decomposed_quantize_per_tensor_default_1398: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_348, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_permute_copy_default_348 = None
2025-03-21T20:31:43.9182712Z             quantized_decomposed_dequantize_per_tensor_default_1934: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1398, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1398 = None
2025-03-21T20:31:43.9183491Z             aten_select_copy_int_410: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1934, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1934 = None
2025-03-21T20:31:43.9184385Z             quantized_decomposed_quantize_per_tensor_default_1399: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_410, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_select_copy_int_410 = None
2025-03-21T20:31:43.9185548Z             quantized_decomposed_dequantize_per_tensor_default_1935: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1399, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1399 = None
2025-03-21T20:31:43.9186333Z             aten_select_copy_int_411: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1935, 0, 1);  quantized_decomposed_dequantize_per_tensor_default_1935 = None
2025-03-21T20:31:43.9187222Z             quantized_decomposed_quantize_per_tensor_default_1400: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_411, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_select_copy_int_411 = None
2025-03-21T20:31:43.9187350Z             
2025-03-21T20:31:43.9188289Z              # File: <eval_with_key>.50:4927 in forward, code: dequantize_per_tensor_default_1557 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1557, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantize_per_tensor_default_1557 = None
2025-03-21T20:31:43.9189455Z             quantized_decomposed_dequantize_per_tensor_default_1936: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1400, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1400 = None
2025-03-21T20:31:43.9189548Z             
2025-03-21T20:31:43.9190188Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9191007Z             aten_permute_copy_default_349: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1890, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1890 = None
2025-03-21T20:31:43.9191971Z             quantized_decomposed_quantize_per_tensor_default_1401: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_349, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_permute_copy_default_349 = None
2025-03-21T20:31:43.9193133Z             quantized_decomposed_dequantize_per_tensor_default_1937: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1401, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1401 = None
2025-03-21T20:31:43.9193890Z             aten_select_copy_int_412: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1937, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1937 = None
2025-03-21T20:31:43.9194844Z             quantized_decomposed_quantize_per_tensor_default_1402: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_412, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_select_copy_int_412 = None
2025-03-21T20:31:43.9196010Z             quantized_decomposed_dequantize_per_tensor_default_1938: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1402, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1402 = None
2025-03-21T20:31:43.9196883Z             aten_select_copy_int_413: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1938, 0, 2);  quantized_decomposed_dequantize_per_tensor_default_1938 = None
2025-03-21T20:31:43.9197800Z             quantized_decomposed_quantize_per_tensor_default_1403: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_413, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_select_copy_int_413 = None
2025-03-21T20:31:43.9197924Z             
2025-03-21T20:31:43.9198875Z              # File: <eval_with_key>.50:4936 in forward, code: dequantize_per_tensor_default_1560 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1560, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantize_per_tensor_default_1560 = None
2025-03-21T20:31:43.9200028Z             quantized_decomposed_dequantize_per_tensor_default_1939: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1403, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1403 = None
2025-03-21T20:31:43.9200158Z             
2025-03-21T20:31:43.9200798Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9201617Z             aten_permute_copy_default_350: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1889, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1889 = None
2025-03-21T20:31:43.9202556Z             quantized_decomposed_quantize_per_tensor_default_1404: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_350, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_permute_copy_default_350 = None
2025-03-21T20:31:43.9203722Z             quantized_decomposed_dequantize_per_tensor_default_1940: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1404, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1404 = None
2025-03-21T20:31:43.9204466Z             aten_select_copy_int_414: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1940, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1940 = None
2025-03-21T20:31:43.9205374Z             quantized_decomposed_quantize_per_tensor_default_1405: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_414, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_select_copy_int_414 = None
2025-03-21T20:31:43.9206556Z             quantized_decomposed_dequantize_per_tensor_default_1941: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1405, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1405 = None
2025-03-21T20:31:43.9207336Z             aten_select_copy_int_415: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1941, 0, 3);  quantized_decomposed_dequantize_per_tensor_default_1941 = None
2025-03-21T20:31:43.9208224Z             quantized_decomposed_quantize_per_tensor_default_1406: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_415, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_select_copy_int_415 = None
2025-03-21T20:31:43.9208323Z             
2025-03-21T20:31:43.9209311Z              # File: <eval_with_key>.50:4945 in forward, code: dequantize_per_tensor_default_1563 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1563, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantize_per_tensor_default_1563 = None
2025-03-21T20:31:43.9210523Z             quantized_decomposed_dequantize_per_tensor_default_1942: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1406, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1406 = None
2025-03-21T20:31:43.9210611Z             
2025-03-21T20:31:43.9211260Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9212060Z             aten_permute_copy_default_351: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1888, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1888 = None
2025-03-21T20:31:43.9213039Z             quantized_decomposed_quantize_per_tensor_default_1407: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_351, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_permute_copy_default_351 = None
2025-03-21T20:31:43.9214186Z             quantized_decomposed_dequantize_per_tensor_default_1943: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1407, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1407 = None
2025-03-21T20:31:43.9214938Z             aten_select_copy_int_416: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1943, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1943 = None
2025-03-21T20:31:43.9215854Z             quantized_decomposed_quantize_per_tensor_default_1408: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_416, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_select_copy_int_416 = None
2025-03-21T20:31:43.9217002Z             quantized_decomposed_dequantize_per_tensor_default_1944: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1408, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1408 = None
2025-03-21T20:31:43.9217747Z             aten_select_copy_int_417: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1944, 0, 4);  quantized_decomposed_dequantize_per_tensor_default_1944 = None
2025-03-21T20:31:43.9218666Z             quantized_decomposed_quantize_per_tensor_default_1409: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_417, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_select_copy_int_417 = None
2025-03-21T20:31:43.9218789Z             
2025-03-21T20:31:43.9219723Z              # File: <eval_with_key>.50:4954 in forward, code: dequantize_per_tensor_default_1566 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1566, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantize_per_tensor_default_1566 = None
2025-03-21T20:31:43.9220873Z             quantized_decomposed_dequantize_per_tensor_default_1945: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1409, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1409 = None
2025-03-21T20:31:43.9220962Z             
2025-03-21T20:31:43.9221612Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9222441Z             aten_permute_copy_default_352: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1887, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1887 = None
2025-03-21T20:31:43.9223393Z             quantized_decomposed_quantize_per_tensor_default_1410: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_352, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_permute_copy_default_352 = None
2025-03-21T20:31:43.9224539Z             quantized_decomposed_dequantize_per_tensor_default_1946: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1410, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1410 = None
2025-03-21T20:31:43.9225321Z             aten_select_copy_int_418: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1946, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1946 = None
2025-03-21T20:31:43.9226211Z             quantized_decomposed_quantize_per_tensor_default_1411: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_418, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_select_copy_int_418 = None
2025-03-21T20:31:43.9227373Z             quantized_decomposed_dequantize_per_tensor_default_1947: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1411, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1411 = None
2025-03-21T20:31:43.9228116Z             aten_select_copy_int_419: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1947, 0, 5);  quantized_decomposed_dequantize_per_tensor_default_1947 = None
2025-03-21T20:31:43.9229018Z             quantized_decomposed_quantize_per_tensor_default_1412: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_419, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_select_copy_int_419 = None
2025-03-21T20:31:43.9229105Z             
2025-03-21T20:31:43.9230055Z              # File: <eval_with_key>.50:4963 in forward, code: dequantize_per_tensor_default_1569 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1569, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantize_per_tensor_default_1569 = None
2025-03-21T20:31:43.9231231Z             quantized_decomposed_dequantize_per_tensor_default_1948: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1412, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1412 = None
2025-03-21T20:31:43.9231367Z             
2025-03-21T20:31:43.9232001Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9233000Z             aten_permute_copy_default_353: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1886, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1886 = None
2025-03-21T20:31:43.9233948Z             quantized_decomposed_quantize_per_tensor_default_1413: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_353, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_permute_copy_default_353 = None
2025-03-21T20:31:43.9235176Z             quantized_decomposed_dequantize_per_tensor_default_1949: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1413, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1413 = None
2025-03-21T20:31:43.9235919Z             aten_select_copy_int_420: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1949, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1949 = None
2025-03-21T20:31:43.9236900Z             quantized_decomposed_quantize_per_tensor_default_1414: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_420, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_select_copy_int_420 = None
2025-03-21T20:31:43.9238048Z             quantized_decomposed_dequantize_per_tensor_default_1950: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1414, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1414 = None
2025-03-21T20:31:43.9238797Z             aten_select_copy_int_421: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1950, 0, 6);  quantized_decomposed_dequantize_per_tensor_default_1950 = None
2025-03-21T20:31:43.9239699Z             quantized_decomposed_quantize_per_tensor_default_1415: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_421, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_select_copy_int_421 = None
2025-03-21T20:31:43.9239794Z             
2025-03-21T20:31:43.9240735Z              # File: <eval_with_key>.50:4972 in forward, code: dequantize_per_tensor_default_1572 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1572, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantize_per_tensor_default_1572 = None
2025-03-21T20:31:43.9241890Z             quantized_decomposed_dequantize_per_tensor_default_1951: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1415, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1415 = None
2025-03-21T20:31:43.9241993Z             
2025-03-21T20:31:43.9242633Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9243478Z             aten_permute_copy_default_354: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1885, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1885 = None
2025-03-21T20:31:43.9244460Z             quantized_decomposed_quantize_per_tensor_default_1416: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_354, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_permute_copy_default_354 = None
2025-03-21T20:31:43.9245619Z             quantized_decomposed_dequantize_per_tensor_default_1952: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1416, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1416 = None
2025-03-21T20:31:43.9246362Z             aten_select_copy_int_422: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1952, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1952 = None
2025-03-21T20:31:43.9247292Z             quantized_decomposed_quantize_per_tensor_default_1417: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_422, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_select_copy_int_422 = None
2025-03-21T20:31:43.9248441Z             quantized_decomposed_dequantize_per_tensor_default_1953: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1417, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1417 = None
2025-03-21T20:31:43.9249220Z             aten_select_copy_int_423: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1953, 0, 7);  quantized_decomposed_dequantize_per_tensor_default_1953 = None
2025-03-21T20:31:43.9250178Z             quantized_decomposed_quantize_per_tensor_default_1418: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_423, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_select_copy_int_423 = None
2025-03-21T20:31:43.9250285Z             
2025-03-21T20:31:43.9251220Z              # File: <eval_with_key>.50:4981 in forward, code: dequantize_per_tensor_default_1575 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1575, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantize_per_tensor_default_1575 = None
2025-03-21T20:31:43.9252381Z             quantized_decomposed_dequantize_per_tensor_default_1954: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1418, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1418 = None
2025-03-21T20:31:43.9252477Z             
2025-03-21T20:31:43.9253130Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9253933Z             aten_permute_copy_default_355: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1884, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1884 = None
2025-03-21T20:31:43.9254885Z             quantized_decomposed_quantize_per_tensor_default_1419: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_355, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_permute_copy_default_355 = None
2025-03-21T20:31:43.9256093Z             quantized_decomposed_dequantize_per_tensor_default_1955: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1419, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1419 = None
2025-03-21T20:31:43.9256849Z             aten_select_copy_int_424: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1955, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1955 = None
2025-03-21T20:31:43.9257738Z             quantized_decomposed_quantize_per_tensor_default_1420: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_424, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_select_copy_int_424 = None
2025-03-21T20:31:43.9258924Z             quantized_decomposed_dequantize_per_tensor_default_1956: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1420, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1420 = None
2025-03-21T20:31:43.9259661Z             aten_select_copy_int_425: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1956, 0, 8);  quantized_decomposed_dequantize_per_tensor_default_1956 = None
2025-03-21T20:31:43.9260561Z             quantized_decomposed_quantize_per_tensor_default_1421: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_425, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_select_copy_int_425 = None
2025-03-21T20:31:43.9260675Z             
2025-03-21T20:31:43.9261622Z              # File: <eval_with_key>.50:4990 in forward, code: dequantize_per_tensor_default_1578 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1578, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantize_per_tensor_default_1578 = None
2025-03-21T20:31:43.9262768Z             quantized_decomposed_dequantize_per_tensor_default_1957: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1421, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1421 = None
2025-03-21T20:31:43.9262872Z             
2025-03-21T20:31:43.9263506Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9264318Z             aten_permute_copy_default_356: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1883, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1883 = None
2025-03-21T20:31:43.9265260Z             quantized_decomposed_quantize_per_tensor_default_1422: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_356, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_permute_copy_default_356 = None
2025-03-21T20:31:43.9266416Z             quantized_decomposed_dequantize_per_tensor_default_1958: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1422, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1422 = None
2025-03-21T20:31:43.9267179Z             aten_select_copy_int_426: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1958, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1958 = None
2025-03-21T20:31:43.9268106Z             quantized_decomposed_quantize_per_tensor_default_1423: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_426, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_select_copy_int_426 = None
2025-03-21T20:31:43.9269260Z             quantized_decomposed_dequantize_per_tensor_default_1959: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1423, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1423 = None
2025-03-21T20:31:43.9269996Z             aten_select_copy_int_427: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1959, 0, 9);  quantized_decomposed_dequantize_per_tensor_default_1959 = None
2025-03-21T20:31:43.9270925Z             quantized_decomposed_quantize_per_tensor_default_1424: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_427, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_select_copy_int_427 = None
2025-03-21T20:31:43.9271013Z             
2025-03-21T20:31:43.9271959Z              # File: <eval_with_key>.50:4999 in forward, code: dequantize_per_tensor_default_1581 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1581, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantize_per_tensor_default_1581 = None
2025-03-21T20:31:43.9273101Z             quantized_decomposed_dequantize_per_tensor_default_1960: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1424, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1424 = None
2025-03-21T20:31:43.9273227Z             
2025-03-21T20:31:43.9273861Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9274674Z             aten_permute_copy_default_357: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1882, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1882 = None
2025-03-21T20:31:43.9275609Z             quantized_decomposed_quantize_per_tensor_default_1425: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_357, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_permute_copy_default_357 = None
2025-03-21T20:31:43.9276771Z             quantized_decomposed_dequantize_per_tensor_default_1961: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1425, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1425 = None
2025-03-21T20:31:43.9277512Z             aten_select_copy_int_428: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1961, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1961 = None
2025-03-21T20:31:43.9278415Z             quantized_decomposed_quantize_per_tensor_default_1426: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_428, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_select_copy_int_428 = None
2025-03-21T20:31:43.9279594Z             quantized_decomposed_dequantize_per_tensor_default_1962: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1426, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1426 = None
2025-03-21T20:31:43.9280368Z             aten_select_copy_int_429: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1962, 0, 10);  quantized_decomposed_dequantize_per_tensor_default_1962 = None
2025-03-21T20:31:43.9281255Z             quantized_decomposed_quantize_per_tensor_default_1427: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_429, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_select_copy_int_429 = None
2025-03-21T20:31:43.9281357Z             
2025-03-21T20:31:43.9282291Z              # File: <eval_with_key>.50:5008 in forward, code: dequantize_per_tensor_default_1584 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1584, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantize_per_tensor_default_1584 = None
2025-03-21T20:31:43.9283476Z             quantized_decomposed_dequantize_per_tensor_default_1963: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1427, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1427 = None
2025-03-21T20:31:43.9283564Z             
2025-03-21T20:31:43.9284208Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9285031Z             aten_permute_copy_default_358: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1881, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1881 = None
2025-03-21T20:31:43.9285987Z             quantized_decomposed_quantize_per_tensor_default_1428: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_358, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_permute_copy_default_358 = None
2025-03-21T20:31:43.9287239Z             quantized_decomposed_dequantize_per_tensor_default_1964: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1428, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1428 = None
2025-03-21T20:31:43.9287997Z             aten_select_copy_int_430: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1964, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_1964 = None
2025-03-21T20:31:43.9288898Z             quantized_decomposed_quantize_per_tensor_default_1429: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_430, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_select_copy_int_430 = None
2025-03-21T20:31:43.9290131Z             quantized_decomposed_dequantize_per_tensor_default_1965: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1429, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1429 = None
2025-03-21T20:31:43.9290874Z             aten_select_copy_int_431: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_1965, 0, 11);  quantized_decomposed_dequantize_per_tensor_default_1965 = None
2025-03-21T20:31:43.9291815Z             quantized_decomposed_quantize_per_tensor_default_1430: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_431, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_select_copy_int_431 = None
2025-03-21T20:31:43.9291932Z             
2025-03-21T20:31:43.9292880Z              # File: <eval_with_key>.50:5017 in forward, code: dequantize_per_tensor_default_1587 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1587, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantize_per_tensor_default_1587 = None
2025-03-21T20:31:43.9294028Z             quantized_decomposed_dequantize_per_tensor_default_1966: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1430, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1430 = None
2025-03-21T20:31:43.9294133Z             
2025-03-21T20:31:43.9294776Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9300573Z             aten_cat_default_35: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_aten_cat_default([quantized_decomposed_dequantize_per_tensor_default_1933, quantized_decomposed_dequantize_per_tensor_default_1936, quantized_decomposed_dequantize_per_tensor_default_1939, quantized_decomposed_dequantize_per_tensor_default_1942, quantized_decomposed_dequantize_per_tensor_default_1945, quantized_decomposed_dequantize_per_tensor_default_1948, quantized_decomposed_dequantize_per_tensor_default_1951, quantized_decomposed_dequantize_per_tensor_default_1954, quantized_decomposed_dequantize_per_tensor_default_1957, quantized_decomposed_dequantize_per_tensor_default_1960, quantized_decomposed_dequantize_per_tensor_default_1963, quantized_decomposed_dequantize_per_tensor_default_1966]);  quantized_decomposed_dequantize_per_tensor_default_1933 = quantized_decomposed_dequantize_per_tensor_default_1936 = quantized_decomposed_dequantize_per_tensor_default_1939 = quantized_decomposed_dequantize_per_tensor_default_1942 = quantized_decomposed_dequantize_per_tensor_default_1945 = quantized_decomposed_dequantize_per_tensor_default_1948 = quantized_decomposed_dequantize_per_tensor_default_1951 = quantized_decomposed_dequantize_per_tensor_default_1954 = quantized_decomposed_dequantize_per_tensor_default_1957 = quantized_decomposed_dequantize_per_tensor_default_1960 = quantized_decomposed_dequantize_per_tensor_default_1963 = quantized_decomposed_dequantize_per_tensor_default_1966 = None
2025-03-21T20:31:43.9301507Z             quantized_decomposed_quantize_per_tensor_default_1431: "i32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_35, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_cat_default_35 = None
2025-03-21T20:31:43.9302676Z             quantized_decomposed_dequantize_per_tensor_default_1967: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1431, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1431 = None
2025-03-21T20:31:43.9303459Z             aten_view_copy_default_154: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1967, [1, 12, 128, 64]);  quantized_decomposed_dequantize_per_tensor_default_1967 = None
2025-03-21T20:31:43.9304386Z             quantized_decomposed_quantize_per_tensor_default_1432: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_154, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  aten_view_copy_default_154 = None
2025-03-21T20:31:43.9304475Z             
2025-03-21T20:31:43.9305483Z              # File: <eval_with_key>.50:5023 in forward, code: dequantize_per_tensor_default_1589 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1589, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantize_per_tensor_default_1589 = None
2025-03-21T20:31:43.9306635Z             quantized_decomposed_dequantize_per_tensor_default_1968: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1432, 0.0001714634709060192, 32914, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1432 = None
2025-03-21T20:31:43.9306739Z             
2025-03-21T20:31:43.9307683Z              # File: <eval_with_key>.50:5024 in forward, code: quantize_per_tensor_default_1590 = torch.ops.quantized_decomposed.quantize_per_tensor.default(dequantize_per_tensor_default_1589, 0.00017223355825990438, 0, -32767, 32767, torch.int16);  dequantize_per_tensor_default_1589 = None
2025-03-21T20:31:43.9308885Z             quantized_decomposed_quantize_per_tensor_default_1433: "i16[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_1968, 0.00017223355825990438, 0, -32767, 32767, torch.int16);  quantized_decomposed_dequantize_per_tensor_default_1968 = None
2025-03-21T20:31:43.9308973Z             
2025-03-21T20:31:43.9309452Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:163 in forward, code: y = attn_weight @ v
2025-03-21T20:31:43.9310610Z             quantized_decomposed_dequantize_per_tensor_default_1969: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1433, 0.00017223355825990438, 0, -32767, 32767, torch.int16);  quantized_decomposed_quantize_per_tensor_default_1433 = None
2025-03-21T20:31:43.9310737Z             
2025-03-21T20:31:43.9311230Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:157 in forward, code: attn_mask = mask[input_pos]
2025-03-21T20:31:43.9312032Z             aten_index_tensor_10: "f32[1, 128]" = executorch_exir_dialects_edge__ops_aten_index_Tensor(quantized_decomposed_dequantize_per_tensor_default_139, [attn_options_input_pos]);  quantized_decomposed_dequantize_per_tensor_default_139 = None
2025-03-21T20:31:43.9312894Z             quantized_decomposed_quantize_per_tensor_default_1434: "i32[1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_tensor_10, 0.0038910505827516317, 65535, 0, 65535, torch.int32);  aten_index_tensor_10 = None
2025-03-21T20:31:43.9312980Z             
2025-03-21T20:31:43.9313475Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:161 in forward, code: attn_weight += attn_mask
2025-03-21T20:31:43.9314622Z             quantized_decomposed_dequantize_per_tensor_default_1970: "f32[1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1434, 0.0038910505827516317, 65535, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1434 = None
2025-03-21T20:31:43.9314723Z             
2025-03-21T20:31:43.9315293Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.9316106Z             aten_permute_copy_default_359: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1930, [0, 1, 3, 2]);  quantized_decomposed_dequantize_per_tensor_default_1930 = None
2025-03-21T20:31:43.9317066Z             quantized_decomposed_quantize_per_tensor_default_1435: "i32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_359, 0.000408027321100235, 35365, 0, 65535, torch.int32);  aten_permute_copy_default_359 = None
2025-03-21T20:31:43.9317193Z             
2025-03-21T20:31:43.9318124Z              # File: <eval_with_key>.50:5031 in forward, code: dequantize_per_tensor_default_1592 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1592, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantize_per_tensor_default_1592 = None
2025-03-21T20:31:43.9319288Z             quantized_decomposed_dequantize_per_tensor_default_1971: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1435, 0.000408027321100235, 35365, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1435 = None
2025-03-21T20:31:43.9319378Z             
2025-03-21T20:31:43.9320331Z              # File: <eval_with_key>.50:5032 in forward, code: quantize_per_tensor_default_1593 = torch.ops.quantized_decomposed.quantize_per_tensor.default(dequantize_per_tensor_default_1592, 0.00044038108899258077, 0, -32767, 32767, torch.int16);  dequantize_per_tensor_default_1592 = None
2025-03-21T20:31:43.9321515Z             quantized_decomposed_quantize_per_tensor_default_1436: "i16[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_1971, 0.00044038108899258077, 0, -32767, 32767, torch.int16);  quantized_decomposed_dequantize_per_tensor_default_1971 = None
2025-03-21T20:31:43.9321620Z             
2025-03-21T20:31:43.9322193Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.9323406Z             quantized_decomposed_dequantize_per_tensor_default_1972: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1436, 0.00044038108899258077, 0, -32767, 32767, torch.int16);  quantized_decomposed_quantize_per_tensor_default_1436 = None
2025-03-21T20:31:43.9324196Z             aten_expand_copy_default_32: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_1866, [1, 12, 1, 64]);  quantized_decomposed_dequantize_per_tensor_default_1866 = None
2025-03-21T20:31:43.9324768Z             aten_view_copy_default_155: "f32[12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_32, [12, 1, 64]);  aten_expand_copy_default_32 = None
2025-03-21T20:31:43.9325564Z             aten_expand_copy_default_33: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_1972, [1, 12, 64, 128]);  quantized_decomposed_dequantize_per_tensor_default_1972 = None
2025-03-21T20:31:43.9326149Z             aten_view_copy_default_156: "f32[12, 64, 128]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_33, [12, 64, 128]);  aten_expand_copy_default_33 = None
2025-03-21T20:31:43.9326805Z             aten_bmm_default_16: "f32[12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_bmm_default(aten_view_copy_default_155, aten_view_copy_default_156);  aten_view_copy_default_155 = aten_view_copy_default_156 = None
2025-03-21T20:31:43.9327337Z             aten_view_copy_default_157: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_bmm_default_16, [1, 12, 1, 128]);  aten_bmm_default_16 = None
2025-03-21T20:31:43.9328250Z             quantized_decomposed_quantize_per_tensor_default_1437: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_157, 0.0028048588428646326, 32779, 0, 65535, torch.int32);  aten_view_copy_default_157 = None
2025-03-21T20:31:43.9329561Z             quantized_decomposed_dequantize_per_tensor_default_1973: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1437, 0.0028048588428646326, 32779, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1437 = None
2025-03-21T20:31:43.9330431Z             quantized_decomposed_dequantize_per_tensor_default_1974: "f32[1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param157, 1.9073777366429567e-06, 0, 0, 65535, torch.int32);  b__frozen_param157 = None
2025-03-21T20:31:43.9331566Z             aten_mul_tensor_130: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1973, quantized_decomposed_dequantize_per_tensor_default_1974);  quantized_decomposed_dequantize_per_tensor_default_1973 = quantized_decomposed_dequantize_per_tensor_default_1974 = None
2025-03-21T20:31:43.9332733Z             quantized_decomposed_quantize_per_tensor_default_1438: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_130, 0.0003506073553580791, 32779, 0, 65535, torch.int32);  aten_mul_tensor_130 = None
2025-03-21T20:31:43.9332829Z             
2025-03-21T20:31:43.9333337Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:161 in forward, code: attn_weight += attn_mask
2025-03-21T20:31:43.9334487Z             quantized_decomposed_dequantize_per_tensor_default_1975: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1438, 0.0003506073553580791, 32779, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1438 = None
2025-03-21T20:31:43.9335669Z             aten_add_tensor_42: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_1975, quantized_decomposed_dequantize_per_tensor_default_1970);  quantized_decomposed_dequantize_per_tensor_default_1975 = quantized_decomposed_dequantize_per_tensor_default_1970 = None
2025-03-21T20:31:43.9336527Z             quantized_decomposed_quantize_per_tensor_default_1439: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_42, 0.0042004697024822235, 62801, 0, 65535, torch.int32);  aten_add_tensor_42 = None
2025-03-21T20:31:43.9336633Z             
2025-03-21T20:31:43.9337199Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:162 in forward, code: attn_weight = torch.softmax(attn_weight, dim=-1)
2025-03-21T20:31:43.9338365Z             quantized_decomposed_dequantize_per_tensor_default_1976: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1439, 0.0042004697024822235, 62801, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1439 = None
2025-03-21T20:31:43.9339149Z             aten__softmax_default_8: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten__softmax_default(quantized_decomposed_dequantize_per_tensor_default_1976, -1, False);  quantized_decomposed_dequantize_per_tensor_default_1976 = None
2025-03-21T20:31:43.9340043Z             quantized_decomposed_quantize_per_tensor_default_1440: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten__softmax_default_8, 1.5259021893143654e-05, 0, 0, 65535, torch.int32);  aten__softmax_default_8 = None
2025-03-21T20:31:43.9340133Z             
2025-03-21T20:31:43.9340609Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:163 in forward, code: y = attn_weight @ v
2025-03-21T20:31:43.9341779Z             quantized_decomposed_dequantize_per_tensor_default_1977: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1440, 1.5259021893143654e-05, 0, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1440 = None
2025-03-21T20:31:43.9342641Z             aten_expand_copy_default_34: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_1977, [1, 12, 1, 128]);  quantized_decomposed_dequantize_per_tensor_default_1977 = None
2025-03-21T20:31:43.9343201Z             aten_view_copy_default_158: "f32[12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_34, [12, 1, 128]);  aten_expand_copy_default_34 = None
2025-03-21T20:31:43.9344010Z             aten_expand_copy_default_35: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_1969, [1, 12, 128, 64]);  quantized_decomposed_dequantize_per_tensor_default_1969 = None
2025-03-21T20:31:43.9344598Z             aten_view_copy_default_159: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_35, [12, 128, 64]);  aten_expand_copy_default_35 = None
2025-03-21T20:31:43.9345261Z             aten_bmm_default_17: "f32[12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_bmm_default(aten_view_copy_default_158, aten_view_copy_default_159);  aten_view_copy_default_158 = aten_view_copy_default_159 = None
2025-03-21T20:31:43.9345770Z             aten_view_copy_default_160: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_bmm_default_17, [1, 12, 1, 64]);  aten_bmm_default_17 = None
2025-03-21T20:31:43.9346714Z             quantized_decomposed_quantize_per_tensor_default_1441: "i32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_160, 9.857307304628193e-05, 32475, 0, 65535, torch.int32);  aten_view_copy_default_160 = None
2025-03-21T20:31:43.9346804Z             
2025-03-21T20:31:43.9347445Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:165 in forward, code: return y.transpose(1, 2).contiguous().view(bsz, seqlen, self.dim)
2025-03-21T20:31:43.9348589Z             quantized_decomposed_dequantize_per_tensor_default_1978: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1441, 9.857307304628193e-05, 32475, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1441 = None
2025-03-21T20:31:43.9349395Z             aten_permute_copy_default_360: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1978, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1978 = None
2025-03-21T20:31:43.9350326Z             quantized_decomposed_quantize_per_tensor_default_1442: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_360, 9.857307304628193e-05, 32475, 0, 65535, torch.int32);  aten_permute_copy_default_360 = None
2025-03-21T20:31:43.9351483Z             quantized_decomposed_dequantize_per_tensor_default_1979: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1442, 9.857307304628193e-05, 32475, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1442 = None
2025-03-21T20:31:43.9352250Z             aten_view_copy_default_161: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_1979, [1, 1, 768]);  quantized_decomposed_dequantize_per_tensor_default_1979 = None
2025-03-21T20:31:43.9353193Z             quantized_decomposed_quantize_per_tensor_default_1443: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_161, 9.857307304628193e-05, 32475, 0, 65535, torch.int32);  aten_view_copy_default_161 = None
2025-03-21T20:31:43.9353309Z             
2025-03-21T20:31:43.9353848Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.9354987Z             quantized_decomposed_dequantize_per_tensor_default_1980: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1443, 9.857307304628193e-05, 32475, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1443 = None
2025-03-21T20:31:43.9355803Z             aten_unsqueeze_copy_default_95: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1980, -1);  quantized_decomposed_dequantize_per_tensor_default_1980 = None
2025-03-21T20:31:43.9356767Z             quantized_decomposed_quantize_per_tensor_default_1444: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_95, 9.857307304628193e-05, 32475, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_95 = None
2025-03-21T20:31:43.9356867Z             
2025-03-21T20:31:43.9357271Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.9358429Z             quantized_decomposed_dequantize_per_tensor_default_1981: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1444, 9.857307304628193e-05, 32475, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1444 = None
2025-03-21T20:31:43.9359258Z             aten_permute_copy_default_361: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1981, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1981 = None
2025-03-21T20:31:43.9360201Z             quantized_decomposed_quantize_per_tensor_default_1445: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_361, 9.857307304628193e-05, 32475, 0, 65535, torch.int32);  aten_permute_copy_default_361 = None
2025-03-21T20:31:43.9360292Z             
2025-03-21T20:31:43.9360669Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.9361813Z             quantized_decomposed_dequantize_per_tensor_default_1982: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1445, 9.857307304628193e-05, 32475, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1445 = None
2025-03-21T20:31:43.9363110Z             aten_convolution_default_59: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_1982, quantized_decomposed_dequantize_per_tensor_default_77, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_1982 = quantized_decomposed_dequantize_per_tensor_default_77 = None
2025-03-21T20:31:43.9364032Z             quantized_decomposed_quantize_per_tensor_default_1446: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_59, 6.995500734774396e-05, 26018, 0, 65535, torch.int32);  aten_convolution_default_59 = None
2025-03-21T20:31:43.9364135Z             
2025-03-21T20:31:43.9364580Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.9365765Z             quantized_decomposed_dequantize_per_tensor_default_1983: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1446, 6.995500734774396e-05, 26018, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1446 = None
2025-03-21T20:31:43.9366563Z             aten_permute_copy_default_362: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1983, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1983 = None
2025-03-21T20:31:43.9367507Z             quantized_decomposed_quantize_per_tensor_default_1447: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_362, 6.995500734774396e-05, 26018, 0, 65535, torch.int32);  aten_permute_copy_default_362 = None
2025-03-21T20:31:43.9367603Z             
2025-03-21T20:31:43.9368188Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.9369402Z             quantized_decomposed_dequantize_per_tensor_default_1984: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1447, 6.995500734774396e-05, 26018, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1447 = None
2025-03-21T20:31:43.9370172Z             aten_squeeze_copy_dims_95: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_1984, [-1]);  quantized_decomposed_dequantize_per_tensor_default_1984 = None
2025-03-21T20:31:43.9371111Z             quantized_decomposed_quantize_per_tensor_default_1448: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_95, 6.995500734774396e-05, 26018, 0, 65535, torch.int32);  aten_squeeze_copy_dims_95 = None
2025-03-21T20:31:43.9371216Z             
2025-03-21T20:31:43.9371590Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:111 in forward, code: h = x + h
2025-03-21T20:31:43.9372741Z             quantized_decomposed_dequantize_per_tensor_default_1985: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1448, 6.995500734774396e-05, 26018, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1448 = None
2025-03-21T20:31:43.9373870Z             aten_add_tensor_43: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_1805, quantized_decomposed_dequantize_per_tensor_default_1985);  quantized_decomposed_dequantize_per_tensor_default_1805 = quantized_decomposed_dequantize_per_tensor_default_1985 = None
2025-03-21T20:31:43.9374735Z             quantized_decomposed_quantize_per_tensor_default_1449: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_43, 0.0026511913165450096, 5838, 0, 65535, torch.int32);  aten_add_tensor_43 = None
2025-03-21T20:31:43.9374822Z             
2025-03-21T20:31:43.9375342Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:115 in forward, code: out = h + self.feed_forward(self.ffn_norm(h))
2025-03-21T20:31:43.9376257Z             quantized_decomposed_dequantize_per_tensor_default_1986: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1449, 0.0026511913165450096, 5838, 0, 65535, torch.int32)
2025-03-21T20:31:43.9377437Z             quantized_decomposed_dequantize_per_tensor_default_1987: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1449, 0.0026511913165450096, 5838, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1449 = None
2025-03-21T20:31:43.9377977Z             aten_pow_tensor_scalar_17: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_pow_Tensor_Scalar(quantized_decomposed_dequantize_per_tensor_default_1987, 2)
2025-03-21T20:31:43.9378448Z             aten_mean_dim_17: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_mean_dim(aten_pow_tensor_scalar_17, [2], True);  aten_pow_tensor_scalar_17 = None
2025-03-21T20:31:43.9378895Z             aten_add_scalar_17: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_add_Scalar(aten_mean_dim_17, 9.999999747378752e-06);  aten_mean_dim_17 = None
2025-03-21T20:31:43.9379335Z             aten_rsqrt_default_17: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_rsqrt_default(aten_add_scalar_17);  aten_add_scalar_17 = None
2025-03-21T20:31:43.9380219Z             aten_mul_tensor_131: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1987, aten_rsqrt_default_17);  quantized_decomposed_dequantize_per_tensor_default_1987 = aten_rsqrt_default_17 = None
2025-03-21T20:31:43.9381047Z             aten_mul_tensor_132: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(aten_mul_tensor_131, quantized_decomposed_dequantize_per_tensor_default_78);  aten_mul_tensor_131 = quantized_decomposed_dequantize_per_tensor_default_78 = None
2025-03-21T20:31:43.9381907Z             quantized_decomposed_quantize_per_tensor_default_1450: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_132, 0.00035757292062044144, 21055, 0, 65535, torch.int32);  aten_mul_tensor_132 = None
2025-03-21T20:31:43.9382033Z             
2025-03-21T20:31:43.9382562Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.9383500Z             quantized_decomposed_dequantize_per_tensor_default_1988: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1450, 0.00035757292062044144, 21055, 0, 65535, torch.int32)
2025-03-21T20:31:43.9384647Z             quantized_decomposed_dequantize_per_tensor_default_1989: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1450, 0.00035757292062044144, 21055, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1450 = None
2025-03-21T20:31:43.9385468Z             aten_unsqueeze_copy_default_96: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1989, -1);  quantized_decomposed_dequantize_per_tensor_default_1989 = None
2025-03-21T20:31:43.9386418Z             quantized_decomposed_quantize_per_tensor_default_1451: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_96, 0.00035757292062044144, 21055, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_96 = None
2025-03-21T20:31:43.9386518Z             
2025-03-21T20:31:43.9386926Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.9388089Z             quantized_decomposed_dequantize_per_tensor_default_1990: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1451, 0.00035757292062044144, 21055, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1451 = None
2025-03-21T20:31:43.9388947Z             aten_permute_copy_default_363: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1990, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1990 = None
2025-03-21T20:31:43.9389898Z             quantized_decomposed_quantize_per_tensor_default_1452: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_363, 0.00035757292062044144, 21055, 0, 65535, torch.int32);  aten_permute_copy_default_363 = None
2025-03-21T20:31:43.9389986Z             
2025-03-21T20:31:43.9390364Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.9391513Z             quantized_decomposed_dequantize_per_tensor_default_1991: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1452, 0.00035757292062044144, 21055, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1452 = None
2025-03-21T20:31:43.9392830Z             aten_convolution_default_60: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_1991, quantized_decomposed_dequantize_per_tensor_default_79, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_1991 = quantized_decomposed_dequantize_per_tensor_default_79 = None
2025-03-21T20:31:43.9393765Z             quantized_decomposed_quantize_per_tensor_default_1453: "i32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_60, 0.00018512652604840696, 30788, 0, 65535, torch.int32);  aten_convolution_default_60 = None
2025-03-21T20:31:43.9393890Z             
2025-03-21T20:31:43.9394315Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.9395490Z             quantized_decomposed_dequantize_per_tensor_default_1992: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1453, 0.00018512652604840696, 30788, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1453 = None
2025-03-21T20:31:43.9396296Z             aten_permute_copy_default_364: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1992, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1992 = None
2025-03-21T20:31:43.9397259Z             quantized_decomposed_quantize_per_tensor_default_1454: "i32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_364, 0.00018512652604840696, 30788, 0, 65535, torch.int32);  aten_permute_copy_default_364 = None
2025-03-21T20:31:43.9397352Z             
2025-03-21T20:31:43.9397905Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.9399064Z             quantized_decomposed_dequantize_per_tensor_default_1993: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1454, 0.00018512652604840696, 30788, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1454 = None
2025-03-21T20:31:43.9399973Z             aten_squeeze_copy_dims_96: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_1993, [-1]);  quantized_decomposed_dequantize_per_tensor_default_1993 = None
2025-03-21T20:31:43.9400924Z             quantized_decomposed_quantize_per_tensor_default_1455: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_96, 0.00018512652604840696, 30788, 0, 65535, torch.int32);  aten_squeeze_copy_dims_96 = None
2025-03-21T20:31:43.9401056Z             
2025-03-21T20:31:43.9401575Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:36 in forward, code: return self.w2(F.silu(self.w1(x)) * self.w3(x))
2025-03-21T20:31:43.9402514Z             quantized_decomposed_dequantize_per_tensor_default_1994: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1455, 0.00018512652604840696, 30788, 0, 65535, torch.int32)
2025-03-21T20:31:43.9403669Z             quantized_decomposed_dequantize_per_tensor_default_1995: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1455, 0.00018512652604840696, 30788, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1455 = None
2025-03-21T20:31:43.9404448Z             aten_sigmoid_default_8: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_sigmoid_default(quantized_decomposed_dequantize_per_tensor_default_1995);  quantized_decomposed_dequantize_per_tensor_default_1995 = None
2025-03-21T20:31:43.9405305Z             quantized_decomposed_quantize_per_tensor_default_1456: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_sigmoid_default_8, 1.52587890625e-05, 0, 0, 65535, torch.int32);  aten_sigmoid_default_8 = None
2025-03-21T20:31:43.9406431Z             quantized_decomposed_dequantize_per_tensor_default_1996: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1456, 1.52587890625e-05, 0, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1456 = None
2025-03-21T20:31:43.9407597Z             aten_mul_tensor_133: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1994, quantized_decomposed_dequantize_per_tensor_default_1996);  quantized_decomposed_dequantize_per_tensor_default_1994 = quantized_decomposed_dequantize_per_tensor_default_1996 = None
2025-03-21T20:31:43.9408476Z             quantized_decomposed_quantize_per_tensor_default_1457: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_133, 0.00010224587458651513, 2723, 0, 65535, torch.int32);  aten_mul_tensor_133 = None
2025-03-21T20:31:43.9409710Z             quantized_decomposed_dequantize_per_tensor_default_1997: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1457, 0.00010224587458651513, 2723, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1457 = None
2025-03-21T20:31:43.9409803Z             
2025-03-21T20:31:43.9410327Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.9411151Z             aten_unsqueeze_copy_default_97: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_1988, -1);  quantized_decomposed_dequantize_per_tensor_default_1988 = None
2025-03-21T20:31:43.9412118Z             quantized_decomposed_quantize_per_tensor_default_1458: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_97, 0.00035757292062044144, 21055, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_97 = None
2025-03-21T20:31:43.9412207Z             
2025-03-21T20:31:43.9412645Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.9413851Z             quantized_decomposed_dequantize_per_tensor_default_1998: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1458, 0.00035757292062044144, 21055, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1458 = None
2025-03-21T20:31:43.9414649Z             aten_permute_copy_default_365: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_1998, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_1998 = None
2025-03-21T20:31:43.9415597Z             quantized_decomposed_quantize_per_tensor_default_1459: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_365, 0.00035757292062044144, 21055, 0, 65535, torch.int32);  aten_permute_copy_default_365 = None
2025-03-21T20:31:43.9415689Z             
2025-03-21T20:31:43.9416065Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.9417239Z             quantized_decomposed_dequantize_per_tensor_default_1999: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1459, 0.00035757292062044144, 21055, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1459 = None
2025-03-21T20:31:43.9418526Z             aten_convolution_default_61: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_1999, quantized_decomposed_dequantize_per_tensor_default_80, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_1999 = quantized_decomposed_dequantize_per_tensor_default_80 = None
2025-03-21T20:31:43.9419502Z             quantized_decomposed_quantize_per_tensor_default_1460: "i32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_61, 0.00020597278489731252, 31383, 0, 65535, torch.int32);  aten_convolution_default_61 = None
2025-03-21T20:31:43.9419590Z             
2025-03-21T20:31:43.9420011Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.9421180Z             quantized_decomposed_dequantize_per_tensor_default_2000: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1460, 0.00020597278489731252, 31383, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1460 = None
2025-03-21T20:31:43.9421994Z             aten_permute_copy_default_366: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2000, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2000 = None
2025-03-21T20:31:43.9422947Z             quantized_decomposed_quantize_per_tensor_default_1461: "i32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_366, 0.00020597278489731252, 31383, 0, 65535, torch.int32);  aten_permute_copy_default_366 = None
2025-03-21T20:31:43.9423047Z             
2025-03-21T20:31:43.9423580Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.9424759Z             quantized_decomposed_dequantize_per_tensor_default_2001: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1461, 0.00020597278489731252, 31383, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1461 = None
2025-03-21T20:31:43.9425560Z             aten_squeeze_copy_dims_97: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_2001, [-1]);  quantized_decomposed_dequantize_per_tensor_default_2001 = None
2025-03-21T20:31:43.9426480Z             quantized_decomposed_quantize_per_tensor_default_1462: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_97, 0.00020597278489731252, 31383, 0, 65535, torch.int32);  aten_squeeze_copy_dims_97 = None
2025-03-21T20:31:43.9426568Z             
2025-03-21T20:31:43.9427082Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:36 in forward, code: return self.w2(F.silu(self.w1(x)) * self.w3(x))
2025-03-21T20:31:43.9428291Z             quantized_decomposed_dequantize_per_tensor_default_2002: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1462, 0.00020597278489731252, 31383, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1462 = None
2025-03-21T20:31:43.9429446Z             aten_mul_tensor_134: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_1997, quantized_decomposed_dequantize_per_tensor_default_2002);  quantized_decomposed_dequantize_per_tensor_default_1997 = quantized_decomposed_dequantize_per_tensor_default_2002 = None
2025-03-21T20:31:43.9430309Z             quantized_decomposed_quantize_per_tensor_default_1463: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_134, 0.00044964838889427483, 39916, 0, 65535, torch.int32);  aten_mul_tensor_134 = None
2025-03-21T20:31:43.9430438Z             
2025-03-21T20:31:43.9430955Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.9432125Z             quantized_decomposed_dequantize_per_tensor_default_2003: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1463, 0.00044964838889427483, 39916, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1463 = None
2025-03-21T20:31:43.9433103Z             aten_unsqueeze_copy_default_98: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_2003, -1);  quantized_decomposed_dequantize_per_tensor_default_2003 = None
2025-03-21T20:31:43.9434081Z             quantized_decomposed_quantize_per_tensor_default_1464: "i32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_98, 0.00044964838889427483, 39916, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_98 = None
2025-03-21T20:31:43.9434170Z             
2025-03-21T20:31:43.9434578Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.9435755Z             quantized_decomposed_dequantize_per_tensor_default_2004: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1464, 0.00044964838889427483, 39916, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1464 = None
2025-03-21T20:31:43.9436570Z             aten_permute_copy_default_367: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2004, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2004 = None
2025-03-21T20:31:43.9437587Z             quantized_decomposed_quantize_per_tensor_default_1465: "i32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_367, 0.00044964838889427483, 39916, 0, 65535, torch.int32);  aten_permute_copy_default_367 = None
2025-03-21T20:31:43.9437726Z             
2025-03-21T20:31:43.9438089Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.9439244Z             quantized_decomposed_dequantize_per_tensor_default_2005: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1465, 0.00044964838889427483, 39916, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1465 = None
2025-03-21T20:31:43.9440575Z             aten_convolution_default_62: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_2005, quantized_decomposed_dequantize_per_tensor_default_81, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_2005 = quantized_decomposed_dequantize_per_tensor_default_81 = None
2025-03-21T20:31:43.9441522Z             quantized_decomposed_quantize_per_tensor_default_1466: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_62, 0.00013728736666962504, 29642, 0, 65535, torch.int32);  aten_convolution_default_62 = None
2025-03-21T20:31:43.9441613Z             
2025-03-21T20:31:43.9442045Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.9443230Z             quantized_decomposed_dequantize_per_tensor_default_2006: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1466, 0.00013728736666962504, 29642, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1466 = None
2025-03-21T20:31:43.9444058Z             aten_permute_copy_default_368: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2006, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2006 = None
2025-03-21T20:31:43.9445000Z             quantized_decomposed_quantize_per_tensor_default_1467: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_368, 0.00013728736666962504, 29642, 0, 65535, torch.int32);  aten_permute_copy_default_368 = None
2025-03-21T20:31:43.9445107Z             
2025-03-21T20:31:43.9445642Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.9446809Z             quantized_decomposed_dequantize_per_tensor_default_2007: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1467, 0.00013728736666962504, 29642, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1467 = None
2025-03-21T20:31:43.9447565Z             aten_squeeze_copy_dims_98: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_2007, [-1]);  quantized_decomposed_dequantize_per_tensor_default_2007 = None
2025-03-21T20:31:43.9448486Z             quantized_decomposed_quantize_per_tensor_default_1468: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_98, 0.00013728736666962504, 29642, 0, 65535, torch.int32);  aten_squeeze_copy_dims_98 = None
2025-03-21T20:31:43.9448580Z             
2025-03-21T20:31:43.9449133Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:115 in forward, code: out = h + self.feed_forward(self.ffn_norm(h))
2025-03-21T20:31:43.9450388Z             quantized_decomposed_dequantize_per_tensor_default_2008: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1468, 0.00013728736666962504, 29642, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1468 = None
2025-03-21T20:31:43.9451535Z             aten_add_tensor_44: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_1986, quantized_decomposed_dequantize_per_tensor_default_2008);  quantized_decomposed_dequantize_per_tensor_default_1986 = quantized_decomposed_dequantize_per_tensor_default_2008 = None
2025-03-21T20:31:43.9452383Z             quantized_decomposed_quantize_per_tensor_default_1469: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_44, 0.002680311445146799, 6713, 0, 65535, torch.int32);  aten_add_tensor_44 = None
2025-03-21T20:31:43.9452490Z             
2025-03-21T20:31:43.9452893Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:111 in forward, code: h = x + h
2025-03-21T20:31:43.9453822Z             quantized_decomposed_dequantize_per_tensor_default_2009: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1469, 0.002680311445146799, 6713, 0, 65535, torch.int32)
2025-03-21T20:31:43.9453912Z             
2025-03-21T20:31:43.9454474Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:108 in forward, code: self.attention_norm(x), freqs_cos, freqs_sin, **attn_options
2025-03-21T20:31:43.9455661Z             quantized_decomposed_dequantize_per_tensor_default_2010: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1469, 0.002680311445146799, 6713, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1469 = None
2025-03-21T20:31:43.9456193Z             aten_pow_tensor_scalar_18: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_pow_Tensor_Scalar(quantized_decomposed_dequantize_per_tensor_default_2010, 2)
2025-03-21T20:31:43.9456653Z             aten_mean_dim_18: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_mean_dim(aten_pow_tensor_scalar_18, [2], True);  aten_pow_tensor_scalar_18 = None
2025-03-21T20:31:43.9457099Z             aten_add_scalar_18: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_add_Scalar(aten_mean_dim_18, 9.999999747378752e-06);  aten_mean_dim_18 = None
2025-03-21T20:31:43.9457543Z             aten_rsqrt_default_18: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_rsqrt_default(aten_add_scalar_18);  aten_add_scalar_18 = None
2025-03-21T20:31:43.9458407Z             aten_mul_tensor_135: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2010, aten_rsqrt_default_18);  quantized_decomposed_dequantize_per_tensor_default_2010 = aten_rsqrt_default_18 = None
2025-03-21T20:31:43.9459239Z             aten_mul_tensor_136: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(aten_mul_tensor_135, quantized_decomposed_dequantize_per_tensor_default_82);  aten_mul_tensor_135 = quantized_decomposed_dequantize_per_tensor_default_82 = None
2025-03-21T20:31:43.9460101Z             quantized_decomposed_quantize_per_tensor_default_1470: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_136, 0.0004660242120735347, 32140, 0, 65535, torch.int32);  aten_mul_tensor_136 = None
2025-03-21T20:31:43.9460206Z             
2025-03-21T20:31:43.9460767Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.9461725Z             quantized_decomposed_dequantize_per_tensor_default_2011: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1470, 0.0004660242120735347, 32140, 0, 65535, torch.int32)
2025-03-21T20:31:43.9462633Z             quantized_decomposed_dequantize_per_tensor_default_2012: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1470, 0.0004660242120735347, 32140, 0, 65535, torch.int32)
2025-03-21T20:31:43.9463792Z             quantized_decomposed_dequantize_per_tensor_default_2013: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1470, 0.0004660242120735347, 32140, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1470 = None
2025-03-21T20:31:43.9464633Z             aten_unsqueeze_copy_default_99: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_2013, -1);  quantized_decomposed_dequantize_per_tensor_default_2013 = None
2025-03-21T20:31:43.9465578Z             quantized_decomposed_quantize_per_tensor_default_1471: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_99, 0.0004660242120735347, 32140, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_99 = None
2025-03-21T20:31:43.9465680Z             
2025-03-21T20:31:43.9466086Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.9467258Z             quantized_decomposed_dequantize_per_tensor_default_2014: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1471, 0.0004660242120735347, 32140, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1471 = None
2025-03-21T20:31:43.9468071Z             aten_permute_copy_default_369: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2014, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2014 = None
2025-03-21T20:31:43.9469015Z             quantized_decomposed_quantize_per_tensor_default_1472: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_369, 0.0004660242120735347, 32140, 0, 65535, torch.int32);  aten_permute_copy_default_369 = None
2025-03-21T20:31:43.9469106Z             
2025-03-21T20:31:43.9469469Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.9470630Z             quantized_decomposed_dequantize_per_tensor_default_2015: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1472, 0.0004660242120735347, 32140, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1472 = None
2025-03-21T20:31:43.9471919Z             aten_convolution_default_63: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_2015, quantized_decomposed_dequantize_per_tensor_default_83, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_2015 = quantized_decomposed_dequantize_per_tensor_default_83 = None
2025-03-21T20:31:43.9472876Z             quantized_decomposed_quantize_per_tensor_default_1473: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_63, 0.00035828881664201617, 31639, 0, 65535, torch.int32);  aten_convolution_default_63 = None
2025-03-21T20:31:43.9472998Z             
2025-03-21T20:31:43.9473417Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.9474585Z             quantized_decomposed_dequantize_per_tensor_default_2016: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1473, 0.00035828881664201617, 31639, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1473 = None
2025-03-21T20:31:43.9475379Z             aten_permute_copy_default_370: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2016, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2016 = None
2025-03-21T20:31:43.9476358Z             quantized_decomposed_quantize_per_tensor_default_1474: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_370, 0.00035828881664201617, 31639, 0, 65535, torch.int32);  aten_permute_copy_default_370 = None
2025-03-21T20:31:43.9476448Z             
2025-03-21T20:31:43.9476993Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.9478143Z             quantized_decomposed_dequantize_per_tensor_default_2017: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1474, 0.00035828881664201617, 31639, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1474 = None
2025-03-21T20:31:43.9478934Z             aten_squeeze_copy_dims_99: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_2017, [-1]);  quantized_decomposed_dequantize_per_tensor_default_2017 = None
2025-03-21T20:31:43.9479840Z             quantized_decomposed_quantize_per_tensor_default_1475: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_99, 0.00035828881664201617, 31639, 0, 65535, torch.int32);  aten_squeeze_copy_dims_99 = None
2025-03-21T20:31:43.9479938Z             
2025-03-21T20:31:43.9480456Z              # File: /pytorch/executorch/examples/models/llama/attention.py:242 in forward, code: q = q.view(bsz, seqlen, self.n_local_heads, self.head_dim)
2025-03-21T20:31:43.9481615Z             quantized_decomposed_dequantize_per_tensor_default_2018: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1475, 0.00035828881664201617, 31639, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1475 = None
2025-03-21T20:31:43.9481710Z             
2025-03-21T20:31:43.9482227Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.9483046Z             aten_unsqueeze_copy_default_100: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_2012, -1);  quantized_decomposed_dequantize_per_tensor_default_2012 = None
2025-03-21T20:31:43.9484001Z             quantized_decomposed_quantize_per_tensor_default_1476: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_100, 0.0004660242120735347, 32140, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_100 = None
2025-03-21T20:31:43.9484101Z             
2025-03-21T20:31:43.9484529Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.9485761Z             quantized_decomposed_dequantize_per_tensor_default_2019: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1476, 0.0004660242120735347, 32140, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1476 = None
2025-03-21T20:31:43.9486558Z             aten_permute_copy_default_371: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2019, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2019 = None
2025-03-21T20:31:43.9487509Z             quantized_decomposed_quantize_per_tensor_default_1477: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_371, 0.0004660242120735347, 32140, 0, 65535, torch.int32);  aten_permute_copy_default_371 = None
2025-03-21T20:31:43.9487602Z             
2025-03-21T20:31:43.9487978Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.9489158Z             quantized_decomposed_dequantize_per_tensor_default_2020: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1477, 0.0004660242120735347, 32140, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1477 = None
2025-03-21T20:31:43.9490630Z             aten_convolution_default_64: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_2020, quantized_decomposed_dequantize_per_tensor_default_84, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_2020 = quantized_decomposed_dequantize_per_tensor_default_84 = None
2025-03-21T20:31:43.9491626Z             quantized_decomposed_quantize_per_tensor_default_1478: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_64, 0.0004303281893953681, 32305, 0, 65535, torch.int32);  aten_convolution_default_64 = None
2025-03-21T20:31:43.9491717Z             
2025-03-21T20:31:43.9492138Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.9493298Z             quantized_decomposed_dequantize_per_tensor_default_2021: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1478, 0.0004303281893953681, 32305, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1478 = None
2025-03-21T20:31:43.9494101Z             aten_permute_copy_default_372: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2021, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2021 = None
2025-03-21T20:31:43.9495048Z             quantized_decomposed_quantize_per_tensor_default_1479: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_372, 0.0004303281893953681, 32305, 0, 65535, torch.int32);  aten_permute_copy_default_372 = None
2025-03-21T20:31:43.9495134Z             
2025-03-21T20:31:43.9495680Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.9497118Z             quantized_decomposed_dequantize_per_tensor_default_2022: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1479, 0.0004303281893953681, 32305, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1479 = None
2025-03-21T20:31:43.9497926Z             aten_squeeze_copy_dims_100: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_2022, [-1]);  quantized_decomposed_dequantize_per_tensor_default_2022 = None
2025-03-21T20:31:43.9498837Z             quantized_decomposed_quantize_per_tensor_default_1480: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_100, 0.0004303281893953681, 32305, 0, 65535, torch.int32);  aten_squeeze_copy_dims_100 = None
2025-03-21T20:31:43.9498938Z             
2025-03-21T20:31:43.9499464Z              # File: /pytorch/executorch/examples/models/llama/attention.py:243 in forward, code: k = k.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.9500621Z             quantized_decomposed_dequantize_per_tensor_default_2023: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1480, 0.0004303281893953681, 32305, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1480 = None
2025-03-21T20:31:43.9500737Z             
2025-03-21T20:31:43.9501488Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:43.9502319Z             aten_unsqueeze_copy_default_101: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_2011, -1);  quantized_decomposed_dequantize_per_tensor_default_2011 = None
2025-03-21T20:31:43.9503297Z             quantized_decomposed_quantize_per_tensor_default_1481: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_101, 0.0004660242120735347, 32140, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_101 = None
2025-03-21T20:31:43.9503450Z             
2025-03-21T20:31:43.9503879Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:43.9505035Z             quantized_decomposed_dequantize_per_tensor_default_2024: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1481, 0.0004660242120735347, 32140, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1481 = None
2025-03-21T20:31:43.9505852Z             aten_permute_copy_default_373: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2024, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2024 = None
2025-03-21T20:31:43.9506792Z             quantized_decomposed_quantize_per_tensor_default_1482: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_373, 0.0004660242120735347, 32140, 0, 65535, torch.int32);  aten_permute_copy_default_373 = None
2025-03-21T20:31:43.9506901Z             
2025-03-21T20:31:43.9507269Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:43.9508433Z             quantized_decomposed_dequantize_per_tensor_default_2025: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1482, 0.0004660242120735347, 32140, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1482 = None
2025-03-21T20:31:43.9509737Z             aten_convolution_default_65: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_2025, quantized_decomposed_dequantize_per_tensor_default_85, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_2025 = quantized_decomposed_dequantize_per_tensor_default_85 = None
2025-03-21T20:31:43.9510705Z             quantized_decomposed_quantize_per_tensor_default_1483: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_65, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_convolution_default_65 = None
2025-03-21T20:31:43.9510793Z             
2025-03-21T20:31:43.9511227Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:43.9512377Z             quantized_decomposed_dequantize_per_tensor_default_2026: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1483, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1483 = None
2025-03-21T20:31:43.9513213Z             aten_permute_copy_default_374: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2026, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2026 = None
2025-03-21T20:31:43.9514145Z             quantized_decomposed_quantize_per_tensor_default_1484: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_374, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_permute_copy_default_374 = None
2025-03-21T20:31:43.9514246Z             
2025-03-21T20:31:43.9514781Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:43.9515977Z             quantized_decomposed_dequantize_per_tensor_default_2027: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1484, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1484 = None
2025-03-21T20:31:43.9516737Z             aten_squeeze_copy_dims_101: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_2027, [-1]);  quantized_decomposed_dequantize_per_tensor_default_2027 = None
2025-03-21T20:31:43.9517655Z             quantized_decomposed_quantize_per_tensor_default_1485: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_101, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_squeeze_copy_dims_101 = None
2025-03-21T20:31:43.9517745Z             
2025-03-21T20:31:43.9518282Z              # File: /pytorch/executorch/examples/models/llama/attention.py:244 in forward, code: v = v.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.9519426Z             quantized_decomposed_dequantize_per_tensor_default_2028: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1485, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1485 = None
2025-03-21T20:31:43.9519528Z             
2025-03-21T20:31:43.9520037Z              # File: /pytorch/executorch/examples/models/llama/attention.py:242 in forward, code: q = q.view(bsz, seqlen, self.n_local_heads, self.head_dim)
2025-03-21T20:31:43.9520817Z             aten_view_copy_default_162: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_2018, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_2018 = None
2025-03-21T20:31:43.9521760Z             quantized_decomposed_quantize_per_tensor_default_1486: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_162, 0.00035828881664201617, 31639, 0, 65535, torch.int32);  aten_view_copy_default_162 = None
2025-03-21T20:31:43.9521883Z             
2025-03-21T20:31:43.9522824Z              # File: <eval_with_key>.50:5191 in forward, code: dequantize_per_tensor_default_1644 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1644, 0.00035828881664201617, 31639, 0, 65535, torch.int32);  quantize_per_tensor_default_1644 = None
2025-03-21T20:31:43.9523984Z             quantized_decomposed_dequantize_per_tensor_default_2029: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1486, 0.00035828881664201617, 31639, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1486 = None
2025-03-21T20:31:43.9524075Z             
2025-03-21T20:31:43.9524609Z              # File: /pytorch/executorch/examples/models/llama/attention.py:243 in forward, code: k = k.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.9525402Z             aten_view_copy_default_163: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_2023, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_2023 = None
2025-03-21T20:31:43.9526323Z             quantized_decomposed_quantize_per_tensor_default_1487: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_163, 0.0004303281893953681, 32305, 0, 65535, torch.int32);  aten_view_copy_default_163 = None
2025-03-21T20:31:43.9526436Z             
2025-03-21T20:31:43.9527382Z              # File: <eval_with_key>.50:5194 in forward, code: dequantize_per_tensor_default_1645 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1645, 0.0004303281893953681, 32305, 0, 65535, torch.int32);  quantize_per_tensor_default_1645 = None
2025-03-21T20:31:43.9528529Z             quantized_decomposed_dequantize_per_tensor_default_2030: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1487, 0.0004303281893953681, 32305, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1487 = None
2025-03-21T20:31:43.9528628Z             
2025-03-21T20:31:43.9529146Z              # File: /pytorch/executorch/examples/models/llama/attention.py:244 in forward, code: v = v.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:43.9530022Z             aten_view_copy_default_164: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_2028, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_2028 = None
2025-03-21T20:31:43.9530937Z             quantized_decomposed_quantize_per_tensor_default_1488: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_164, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_view_copy_default_164 = None
2025-03-21T20:31:43.9531038Z             
2025-03-21T20:31:43.9531709Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:346 in update, code: v_out = torch.ops.aten.index_put_(self.past_v_caches, [None, input_pos], v_val)
2025-03-21T20:31:43.9533032Z             quantized_decomposed_dequantize_per_tensor_default_2031: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1488, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1488 = None
2025-03-21T20:31:43.9533127Z             
2025-03-21T20:31:43.9534040Z              # File: <eval_with_key>.50:5199 in forward, code: quantize_per_tensor_default_1647 = torch.ops.quantized_decomposed.quantize_per_tensor.default(_to_copy_18, 0.00035828881664201617, 31639, 0, 65535, torch.int32);  _to_copy_18 = None
2025-03-21T20:31:43.9535189Z             quantized_decomposed_quantize_per_tensor_default_1489: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_2029, 0.00035828881664201617, 31639, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_2029 = None
2025-03-21T20:31:43.9535291Z             
2025-03-21T20:31:43.9535814Z              # File: /pytorch/executorch/examples/models/llama/rope.py:84 in apply_rotary_emb, code: xq_r, xq_i = xq.float().reshape(xq.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.9536982Z             quantized_decomposed_dequantize_per_tensor_default_2032: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1489, 0.00035828881664201617, 31639, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1489 = None
2025-03-21T20:31:43.9537793Z             aten_view_copy_default_165: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_2032, [1, 1, 12, -1, 2]);  quantized_decomposed_dequantize_per_tensor_default_2032 = None
2025-03-21T20:31:43.9538720Z             quantized_decomposed_quantize_per_tensor_default_1490: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_165, 0.00035828881664201617, 31639, 0, 65535, torch.int32);  aten_view_copy_default_165 = None
2025-03-21T20:31:43.9539901Z             quantized_decomposed_dequantize_per_tensor_default_2033: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1490, 0.00035828881664201617, 31639, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1490 = None
2025-03-21T20:31:43.9540450Z             aten_slice_copy_tensor_36: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_2033, 4, 0, 1)
2025-03-21T20:31:43.9541205Z             aten_slice_copy_tensor_37: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_2033, 4, 1, 2);  quantized_decomposed_dequantize_per_tensor_default_2033 = None
2025-03-21T20:31:43.9541742Z             aten_squeeze_copy_dims_102: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_36, [4]);  aten_slice_copy_tensor_36 = None
2025-03-21T20:31:43.9542268Z             aten_squeeze_copy_dims_103: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_37, [4]);  aten_slice_copy_tensor_37 = None
2025-03-21T20:31:43.9543198Z             quantized_decomposed_quantize_per_tensor_default_1491: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_102, 0.00035828881664201617, 31639, 0, 65535, torch.int32);  aten_squeeze_copy_dims_102 = None
2025-03-21T20:31:43.9543286Z             
2025-03-21T20:31:43.9543775Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.9544696Z             quantized_decomposed_dequantize_per_tensor_default_2034: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1491, 0.00035828881664201617, 31639, 0, 65535, torch.int32)
2025-03-21T20:31:43.9544802Z             
2025-03-21T20:31:43.9545321Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.9546486Z             quantized_decomposed_dequantize_per_tensor_default_2035: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1491, 0.00035828881664201617, 31639, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1491 = None
2025-03-21T20:31:43.9546573Z             
2025-03-21T20:31:43.9547093Z              # File: /pytorch/executorch/examples/models/llama/rope.py:84 in apply_rotary_emb, code: xq_r, xq_i = xq.float().reshape(xq.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.9548022Z             quantized_decomposed_quantize_per_tensor_default_1492: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_103, 0.00032475838088430464, 31202, 0, 65535, torch.int32);  aten_squeeze_copy_dims_103 = None
2025-03-21T20:31:43.9548109Z             
2025-03-21T20:31:43.9548630Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.9549550Z             quantized_decomposed_dequantize_per_tensor_default_2036: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1492, 0.00032475838088430464, 31202, 0, 65535, torch.int32)
2025-03-21T20:31:43.9549649Z             
2025-03-21T20:31:43.9550118Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.9551312Z             quantized_decomposed_dequantize_per_tensor_default_2037: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1492, 0.00032475838088430464, 31202, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1492 = None
2025-03-21T20:31:43.9551401Z             
2025-03-21T20:31:43.9552239Z              # File: <eval_with_key>.50:5214 in forward, code: quantize_per_tensor_default_1651 = torch.ops.quantized_decomposed.quantize_per_tensor.default(_to_copy_19, 0.0004303281893953681, 32305, 0, 65535, torch.int32);  _to_copy_19 = None
2025-03-21T20:31:43.9553381Z             quantized_decomposed_quantize_per_tensor_default_1493: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_2030, 0.0004303281893953681, 32305, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_2030 = None
2025-03-21T20:31:43.9553482Z             
2025-03-21T20:31:43.9554003Z              # File: /pytorch/executorch/examples/models/llama/rope.py:85 in apply_rotary_emb, code: xk_r, xk_i = xk.float().reshape(xk.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.9560902Z             quantized_decomposed_dequantize_per_tensor_default_2038: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1493, 0.0004303281893953681, 32305, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1493 = None
2025-03-21T20:31:43.9561764Z             aten_view_copy_default_166: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_2038, [1, 1, 12, -1, 2]);  quantized_decomposed_dequantize_per_tensor_default_2038 = None
2025-03-21T20:31:43.9562771Z             quantized_decomposed_quantize_per_tensor_default_1494: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_166, 0.0004303281893953681, 32305, 0, 65535, torch.int32);  aten_view_copy_default_166 = None
2025-03-21T20:31:43.9563971Z             quantized_decomposed_dequantize_per_tensor_default_2039: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1494, 0.0004303281893953681, 32305, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1494 = None
2025-03-21T20:31:43.9564511Z             aten_slice_copy_tensor_38: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_2039, 4, 0, 1)
2025-03-21T20:31:43.9565277Z             aten_slice_copy_tensor_39: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_2039, 4, 1, 2);  quantized_decomposed_dequantize_per_tensor_default_2039 = None
2025-03-21T20:31:43.9565806Z             aten_squeeze_copy_dims_104: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_38, [4]);  aten_slice_copy_tensor_38 = None
2025-03-21T20:31:43.9566369Z             aten_squeeze_copy_dims_105: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_39, [4]);  aten_slice_copy_tensor_39 = None
2025-03-21T20:31:43.9567276Z             quantized_decomposed_quantize_per_tensor_default_1495: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_104, 0.000411502318456769, 33783, 0, 65535, torch.int32);  aten_squeeze_copy_dims_104 = None
2025-03-21T20:31:43.9567384Z             
2025-03-21T20:31:43.9567870Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.9568828Z             quantized_decomposed_dequantize_per_tensor_default_2040: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1495, 0.000411502318456769, 33783, 0, 65535, torch.int32)
2025-03-21T20:31:43.9568920Z             
2025-03-21T20:31:43.9569524Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.9570670Z             quantized_decomposed_dequantize_per_tensor_default_2041: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1495, 0.000411502318456769, 33783, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1495 = None
2025-03-21T20:31:43.9570775Z             
2025-03-21T20:31:43.9571298Z              # File: /pytorch/executorch/examples/models/llama/rope.py:85 in apply_rotary_emb, code: xk_r, xk_i = xk.float().reshape(xk.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:43.9572230Z             quantized_decomposed_quantize_per_tensor_default_1496: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_105, 0.0004275636747479439, 32090, 0, 65535, torch.int32);  aten_squeeze_copy_dims_105 = None
2025-03-21T20:31:43.9572321Z             
2025-03-21T20:31:43.9572794Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.9573724Z             quantized_decomposed_dequantize_per_tensor_default_2042: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1496, 0.0004275636747479439, 32090, 0, 65535, torch.int32)
2025-03-21T20:31:43.9573815Z             
2025-03-21T20:31:43.9574299Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.9575502Z             quantized_decomposed_dequantize_per_tensor_default_2043: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1496, 0.0004275636747479439, 32090, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1496 = None
2025-03-21T20:31:43.9575604Z             
2025-03-21T20:31:43.9576042Z              # File: /pytorch/executorch/examples/models/llama/rope.py:78 in reshape_for_broadcast, code: return freqs_cis.view(shape)
2025-03-21T20:31:43.9576808Z             aten_view_copy_default_167: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_153, [1, 1, 1, 32]);  quantized_decomposed_dequantize_per_tensor_default_153 = None
2025-03-21T20:31:43.9577711Z             quantized_decomposed_quantize_per_tensor_default_1497: "i32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_167, 3.051804378628731e-05, 32768, 0, 65535, torch.int32);  aten_view_copy_default_167 = None
2025-03-21T20:31:43.9577811Z             
2025-03-21T20:31:43.9578308Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.9579238Z             quantized_decomposed_dequantize_per_tensor_default_2044: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1497, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.9579325Z             
2025-03-21T20:31:43.9579832Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.9580740Z             quantized_decomposed_dequantize_per_tensor_default_2045: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1497, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.9580844Z             
2025-03-21T20:31:43.9581312Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.9582234Z             quantized_decomposed_dequantize_per_tensor_default_2046: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1497, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:43.9582321Z             
2025-03-21T20:31:43.9582791Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.9583941Z             quantized_decomposed_dequantize_per_tensor_default_2047: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1497, 3.051804378628731e-05, 32768, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1497 = None
2025-03-21T20:31:43.9584029Z             
2025-03-21T20:31:43.9584477Z              # File: /pytorch/executorch/examples/models/llama/rope.py:78 in reshape_for_broadcast, code: return freqs_cis.view(shape)
2025-03-21T20:31:43.9585234Z             aten_view_copy_default_168: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_165, [1, 1, 1, 32]);  quantized_decomposed_dequantize_per_tensor_default_165 = None
2025-03-21T20:31:43.9586169Z             quantized_decomposed_quantize_per_tensor_default_1498: "i32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_168, 3.051786916330457e-05, 32767, 0, 65535, torch.int32);  aten_view_copy_default_168 = None
2025-03-21T20:31:43.9586279Z             
2025-03-21T20:31:43.9586762Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.9587672Z             quantized_decomposed_dequantize_per_tensor_default_2048: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1498, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.9587771Z             
2025-03-21T20:31:43.9588238Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.9589162Z             quantized_decomposed_dequantize_per_tensor_default_2049: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1498, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.9589250Z             
2025-03-21T20:31:43.9589764Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.9590674Z             quantized_decomposed_dequantize_per_tensor_default_2050: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1498, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:43.9590774Z             
2025-03-21T20:31:43.9591242Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.9592417Z             quantized_decomposed_dequantize_per_tensor_default_2051: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1498, 3.051786916330457e-05, 32767, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1498 = None
2025-03-21T20:31:43.9592507Z             
2025-03-21T20:31:43.9592976Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:43.9594122Z             aten_mul_tensor_137: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2035, quantized_decomposed_dequantize_per_tensor_default_2047);  quantized_decomposed_dequantize_per_tensor_default_2035 = quantized_decomposed_dequantize_per_tensor_default_2047 = None
2025-03-21T20:31:43.9594981Z             quantized_decomposed_quantize_per_tensor_default_1499: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_137, 0.0003548612876329571, 31922, 0, 65535, torch.int32);  aten_mul_tensor_137 = None
2025-03-21T20:31:43.9596134Z             quantized_decomposed_dequantize_per_tensor_default_2052: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1499, 0.0003548612876329571, 31922, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1499 = None
2025-03-21T20:31:43.9597273Z             aten_mul_tensor_138: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2036, quantized_decomposed_dequantize_per_tensor_default_2050);  quantized_decomposed_dequantize_per_tensor_default_2036 = quantized_decomposed_dequantize_per_tensor_default_2050 = None
2025-03-21T20:31:43.9598168Z             quantized_decomposed_quantize_per_tensor_default_1500: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_138, 0.00014130776980891824, 32945, 0, 65535, torch.int32);  aten_mul_tensor_138 = None
2025-03-21T20:31:43.9599364Z             quantized_decomposed_dequantize_per_tensor_default_2053: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1500, 0.00014130776980891824, 32945, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1500 = None
2025-03-21T20:31:43.9600479Z             aten_sub_tensor_18: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_sub_Tensor(quantized_decomposed_dequantize_per_tensor_default_2052, quantized_decomposed_dequantize_per_tensor_default_2053);  quantized_decomposed_dequantize_per_tensor_default_2052 = quantized_decomposed_dequantize_per_tensor_default_2053 = None
2025-03-21T20:31:43.9601342Z             quantized_decomposed_quantize_per_tensor_default_1501: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_sub_tensor_18, 0.00035090342862531543, 32108, 0, 65535, torch.int32);  aten_sub_tensor_18 = None
2025-03-21T20:31:43.9601431Z             
2025-03-21T20:31:43.9602414Z              # File: <eval_with_key>.50:5248 in forward, code: dequantize_per_tensor_default_1659 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1659, 0.00035090342862531543, 32108, 0, 65535, torch.int32);  quantize_per_tensor_default_1659 = None
2025-03-21T20:31:43.9603714Z             quantized_decomposed_dequantize_per_tensor_default_2054: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1501, 0.00035090342862531543, 32108, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1501 = None
2025-03-21T20:31:43.9603851Z             
2025-03-21T20:31:43.9604325Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:43.9605469Z             aten_mul_tensor_139: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2034, quantized_decomposed_dequantize_per_tensor_default_2051);  quantized_decomposed_dequantize_per_tensor_default_2034 = quantized_decomposed_dequantize_per_tensor_default_2051 = None
2025-03-21T20:31:43.9606328Z             quantized_decomposed_quantize_per_tensor_default_1502: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_139, 0.00016020808834582567, 31073, 0, 65535, torch.int32);  aten_mul_tensor_139 = None
2025-03-21T20:31:43.9607487Z             quantized_decomposed_dequantize_per_tensor_default_2055: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1502, 0.00016020808834582567, 31073, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1502 = None
2025-03-21T20:31:43.9608615Z             aten_mul_tensor_140: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2037, quantized_decomposed_dequantize_per_tensor_default_2046);  quantized_decomposed_dequantize_per_tensor_default_2037 = quantized_decomposed_dequantize_per_tensor_default_2046 = None
2025-03-21T20:31:43.9609595Z             quantized_decomposed_quantize_per_tensor_default_1503: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_140, 0.0003209649003110826, 31569, 0, 65535, torch.int32);  aten_mul_tensor_140 = None
2025-03-21T20:31:43.9610771Z             quantized_decomposed_dequantize_per_tensor_default_2056: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1503, 0.0003209649003110826, 31569, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1503 = None
2025-03-21T20:31:43.9611935Z             aten_add_tensor_45: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_2055, quantized_decomposed_dequantize_per_tensor_default_2056);  quantized_decomposed_dequantize_per_tensor_default_2055 = quantized_decomposed_dequantize_per_tensor_default_2056 = None
2025-03-21T20:31:43.9612802Z             quantized_decomposed_quantize_per_tensor_default_1504: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_45, 0.00031776822288520634, 31840, 0, 65535, torch.int32);  aten_add_tensor_45 = None
2025-03-21T20:31:43.9612894Z             
2025-03-21T20:31:43.9613851Z              # File: <eval_with_key>.50:5257 in forward, code: dequantize_per_tensor_default_1662 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1662, 0.00031776822288520634, 31840, 0, 65535, torch.int32);  quantize_per_tensor_default_1662 = None
2025-03-21T20:31:43.9615020Z             quantized_decomposed_dequantize_per_tensor_default_2057: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1504, 0.00031776822288520634, 31840, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1504 = None
2025-03-21T20:31:43.9615125Z             
2025-03-21T20:31:43.9615604Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:43.9616778Z             aten_mul_tensor_141: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2041, quantized_decomposed_dequantize_per_tensor_default_2045);  quantized_decomposed_dequantize_per_tensor_default_2041 = quantized_decomposed_dequantize_per_tensor_default_2045 = None
2025-03-21T20:31:43.9617642Z             quantized_decomposed_quantize_per_tensor_default_1505: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_141, 0.00040689806337468326, 33489, 0, 65535, torch.int32);  aten_mul_tensor_141 = None
2025-03-21T20:31:43.9618801Z             quantized_decomposed_dequantize_per_tensor_default_2058: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1505, 0.00040689806337468326, 33489, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1505 = None
2025-03-21T20:31:43.9619931Z             aten_mul_tensor_142: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2042, quantized_decomposed_dequantize_per_tensor_default_2048);  quantized_decomposed_dequantize_per_tensor_default_2042 = quantized_decomposed_dequantize_per_tensor_default_2048 = None
2025-03-21T20:31:43.9620807Z             quantized_decomposed_quantize_per_tensor_default_1506: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_142, 0.00016605170094408095, 36087, 0, 65535, torch.int32);  aten_mul_tensor_142 = None
2025-03-21T20:31:43.9621955Z             quantized_decomposed_dequantize_per_tensor_default_2059: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1506, 0.00016605170094408095, 36087, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1506 = None
2025-03-21T20:31:43.9623115Z             aten_sub_tensor_19: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_sub_Tensor(quantized_decomposed_dequantize_per_tensor_default_2058, quantized_decomposed_dequantize_per_tensor_default_2059);  quantized_decomposed_dequantize_per_tensor_default_2058 = quantized_decomposed_dequantize_per_tensor_default_2059 = None
2025-03-21T20:31:43.9623993Z             quantized_decomposed_quantize_per_tensor_default_1507: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_sub_tensor_19, 0.0004013704019598663, 32912, 0, 65535, torch.int32);  aten_sub_tensor_19 = None
2025-03-21T20:31:43.9624092Z             
2025-03-21T20:31:43.9625028Z              # File: <eval_with_key>.50:5266 in forward, code: dequantize_per_tensor_default_1665 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1665, 0.0004013704019598663, 32912, 0, 65535, torch.int32);  quantize_per_tensor_default_1665 = None
2025-03-21T20:31:43.9626184Z             quantized_decomposed_dequantize_per_tensor_default_2060: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1507, 0.0004013704019598663, 32912, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1507 = None
2025-03-21T20:31:43.9626294Z             
2025-03-21T20:31:43.9626784Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:43.9627912Z             aten_mul_tensor_143: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2040, quantized_decomposed_dequantize_per_tensor_default_2049);  quantized_decomposed_dequantize_per_tensor_default_2040 = quantized_decomposed_dequantize_per_tensor_default_2049 = None
2025-03-21T20:31:43.9628805Z             quantized_decomposed_quantize_per_tensor_default_1508: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_143, 0.0001810029789339751, 34754, 0, 65535, torch.int32);  aten_mul_tensor_143 = None
2025-03-21T20:31:43.9629950Z             quantized_decomposed_dequantize_per_tensor_default_2061: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1508, 0.0001810029789339751, 34754, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1508 = None
2025-03-21T20:31:43.9631094Z             aten_mul_tensor_144: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2043, quantized_decomposed_dequantize_per_tensor_default_2044);  quantized_decomposed_dequantize_per_tensor_default_2043 = quantized_decomposed_dequantize_per_tensor_default_2044 = None
2025-03-21T20:31:43.9631965Z             quantized_decomposed_quantize_per_tensor_default_1509: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_144, 0.00041482385131530464, 31860, 0, 65535, torch.int32);  aten_mul_tensor_144 = None
2025-03-21T20:31:43.9633304Z             quantized_decomposed_dequantize_per_tensor_default_2062: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1509, 0.00041482385131530464, 31860, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1509 = None
2025-03-21T20:31:43.9634444Z             aten_add_tensor_46: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_2061, quantized_decomposed_dequantize_per_tensor_default_2062);  quantized_decomposed_dequantize_per_tensor_default_2061 = quantized_decomposed_dequantize_per_tensor_default_2062 = None
2025-03-21T20:31:43.9635363Z             quantized_decomposed_quantize_per_tensor_default_1510: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_46, 0.0004134253249503672, 31723, 0, 65535, torch.int32);  aten_add_tensor_46 = None
2025-03-21T20:31:43.9635496Z             
2025-03-21T20:31:43.9636438Z              # File: <eval_with_key>.50:5275 in forward, code: dequantize_per_tensor_default_1668 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1668, 0.0004134253249503672, 31723, 0, 65535, torch.int32);  quantize_per_tensor_default_1668 = None
2025-03-21T20:31:43.9637592Z             quantized_decomposed_dequantize_per_tensor_default_2063: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1510, 0.0004134253249503672, 31723, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1510 = None
2025-03-21T20:31:43.9637682Z             
2025-03-21T20:31:43.9638218Z              # File: /pytorch/executorch/examples/models/llama/rope.py:95 in apply_rotary_emb, code: xq_out = torch.stack([xq_out_r, xq_out_i], dim=-1).flatten(3)
2025-03-21T20:31:43.9639066Z             aten_unsqueeze_copy_default_102: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_2054, 4);  quantized_decomposed_dequantize_per_tensor_default_2054 = None
2025-03-21T20:31:43.9639877Z             aten_unsqueeze_copy_default_103: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_2057, 4);  quantized_decomposed_dequantize_per_tensor_default_2057 = None
2025-03-21T20:31:43.9640625Z             aten_cat_default_36: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_cat_default([aten_unsqueeze_copy_default_102, aten_unsqueeze_copy_default_103], -1);  aten_unsqueeze_copy_default_102 = aten_unsqueeze_copy_default_103 = None
2025-03-21T20:31:43.9641537Z             quantized_decomposed_quantize_per_tensor_default_1511: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_36, 0.00035090342862531543, 32108, 0, 65535, torch.int32);  aten_cat_default_36 = None
2025-03-21T20:31:43.9642685Z             quantized_decomposed_dequantize_per_tensor_default_2064: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1511, 0.00035090342862531543, 32108, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1511 = None
2025-03-21T20:31:43.9643462Z             aten_view_copy_default_169: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_2064, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_2064 = None
2025-03-21T20:31:43.9644375Z             quantized_decomposed_quantize_per_tensor_default_1512: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_169, 0.00035090342862531543, 32108, 0, 65535, torch.int32);  aten_view_copy_default_169 = None
2025-03-21T20:31:43.9644478Z             
2025-03-21T20:31:43.9645414Z              # File: <eval_with_key>.50:5281 in forward, code: dequantize_per_tensor_default_1670 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1670, 0.00035090342862531543, 32108, 0, 65535, torch.int32);  quantize_per_tensor_default_1670 = None
2025-03-21T20:31:43.9646573Z             quantized_decomposed_dequantize_per_tensor_default_2065: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1512, 0.00035090342862531543, 32108, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1512 = None
2025-03-21T20:31:43.9646664Z             
2025-03-21T20:31:43.9647256Z              # File: /pytorch/executorch/examples/models/llama/rope.py:96 in apply_rotary_emb, code: xk_out = torch.stack([xk_out_r, xk_out_i], dim=-1).flatten(3)
2025-03-21T20:31:43.9648060Z             aten_unsqueeze_copy_default_104: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_2060, 4);  quantized_decomposed_dequantize_per_tensor_default_2060 = None
2025-03-21T20:31:43.9648867Z             aten_unsqueeze_copy_default_105: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_2063, 4);  quantized_decomposed_dequantize_per_tensor_default_2063 = None
2025-03-21T20:31:43.9649684Z             aten_cat_default_37: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_cat_default([aten_unsqueeze_copy_default_104, aten_unsqueeze_copy_default_105], -1);  aten_unsqueeze_copy_default_104 = aten_unsqueeze_copy_default_105 = None
2025-03-21T20:31:43.9650604Z             quantized_decomposed_quantize_per_tensor_default_1513: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_37, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_cat_default_37 = None
2025-03-21T20:31:43.9651750Z             quantized_decomposed_dequantize_per_tensor_default_2066: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1513, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1513 = None
2025-03-21T20:31:43.9652527Z             aten_view_copy_default_170: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_2066, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_2066 = None
2025-03-21T20:31:43.9653465Z             quantized_decomposed_quantize_per_tensor_default_1514: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_170, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_view_copy_default_170 = None
2025-03-21T20:31:43.9653568Z             
2025-03-21T20:31:43.9654507Z              # File: <eval_with_key>.50:5287 in forward, code: dequantize_per_tensor_default_1672 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1672, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantize_per_tensor_default_1672 = None
2025-03-21T20:31:43.9655662Z             quantized_decomposed_dequantize_per_tensor_default_2067: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1514, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1514 = None
2025-03-21T20:31:43.9655752Z             
2025-03-21T20:31:43.9656527Z              # File: <eval_with_key>.50:5289 in forward, code: quantize_per_tensor_default_1673 = torch.ops.quantized_decomposed.quantize_per_tensor.default(type_as_18, 0.00035090342862531543, 32108, 0, 65535, torch.int32);  type_as_18 = None
2025-03-21T20:31:43.9657667Z             quantized_decomposed_quantize_per_tensor_default_1515: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_2065, 0.00035090342862531543, 32108, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_2065 = None
2025-03-21T20:31:43.9657766Z             
2025-03-21T20:31:43.9658294Z              # File: /pytorch/executorch/examples/models/llama/attention.py:249 in forward, code: q = q.transpose(1, 2)  # (bs, n_local_heads, seqlen, head_dim)
2025-03-21T20:31:43.9659479Z             quantized_decomposed_dequantize_per_tensor_default_2068: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1515, 0.00035090342862531543, 32108, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1515 = None
2025-03-21T20:31:43.9659591Z             
2025-03-21T20:31:43.9660360Z              # File: <eval_with_key>.50:5292 in forward, code: quantize_per_tensor_default_1674 = torch.ops.quantized_decomposed.quantize_per_tensor.default(type_as_19, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  type_as_19 = None
2025-03-21T20:31:43.9661506Z             quantized_decomposed_quantize_per_tensor_default_1516: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_2067, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_2067 = None
2025-03-21T20:31:43.9661609Z             
2025-03-21T20:31:43.9662281Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:345 in update, code: k_out = torch.ops.aten.index_put_(self.past_k_caches, [None, input_pos], k_val)
2025-03-21T20:31:43.9663469Z             quantized_decomposed_dequantize_per_tensor_default_2069: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1516, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1516 = None
2025-03-21T20:31:43.9663559Z             
2025-03-21T20:31:43.9664095Z              # File: /pytorch/executorch/examples/models/llama/attention.py:249 in forward, code: q = q.transpose(1, 2)  # (bs, n_local_heads, seqlen, head_dim)
2025-03-21T20:31:43.9664917Z             aten_permute_copy_default_375: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2068, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2068 = None
2025-03-21T20:31:43.9665870Z             quantized_decomposed_quantize_per_tensor_default_1517: "i32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_375, 0.00035090342862531543, 32108, 0, 65535, torch.int32);  aten_permute_copy_default_375 = None
2025-03-21T20:31:43.9665957Z             
2025-03-21T20:31:43.9666541Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.9667686Z             quantized_decomposed_dequantize_per_tensor_default_2070: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1517, 0.00035090342862531543, 32108, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1517 = None
2025-03-21T20:31:43.9667790Z             
2025-03-21T20:31:43.9668459Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:345 in update, code: k_out = torch.ops.aten.index_put_(self.past_k_caches, [None, input_pos], k_val)
2025-03-21T20:31:43.9669753Z             aten_index_put_default_18: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_index_put_default(quantized_decomposed_dequantize_per_tensor_default_140, [None, attn_options_input_pos], quantized_decomposed_dequantize_per_tensor_default_2069);  quantized_decomposed_dequantize_per_tensor_default_140 = quantized_decomposed_dequantize_per_tensor_default_2069 = None
2025-03-21T20:31:43.9670663Z             quantized_decomposed_quantize_per_tensor_default_1518: "i32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_put_default_18, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_index_put_default_18 = None
2025-03-21T20:31:43.9670792Z             
2025-03-21T20:31:43.9671608Z              # File: <eval_with_key>.50:5299 in forward, code: dequantize_per_tensor_default_1676 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1676, 0.00041487260023131967, 31841, 0, 65535, torch.int32)
2025-03-21T20:31:43.9672550Z             quantized_decomposed_dequantize_per_tensor_default_2071: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1518, 0.00041487260023131967, 31841, 0, 65535, torch.int32)
2025-03-21T20:31:43.9672637Z             
2025-03-21T20:31:43.9673284Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9674214Z             quantized_decomposed_dequantize_per_tensor_default_2072: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1518, 0.00041487260023131967, 31841, 0, 65535, torch.int32)
2025-03-21T20:31:43.9675172Z             quantized_decomposed_dequantize_per_tensor_default_2073: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1518, 0.00041487260023131967, 31841, 0, 65535, torch.int32)
2025-03-21T20:31:43.9676094Z             quantized_decomposed_dequantize_per_tensor_default_2074: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1518, 0.00041487260023131967, 31841, 0, 65535, torch.int32)
2025-03-21T20:31:43.9677052Z             quantized_decomposed_dequantize_per_tensor_default_2075: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1518, 0.00041487260023131967, 31841, 0, 65535, torch.int32)
2025-03-21T20:31:43.9677978Z             quantized_decomposed_dequantize_per_tensor_default_2076: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1518, 0.00041487260023131967, 31841, 0, 65535, torch.int32)
2025-03-21T20:31:43.9678912Z             quantized_decomposed_dequantize_per_tensor_default_2077: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1518, 0.00041487260023131967, 31841, 0, 65535, torch.int32)
2025-03-21T20:31:43.9679835Z             quantized_decomposed_dequantize_per_tensor_default_2078: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1518, 0.00041487260023131967, 31841, 0, 65535, torch.int32)
2025-03-21T20:31:43.9680777Z             quantized_decomposed_dequantize_per_tensor_default_2079: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1518, 0.00041487260023131967, 31841, 0, 65535, torch.int32)
2025-03-21T20:31:43.9681703Z             quantized_decomposed_dequantize_per_tensor_default_2080: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1518, 0.00041487260023131967, 31841, 0, 65535, torch.int32)
2025-03-21T20:31:43.9682638Z             quantized_decomposed_dequantize_per_tensor_default_2081: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1518, 0.00041487260023131967, 31841, 0, 65535, torch.int32)
2025-03-21T20:31:43.9683587Z             quantized_decomposed_dequantize_per_tensor_default_2082: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1518, 0.00041487260023131967, 31841, 0, 65535, torch.int32)
2025-03-21T20:31:43.9684777Z             quantized_decomposed_dequantize_per_tensor_default_2083: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1518, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1518 = None
2025-03-21T20:31:43.9684869Z             
2025-03-21T20:31:43.9685557Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:346 in update, code: v_out = torch.ops.aten.index_put_(self.past_v_caches, [None, input_pos], v_val)
2025-03-21T20:31:43.9686875Z             aten_index_put_default_19: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_index_put_default(quantized_decomposed_dequantize_per_tensor_default_141, [None, attn_options_input_pos], quantized_decomposed_dequantize_per_tensor_default_2031);  quantized_decomposed_dequantize_per_tensor_default_141 = quantized_decomposed_dequantize_per_tensor_default_2031 = None
2025-03-21T20:31:43.9687802Z             quantized_decomposed_quantize_per_tensor_default_1519: "i32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_put_default_19, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_index_put_default_19 = None
2025-03-21T20:31:43.9687890Z             
2025-03-21T20:31:43.9688696Z              # File: <eval_with_key>.50:5314 in forward, code: dequantize_per_tensor_default_1677 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1677, 0.0001724863686831668, 32338, 0, 65535, torch.int32)
2025-03-21T20:31:43.9689717Z             quantized_decomposed_dequantize_per_tensor_default_2084: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1519, 0.0001724863686831668, 32338, 0, 65535, torch.int32)
2025-03-21T20:31:43.9689828Z             
2025-03-21T20:31:43.9690465Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9691405Z             quantized_decomposed_dequantize_per_tensor_default_2085: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1519, 0.0001724863686831668, 32338, 0, 65535, torch.int32)
2025-03-21T20:31:43.9692328Z             quantized_decomposed_dequantize_per_tensor_default_2086: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1519, 0.0001724863686831668, 32338, 0, 65535, torch.int32)
2025-03-21T20:31:43.9693262Z             quantized_decomposed_dequantize_per_tensor_default_2087: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1519, 0.0001724863686831668, 32338, 0, 65535, torch.int32)
2025-03-21T20:31:43.9694302Z             quantized_decomposed_dequantize_per_tensor_default_2088: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1519, 0.0001724863686831668, 32338, 0, 65535, torch.int32)
2025-03-21T20:31:43.9695228Z             quantized_decomposed_dequantize_per_tensor_default_2089: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1519, 0.0001724863686831668, 32338, 0, 65535, torch.int32)
2025-03-21T20:31:43.9696236Z             quantized_decomposed_dequantize_per_tensor_default_2090: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1519, 0.0001724863686831668, 32338, 0, 65535, torch.int32)
2025-03-21T20:31:43.9697154Z             quantized_decomposed_dequantize_per_tensor_default_2091: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1519, 0.0001724863686831668, 32338, 0, 65535, torch.int32)
2025-03-21T20:31:43.9698086Z             quantized_decomposed_dequantize_per_tensor_default_2092: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1519, 0.0001724863686831668, 32338, 0, 65535, torch.int32)
2025-03-21T20:31:43.9699033Z             quantized_decomposed_dequantize_per_tensor_default_2093: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1519, 0.0001724863686831668, 32338, 0, 65535, torch.int32)
2025-03-21T20:31:43.9699966Z             quantized_decomposed_dequantize_per_tensor_default_2094: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1519, 0.0001724863686831668, 32338, 0, 65535, torch.int32)
2025-03-21T20:31:43.9700885Z             quantized_decomposed_dequantize_per_tensor_default_2095: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1519, 0.0001724863686831668, 32338, 0, 65535, torch.int32)
2025-03-21T20:31:43.9702075Z             quantized_decomposed_dequantize_per_tensor_default_2096: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1519, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1519 = None
2025-03-21T20:31:43.9702168Z             
2025-03-21T20:31:43.9702820Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9703625Z             aten_permute_copy_default_376: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2083, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2083 = None
2025-03-21T20:31:43.9704707Z             quantized_decomposed_quantize_per_tensor_default_1520: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_376, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_permute_copy_default_376 = None
2025-03-21T20:31:43.9706026Z             quantized_decomposed_dequantize_per_tensor_default_2097: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1520, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1520 = None
2025-03-21T20:31:43.9706788Z             aten_select_copy_int_432: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2097, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2097 = None
2025-03-21T20:31:43.9707735Z             quantized_decomposed_quantize_per_tensor_default_1521: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_432, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_select_copy_int_432 = None
2025-03-21T20:31:43.9708929Z             quantized_decomposed_dequantize_per_tensor_default_2098: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1521, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1521 = None
2025-03-21T20:31:43.9709678Z             aten_select_copy_int_433: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2098, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2098 = None
2025-03-21T20:31:43.9710568Z             quantized_decomposed_quantize_per_tensor_default_1522: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_433, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_select_copy_int_433 = None
2025-03-21T20:31:43.9710675Z             
2025-03-21T20:31:43.9711641Z              # File: <eval_with_key>.50:5335 in forward, code: dequantize_per_tensor_default_1680 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1680, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantize_per_tensor_default_1680 = None
2025-03-21T20:31:43.9712802Z             quantized_decomposed_dequantize_per_tensor_default_2099: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1522, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1522 = None
2025-03-21T20:31:43.9712890Z             
2025-03-21T20:31:43.9713524Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9714367Z             aten_permute_copy_default_377: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2082, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2082 = None
2025-03-21T20:31:43.9715316Z             quantized_decomposed_quantize_per_tensor_default_1523: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_377, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_permute_copy_default_377 = None
2025-03-21T20:31:43.9716485Z             quantized_decomposed_dequantize_per_tensor_default_2100: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1523, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1523 = None
2025-03-21T20:31:43.9717239Z             aten_select_copy_int_434: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2100, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2100 = None
2025-03-21T20:31:43.9718135Z             quantized_decomposed_quantize_per_tensor_default_1524: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_434, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_select_copy_int_434 = None
2025-03-21T20:31:43.9719294Z             quantized_decomposed_dequantize_per_tensor_default_2101: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1524, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1524 = None
2025-03-21T20:31:43.9720060Z             aten_select_copy_int_435: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2101, 0, 1);  quantized_decomposed_dequantize_per_tensor_default_2101 = None
2025-03-21T20:31:43.9720996Z             quantized_decomposed_quantize_per_tensor_default_1525: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_435, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_select_copy_int_435 = None
2025-03-21T20:31:43.9721089Z             
2025-03-21T20:31:43.9722043Z              # File: <eval_with_key>.50:5344 in forward, code: dequantize_per_tensor_default_1683 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1683, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantize_per_tensor_default_1683 = None
2025-03-21T20:31:43.9723198Z             quantized_decomposed_dequantize_per_tensor_default_2102: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1525, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1525 = None
2025-03-21T20:31:43.9723307Z             
2025-03-21T20:31:43.9723972Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9724789Z             aten_permute_copy_default_378: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2081, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2081 = None
2025-03-21T20:31:43.9725738Z             quantized_decomposed_quantize_per_tensor_default_1526: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_378, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_permute_copy_default_378 = None
2025-03-21T20:31:43.9726962Z             quantized_decomposed_dequantize_per_tensor_default_2103: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1526, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1526 = None
2025-03-21T20:31:43.9727704Z             aten_select_copy_int_436: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2103, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2103 = None
2025-03-21T20:31:43.9728614Z             quantized_decomposed_quantize_per_tensor_default_1527: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_436, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_select_copy_int_436 = None
2025-03-21T20:31:43.9729844Z             quantized_decomposed_dequantize_per_tensor_default_2104: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1527, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1527 = None
2025-03-21T20:31:43.9730598Z             aten_select_copy_int_437: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2104, 0, 2);  quantized_decomposed_dequantize_per_tensor_default_2104 = None
2025-03-21T20:31:43.9731494Z             quantized_decomposed_quantize_per_tensor_default_1528: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_437, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_select_copy_int_437 = None
2025-03-21T20:31:43.9731600Z             
2025-03-21T20:31:43.9732768Z              # File: <eval_with_key>.50:5353 in forward, code: dequantize_per_tensor_default_1686 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1686, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantize_per_tensor_default_1686 = None
2025-03-21T20:31:43.9733969Z             quantized_decomposed_dequantize_per_tensor_default_2105: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1528, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1528 = None
2025-03-21T20:31:43.9734058Z             
2025-03-21T20:31:43.9734708Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9735511Z             aten_permute_copy_default_379: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2080, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2080 = None
2025-03-21T20:31:43.9736517Z             quantized_decomposed_quantize_per_tensor_default_1529: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_379, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_permute_copy_default_379 = None
2025-03-21T20:31:43.9737675Z             quantized_decomposed_dequantize_per_tensor_default_2106: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1529, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1529 = None
2025-03-21T20:31:43.9738463Z             aten_select_copy_int_438: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2106, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2106 = None
2025-03-21T20:31:43.9739378Z             quantized_decomposed_quantize_per_tensor_default_1530: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_438, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_select_copy_int_438 = None
2025-03-21T20:31:43.9740524Z             quantized_decomposed_dequantize_per_tensor_default_2107: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1530, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1530 = None
2025-03-21T20:31:43.9741279Z             aten_select_copy_int_439: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2107, 0, 3);  quantized_decomposed_dequantize_per_tensor_default_2107 = None
2025-03-21T20:31:43.9742172Z             quantized_decomposed_quantize_per_tensor_default_1531: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_439, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_select_copy_int_439 = None
2025-03-21T20:31:43.9742272Z             
2025-03-21T20:31:43.9743208Z              # File: <eval_with_key>.50:5362 in forward, code: dequantize_per_tensor_default_1689 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1689, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantize_per_tensor_default_1689 = None
2025-03-21T20:31:43.9744397Z             quantized_decomposed_dequantize_per_tensor_default_2108: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1531, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1531 = None
2025-03-21T20:31:43.9744510Z             
2025-03-21T20:31:43.9745160Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9745959Z             aten_permute_copy_default_380: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2079, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2079 = None
2025-03-21T20:31:43.9746912Z             quantized_decomposed_quantize_per_tensor_default_1532: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_380, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_permute_copy_default_380 = None
2025-03-21T20:31:43.9748090Z             quantized_decomposed_dequantize_per_tensor_default_2109: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1532, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1532 = None
2025-03-21T20:31:43.9748845Z             aten_select_copy_int_440: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2109, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2109 = None
2025-03-21T20:31:43.9749744Z             quantized_decomposed_quantize_per_tensor_default_1533: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_440, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_select_copy_int_440 = None
2025-03-21T20:31:43.9750932Z             quantized_decomposed_dequantize_per_tensor_default_2110: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1533, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1533 = None
2025-03-21T20:31:43.9751670Z             aten_select_copy_int_441: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2110, 0, 4);  quantized_decomposed_dequantize_per_tensor_default_2110 = None
2025-03-21T20:31:43.9752576Z             quantized_decomposed_quantize_per_tensor_default_1534: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_441, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_select_copy_int_441 = None
2025-03-21T20:31:43.9752666Z             
2025-03-21T20:31:43.9753621Z              # File: <eval_with_key>.50:5371 in forward, code: dequantize_per_tensor_default_1692 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1692, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantize_per_tensor_default_1692 = None
2025-03-21T20:31:43.9754773Z             quantized_decomposed_dequantize_per_tensor_default_2111: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1534, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1534 = None
2025-03-21T20:31:43.9754873Z             
2025-03-21T20:31:43.9755507Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9756343Z             aten_permute_copy_default_381: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2078, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2078 = None
2025-03-21T20:31:43.9757309Z             quantized_decomposed_quantize_per_tensor_default_1535: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_381, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_permute_copy_default_381 = None
2025-03-21T20:31:43.9758469Z             quantized_decomposed_dequantize_per_tensor_default_2112: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1535, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1535 = None
2025-03-21T20:31:43.9759207Z             aten_select_copy_int_442: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2112, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2112 = None
2025-03-21T20:31:43.9760140Z             quantized_decomposed_quantize_per_tensor_default_1536: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_442, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_select_copy_int_442 = None
2025-03-21T20:31:43.9761288Z             quantized_decomposed_dequantize_per_tensor_default_2113: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1536, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1536 = None
2025-03-21T20:31:43.9762035Z             aten_select_copy_int_443: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2113, 0, 5);  quantized_decomposed_dequantize_per_tensor_default_2113 = None
2025-03-21T20:31:43.9762970Z             quantized_decomposed_quantize_per_tensor_default_1537: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_443, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_select_copy_int_443 = None
2025-03-21T20:31:43.9763059Z             
2025-03-21T20:31:43.9763999Z              # File: <eval_with_key>.50:5380 in forward, code: dequantize_per_tensor_default_1695 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1695, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantize_per_tensor_default_1695 = None
2025-03-21T20:31:43.9765156Z             quantized_decomposed_dequantize_per_tensor_default_2114: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1537, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1537 = None
2025-03-21T20:31:43.9765245Z             
2025-03-21T20:31:43.9765893Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9766698Z             aten_permute_copy_default_382: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2077, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2077 = None
2025-03-21T20:31:43.9767649Z             quantized_decomposed_quantize_per_tensor_default_1538: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_382, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_permute_copy_default_382 = None
2025-03-21T20:31:43.9768839Z             quantized_decomposed_dequantize_per_tensor_default_2115: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1538, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1538 = None
2025-03-21T20:31:43.9769676Z             aten_select_copy_int_444: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2115, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2115 = None
2025-03-21T20:31:43.9770588Z             quantized_decomposed_quantize_per_tensor_default_1539: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_444, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_select_copy_int_444 = None
2025-03-21T20:31:43.9771741Z             quantized_decomposed_dequantize_per_tensor_default_2116: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1539, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1539 = None
2025-03-21T20:31:43.9772521Z             aten_select_copy_int_445: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2116, 0, 6);  quantized_decomposed_dequantize_per_tensor_default_2116 = None
2025-03-21T20:31:43.9773414Z             quantized_decomposed_quantize_per_tensor_default_1540: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_445, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_select_copy_int_445 = None
2025-03-21T20:31:43.9773516Z             
2025-03-21T20:31:43.9774483Z              # File: <eval_with_key>.50:5389 in forward, code: dequantize_per_tensor_default_1698 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1698, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantize_per_tensor_default_1698 = None
2025-03-21T20:31:43.9775649Z             quantized_decomposed_dequantize_per_tensor_default_2117: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1540, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1540 = None
2025-03-21T20:31:43.9775738Z             
2025-03-21T20:31:43.9776387Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9777188Z             aten_permute_copy_default_383: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2076, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2076 = None
2025-03-21T20:31:43.9778147Z             quantized_decomposed_quantize_per_tensor_default_1541: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_383, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_permute_copy_default_383 = None
2025-03-21T20:31:43.9779300Z             quantized_decomposed_dequantize_per_tensor_default_2118: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1541, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1541 = None
2025-03-21T20:31:43.9780048Z             aten_select_copy_int_446: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2118, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2118 = None
2025-03-21T20:31:43.9780972Z             quantized_decomposed_quantize_per_tensor_default_1542: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_446, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_select_copy_int_446 = None
2025-03-21T20:31:43.9782170Z             quantized_decomposed_dequantize_per_tensor_default_2119: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1542, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1542 = None
2025-03-21T20:31:43.9782903Z             aten_select_copy_int_447: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2119, 0, 7);  quantized_decomposed_dequantize_per_tensor_default_2119 = None
2025-03-21T20:31:43.9783810Z             quantized_decomposed_quantize_per_tensor_default_1543: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_447, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_select_copy_int_447 = None
2025-03-21T20:31:43.9783903Z             
2025-03-21T20:31:43.9784875Z              # File: <eval_with_key>.50:5398 in forward, code: dequantize_per_tensor_default_1701 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1701, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantize_per_tensor_default_1701 = None
2025-03-21T20:31:43.9786022Z             quantized_decomposed_dequantize_per_tensor_default_2120: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1543, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1543 = None
2025-03-21T20:31:43.9786144Z             
2025-03-21T20:31:43.9786780Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9787595Z             aten_permute_copy_default_384: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2075, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2075 = None
2025-03-21T20:31:43.9788538Z             quantized_decomposed_quantize_per_tensor_default_1544: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_384, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_permute_copy_default_384 = None
2025-03-21T20:31:43.9789704Z             quantized_decomposed_dequantize_per_tensor_default_2121: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1544, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1544 = None
2025-03-21T20:31:43.9790445Z             aten_select_copy_int_448: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2121, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2121 = None
2025-03-21T20:31:43.9791350Z             quantized_decomposed_quantize_per_tensor_default_1545: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_448, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_select_copy_int_448 = None
2025-03-21T20:31:43.9792540Z             quantized_decomposed_dequantize_per_tensor_default_2122: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1545, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1545 = None
2025-03-21T20:31:43.9793304Z             aten_select_copy_int_449: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2122, 0, 8);  quantized_decomposed_dequantize_per_tensor_default_2122 = None
2025-03-21T20:31:43.9794210Z             quantized_decomposed_quantize_per_tensor_default_1546: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_449, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_select_copy_int_449 = None
2025-03-21T20:31:43.9794298Z             
2025-03-21T20:31:43.9795250Z              # File: <eval_with_key>.50:5407 in forward, code: dequantize_per_tensor_default_1704 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1704, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantize_per_tensor_default_1704 = None
2025-03-21T20:31:43.9796441Z             quantized_decomposed_dequantize_per_tensor_default_2123: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1546, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1546 = None
2025-03-21T20:31:43.9796544Z             
2025-03-21T20:31:43.9797179Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9797994Z             aten_permute_copy_default_385: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2074, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2074 = None
2025-03-21T20:31:43.9798961Z             quantized_decomposed_quantize_per_tensor_default_1547: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_385, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_permute_copy_default_385 = None
2025-03-21T20:31:43.9800125Z             quantized_decomposed_dequantize_per_tensor_default_2124: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1547, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1547 = None
2025-03-21T20:31:43.9800868Z             aten_select_copy_int_450: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2124, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2124 = None
2025-03-21T20:31:43.9801782Z             quantized_decomposed_quantize_per_tensor_default_1548: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_450, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_select_copy_int_450 = None
2025-03-21T20:31:43.9802935Z             quantized_decomposed_dequantize_per_tensor_default_2125: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1548, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1548 = None
2025-03-21T20:31:43.9803686Z             aten_select_copy_int_451: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2125, 0, 9);  quantized_decomposed_dequantize_per_tensor_default_2125 = None
2025-03-21T20:31:43.9804602Z             quantized_decomposed_quantize_per_tensor_default_1549: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_451, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_select_copy_int_451 = None
2025-03-21T20:31:43.9804725Z             
2025-03-21T20:31:43.9805667Z              # File: <eval_with_key>.50:5416 in forward, code: dequantize_per_tensor_default_1707 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1707, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantize_per_tensor_default_1707 = None
2025-03-21T20:31:43.9806967Z             quantized_decomposed_dequantize_per_tensor_default_2126: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1549, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1549 = None
2025-03-21T20:31:43.9807062Z             
2025-03-21T20:31:43.9807709Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9808546Z             aten_permute_copy_default_386: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2073, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2073 = None
2025-03-21T20:31:43.9809579Z             quantized_decomposed_quantize_per_tensor_default_1550: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_386, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_permute_copy_default_386 = None
2025-03-21T20:31:43.9810734Z             quantized_decomposed_dequantize_per_tensor_default_2127: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1550, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1550 = None
2025-03-21T20:31:43.9811528Z             aten_select_copy_int_452: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2127, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2127 = None
2025-03-21T20:31:43.9812424Z             quantized_decomposed_quantize_per_tensor_default_1551: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_452, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_select_copy_int_452 = None
2025-03-21T20:31:43.9813588Z             quantized_decomposed_dequantize_per_tensor_default_2128: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1551, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1551 = None
2025-03-21T20:31:43.9814333Z             aten_select_copy_int_453: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2128, 0, 10);  quantized_decomposed_dequantize_per_tensor_default_2128 = None
2025-03-21T20:31:43.9815244Z             quantized_decomposed_quantize_per_tensor_default_1552: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_453, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_select_copy_int_453 = None
2025-03-21T20:31:43.9815349Z             
2025-03-21T20:31:43.9816286Z              # File: <eval_with_key>.50:5425 in forward, code: dequantize_per_tensor_default_1710 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1710, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantize_per_tensor_default_1710 = None
2025-03-21T20:31:43.9817473Z             quantized_decomposed_dequantize_per_tensor_default_2129: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1552, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1552 = None
2025-03-21T20:31:43.9817592Z             
2025-03-21T20:31:43.9818239Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9819038Z             aten_permute_copy_default_387: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2072, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2072 = None
2025-03-21T20:31:43.9820004Z             quantized_decomposed_quantize_per_tensor_default_1553: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_387, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_permute_copy_default_387 = None
2025-03-21T20:31:43.9821198Z             quantized_decomposed_dequantize_per_tensor_default_2130: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1553, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1553 = None
2025-03-21T20:31:43.9821940Z             aten_select_copy_int_454: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2130, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2130 = None
2025-03-21T20:31:43.9822847Z             quantized_decomposed_quantize_per_tensor_default_1554: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_454, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_select_copy_int_454 = None
2025-03-21T20:31:43.9824026Z             quantized_decomposed_dequantize_per_tensor_default_2131: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1554, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1554 = None
2025-03-21T20:31:43.9824774Z             aten_select_copy_int_455: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2131, 0, 11);  quantized_decomposed_dequantize_per_tensor_default_2131 = None
2025-03-21T20:31:43.9825666Z             quantized_decomposed_quantize_per_tensor_default_1555: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_455, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_select_copy_int_455 = None
2025-03-21T20:31:43.9825772Z             
2025-03-21T20:31:43.9826712Z              # File: <eval_with_key>.50:5434 in forward, code: dequantize_per_tensor_default_1713 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1713, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantize_per_tensor_default_1713 = None
2025-03-21T20:31:43.9827875Z             quantized_decomposed_dequantize_per_tensor_default_2132: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1555, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1555 = None
2025-03-21T20:31:43.9827967Z             
2025-03-21T20:31:43.9828613Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9834365Z             aten_cat_default_38: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_aten_cat_default([quantized_decomposed_dequantize_per_tensor_default_2099, quantized_decomposed_dequantize_per_tensor_default_2102, quantized_decomposed_dequantize_per_tensor_default_2105, quantized_decomposed_dequantize_per_tensor_default_2108, quantized_decomposed_dequantize_per_tensor_default_2111, quantized_decomposed_dequantize_per_tensor_default_2114, quantized_decomposed_dequantize_per_tensor_default_2117, quantized_decomposed_dequantize_per_tensor_default_2120, quantized_decomposed_dequantize_per_tensor_default_2123, quantized_decomposed_dequantize_per_tensor_default_2126, quantized_decomposed_dequantize_per_tensor_default_2129, quantized_decomposed_dequantize_per_tensor_default_2132]);  quantized_decomposed_dequantize_per_tensor_default_2099 = quantized_decomposed_dequantize_per_tensor_default_2102 = quantized_decomposed_dequantize_per_tensor_default_2105 = quantized_decomposed_dequantize_per_tensor_default_2108 = quantized_decomposed_dequantize_per_tensor_default_2111 = quantized_decomposed_dequantize_per_tensor_default_2114 = quantized_decomposed_dequantize_per_tensor_default_2117 = quantized_decomposed_dequantize_per_tensor_default_2120 = quantized_decomposed_dequantize_per_tensor_default_2123 = quantized_decomposed_dequantize_per_tensor_default_2126 = quantized_decomposed_dequantize_per_tensor_default_2129 = quantized_decomposed_dequantize_per_tensor_default_2132 = None
2025-03-21T20:31:43.9835306Z             quantized_decomposed_quantize_per_tensor_default_1556: "i32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_38, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_cat_default_38 = None
2025-03-21T20:31:43.9836475Z             quantized_decomposed_dequantize_per_tensor_default_2133: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1556, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1556 = None
2025-03-21T20:31:43.9837295Z             aten_view_copy_default_171: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_2133, [1, 12, 128, 64]);  quantized_decomposed_dequantize_per_tensor_default_2133 = None
2025-03-21T20:31:43.9838226Z             quantized_decomposed_quantize_per_tensor_default_1557: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_171, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_view_copy_default_171 = None
2025-03-21T20:31:43.9838318Z             
2025-03-21T20:31:43.9838909Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.9840073Z             quantized_decomposed_dequantize_per_tensor_default_2134: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1557, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1557 = None
2025-03-21T20:31:43.9840176Z             
2025-03-21T20:31:43.9840810Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9841623Z             aten_permute_copy_default_388: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2096, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2096 = None
2025-03-21T20:31:43.9842602Z             quantized_decomposed_quantize_per_tensor_default_1558: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_388, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_permute_copy_default_388 = None
2025-03-21T20:31:43.9843791Z             quantized_decomposed_dequantize_per_tensor_default_2135: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1558, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1558 = None
2025-03-21T20:31:43.9844530Z             aten_select_copy_int_456: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2135, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2135 = None
2025-03-21T20:31:43.9845441Z             quantized_decomposed_quantize_per_tensor_default_1559: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_456, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_select_copy_int_456 = None
2025-03-21T20:31:43.9846614Z             quantized_decomposed_dequantize_per_tensor_default_2136: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1559, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1559 = None
2025-03-21T20:31:43.9847361Z             aten_select_copy_int_457: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2136, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2136 = None
2025-03-21T20:31:43.9848258Z             quantized_decomposed_quantize_per_tensor_default_1560: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_457, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_select_copy_int_457 = None
2025-03-21T20:31:43.9848374Z             
2025-03-21T20:31:43.9849383Z              # File: <eval_with_key>.50:5449 in forward, code: dequantize_per_tensor_default_1718 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1718, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantize_per_tensor_default_1718 = None
2025-03-21T20:31:43.9850748Z             quantized_decomposed_dequantize_per_tensor_default_2137: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1560, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1560 = None
2025-03-21T20:31:43.9850842Z             
2025-03-21T20:31:43.9851492Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9852298Z             aten_permute_copy_default_389: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2095, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2095 = None
2025-03-21T20:31:43.9853246Z             quantized_decomposed_quantize_per_tensor_default_1561: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_389, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_permute_copy_default_389 = None
2025-03-21T20:31:43.9854402Z             quantized_decomposed_dequantize_per_tensor_default_2138: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1561, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1561 = None
2025-03-21T20:31:43.9855210Z             aten_select_copy_int_458: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2138, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2138 = None
2025-03-21T20:31:43.9856120Z             quantized_decomposed_quantize_per_tensor_default_1562: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_458, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_select_copy_int_458 = None
2025-03-21T20:31:43.9857263Z             quantized_decomposed_dequantize_per_tensor_default_2139: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1562, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1562 = None
2025-03-21T20:31:43.9858011Z             aten_select_copy_int_459: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2139, 0, 1);  quantized_decomposed_dequantize_per_tensor_default_2139 = None
2025-03-21T20:31:43.9858928Z             quantized_decomposed_quantize_per_tensor_default_1563: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_459, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_select_copy_int_459 = None
2025-03-21T20:31:43.9859029Z             
2025-03-21T20:31:43.9859962Z              # File: <eval_with_key>.50:5458 in forward, code: dequantize_per_tensor_default_1721 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1721, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantize_per_tensor_default_1721 = None
2025-03-21T20:31:43.9861144Z             quantized_decomposed_dequantize_per_tensor_default_2140: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1563, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1563 = None
2025-03-21T20:31:43.9861232Z             
2025-03-21T20:31:43.9861880Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9862679Z             aten_permute_copy_default_390: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2094, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2094 = None
2025-03-21T20:31:43.9863628Z             quantized_decomposed_quantize_per_tensor_default_1564: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_390, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_permute_copy_default_390 = None
2025-03-21T20:31:43.9864775Z             quantized_decomposed_dequantize_per_tensor_default_2141: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1564, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1564 = None
2025-03-21T20:31:43.9865528Z             aten_select_copy_int_460: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2141, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2141 = None
2025-03-21T20:31:43.9866420Z             quantized_decomposed_quantize_per_tensor_default_1565: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_460, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_select_copy_int_460 = None
2025-03-21T20:31:43.9867632Z             quantized_decomposed_dequantize_per_tensor_default_2142: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1565, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1565 = None
2025-03-21T20:31:43.9868370Z             aten_select_copy_int_461: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2142, 0, 2);  quantized_decomposed_dequantize_per_tensor_default_2142 = None
2025-03-21T20:31:43.9869267Z             quantized_decomposed_quantize_per_tensor_default_1566: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_461, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_select_copy_int_461 = None
2025-03-21T20:31:43.9869356Z             
2025-03-21T20:31:43.9870327Z              # File: <eval_with_key>.50:5467 in forward, code: dequantize_per_tensor_default_1724 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1724, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantize_per_tensor_default_1724 = None
2025-03-21T20:31:43.9871471Z             quantized_decomposed_dequantize_per_tensor_default_2143: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1566, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1566 = None
2025-03-21T20:31:43.9871569Z             
2025-03-21T20:31:43.9872206Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9873057Z             aten_permute_copy_default_391: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2093, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2093 = None
2025-03-21T20:31:43.9873999Z             quantized_decomposed_quantize_per_tensor_default_1567: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_391, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_permute_copy_default_391 = None
2025-03-21T20:31:43.9875156Z             quantized_decomposed_dequantize_per_tensor_default_2144: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1567, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1567 = None
2025-03-21T20:31:43.9875898Z             aten_select_copy_int_462: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2144, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2144 = None
2025-03-21T20:31:43.9876801Z             quantized_decomposed_quantize_per_tensor_default_1568: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_462, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_select_copy_int_462 = None
2025-03-21T20:31:43.9877954Z             quantized_decomposed_dequantize_per_tensor_default_2145: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1568, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1568 = None
2025-03-21T20:31:43.9878716Z             aten_select_copy_int_463: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2145, 0, 3);  quantized_decomposed_dequantize_per_tensor_default_2145 = None
2025-03-21T20:31:43.9879638Z             quantized_decomposed_quantize_per_tensor_default_1569: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_463, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_select_copy_int_463 = None
2025-03-21T20:31:43.9879726Z             
2025-03-21T20:31:43.9880672Z              # File: <eval_with_key>.50:5476 in forward, code: dequantize_per_tensor_default_1727 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1727, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantize_per_tensor_default_1727 = None
2025-03-21T20:31:43.9881813Z             quantized_decomposed_dequantize_per_tensor_default_2146: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1569, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1569 = None
2025-03-21T20:31:43.9881916Z             
2025-03-21T20:31:43.9882573Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9883386Z             aten_permute_copy_default_392: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2092, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2092 = None
2025-03-21T20:31:43.9884323Z             quantized_decomposed_quantize_per_tensor_default_1570: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_392, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_permute_copy_default_392 = None
2025-03-21T20:31:43.9885513Z             quantized_decomposed_dequantize_per_tensor_default_2147: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1570, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1570 = None
2025-03-21T20:31:43.9886252Z             aten_select_copy_int_464: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2147, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2147 = None
2025-03-21T20:31:43.9887158Z             quantized_decomposed_quantize_per_tensor_default_1571: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_464, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_select_copy_int_464 = None
2025-03-21T20:31:43.9888308Z             quantized_decomposed_dequantize_per_tensor_default_2148: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1571, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1571 = None
2025-03-21T20:31:43.9889061Z             aten_select_copy_int_465: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2148, 0, 4);  quantized_decomposed_dequantize_per_tensor_default_2148 = None
2025-03-21T20:31:43.9890036Z             quantized_decomposed_quantize_per_tensor_default_1572: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_465, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_select_copy_int_465 = None
2025-03-21T20:31:43.9890147Z             
2025-03-21T20:31:43.9891124Z              # File: <eval_with_key>.50:5485 in forward, code: dequantize_per_tensor_default_1730 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1730, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantize_per_tensor_default_1730 = None
2025-03-21T20:31:43.9892308Z             quantized_decomposed_dequantize_per_tensor_default_2149: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1572, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1572 = None
2025-03-21T20:31:43.9892397Z             
2025-03-21T20:31:43.9893047Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9893851Z             aten_permute_copy_default_393: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2091, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2091 = None
2025-03-21T20:31:43.9894829Z             quantized_decomposed_quantize_per_tensor_default_1573: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_393, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_permute_copy_default_393 = None
2025-03-21T20:31:43.9895976Z             quantized_decomposed_dequantize_per_tensor_default_2150: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1573, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1573 = None
2025-03-21T20:31:43.9896747Z             aten_select_copy_int_466: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2150, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2150 = None
2025-03-21T20:31:43.9897760Z             quantized_decomposed_quantize_per_tensor_default_1574: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_466, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_select_copy_int_466 = None
2025-03-21T20:31:43.9898918Z             quantized_decomposed_dequantize_per_tensor_default_2151: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1574, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1574 = None
2025-03-21T20:31:43.9899654Z             aten_select_copy_int_467: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2151, 0, 5);  quantized_decomposed_dequantize_per_tensor_default_2151 = None
2025-03-21T20:31:43.9900560Z             quantized_decomposed_quantize_per_tensor_default_1575: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_467, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_select_copy_int_467 = None
2025-03-21T20:31:43.9900648Z             
2025-03-21T20:31:43.9901593Z              # File: <eval_with_key>.50:5494 in forward, code: dequantize_per_tensor_default_1733 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1733, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantize_per_tensor_default_1733 = None
2025-03-21T20:31:43.9902735Z             quantized_decomposed_dequantize_per_tensor_default_2152: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1575, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1575 = None
2025-03-21T20:31:43.9902870Z             
2025-03-21T20:31:43.9903529Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9904341Z             aten_permute_copy_default_394: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2090, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2090 = None
2025-03-21T20:31:43.9905274Z             quantized_decomposed_quantize_per_tensor_default_1576: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_394, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_permute_copy_default_394 = None
2025-03-21T20:31:43.9906436Z             quantized_decomposed_dequantize_per_tensor_default_2153: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1576, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1576 = None
2025-03-21T20:31:43.9907222Z             aten_select_copy_int_468: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2153, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2153 = None
2025-03-21T20:31:43.9908302Z             quantized_decomposed_quantize_per_tensor_default_1577: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_468, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_select_copy_int_468 = None
2025-03-21T20:31:43.9909624Z             quantized_decomposed_dequantize_per_tensor_default_2154: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1577, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1577 = None
2025-03-21T20:31:43.9910369Z             aten_select_copy_int_469: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2154, 0, 6);  quantized_decomposed_dequantize_per_tensor_default_2154 = None
2025-03-21T20:31:43.9911271Z             quantized_decomposed_quantize_per_tensor_default_1578: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_469, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_select_copy_int_469 = None
2025-03-21T20:31:43.9911359Z             
2025-03-21T20:31:43.9912311Z              # File: <eval_with_key>.50:5503 in forward, code: dequantize_per_tensor_default_1736 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1736, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantize_per_tensor_default_1736 = None
2025-03-21T20:31:43.9913456Z             quantized_decomposed_dequantize_per_tensor_default_2155: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1578, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1578 = None
2025-03-21T20:31:43.9913557Z             
2025-03-21T20:31:43.9914194Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9915009Z             aten_permute_copy_default_395: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2089, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2089 = None
2025-03-21T20:31:43.9916011Z             quantized_decomposed_quantize_per_tensor_default_1579: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_395, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_permute_copy_default_395 = None
2025-03-21T20:31:43.9917171Z             quantized_decomposed_dequantize_per_tensor_default_2156: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1579, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1579 = None
2025-03-21T20:31:43.9917905Z             aten_select_copy_int_470: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2156, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2156 = None
2025-03-21T20:31:43.9918812Z             quantized_decomposed_quantize_per_tensor_default_1580: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_470, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_select_copy_int_470 = None
2025-03-21T20:31:43.9920018Z             quantized_decomposed_dequantize_per_tensor_default_2157: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1580, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1580 = None
2025-03-21T20:31:43.9920762Z             aten_select_copy_int_471: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2157, 0, 7);  quantized_decomposed_dequantize_per_tensor_default_2157 = None
2025-03-21T20:31:43.9921674Z             quantized_decomposed_quantize_per_tensor_default_1581: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_471, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_select_copy_int_471 = None
2025-03-21T20:31:43.9921776Z             
2025-03-21T20:31:43.9922709Z              # File: <eval_with_key>.50:5512 in forward, code: dequantize_per_tensor_default_1739 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1739, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantize_per_tensor_default_1739 = None
2025-03-21T20:31:43.9923864Z             quantized_decomposed_dequantize_per_tensor_default_2158: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1581, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1581 = None
2025-03-21T20:31:43.9923953Z             
2025-03-21T20:31:43.9924599Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9925403Z             aten_permute_copy_default_396: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2088, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2088 = None
2025-03-21T20:31:43.9926350Z             quantized_decomposed_quantize_per_tensor_default_1582: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_396, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_permute_copy_default_396 = None
2025-03-21T20:31:43.9927522Z             quantized_decomposed_dequantize_per_tensor_default_2159: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1582, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1582 = None
2025-03-21T20:31:43.9928298Z             aten_select_copy_int_472: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2159, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2159 = None
2025-03-21T20:31:43.9929190Z             quantized_decomposed_quantize_per_tensor_default_1583: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_472, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_select_copy_int_472 = None
2025-03-21T20:31:43.9930439Z             quantized_decomposed_dequantize_per_tensor_default_2160: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1583, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1583 = None
2025-03-21T20:31:43.9931226Z             aten_select_copy_int_473: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2160, 0, 8);  quantized_decomposed_dequantize_per_tensor_default_2160 = None
2025-03-21T20:31:43.9932118Z             quantized_decomposed_quantize_per_tensor_default_1584: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_473, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_select_copy_int_473 = None
2025-03-21T20:31:43.9932368Z             
2025-03-21T20:31:43.9933330Z              # File: <eval_with_key>.50:5521 in forward, code: dequantize_per_tensor_default_1742 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1742, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantize_per_tensor_default_1742 = None
2025-03-21T20:31:43.9934566Z             quantized_decomposed_dequantize_per_tensor_default_2161: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1584, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1584 = None
2025-03-21T20:31:43.9934656Z             
2025-03-21T20:31:43.9935291Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9936107Z             aten_permute_copy_default_397: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2087, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2087 = None
2025-03-21T20:31:43.9937048Z             quantized_decomposed_quantize_per_tensor_default_1585: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_397, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_permute_copy_default_397 = None
2025-03-21T20:31:43.9938220Z             quantized_decomposed_dequantize_per_tensor_default_2162: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1585, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1585 = None
2025-03-21T20:31:43.9938976Z             aten_select_copy_int_474: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2162, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2162 = None
2025-03-21T20:31:43.9939914Z             quantized_decomposed_quantize_per_tensor_default_1586: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_474, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_select_copy_int_474 = None
2025-03-21T20:31:43.9941116Z             quantized_decomposed_dequantize_per_tensor_default_2163: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1586, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1586 = None
2025-03-21T20:31:43.9941857Z             aten_select_copy_int_475: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2163, 0, 9);  quantized_decomposed_dequantize_per_tensor_default_2163 = None
2025-03-21T20:31:43.9942768Z             quantized_decomposed_quantize_per_tensor_default_1587: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_475, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_select_copy_int_475 = None
2025-03-21T20:31:43.9942862Z             
2025-03-21T20:31:43.9943844Z              # File: <eval_with_key>.50:5530 in forward, code: dequantize_per_tensor_default_1745 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1745, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantize_per_tensor_default_1745 = None
2025-03-21T20:31:43.9944998Z             quantized_decomposed_dequantize_per_tensor_default_2164: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1587, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1587 = None
2025-03-21T20:31:43.9945123Z             
2025-03-21T20:31:43.9945760Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9946574Z             aten_permute_copy_default_398: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2086, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2086 = None
2025-03-21T20:31:43.9947508Z             quantized_decomposed_quantize_per_tensor_default_1588: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_398, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_permute_copy_default_398 = None
2025-03-21T20:31:43.9948666Z             quantized_decomposed_dequantize_per_tensor_default_2165: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1588, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1588 = None
2025-03-21T20:31:43.9949412Z             aten_select_copy_int_476: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2165, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2165 = None
2025-03-21T20:31:43.9950315Z             quantized_decomposed_quantize_per_tensor_default_1589: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_476, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_select_copy_int_476 = None
2025-03-21T20:31:43.9951461Z             quantized_decomposed_dequantize_per_tensor_default_2166: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1589, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1589 = None
2025-03-21T20:31:43.9952237Z             aten_select_copy_int_477: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2166, 0, 10);  quantized_decomposed_dequantize_per_tensor_default_2166 = None
2025-03-21T20:31:43.9953155Z             quantized_decomposed_quantize_per_tensor_default_1590: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_477, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_select_copy_int_477 = None
2025-03-21T20:31:43.9953258Z             
2025-03-21T20:31:43.9954192Z              # File: <eval_with_key>.50:5539 in forward, code: dequantize_per_tensor_default_1748 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1748, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantize_per_tensor_default_1748 = None
2025-03-21T20:31:43.9955356Z             quantized_decomposed_dequantize_per_tensor_default_2167: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1590, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1590 = None
2025-03-21T20:31:43.9955471Z             
2025-03-21T20:31:43.9956117Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9956918Z             aten_permute_copy_default_399: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2085, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2085 = None
2025-03-21T20:31:43.9957892Z             quantized_decomposed_quantize_per_tensor_default_1591: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_399, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_permute_copy_default_399 = None
2025-03-21T20:31:43.9959039Z             quantized_decomposed_dequantize_per_tensor_default_2168: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1591, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1591 = None
2025-03-21T20:31:43.9959793Z             aten_select_copy_int_478: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2168, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2168 = None
2025-03-21T20:31:43.9960686Z             quantized_decomposed_quantize_per_tensor_default_1592: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_478, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_select_copy_int_478 = None
2025-03-21T20:31:43.9961853Z             quantized_decomposed_dequantize_per_tensor_default_2169: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1592, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1592 = None
2025-03-21T20:31:43.9962606Z             aten_select_copy_int_479: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2169, 0, 11);  quantized_decomposed_dequantize_per_tensor_default_2169 = None
2025-03-21T20:31:43.9963495Z             quantized_decomposed_quantize_per_tensor_default_1593: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_479, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_select_copy_int_479 = None
2025-03-21T20:31:43.9963596Z             
2025-03-21T20:31:43.9964598Z              # File: <eval_with_key>.50:5548 in forward, code: dequantize_per_tensor_default_1751 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1751, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantize_per_tensor_default_1751 = None
2025-03-21T20:31:43.9965759Z             quantized_decomposed_dequantize_per_tensor_default_2170: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1593, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1593 = None
2025-03-21T20:31:43.9965849Z             
2025-03-21T20:31:43.9966499Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:43.9972077Z             aten_cat_default_39: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_aten_cat_default([quantized_decomposed_dequantize_per_tensor_default_2137, quantized_decomposed_dequantize_per_tensor_default_2140, quantized_decomposed_dequantize_per_tensor_default_2143, quantized_decomposed_dequantize_per_tensor_default_2146, quantized_decomposed_dequantize_per_tensor_default_2149, quantized_decomposed_dequantize_per_tensor_default_2152, quantized_decomposed_dequantize_per_tensor_default_2155, quantized_decomposed_dequantize_per_tensor_default_2158, quantized_decomposed_dequantize_per_tensor_default_2161, quantized_decomposed_dequantize_per_tensor_default_2164, quantized_decomposed_dequantize_per_tensor_default_2167, quantized_decomposed_dequantize_per_tensor_default_2170]);  quantized_decomposed_dequantize_per_tensor_default_2137 = quantized_decomposed_dequantize_per_tensor_default_2140 = quantized_decomposed_dequantize_per_tensor_default_2143 = quantized_decomposed_dequantize_per_tensor_default_2146 = quantized_decomposed_dequantize_per_tensor_default_2149 = quantized_decomposed_dequantize_per_tensor_default_2152 = quantized_decomposed_dequantize_per_tensor_default_2155 = quantized_decomposed_dequantize_per_tensor_default_2158 = quantized_decomposed_dequantize_per_tensor_default_2161 = quantized_decomposed_dequantize_per_tensor_default_2164 = quantized_decomposed_dequantize_per_tensor_default_2167 = quantized_decomposed_dequantize_per_tensor_default_2170 = None
2025-03-21T20:31:43.9972995Z             quantized_decomposed_quantize_per_tensor_default_1594: "i32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_39, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_cat_default_39 = None
2025-03-21T20:31:43.9974160Z             quantized_decomposed_dequantize_per_tensor_default_2171: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1594, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1594 = None
2025-03-21T20:31:43.9974947Z             aten_view_copy_default_172: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_2171, [1, 12, 128, 64]);  quantized_decomposed_dequantize_per_tensor_default_2171 = None
2025-03-21T20:31:43.9975874Z             quantized_decomposed_quantize_per_tensor_default_1595: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_172, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  aten_view_copy_default_172 = None
2025-03-21T20:31:43.9975964Z             
2025-03-21T20:31:43.9976914Z              # File: <eval_with_key>.50:5554 in forward, code: dequantize_per_tensor_default_1753 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1753, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantize_per_tensor_default_1753 = None
2025-03-21T20:31:43.9978115Z             quantized_decomposed_dequantize_per_tensor_default_2172: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1595, 0.0001724863686831668, 32338, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1595 = None
2025-03-21T20:31:43.9978222Z             
2025-03-21T20:31:43.9979160Z              # File: <eval_with_key>.50:5555 in forward, code: quantize_per_tensor_default_1754 = torch.ops.quantized_decomposed.quantize_per_tensor.default(dequantize_per_tensor_default_1753, 0.0001747508649714291, 0, -32767, 32767, torch.int16);  dequantize_per_tensor_default_1753 = None
2025-03-21T20:31:43.9980329Z             quantized_decomposed_quantize_per_tensor_default_1596: "i16[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_2172, 0.0001747508649714291, 0, -32767, 32767, torch.int16);  quantized_decomposed_dequantize_per_tensor_default_2172 = None
2025-03-21T20:31:43.9980420Z             
2025-03-21T20:31:43.9980922Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:163 in forward, code: y = attn_weight @ v
2025-03-21T20:31:43.9982075Z             quantized_decomposed_dequantize_per_tensor_default_2173: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1596, 0.0001747508649714291, 0, -32767, 32767, torch.int16);  quantized_decomposed_quantize_per_tensor_default_1596 = None
2025-03-21T20:31:43.9982178Z             
2025-03-21T20:31:43.9982664Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:157 in forward, code: attn_mask = mask[input_pos]
2025-03-21T20:31:43.9983493Z             aten_index_tensor_11: "f32[1, 128]" = executorch_exir_dialects_edge__ops_aten_index_Tensor(quantized_decomposed_dequantize_per_tensor_default_142, [attn_options_input_pos]);  quantized_decomposed_dequantize_per_tensor_default_142 = None
2025-03-21T20:31:43.9984365Z             quantized_decomposed_quantize_per_tensor_default_1597: "i32[1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_tensor_11, 0.0038910505827516317, 65535, 0, 65535, torch.int32);  aten_index_tensor_11 = None
2025-03-21T20:31:43.9984464Z             
2025-03-21T20:31:43.9984942Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:161 in forward, code: attn_weight += attn_mask
2025-03-21T20:31:43.9986091Z             quantized_decomposed_dequantize_per_tensor_default_2174: "f32[1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1597, 0.0038910505827516317, 65535, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1597 = None
2025-03-21T20:31:43.9986185Z             
2025-03-21T20:31:43.9986757Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.9987570Z             aten_permute_copy_default_400: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2134, [0, 1, 3, 2]);  quantized_decomposed_dequantize_per_tensor_default_2134 = None
2025-03-21T20:31:43.9988528Z             quantized_decomposed_quantize_per_tensor_default_1598: "i32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_400, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  aten_permute_copy_default_400 = None
2025-03-21T20:31:43.9988616Z             
2025-03-21T20:31:43.9989585Z              # File: <eval_with_key>.50:5562 in forward, code: dequantize_per_tensor_default_1756 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1756, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantize_per_tensor_default_1756 = None
2025-03-21T20:31:43.9990777Z             quantized_decomposed_dequantize_per_tensor_default_2175: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1598, 0.00041487260023131967, 31841, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1598 = None
2025-03-21T20:31:43.9990863Z             
2025-03-21T20:31:43.9991809Z              # File: <eval_with_key>.50:5563 in forward, code: quantize_per_tensor_default_1757 = torch.ops.quantized_decomposed.quantize_per_tensor.default(dequantize_per_tensor_default_1756, 0.0004266138712409884, 0, -32767, 32767, torch.int16);  dequantize_per_tensor_default_1756 = None
2025-03-21T20:31:43.9993006Z             quantized_decomposed_quantize_per_tensor_default_1599: "i16[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_2175, 0.0004266138712409884, 0, -32767, 32767, torch.int16);  quantized_decomposed_dequantize_per_tensor_default_2175 = None
2025-03-21T20:31:43.9993095Z             
2025-03-21T20:31:43.9993669Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:43.9994829Z             quantized_decomposed_dequantize_per_tensor_default_2176: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1599, 0.0004266138712409884, 0, -32767, 32767, torch.int16);  quantized_decomposed_quantize_per_tensor_default_1599 = None
2025-03-21T20:31:43.9995651Z             aten_expand_copy_default_36: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_2070, [1, 12, 1, 64]);  quantized_decomposed_dequantize_per_tensor_default_2070 = None
2025-03-21T20:31:43.9996207Z             aten_view_copy_default_173: "f32[12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_36, [12, 1, 64]);  aten_expand_copy_default_36 = None
2025-03-21T20:31:43.9997010Z             aten_expand_copy_default_37: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_2176, [1, 12, 64, 128]);  quantized_decomposed_dequantize_per_tensor_default_2176 = None
2025-03-21T20:31:43.9997573Z             aten_view_copy_default_174: "f32[12, 64, 128]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_37, [12, 64, 128]);  aten_expand_copy_default_37 = None
2025-03-21T20:31:43.9998244Z             aten_bmm_default_18: "f32[12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_bmm_default(aten_view_copy_default_173, aten_view_copy_default_174);  aten_view_copy_default_173 = aten_view_copy_default_174 = None
2025-03-21T20:31:43.9998762Z             aten_view_copy_default_175: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_bmm_default_18, [1, 12, 1, 128]);  aten_bmm_default_18 = None
2025-03-21T20:31:43.9999692Z             quantized_decomposed_quantize_per_tensor_default_1600: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_175, 0.0032424358651041985, 35894, 0, 65535, torch.int32);  aten_view_copy_default_175 = None
2025-03-21T20:31:44.0000867Z             quantized_decomposed_dequantize_per_tensor_default_2177: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1600, 0.0032424358651041985, 35894, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1600 = None
2025-03-21T20:31:44.0001762Z             quantized_decomposed_dequantize_per_tensor_default_2178: "f32[1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param158, 1.9073777366429567e-06, 0, 0, 65535, torch.int32);  b__frozen_param158 = None
2025-03-21T20:31:44.0002894Z             aten_mul_tensor_145: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2177, quantized_decomposed_dequantize_per_tensor_default_2178);  quantized_decomposed_dequantize_per_tensor_default_2177 = quantized_decomposed_dequantize_per_tensor_default_2178 = None
2025-03-21T20:31:44.0003770Z             quantized_decomposed_quantize_per_tensor_default_1601: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_145, 0.0004053044831380248, 35894, 0, 65535, torch.int32);  aten_mul_tensor_145 = None
2025-03-21T20:31:44.0003869Z             
2025-03-21T20:31:44.0004377Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:161 in forward, code: attn_weight += attn_mask
2025-03-21T20:31:44.0005547Z             quantized_decomposed_dequantize_per_tensor_default_2179: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1601, 0.0004053044831380248, 35894, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1601 = None
2025-03-21T20:31:44.0006693Z             aten_add_tensor_47: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_2179, quantized_decomposed_dequantize_per_tensor_default_2174);  quantized_decomposed_dequantize_per_tensor_default_2179 = quantized_decomposed_dequantize_per_tensor_default_2174 = None
2025-03-21T20:31:44.0007572Z             quantized_decomposed_quantize_per_tensor_default_1602: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_47, 0.004210181534290314, 63056, 0, 65535, torch.int32);  aten_add_tensor_47 = None
2025-03-21T20:31:44.0007675Z             
2025-03-21T20:31:44.0008239Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:162 in forward, code: attn_weight = torch.softmax(attn_weight, dim=-1)
2025-03-21T20:31:44.0009461Z             quantized_decomposed_dequantize_per_tensor_default_2180: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1602, 0.004210181534290314, 63056, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1602 = None
2025-03-21T20:31:44.0010386Z             aten__softmax_default_9: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten__softmax_default(quantized_decomposed_dequantize_per_tensor_default_2180, -1, False);  quantized_decomposed_dequantize_per_tensor_default_2180 = None
2025-03-21T20:31:44.0011292Z             quantized_decomposed_quantize_per_tensor_default_1603: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten__softmax_default_9, 1.5259021893143654e-05, 0, 0, 65535, torch.int32);  aten__softmax_default_9 = None
2025-03-21T20:31:44.0011382Z             
2025-03-21T20:31:44.0011854Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:163 in forward, code: y = attn_weight @ v
2025-03-21T20:31:44.0012985Z             quantized_decomposed_dequantize_per_tensor_default_2181: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1603, 1.5259021893143654e-05, 0, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1603 = None
2025-03-21T20:31:44.0013881Z             aten_expand_copy_default_38: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_2181, [1, 12, 1, 128]);  quantized_decomposed_dequantize_per_tensor_default_2181 = None
2025-03-21T20:31:44.0014441Z             aten_view_copy_default_176: "f32[12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_38, [12, 1, 128]);  aten_expand_copy_default_38 = None
2025-03-21T20:31:44.0015246Z             aten_expand_copy_default_39: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_2173, [1, 12, 128, 64]);  quantized_decomposed_dequantize_per_tensor_default_2173 = None
2025-03-21T20:31:44.0015818Z             aten_view_copy_default_177: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_39, [12, 128, 64]);  aten_expand_copy_default_39 = None
2025-03-21T20:31:44.0016507Z             aten_bmm_default_19: "f32[12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_bmm_default(aten_view_copy_default_176, aten_view_copy_default_177);  aten_view_copy_default_176 = aten_view_copy_default_177 = None
2025-03-21T20:31:44.0017020Z             aten_view_copy_default_178: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_bmm_default_19, [1, 12, 1, 64]);  aten_bmm_default_19 = None
2025-03-21T20:31:44.0017947Z             quantized_decomposed_quantize_per_tensor_default_1604: "i32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_178, 0.00012377489474602044, 34871, 0, 65535, torch.int32);  aten_view_copy_default_178 = None
2025-03-21T20:31:44.0018057Z             
2025-03-21T20:31:44.0018691Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:165 in forward, code: return y.transpose(1, 2).contiguous().view(bsz, seqlen, self.dim)
2025-03-21T20:31:44.0019841Z             quantized_decomposed_dequantize_per_tensor_default_2182: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1604, 0.00012377489474602044, 34871, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1604 = None
2025-03-21T20:31:44.0020644Z             aten_permute_copy_default_401: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2182, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2182 = None
2025-03-21T20:31:44.0021577Z             quantized_decomposed_quantize_per_tensor_default_1605: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_401, 0.00012377489474602044, 34871, 0, 65535, torch.int32);  aten_permute_copy_default_401 = None
2025-03-21T20:31:44.0022740Z             quantized_decomposed_dequantize_per_tensor_default_2183: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1605, 0.00012377489474602044, 34871, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1605 = None
2025-03-21T20:31:44.0023513Z             aten_view_copy_default_179: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_2183, [1, 1, 768]);  quantized_decomposed_dequantize_per_tensor_default_2183 = None
2025-03-21T20:31:44.0024433Z             quantized_decomposed_quantize_per_tensor_default_1606: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_179, 0.00012377489474602044, 34871, 0, 65535, torch.int32);  aten_view_copy_default_179 = None
2025-03-21T20:31:44.0024523Z             
2025-03-21T20:31:44.0025110Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:44.0026267Z             quantized_decomposed_dequantize_per_tensor_default_2184: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1606, 0.00012377489474602044, 34871, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1606 = None
2025-03-21T20:31:44.0027088Z             aten_unsqueeze_copy_default_106: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_2184, -1);  quantized_decomposed_dequantize_per_tensor_default_2184 = None
2025-03-21T20:31:44.0028046Z             quantized_decomposed_quantize_per_tensor_default_1607: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_106, 0.00012377489474602044, 34871, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_106 = None
2025-03-21T20:31:44.0028150Z             
2025-03-21T20:31:44.0028583Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:44.0029749Z             quantized_decomposed_dequantize_per_tensor_default_2185: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1607, 0.00012377489474602044, 34871, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1607 = None
2025-03-21T20:31:44.0030544Z             aten_permute_copy_default_402: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2185, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2185 = None
2025-03-21T20:31:44.0031529Z             quantized_decomposed_quantize_per_tensor_default_1608: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_402, 0.00012377489474602044, 34871, 0, 65535, torch.int32);  aten_permute_copy_default_402 = None
2025-03-21T20:31:44.0031616Z             
2025-03-21T20:31:44.0031991Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:44.0033317Z             quantized_decomposed_dequantize_per_tensor_default_2186: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1608, 0.00012377489474602044, 34871, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1608 = None
2025-03-21T20:31:44.0034619Z             aten_convolution_default_66: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_2186, quantized_decomposed_dequantize_per_tensor_default_86, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_2186 = quantized_decomposed_dequantize_per_tensor_default_86 = None
2025-03-21T20:31:44.0035552Z             quantized_decomposed_quantize_per_tensor_default_1609: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_66, 0.00013408258382696658, 24208, 0, 65535, torch.int32);  aten_convolution_default_66 = None
2025-03-21T20:31:44.0035655Z             
2025-03-21T20:31:44.0036074Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:44.0037312Z             quantized_decomposed_dequantize_per_tensor_default_2187: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1609, 0.00013408258382696658, 24208, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1609 = None
2025-03-21T20:31:44.0038142Z             aten_permute_copy_default_403: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2187, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2187 = None
2025-03-21T20:31:44.0039096Z             quantized_decomposed_quantize_per_tensor_default_1610: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_403, 0.00013408258382696658, 24208, 0, 65535, torch.int32);  aten_permute_copy_default_403 = None
2025-03-21T20:31:44.0039186Z             
2025-03-21T20:31:44.0039738Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:44.0040931Z             quantized_decomposed_dequantize_per_tensor_default_2188: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1610, 0.00013408258382696658, 24208, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1610 = None
2025-03-21T20:31:44.0041705Z             aten_squeeze_copy_dims_106: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_2188, [-1]);  quantized_decomposed_dequantize_per_tensor_default_2188 = None
2025-03-21T20:31:44.0042614Z             quantized_decomposed_quantize_per_tensor_default_1611: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_106, 0.00013408258382696658, 24208, 0, 65535, torch.int32);  aten_squeeze_copy_dims_106 = None
2025-03-21T20:31:44.0042752Z             
2025-03-21T20:31:44.0043127Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:111 in forward, code: h = x + h
2025-03-21T20:31:44.0044290Z             quantized_decomposed_dequantize_per_tensor_default_2189: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1611, 0.00013408258382696658, 24208, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1611 = None
2025-03-21T20:31:44.0045411Z             aten_add_tensor_48: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_2009, quantized_decomposed_dequantize_per_tensor_default_2189);  quantized_decomposed_dequantize_per_tensor_default_2009 = quantized_decomposed_dequantize_per_tensor_default_2189 = None
2025-03-21T20:31:44.0046271Z             quantized_decomposed_quantize_per_tensor_default_1612: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_48, 0.002711330307647586, 7452, 0, 65535, torch.int32);  aten_add_tensor_48 = None
2025-03-21T20:31:44.0046361Z             
2025-03-21T20:31:44.0046885Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:115 in forward, code: out = h + self.feed_forward(self.ffn_norm(h))
2025-03-21T20:31:44.0047793Z             quantized_decomposed_dequantize_per_tensor_default_2190: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1612, 0.002711330307647586, 7452, 0, 65535, torch.int32)
2025-03-21T20:31:44.0048939Z             quantized_decomposed_dequantize_per_tensor_default_2191: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1612, 0.002711330307647586, 7452, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1612 = None
2025-03-21T20:31:44.0049580Z             aten_pow_tensor_scalar_19: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_pow_Tensor_Scalar(quantized_decomposed_dequantize_per_tensor_default_2191, 2)
2025-03-21T20:31:44.0050057Z             aten_mean_dim_19: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_mean_dim(aten_pow_tensor_scalar_19, [2], True);  aten_pow_tensor_scalar_19 = None
2025-03-21T20:31:44.0050508Z             aten_add_scalar_19: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_add_Scalar(aten_mean_dim_19, 9.999999747378752e-06);  aten_mean_dim_19 = None
2025-03-21T20:31:44.0050949Z             aten_rsqrt_default_19: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_rsqrt_default(aten_add_scalar_19);  aten_add_scalar_19 = None
2025-03-21T20:31:44.0051812Z             aten_mul_tensor_146: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2191, aten_rsqrt_default_19);  quantized_decomposed_dequantize_per_tensor_default_2191 = aten_rsqrt_default_19 = None
2025-03-21T20:31:44.0052671Z             aten_mul_tensor_147: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(aten_mul_tensor_146, quantized_decomposed_dequantize_per_tensor_default_87);  aten_mul_tensor_146 = quantized_decomposed_dequantize_per_tensor_default_87 = None
2025-03-21T20:31:44.0053534Z             quantized_decomposed_quantize_per_tensor_default_1613: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_147, 0.00043149059638381004, 21157, 0, 65535, torch.int32);  aten_mul_tensor_147 = None
2025-03-21T20:31:44.0053640Z             
2025-03-21T20:31:44.0054163Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:44.0055137Z             quantized_decomposed_dequantize_per_tensor_default_2192: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1613, 0.00043149059638381004, 21157, 0, 65535, torch.int32)
2025-03-21T20:31:44.0056290Z             quantized_decomposed_dequantize_per_tensor_default_2193: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1613, 0.00043149059638381004, 21157, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1613 = None
2025-03-21T20:31:44.0057109Z             aten_unsqueeze_copy_default_107: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_2193, -1);  quantized_decomposed_dequantize_per_tensor_default_2193 = None
2025-03-21T20:31:44.0058072Z             quantized_decomposed_quantize_per_tensor_default_1614: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_107, 0.00043149059638381004, 21157, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_107 = None
2025-03-21T20:31:44.0058173Z             
2025-03-21T20:31:44.0058581Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:44.0059739Z             quantized_decomposed_dequantize_per_tensor_default_2194: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1614, 0.00043149059638381004, 21157, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1614 = None
2025-03-21T20:31:44.0060536Z             aten_permute_copy_default_404: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2194, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2194 = None
2025-03-21T20:31:44.0061544Z             quantized_decomposed_quantize_per_tensor_default_1615: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_404, 0.00043149059638381004, 21157, 0, 65535, torch.int32);  aten_permute_copy_default_404 = None
2025-03-21T20:31:44.0061632Z             
2025-03-21T20:31:44.0062010Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:44.0063159Z             quantized_decomposed_dequantize_per_tensor_default_2195: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1615, 0.00043149059638381004, 21157, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1615 = None
2025-03-21T20:31:44.0064474Z             aten_convolution_default_67: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_2195, quantized_decomposed_dequantize_per_tensor_default_88, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_2195 = quantized_decomposed_dequantize_per_tensor_default_88 = None
2025-03-21T20:31:44.0065411Z             quantized_decomposed_quantize_per_tensor_default_1616: "i32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_67, 0.0001975321938516572, 32198, 0, 65535, torch.int32);  aten_convolution_default_67 = None
2025-03-21T20:31:44.0065513Z             
2025-03-21T20:31:44.0065933Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:44.0067125Z             quantized_decomposed_dequantize_per_tensor_default_2196: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1616, 0.0001975321938516572, 32198, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1616 = None
2025-03-21T20:31:44.0067931Z             aten_permute_copy_default_405: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2196, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2196 = None
2025-03-21T20:31:44.0068884Z             quantized_decomposed_quantize_per_tensor_default_1617: "i32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_405, 0.0001975321938516572, 32198, 0, 65535, torch.int32);  aten_permute_copy_default_405 = None
2025-03-21T20:31:44.0068974Z             
2025-03-21T20:31:44.0069521Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:44.0070682Z             quantized_decomposed_dequantize_per_tensor_default_2197: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1617, 0.0001975321938516572, 32198, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1617 = None
2025-03-21T20:31:44.0071458Z             aten_squeeze_copy_dims_107: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_2197, [-1]);  quantized_decomposed_dequantize_per_tensor_default_2197 = None
2025-03-21T20:31:44.0072369Z             quantized_decomposed_quantize_per_tensor_default_1618: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_107, 0.0001975321938516572, 32198, 0, 65535, torch.int32);  aten_squeeze_copy_dims_107 = None
2025-03-21T20:31:44.0072471Z             
2025-03-21T20:31:44.0073037Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:36 in forward, code: return self.w2(F.silu(self.w1(x)) * self.w3(x))
2025-03-21T20:31:44.0073971Z             quantized_decomposed_dequantize_per_tensor_default_2198: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1618, 0.0001975321938516572, 32198, 0, 65535, torch.int32)
2025-03-21T20:31:44.0075118Z             quantized_decomposed_dequantize_per_tensor_default_2199: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1618, 0.0001975321938516572, 32198, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1618 = None
2025-03-21T20:31:44.0075875Z             aten_sigmoid_default_9: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_sigmoid_default(quantized_decomposed_dequantize_per_tensor_default_2199);  quantized_decomposed_dequantize_per_tensor_default_2199 = None
2025-03-21T20:31:44.0076759Z             quantized_decomposed_quantize_per_tensor_default_1619: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_sigmoid_default_9, 1.52587890625e-05, 0, 0, 65535, torch.int32);  aten_sigmoid_default_9 = None
2025-03-21T20:31:44.0077885Z             quantized_decomposed_dequantize_per_tensor_default_2200: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1619, 1.52587890625e-05, 0, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1619 = None
2025-03-21T20:31:44.0079055Z             aten_mul_tensor_148: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2198, quantized_decomposed_dequantize_per_tensor_default_2200);  quantized_decomposed_dequantize_per_tensor_default_2198 = quantized_decomposed_dequantize_per_tensor_default_2200 = None
2025-03-21T20:31:44.0079912Z             quantized_decomposed_quantize_per_tensor_default_1620: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_148, 0.0001045933531713672, 2662, 0, 65535, torch.int32);  aten_mul_tensor_148 = None
2025-03-21T20:31:44.0081065Z             quantized_decomposed_dequantize_per_tensor_default_2201: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1620, 0.0001045933531713672, 2662, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1620 = None
2025-03-21T20:31:44.0081155Z             
2025-03-21T20:31:44.0081687Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:44.0082499Z             aten_unsqueeze_copy_default_108: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_2192, -1);  quantized_decomposed_dequantize_per_tensor_default_2192 = None
2025-03-21T20:31:44.0083481Z             quantized_decomposed_quantize_per_tensor_default_1621: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_108, 0.00043149059638381004, 21157, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_108 = None
2025-03-21T20:31:44.0083571Z             
2025-03-21T20:31:44.0083986Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:44.0085167Z             quantized_decomposed_dequantize_per_tensor_default_2202: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1621, 0.00043149059638381004, 21157, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1621 = None
2025-03-21T20:31:44.0086004Z             aten_permute_copy_default_406: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2202, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2202 = None
2025-03-21T20:31:44.0086941Z             quantized_decomposed_quantize_per_tensor_default_1622: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_406, 0.00043149059638381004, 21157, 0, 65535, torch.int32);  aten_permute_copy_default_406 = None
2025-03-21T20:31:44.0087049Z             
2025-03-21T20:31:44.0087414Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:44.0088609Z             quantized_decomposed_dequantize_per_tensor_default_2203: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1622, 0.00043149059638381004, 21157, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1622 = None
2025-03-21T20:31:44.0089961Z             aten_convolution_default_68: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_2203, quantized_decomposed_dequantize_per_tensor_default_89, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_2203 = quantized_decomposed_dequantize_per_tensor_default_89 = None
2025-03-21T20:31:44.0090954Z             quantized_decomposed_quantize_per_tensor_default_1623: "i32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_68, 0.00024529712391085923, 28114, 0, 65535, torch.int32);  aten_convolution_default_68 = None
2025-03-21T20:31:44.0091045Z             
2025-03-21T20:31:44.0091481Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:44.0092641Z             quantized_decomposed_dequantize_per_tensor_default_2204: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1623, 0.00024529712391085923, 28114, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1623 = None
2025-03-21T20:31:44.0093456Z             aten_permute_copy_default_407: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2204, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2204 = None
2025-03-21T20:31:44.0094405Z             quantized_decomposed_quantize_per_tensor_default_1624: "i32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_407, 0.00024529712391085923, 28114, 0, 65535, torch.int32);  aten_permute_copy_default_407 = None
2025-03-21T20:31:44.0094513Z             
2025-03-21T20:31:44.0095049Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:44.0096221Z             quantized_decomposed_dequantize_per_tensor_default_2205: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1624, 0.00024529712391085923, 28114, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1624 = None
2025-03-21T20:31:44.0097017Z             aten_squeeze_copy_dims_108: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_2205, [-1]);  quantized_decomposed_dequantize_per_tensor_default_2205 = None
2025-03-21T20:31:44.0097976Z             quantized_decomposed_quantize_per_tensor_default_1625: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_108, 0.00024529712391085923, 28114, 0, 65535, torch.int32);  aten_squeeze_copy_dims_108 = None
2025-03-21T20:31:44.0098069Z             
2025-03-21T20:31:44.0098599Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:36 in forward, code: return self.w2(F.silu(self.w1(x)) * self.w3(x))
2025-03-21T20:31:44.0099753Z             quantized_decomposed_dequantize_per_tensor_default_2206: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1625, 0.00024529712391085923, 28114, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1625 = None
2025-03-21T20:31:44.0101061Z             aten_mul_tensor_149: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2201, quantized_decomposed_dequantize_per_tensor_default_2206);  quantized_decomposed_dequantize_per_tensor_default_2201 = quantized_decomposed_dequantize_per_tensor_default_2206 = None
2025-03-21T20:31:44.0101931Z             quantized_decomposed_quantize_per_tensor_default_1626: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_149, 0.0006203429074957967, 26598, 0, 65535, torch.int32);  aten_mul_tensor_149 = None
2025-03-21T20:31:44.0102032Z             
2025-03-21T20:31:44.0102551Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:44.0103746Z             quantized_decomposed_dequantize_per_tensor_default_2207: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1626, 0.0006203429074957967, 26598, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1626 = None
2025-03-21T20:31:44.0104556Z             aten_unsqueeze_copy_default_109: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_2207, -1);  quantized_decomposed_dequantize_per_tensor_default_2207 = None
2025-03-21T20:31:44.0105525Z             quantized_decomposed_quantize_per_tensor_default_1627: "i32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_109, 0.0006203429074957967, 26598, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_109 = None
2025-03-21T20:31:44.0105614Z             
2025-03-21T20:31:44.0106037Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:44.0107195Z             quantized_decomposed_dequantize_per_tensor_default_2208: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1627, 0.0006203429074957967, 26598, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1627 = None
2025-03-21T20:31:44.0108012Z             aten_permute_copy_default_408: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2208, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2208 = None
2025-03-21T20:31:44.0108951Z             quantized_decomposed_quantize_per_tensor_default_1628: "i32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_408, 0.0006203429074957967, 26598, 0, 65535, torch.int32);  aten_permute_copy_default_408 = None
2025-03-21T20:31:44.0109132Z             
2025-03-21T20:31:44.0109496Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:44.0110658Z             quantized_decomposed_dequantize_per_tensor_default_2209: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1628, 0.0006203429074957967, 26598, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1628 = None
2025-03-21T20:31:44.0112209Z             aten_convolution_default_69: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_2209, quantized_decomposed_dequantize_per_tensor_default_90, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_2209 = quantized_decomposed_dequantize_per_tensor_default_90 = None
2025-03-21T20:31:44.0113208Z             quantized_decomposed_quantize_per_tensor_default_1629: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_69, 0.0003197697224095464, 32722, 0, 65535, torch.int32);  aten_convolution_default_69 = None
2025-03-21T20:31:44.0113298Z             
2025-03-21T20:31:44.0113733Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:44.0114877Z             quantized_decomposed_dequantize_per_tensor_default_2210: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1629, 0.0003197697224095464, 32722, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1629 = None
2025-03-21T20:31:44.0115711Z             aten_permute_copy_default_409: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2210, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2210 = None
2025-03-21T20:31:44.0116646Z             quantized_decomposed_quantize_per_tensor_default_1630: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_409, 0.0003197697224095464, 32722, 0, 65535, torch.int32);  aten_permute_copy_default_409 = None
2025-03-21T20:31:44.0116744Z             
2025-03-21T20:31:44.0117282Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:44.0118445Z             quantized_decomposed_dequantize_per_tensor_default_2211: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1630, 0.0003197697224095464, 32722, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1630 = None
2025-03-21T20:31:44.0119206Z             aten_squeeze_copy_dims_109: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_2211, [-1]);  quantized_decomposed_dequantize_per_tensor_default_2211 = None
2025-03-21T20:31:44.0120124Z             quantized_decomposed_quantize_per_tensor_default_1631: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_109, 0.0003197697224095464, 32722, 0, 65535, torch.int32);  aten_squeeze_copy_dims_109 = None
2025-03-21T20:31:44.0120213Z             
2025-03-21T20:31:44.0120731Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:115 in forward, code: out = h + self.feed_forward(self.ffn_norm(h))
2025-03-21T20:31:44.0121900Z             quantized_decomposed_dequantize_per_tensor_default_2212: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1631, 0.0003197697224095464, 32722, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1631 = None
2025-03-21T20:31:44.0123064Z             aten_add_tensor_49: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_2190, quantized_decomposed_dequantize_per_tensor_default_2212);  quantized_decomposed_dequantize_per_tensor_default_2190 = quantized_decomposed_dequantize_per_tensor_default_2212 = None
2025-03-21T20:31:44.0123905Z             quantized_decomposed_quantize_per_tensor_default_1632: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_49, 0.002727663842961192, 9020, 0, 65535, torch.int32);  aten_add_tensor_49 = None
2025-03-21T20:31:44.0124010Z             
2025-03-21T20:31:44.0124385Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:111 in forward, code: h = x + h
2025-03-21T20:31:44.0125334Z             quantized_decomposed_dequantize_per_tensor_default_2213: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1632, 0.002727663842961192, 9020, 0, 65535, torch.int32)
2025-03-21T20:31:44.0125424Z             
2025-03-21T20:31:44.0126003Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:108 in forward, code: self.attention_norm(x), freqs_cos, freqs_sin, **attn_options
2025-03-21T20:31:44.0127138Z             quantized_decomposed_dequantize_per_tensor_default_2214: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1632, 0.002727663842961192, 9020, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1632 = None
2025-03-21T20:31:44.0127695Z             aten_pow_tensor_scalar_20: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_pow_Tensor_Scalar(quantized_decomposed_dequantize_per_tensor_default_2214, 2)
2025-03-21T20:31:44.0128156Z             aten_mean_dim_20: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_mean_dim(aten_pow_tensor_scalar_20, [2], True);  aten_pow_tensor_scalar_20 = None
2025-03-21T20:31:44.0128614Z             aten_add_scalar_20: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_add_Scalar(aten_mean_dim_20, 9.999999747378752e-06);  aten_mean_dim_20 = None
2025-03-21T20:31:44.0129037Z             aten_rsqrt_default_20: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_rsqrt_default(aten_add_scalar_20);  aten_add_scalar_20 = None
2025-03-21T20:31:44.0129981Z             aten_mul_tensor_150: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2214, aten_rsqrt_default_20);  quantized_decomposed_dequantize_per_tensor_default_2214 = aten_rsqrt_default_20 = None
2025-03-21T20:31:44.0130812Z             aten_mul_tensor_151: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(aten_mul_tensor_150, quantized_decomposed_dequantize_per_tensor_default_91);  aten_mul_tensor_150 = quantized_decomposed_dequantize_per_tensor_default_91 = None
2025-03-21T20:31:44.0131676Z             quantized_decomposed_quantize_per_tensor_default_1633: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_151, 0.000514648447278887, 33371, 0, 65535, torch.int32);  aten_mul_tensor_151 = None
2025-03-21T20:31:44.0131764Z             
2025-03-21T20:31:44.0132465Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:44.0133464Z             quantized_decomposed_dequantize_per_tensor_default_2215: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1633, 0.000514648447278887, 33371, 0, 65535, torch.int32)
2025-03-21T20:31:44.0134424Z             quantized_decomposed_dequantize_per_tensor_default_2216: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1633, 0.000514648447278887, 33371, 0, 65535, torch.int32)
2025-03-21T20:31:44.0135561Z             quantized_decomposed_dequantize_per_tensor_default_2217: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1633, 0.000514648447278887, 33371, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1633 = None
2025-03-21T20:31:44.0136386Z             aten_unsqueeze_copy_default_110: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_2217, -1);  quantized_decomposed_dequantize_per_tensor_default_2217 = None
2025-03-21T20:31:44.0137366Z             quantized_decomposed_quantize_per_tensor_default_1634: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_110, 0.000514648447278887, 33371, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_110 = None
2025-03-21T20:31:44.0137467Z             
2025-03-21T20:31:44.0137877Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:44.0139033Z             quantized_decomposed_dequantize_per_tensor_default_2218: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1634, 0.000514648447278887, 33371, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1634 = None
2025-03-21T20:31:44.0139863Z             aten_permute_copy_default_410: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2218, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2218 = None
2025-03-21T20:31:44.0140808Z             quantized_decomposed_quantize_per_tensor_default_1635: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_410, 0.000514648447278887, 33371, 0, 65535, torch.int32);  aten_permute_copy_default_410 = None
2025-03-21T20:31:44.0140897Z             
2025-03-21T20:31:44.0141273Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:44.0142415Z             quantized_decomposed_dequantize_per_tensor_default_2219: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1635, 0.000514648447278887, 33371, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1635 = None
2025-03-21T20:31:44.0143701Z             aten_convolution_default_70: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_2219, quantized_decomposed_dequantize_per_tensor_default_92, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_2219 = quantized_decomposed_dequantize_per_tensor_default_92 = None
2025-03-21T20:31:44.0144624Z             quantized_decomposed_quantize_per_tensor_default_1636: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_70, 0.000400586926843971, 33468, 0, 65535, torch.int32);  aten_convolution_default_70 = None
2025-03-21T20:31:44.0144728Z             
2025-03-21T20:31:44.0145147Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:44.0146369Z             quantized_decomposed_dequantize_per_tensor_default_2220: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1636, 0.000400586926843971, 33468, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1636 = None
2025-03-21T20:31:44.0147168Z             aten_permute_copy_default_411: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2220, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2220 = None
2025-03-21T20:31:44.0148112Z             quantized_decomposed_quantize_per_tensor_default_1637: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_411, 0.000400586926843971, 33468, 0, 65535, torch.int32);  aten_permute_copy_default_411 = None
2025-03-21T20:31:44.0148205Z             
2025-03-21T20:31:44.0148755Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:44.0149924Z             quantized_decomposed_dequantize_per_tensor_default_2221: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1637, 0.000400586926843971, 33468, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1637 = None
2025-03-21T20:31:44.0150697Z             aten_squeeze_copy_dims_110: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_2221, [-1]);  quantized_decomposed_dequantize_per_tensor_default_2221 = None
2025-03-21T20:31:44.0151624Z             quantized_decomposed_quantize_per_tensor_default_1638: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_110, 0.000400586926843971, 33468, 0, 65535, torch.int32);  aten_squeeze_copy_dims_110 = None
2025-03-21T20:31:44.0151727Z             
2025-03-21T20:31:44.0152243Z              # File: /pytorch/executorch/examples/models/llama/attention.py:242 in forward, code: q = q.view(bsz, seqlen, self.n_local_heads, self.head_dim)
2025-03-21T20:31:44.0153397Z             quantized_decomposed_dequantize_per_tensor_default_2222: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1638, 0.000400586926843971, 33468, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1638 = None
2025-03-21T20:31:44.0153490Z             
2025-03-21T20:31:44.0154015Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:44.0154830Z             aten_unsqueeze_copy_default_111: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_2216, -1);  quantized_decomposed_dequantize_per_tensor_default_2216 = None
2025-03-21T20:31:44.0155792Z             quantized_decomposed_quantize_per_tensor_default_1639: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_111, 0.000514648447278887, 33371, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_111 = None
2025-03-21T20:31:44.0155883Z             
2025-03-21T20:31:44.0156290Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:44.0157482Z             quantized_decomposed_dequantize_per_tensor_default_2223: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1639, 0.000514648447278887, 33371, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1639 = None
2025-03-21T20:31:44.0158317Z             aten_permute_copy_default_412: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2223, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2223 = None
2025-03-21T20:31:44.0159245Z             quantized_decomposed_quantize_per_tensor_default_1640: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_412, 0.000514648447278887, 33371, 0, 65535, torch.int32);  aten_permute_copy_default_412 = None
2025-03-21T20:31:44.0159350Z             
2025-03-21T20:31:44.0159719Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:44.0160887Z             quantized_decomposed_dequantize_per_tensor_default_2224: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1640, 0.000514648447278887, 33371, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1640 = None
2025-03-21T20:31:44.0162176Z             aten_convolution_default_71: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_2224, quantized_decomposed_dequantize_per_tensor_default_93, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_2224 = quantized_decomposed_dequantize_per_tensor_default_93 = None
2025-03-21T20:31:44.0163118Z             quantized_decomposed_quantize_per_tensor_default_1641: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_71, 0.0004142843827139586, 29754, 0, 65535, torch.int32);  aten_convolution_default_71 = None
2025-03-21T20:31:44.0163233Z             
2025-03-21T20:31:44.0163664Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:44.0164813Z             quantized_decomposed_dequantize_per_tensor_default_2225: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1641, 0.0004142843827139586, 29754, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1641 = None
2025-03-21T20:31:44.0165617Z             aten_permute_copy_default_413: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2225, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2225 = None
2025-03-21T20:31:44.0166555Z             quantized_decomposed_quantize_per_tensor_default_1642: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_413, 0.0004142843827139586, 29754, 0, 65535, torch.int32);  aten_permute_copy_default_413 = None
2025-03-21T20:31:44.0166656Z             
2025-03-21T20:31:44.0167195Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:44.0168354Z             quantized_decomposed_dequantize_per_tensor_default_2226: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1642, 0.0004142843827139586, 29754, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1642 = None
2025-03-21T20:31:44.0169140Z             aten_squeeze_copy_dims_111: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_2226, [-1]);  quantized_decomposed_dequantize_per_tensor_default_2226 = None
2025-03-21T20:31:44.0170161Z             quantized_decomposed_quantize_per_tensor_default_1643: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_111, 0.0004142843827139586, 29754, 0, 65535, torch.int32);  aten_squeeze_copy_dims_111 = None
2025-03-21T20:31:44.0170253Z             
2025-03-21T20:31:44.0170789Z              # File: /pytorch/executorch/examples/models/llama/attention.py:243 in forward, code: k = k.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:44.0171934Z             quantized_decomposed_dequantize_per_tensor_default_2227: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1643, 0.0004142843827139586, 29754, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1643 = None
2025-03-21T20:31:44.0172037Z             
2025-03-21T20:31:44.0172555Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:44.0173389Z             aten_unsqueeze_copy_default_112: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_2215, -1);  quantized_decomposed_dequantize_per_tensor_default_2215 = None
2025-03-21T20:31:44.0174348Z             quantized_decomposed_quantize_per_tensor_default_1644: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_112, 0.000514648447278887, 33371, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_112 = None
2025-03-21T20:31:44.0174458Z             
2025-03-21T20:31:44.0174875Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:44.0176020Z             quantized_decomposed_dequantize_per_tensor_default_2228: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1644, 0.000514648447278887, 33371, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1644 = None
2025-03-21T20:31:44.0176832Z             aten_permute_copy_default_414: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2228, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2228 = None
2025-03-21T20:31:44.0177758Z             quantized_decomposed_quantize_per_tensor_default_1645: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_414, 0.000514648447278887, 33371, 0, 65535, torch.int32);  aten_permute_copy_default_414 = None
2025-03-21T20:31:44.0177858Z             
2025-03-21T20:31:44.0178225Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:44.0179380Z             quantized_decomposed_dequantize_per_tensor_default_2229: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1645, 0.000514648447278887, 33371, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1645 = None
2025-03-21T20:31:44.0180646Z             aten_convolution_default_72: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_2229, quantized_decomposed_dequantize_per_tensor_default_94, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_2229 = quantized_decomposed_dequantize_per_tensor_default_94 = None
2025-03-21T20:31:44.0181613Z             quantized_decomposed_quantize_per_tensor_default_1646: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_72, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_convolution_default_72 = None
2025-03-21T20:31:44.0181726Z             
2025-03-21T20:31:44.0182159Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:44.0183308Z             quantized_decomposed_dequantize_per_tensor_default_2230: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1646, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1646 = None
2025-03-21T20:31:44.0184115Z             aten_permute_copy_default_415: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2230, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2230 = None
2025-03-21T20:31:44.0185089Z             quantized_decomposed_quantize_per_tensor_default_1647: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_415, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_permute_copy_default_415 = None
2025-03-21T20:31:44.0185178Z             
2025-03-21T20:31:44.0185713Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:44.0186878Z             quantized_decomposed_dequantize_per_tensor_default_2231: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1647, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1647 = None
2025-03-21T20:31:44.0187666Z             aten_squeeze_copy_dims_112: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_2231, [-1]);  quantized_decomposed_dequantize_per_tensor_default_2231 = None
2025-03-21T20:31:44.0188591Z             quantized_decomposed_quantize_per_tensor_default_1648: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_112, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_squeeze_copy_dims_112 = None
2025-03-21T20:31:44.0188679Z             
2025-03-21T20:31:44.0189215Z              # File: /pytorch/executorch/examples/models/llama/attention.py:244 in forward, code: v = v.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:44.0190368Z             quantized_decomposed_dequantize_per_tensor_default_2232: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1648, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1648 = None
2025-03-21T20:31:44.0190471Z             
2025-03-21T20:31:44.0190982Z              # File: /pytorch/executorch/examples/models/llama/attention.py:242 in forward, code: q = q.view(bsz, seqlen, self.n_local_heads, self.head_dim)
2025-03-21T20:31:44.0191765Z             aten_view_copy_default_180: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_2222, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_2222 = None
2025-03-21T20:31:44.0192663Z             quantized_decomposed_quantize_per_tensor_default_1649: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_180, 0.000400586926843971, 33468, 0, 65535, torch.int32);  aten_view_copy_default_180 = None
2025-03-21T20:31:44.0192804Z             
2025-03-21T20:31:44.0193757Z              # File: <eval_with_key>.50:5722 in forward, code: dequantize_per_tensor_default_1808 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1808, 0.000400586926843971, 33468, 0, 65535, torch.int32);  quantize_per_tensor_default_1808 = None
2025-03-21T20:31:44.0194908Z             quantized_decomposed_dequantize_per_tensor_default_2233: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1649, 0.000400586926843971, 33468, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1649 = None
2025-03-21T20:31:44.0194995Z             
2025-03-21T20:31:44.0195527Z              # File: /pytorch/executorch/examples/models/llama/attention.py:243 in forward, code: k = k.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:44.0196297Z             aten_view_copy_default_181: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_2227, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_2227 = None
2025-03-21T20:31:44.0197240Z             quantized_decomposed_quantize_per_tensor_default_1650: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_181, 0.0004142843827139586, 29754, 0, 65535, torch.int32);  aten_view_copy_default_181 = None
2025-03-21T20:31:44.0197330Z             
2025-03-21T20:31:44.0198273Z              # File: <eval_with_key>.50:5725 in forward, code: dequantize_per_tensor_default_1809 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1809, 0.0004142843827139586, 29754, 0, 65535, torch.int32);  quantize_per_tensor_default_1809 = None
2025-03-21T20:31:44.0199447Z             quantized_decomposed_dequantize_per_tensor_default_2234: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1650, 0.0004142843827139586, 29754, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1650 = None
2025-03-21T20:31:44.0199550Z             
2025-03-21T20:31:44.0200072Z              # File: /pytorch/executorch/examples/models/llama/attention.py:244 in forward, code: v = v.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:44.0200848Z             aten_view_copy_default_182: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_2232, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_2232 = None
2025-03-21T20:31:44.0201758Z             quantized_decomposed_quantize_per_tensor_default_1651: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_182, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_view_copy_default_182 = None
2025-03-21T20:31:44.0201862Z             
2025-03-21T20:31:44.0202532Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:346 in update, code: v_out = torch.ops.aten.index_put_(self.past_v_caches, [None, input_pos], v_val)
2025-03-21T20:31:44.0203697Z             quantized_decomposed_dequantize_per_tensor_default_2235: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1651, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1651 = None
2025-03-21T20:31:44.0203788Z             
2025-03-21T20:31:44.0204559Z              # File: <eval_with_key>.50:5730 in forward, code: quantize_per_tensor_default_1811 = torch.ops.quantized_decomposed.quantize_per_tensor.default(_to_copy_20, 0.000400586926843971, 33468, 0, 65535, torch.int32);  _to_copy_20 = None
2025-03-21T20:31:44.0205757Z             quantized_decomposed_quantize_per_tensor_default_1652: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_2233, 0.000400586926843971, 33468, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_2233 = None
2025-03-21T20:31:44.0205864Z             
2025-03-21T20:31:44.0206388Z              # File: /pytorch/executorch/examples/models/llama/rope.py:84 in apply_rotary_emb, code: xq_r, xq_i = xq.float().reshape(xq.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:44.0207543Z             quantized_decomposed_dequantize_per_tensor_default_2236: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1652, 0.000400586926843971, 33468, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1652 = None
2025-03-21T20:31:44.0208322Z             aten_view_copy_default_183: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_2236, [1, 1, 12, -1, 2]);  quantized_decomposed_dequantize_per_tensor_default_2236 = None
2025-03-21T20:31:44.0209375Z             quantized_decomposed_quantize_per_tensor_default_1653: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_183, 0.000400586926843971, 33468, 0, 65535, torch.int32);  aten_view_copy_default_183 = None
2025-03-21T20:31:44.0210526Z             quantized_decomposed_dequantize_per_tensor_default_2237: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1653, 0.000400586926843971, 33468, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1653 = None
2025-03-21T20:31:44.0211107Z             aten_slice_copy_tensor_40: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_2237, 4, 0, 1)
2025-03-21T20:31:44.0211864Z             aten_slice_copy_tensor_41: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_2237, 4, 1, 2);  quantized_decomposed_dequantize_per_tensor_default_2237 = None
2025-03-21T20:31:44.0212402Z             aten_squeeze_copy_dims_113: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_40, [4]);  aten_slice_copy_tensor_40 = None
2025-03-21T20:31:44.0212925Z             aten_squeeze_copy_dims_114: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_41, [4]);  aten_slice_copy_tensor_41 = None
2025-03-21T20:31:44.0213990Z             quantized_decomposed_quantize_per_tensor_default_1654: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_113, 0.0003711249737534672, 36125, 0, 65535, torch.int32);  aten_squeeze_copy_dims_113 = None
2025-03-21T20:31:44.0214087Z             
2025-03-21T20:31:44.0214579Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:44.0215500Z             quantized_decomposed_dequantize_per_tensor_default_2238: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1654, 0.0003711249737534672, 36125, 0, 65535, torch.int32)
2025-03-21T20:31:44.0215603Z             
2025-03-21T20:31:44.0216075Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:44.0217267Z             quantized_decomposed_dequantize_per_tensor_default_2239: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1654, 0.0003711249737534672, 36125, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1654 = None
2025-03-21T20:31:44.0217383Z             
2025-03-21T20:31:44.0217918Z              # File: /pytorch/executorch/examples/models/llama/rope.py:84 in apply_rotary_emb, code: xq_r, xq_i = xq.float().reshape(xq.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:44.0218827Z             quantized_decomposed_quantize_per_tensor_default_1655: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_114, 0.0003442920569796115, 28225, 0, 65535, torch.int32);  aten_squeeze_copy_dims_114 = None
2025-03-21T20:31:44.0218933Z             
2025-03-21T20:31:44.0219406Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:44.0220348Z             quantized_decomposed_dequantize_per_tensor_default_2240: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1655, 0.0003442920569796115, 28225, 0, 65535, torch.int32)
2025-03-21T20:31:44.0220452Z             
2025-03-21T20:31:44.0220924Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:44.0222088Z             quantized_decomposed_dequantize_per_tensor_default_2241: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1655, 0.0003442920569796115, 28225, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1655 = None
2025-03-21T20:31:44.0222198Z             
2025-03-21T20:31:44.0222971Z              # File: <eval_with_key>.50:5745 in forward, code: quantize_per_tensor_default_1815 = torch.ops.quantized_decomposed.quantize_per_tensor.default(_to_copy_21, 0.0004142843827139586, 29754, 0, 65535, torch.int32);  _to_copy_21 = None
2025-03-21T20:31:44.0224119Z             quantized_decomposed_quantize_per_tensor_default_1656: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_2234, 0.0004142843827139586, 29754, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_2234 = None
2025-03-21T20:31:44.0224219Z             
2025-03-21T20:31:44.0224737Z              # File: /pytorch/executorch/examples/models/llama/rope.py:85 in apply_rotary_emb, code: xk_r, xk_i = xk.float().reshape(xk.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:44.0225892Z             quantized_decomposed_dequantize_per_tensor_default_2242: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1656, 0.0004142843827139586, 29754, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1656 = None
2025-03-21T20:31:44.0226669Z             aten_view_copy_default_184: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_2242, [1, 1, 12, -1, 2]);  quantized_decomposed_dequantize_per_tensor_default_2242 = None
2025-03-21T20:31:44.0227587Z             quantized_decomposed_quantize_per_tensor_default_1657: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_184, 0.0004142843827139586, 29754, 0, 65535, torch.int32);  aten_view_copy_default_184 = None
2025-03-21T20:31:44.0228754Z             quantized_decomposed_dequantize_per_tensor_default_2243: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1657, 0.0004142843827139586, 29754, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1657 = None
2025-03-21T20:31:44.0229326Z             aten_slice_copy_tensor_42: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_2243, 4, 0, 1)
2025-03-21T20:31:44.0230082Z             aten_slice_copy_tensor_43: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_2243, 4, 1, 2);  quantized_decomposed_dequantize_per_tensor_default_2243 = None
2025-03-21T20:31:44.0230617Z             aten_squeeze_copy_dims_115: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_42, [4]);  aten_slice_copy_tensor_42 = None
2025-03-21T20:31:44.0231140Z             aten_squeeze_copy_dims_116: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_43, [4]);  aten_slice_copy_tensor_43 = None
2025-03-21T20:31:44.0232086Z             quantized_decomposed_quantize_per_tensor_default_1658: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_115, 0.00039733032463118434, 28227, 0, 65535, torch.int32);  aten_squeeze_copy_dims_115 = None
2025-03-21T20:31:44.0232175Z             
2025-03-21T20:31:44.0232861Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:44.0233779Z             quantized_decomposed_dequantize_per_tensor_default_2244: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1658, 0.00039733032463118434, 28227, 0, 65535, torch.int32)
2025-03-21T20:31:44.0233957Z             
2025-03-21T20:31:44.0234430Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:44.0235594Z             quantized_decomposed_dequantize_per_tensor_default_2245: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1658, 0.00039733032463118434, 28227, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1658 = None
2025-03-21T20:31:44.0235680Z             
2025-03-21T20:31:44.0236212Z              # File: /pytorch/executorch/examples/models/llama/rope.py:85 in apply_rotary_emb, code: xk_r, xk_i = xk.float().reshape(xk.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:44.0237120Z             quantized_decomposed_quantize_per_tensor_default_1659: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_116, 0.00039120655856095254, 31509, 0, 65535, torch.int32);  aten_squeeze_copy_dims_116 = None
2025-03-21T20:31:44.0237225Z             
2025-03-21T20:31:44.0237696Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:44.0238626Z             quantized_decomposed_dequantize_per_tensor_default_2246: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1659, 0.00039120655856095254, 31509, 0, 65535, torch.int32)
2025-03-21T20:31:44.0238715Z             
2025-03-21T20:31:44.0239193Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:44.0240374Z             quantized_decomposed_dequantize_per_tensor_default_2247: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1659, 0.00039120655856095254, 31509, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1659 = None
2025-03-21T20:31:44.0240514Z             
2025-03-21T20:31:44.0240953Z              # File: /pytorch/executorch/examples/models/llama/rope.py:78 in reshape_for_broadcast, code: return freqs_cis.view(shape)
2025-03-21T20:31:44.0241711Z             aten_view_copy_default_185: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_152, [1, 1, 1, 32]);  quantized_decomposed_dequantize_per_tensor_default_152 = None
2025-03-21T20:31:44.0242624Z             quantized_decomposed_quantize_per_tensor_default_1660: "i32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_185, 3.051804378628731e-05, 32768, 0, 65535, torch.int32);  aten_view_copy_default_185 = None
2025-03-21T20:31:44.0242713Z             
2025-03-21T20:31:44.0243200Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:44.0244149Z             quantized_decomposed_dequantize_per_tensor_default_2248: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1660, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:44.0244252Z             
2025-03-21T20:31:44.0244721Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:44.0245646Z             quantized_decomposed_dequantize_per_tensor_default_2249: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1660, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:44.0245762Z             
2025-03-21T20:31:44.0246245Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:44.0247155Z             quantized_decomposed_dequantize_per_tensor_default_2250: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1660, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:44.0247258Z             
2025-03-21T20:31:44.0247726Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:44.0248876Z             quantized_decomposed_dequantize_per_tensor_default_2251: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1660, 3.051804378628731e-05, 32768, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1660 = None
2025-03-21T20:31:44.0248968Z             
2025-03-21T20:31:44.0249490Z              # File: /pytorch/executorch/examples/models/llama/rope.py:78 in reshape_for_broadcast, code: return freqs_cis.view(shape)
2025-03-21T20:31:44.0250250Z             aten_view_copy_default_186: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_164, [1, 1, 1, 32]);  quantized_decomposed_dequantize_per_tensor_default_164 = None
2025-03-21T20:31:44.0251160Z             quantized_decomposed_quantize_per_tensor_default_1661: "i32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_186, 3.051786916330457e-05, 32767, 0, 65535, torch.int32);  aten_view_copy_default_186 = None
2025-03-21T20:31:44.0251250Z             
2025-03-21T20:31:44.0251764Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:44.0252713Z             quantized_decomposed_dequantize_per_tensor_default_2252: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1661, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:44.0252802Z             
2025-03-21T20:31:44.0253289Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:44.0254201Z             quantized_decomposed_dequantize_per_tensor_default_2253: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1661, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:44.0254304Z             
2025-03-21T20:31:44.0254774Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:44.0255721Z             quantized_decomposed_dequantize_per_tensor_default_2254: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1661, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:44.0255811Z             
2025-03-21T20:31:44.0256291Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:44.0257428Z             quantized_decomposed_dequantize_per_tensor_default_2255: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1661, 3.051786916330457e-05, 32767, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1661 = None
2025-03-21T20:31:44.0257556Z             
2025-03-21T20:31:44.0258030Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:44.0259177Z             aten_mul_tensor_152: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2239, quantized_decomposed_dequantize_per_tensor_default_2251);  quantized_decomposed_dequantize_per_tensor_default_2239 = quantized_decomposed_dequantize_per_tensor_default_2251 = None
2025-03-21T20:31:44.0260033Z             quantized_decomposed_quantize_per_tensor_default_1662: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_152, 0.0003691529855132103, 36256, 0, 65535, torch.int32);  aten_mul_tensor_152 = None
2025-03-21T20:31:44.0261189Z             quantized_decomposed_dequantize_per_tensor_default_2256: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1662, 0.0003691529855132103, 36256, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1662 = None
2025-03-21T20:31:44.0262319Z             aten_mul_tensor_153: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2240, quantized_decomposed_dequantize_per_tensor_default_2254);  quantized_decomposed_dequantize_per_tensor_default_2240 = quantized_decomposed_dequantize_per_tensor_default_2254 = None
2025-03-21T20:31:44.0263194Z             quantized_decomposed_quantize_per_tensor_default_1663: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_153, 0.00017168192425742745, 31044, 0, 65535, torch.int32);  aten_mul_tensor_153 = None
2025-03-21T20:31:44.0264369Z             quantized_decomposed_dequantize_per_tensor_default_2257: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1663, 0.00017168192425742745, 31044, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1663 = None
2025-03-21T20:31:44.0265538Z             aten_sub_tensor_20: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_sub_Tensor(quantized_decomposed_dequantize_per_tensor_default_2256, quantized_decomposed_dequantize_per_tensor_default_2257);  quantized_decomposed_dequantize_per_tensor_default_2256 = quantized_decomposed_dequantize_per_tensor_default_2257 = None
2025-03-21T20:31:44.0266405Z             quantized_decomposed_quantize_per_tensor_default_1664: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_sub_tensor_20, 0.00036686332896351814, 36433, 0, 65535, torch.int32);  aten_sub_tensor_20 = None
2025-03-21T20:31:44.0266498Z             
2025-03-21T20:31:44.0267469Z              # File: <eval_with_key>.50:5779 in forward, code: dequantize_per_tensor_default_1823 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1823, 0.00036686332896351814, 36433, 0, 65535, torch.int32);  quantize_per_tensor_default_1823 = None
2025-03-21T20:31:44.0268633Z             quantized_decomposed_dequantize_per_tensor_default_2258: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1664, 0.00036686332896351814, 36433, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1664 = None
2025-03-21T20:31:44.0268739Z             
2025-03-21T20:31:44.0269216Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:44.0270376Z             aten_mul_tensor_154: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2238, quantized_decomposed_dequantize_per_tensor_default_2255);  quantized_decomposed_dequantize_per_tensor_default_2238 = quantized_decomposed_dequantize_per_tensor_default_2255 = None
2025-03-21T20:31:44.0271255Z             quantized_decomposed_quantize_per_tensor_default_1665: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_154, 0.00014334538718685508, 33099, 0, 65535, torch.int32);  aten_mul_tensor_154 = None
2025-03-21T20:31:44.0272413Z             quantized_decomposed_dequantize_per_tensor_default_2259: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1665, 0.00014334538718685508, 33099, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1665 = None
2025-03-21T20:31:44.0273544Z             aten_mul_tensor_155: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2241, quantized_decomposed_dequantize_per_tensor_default_2250);  quantized_decomposed_dequantize_per_tensor_default_2241 = quantized_decomposed_dequantize_per_tensor_default_2250 = None
2025-03-21T20:31:44.0274416Z             quantized_decomposed_quantize_per_tensor_default_1666: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_155, 0.00034285150468349457, 28223, 0, 65535, torch.int32);  aten_mul_tensor_155 = None
2025-03-21T20:31:44.0275557Z             quantized_decomposed_dequantize_per_tensor_default_2260: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1666, 0.00034285150468349457, 28223, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1666 = None
2025-03-21T20:31:44.0276717Z             aten_add_tensor_50: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_2259, quantized_decomposed_dequantize_per_tensor_default_2260);  quantized_decomposed_dequantize_per_tensor_default_2259 = quantized_decomposed_dequantize_per_tensor_default_2260 = None
2025-03-21T20:31:44.0277587Z             quantized_decomposed_quantize_per_tensor_default_1667: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_50, 0.0003369115001987666, 28096, 0, 65535, torch.int32);  aten_add_tensor_50 = None
2025-03-21T20:31:44.0277687Z             
2025-03-21T20:31:44.0278619Z              # File: <eval_with_key>.50:5788 in forward, code: dequantize_per_tensor_default_1826 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1826, 0.0003369115001987666, 28096, 0, 65535, torch.int32);  quantize_per_tensor_default_1826 = None
2025-03-21T20:31:44.0279812Z             quantized_decomposed_dequantize_per_tensor_default_2261: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1667, 0.0003369115001987666, 28096, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1667 = None
2025-03-21T20:31:44.0279903Z             
2025-03-21T20:31:44.0280393Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:44.0281520Z             aten_mul_tensor_156: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2245, quantized_decomposed_dequantize_per_tensor_default_2249);  quantized_decomposed_dequantize_per_tensor_default_2245 = quantized_decomposed_dequantize_per_tensor_default_2249 = None
2025-03-21T20:31:44.0282412Z             quantized_decomposed_quantize_per_tensor_default_1668: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_156, 0.0003857550327666104, 28901, 0, 65535, torch.int32);  aten_mul_tensor_156 = None
2025-03-21T20:31:44.0283556Z             quantized_decomposed_dequantize_per_tensor_default_2262: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1668, 0.0003857550327666104, 28901, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1668 = None
2025-03-21T20:31:44.0284690Z             aten_mul_tensor_157: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2246, quantized_decomposed_dequantize_per_tensor_default_2252);  quantized_decomposed_dequantize_per_tensor_default_2246 = quantized_decomposed_dequantize_per_tensor_default_2252 = None
2025-03-21T20:31:44.0285549Z             quantized_decomposed_quantize_per_tensor_default_1669: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_157, 0.00017581522115506232, 32153, 0, 65535, torch.int32);  aten_mul_tensor_157 = None
2025-03-21T20:31:44.0286705Z             quantized_decomposed_dequantize_per_tensor_default_2263: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1669, 0.00017581522115506232, 32153, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1669 = None
2025-03-21T20:31:44.0287836Z             aten_sub_tensor_21: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_sub_Tensor(quantized_decomposed_dequantize_per_tensor_default_2262, quantized_decomposed_dequantize_per_tensor_default_2263);  quantized_decomposed_dequantize_per_tensor_default_2262 = quantized_decomposed_dequantize_per_tensor_default_2263 = None
2025-03-21T20:31:44.0288711Z             quantized_decomposed_quantize_per_tensor_default_1670: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_sub_tensor_21, 0.00037492933915928006, 29584, 0, 65535, torch.int32);  aten_sub_tensor_21 = None
2025-03-21T20:31:44.0288836Z             
2025-03-21T20:31:44.0289850Z              # File: <eval_with_key>.50:5797 in forward, code: dequantize_per_tensor_default_1829 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1829, 0.00037492933915928006, 29584, 0, 65535, torch.int32);  quantize_per_tensor_default_1829 = None
2025-03-21T20:31:44.0291011Z             quantized_decomposed_dequantize_per_tensor_default_2264: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1670, 0.00037492933915928006, 29584, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1670 = None
2025-03-21T20:31:44.0291105Z             
2025-03-21T20:31:44.0291595Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:44.0292750Z             aten_mul_tensor_158: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2244, quantized_decomposed_dequantize_per_tensor_default_2253);  quantized_decomposed_dequantize_per_tensor_default_2244 = quantized_decomposed_dequantize_per_tensor_default_2253 = None
2025-03-21T20:31:44.0293622Z             quantized_decomposed_quantize_per_tensor_default_1671: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_158, 0.00016251628403551877, 33632, 0, 65535, torch.int32);  aten_mul_tensor_158 = None
2025-03-21T20:31:44.0294796Z             quantized_decomposed_dequantize_per_tensor_default_2265: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1671, 0.00016251628403551877, 33632, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1671 = None
2025-03-21T20:31:44.0295938Z             aten_mul_tensor_159: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2247, quantized_decomposed_dequantize_per_tensor_default_2248);  quantized_decomposed_dequantize_per_tensor_default_2247 = quantized_decomposed_dequantize_per_tensor_default_2248 = None
2025-03-21T20:31:44.0296792Z             quantized_decomposed_quantize_per_tensor_default_1672: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_159, 0.0003872132219839841, 31182, 0, 65535, torch.int32);  aten_mul_tensor_159 = None
2025-03-21T20:31:44.0297942Z             quantized_decomposed_dequantize_per_tensor_default_2266: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1672, 0.0003872132219839841, 31182, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1672 = None
2025-03-21T20:31:44.0299066Z             aten_add_tensor_51: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_2265, quantized_decomposed_dequantize_per_tensor_default_2266);  quantized_decomposed_dequantize_per_tensor_default_2265 = quantized_decomposed_dequantize_per_tensor_default_2266 = None
2025-03-21T20:31:44.0299924Z             quantized_decomposed_quantize_per_tensor_default_1673: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_51, 0.0003922595642507076, 31433, 0, 65535, torch.int32);  aten_add_tensor_51 = None
2025-03-21T20:31:44.0300013Z             
2025-03-21T20:31:44.0301012Z              # File: <eval_with_key>.50:5806 in forward, code: dequantize_per_tensor_default_1832 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1832, 0.0003922595642507076, 31433, 0, 65535, torch.int32);  quantize_per_tensor_default_1832 = None
2025-03-21T20:31:44.0302182Z             quantized_decomposed_dequantize_per_tensor_default_2267: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1673, 0.0003922595642507076, 31433, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1673 = None
2025-03-21T20:31:44.0302282Z             
2025-03-21T20:31:44.0302806Z              # File: /pytorch/executorch/examples/models/llama/rope.py:95 in apply_rotary_emb, code: xq_out = torch.stack([xq_out_r, xq_out_i], dim=-1).flatten(3)
2025-03-21T20:31:44.0303621Z             aten_unsqueeze_copy_default_113: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_2258, 4);  quantized_decomposed_dequantize_per_tensor_default_2258 = None
2025-03-21T20:31:44.0304553Z             aten_unsqueeze_copy_default_114: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_2261, 4);  quantized_decomposed_dequantize_per_tensor_default_2261 = None
2025-03-21T20:31:44.0305327Z             aten_cat_default_40: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_cat_default([aten_unsqueeze_copy_default_113, aten_unsqueeze_copy_default_114], -1);  aten_unsqueeze_copy_default_113 = aten_unsqueeze_copy_default_114 = None
2025-03-21T20:31:44.0306195Z             quantized_decomposed_quantize_per_tensor_default_1674: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_40, 0.00039642397314310074, 33716, 0, 65535, torch.int32);  aten_cat_default_40 = None
2025-03-21T20:31:44.0307385Z             quantized_decomposed_dequantize_per_tensor_default_2268: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1674, 0.00039642397314310074, 33716, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1674 = None
2025-03-21T20:31:44.0308155Z             aten_view_copy_default_187: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_2268, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_2268 = None
2025-03-21T20:31:44.0309085Z             quantized_decomposed_quantize_per_tensor_default_1675: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_187, 0.00039642397314310074, 33716, 0, 65535, torch.int32);  aten_view_copy_default_187 = None
2025-03-21T20:31:44.0309175Z             
2025-03-21T20:31:44.0310131Z              # File: <eval_with_key>.50:5812 in forward, code: dequantize_per_tensor_default_1834 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1834, 0.00039642397314310074, 33716, 0, 65535, torch.int32);  quantize_per_tensor_default_1834 = None
2025-03-21T20:31:44.0311288Z             quantized_decomposed_dequantize_per_tensor_default_2269: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1675, 0.00039642397314310074, 33716, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1675 = None
2025-03-21T20:31:44.0311376Z             
2025-03-21T20:31:44.0311898Z              # File: /pytorch/executorch/examples/models/llama/rope.py:96 in apply_rotary_emb, code: xk_out = torch.stack([xk_out_r, xk_out_i], dim=-1).flatten(3)
2025-03-21T20:31:44.0312741Z             aten_unsqueeze_copy_default_115: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_2264, 4);  quantized_decomposed_dequantize_per_tensor_default_2264 = None
2025-03-21T20:31:44.0313556Z             aten_unsqueeze_copy_default_116: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_2267, 4);  quantized_decomposed_dequantize_per_tensor_default_2267 = None
2025-03-21T20:31:44.0314316Z             aten_cat_default_41: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_cat_default([aten_unsqueeze_copy_default_115, aten_unsqueeze_copy_default_116], -1);  aten_unsqueeze_copy_default_115 = aten_unsqueeze_copy_default_116 = None
2025-03-21T20:31:44.0315455Z             quantized_decomposed_quantize_per_tensor_default_1676: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_41, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_cat_default_41 = None
2025-03-21T20:31:44.0316653Z             quantized_decomposed_dequantize_per_tensor_default_2270: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1676, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1676 = None
2025-03-21T20:31:44.0317433Z             aten_view_copy_default_188: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_2270, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_2270 = None
2025-03-21T20:31:44.0318342Z             quantized_decomposed_quantize_per_tensor_default_1677: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_188, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_view_copy_default_188 = None
2025-03-21T20:31:44.0318469Z             
2025-03-21T20:31:44.0319411Z              # File: <eval_with_key>.50:5818 in forward, code: dequantize_per_tensor_default_1836 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1836, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantize_per_tensor_default_1836 = None
2025-03-21T20:31:44.0320568Z             quantized_decomposed_dequantize_per_tensor_default_2271: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1677, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1677 = None
2025-03-21T20:31:44.0320655Z             
2025-03-21T20:31:44.0321434Z              # File: <eval_with_key>.50:5820 in forward, code: quantize_per_tensor_default_1837 = torch.ops.quantized_decomposed.quantize_per_tensor.default(type_as_20, 0.00039642397314310074, 33716, 0, 65535, torch.int32);  type_as_20 = None
2025-03-21T20:31:44.0322585Z             quantized_decomposed_quantize_per_tensor_default_1678: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_2269, 0.00039642397314310074, 33716, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_2269 = None
2025-03-21T20:31:44.0322688Z             
2025-03-21T20:31:44.0323215Z              # File: /pytorch/executorch/examples/models/llama/attention.py:249 in forward, code: q = q.transpose(1, 2)  # (bs, n_local_heads, seqlen, head_dim)
2025-03-21T20:31:44.0324374Z             quantized_decomposed_dequantize_per_tensor_default_2272: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1678, 0.00039642397314310074, 33716, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1678 = None
2025-03-21T20:31:44.0324491Z             
2025-03-21T20:31:44.0325299Z              # File: <eval_with_key>.50:5823 in forward, code: quantize_per_tensor_default_1838 = torch.ops.quantized_decomposed.quantize_per_tensor.default(type_as_21, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  type_as_21 = None
2025-03-21T20:31:44.0326444Z             quantized_decomposed_quantize_per_tensor_default_1679: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_2271, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_2271 = None
2025-03-21T20:31:44.0326549Z             
2025-03-21T20:31:44.0327217Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:345 in update, code: k_out = torch.ops.aten.index_put_(self.past_k_caches, [None, input_pos], k_val)
2025-03-21T20:31:44.0328404Z             quantized_decomposed_dequantize_per_tensor_default_2273: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1679, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1679 = None
2025-03-21T20:31:44.0328495Z             
2025-03-21T20:31:44.0329015Z              # File: /pytorch/executorch/examples/models/llama/attention.py:249 in forward, code: q = q.transpose(1, 2)  # (bs, n_local_heads, seqlen, head_dim)
2025-03-21T20:31:44.0329898Z             aten_permute_copy_default_416: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2272, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2272 = None
2025-03-21T20:31:44.0330881Z             quantized_decomposed_quantize_per_tensor_default_1680: "i32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_416, 0.00039642397314310074, 33716, 0, 65535, torch.int32);  aten_permute_copy_default_416 = None
2025-03-21T20:31:44.0330988Z             
2025-03-21T20:31:44.0331566Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:44.0332899Z             quantized_decomposed_dequantize_per_tensor_default_2274: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1680, 0.00039642397314310074, 33716, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1680 = None
2025-03-21T20:31:44.0332994Z             
2025-03-21T20:31:44.0333680Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:345 in update, code: k_out = torch.ops.aten.index_put_(self.past_k_caches, [None, input_pos], k_val)
2025-03-21T20:31:44.0334973Z             aten_index_put_default_20: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_index_put_default(quantized_decomposed_dequantize_per_tensor_default_143, [None, attn_options_input_pos], quantized_decomposed_dequantize_per_tensor_default_2273);  quantized_decomposed_dequantize_per_tensor_default_143 = quantized_decomposed_dequantize_per_tensor_default_2273 = None
2025-03-21T20:31:44.0335899Z             quantized_decomposed_quantize_per_tensor_default_1681: "i32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_put_default_20, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_index_put_default_20 = None
2025-03-21T20:31:44.0335989Z             
2025-03-21T20:31:44.0336798Z              # File: <eval_with_key>.50:5830 in forward, code: dequantize_per_tensor_default_1840 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1840, 0.00039381824899464846, 31308, 0, 65535, torch.int32)
2025-03-21T20:31:44.0337835Z             quantized_decomposed_dequantize_per_tensor_default_2275: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1681, 0.00039381824899464846, 31308, 0, 65535, torch.int32)
2025-03-21T20:31:44.0337940Z             
2025-03-21T20:31:44.0338577Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.0339514Z             quantized_decomposed_dequantize_per_tensor_default_2276: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1681, 0.00039381824899464846, 31308, 0, 65535, torch.int32)
2025-03-21T20:31:44.0340435Z             quantized_decomposed_dequantize_per_tensor_default_2277: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1681, 0.00039381824899464846, 31308, 0, 65535, torch.int32)
2025-03-21T20:31:44.0341404Z             quantized_decomposed_dequantize_per_tensor_default_2278: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1681, 0.00039381824899464846, 31308, 0, 65535, torch.int32)
2025-03-21T20:31:44.0342327Z             quantized_decomposed_dequantize_per_tensor_default_2279: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1681, 0.00039381824899464846, 31308, 0, 65535, torch.int32)
2025-03-21T20:31:44.0343297Z             quantized_decomposed_dequantize_per_tensor_default_2280: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1681, 0.00039381824899464846, 31308, 0, 65535, torch.int32)
2025-03-21T20:31:44.0344225Z             quantized_decomposed_dequantize_per_tensor_default_2281: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1681, 0.00039381824899464846, 31308, 0, 65535, torch.int32)
2025-03-21T20:31:44.0345158Z             quantized_decomposed_dequantize_per_tensor_default_2282: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1681, 0.00039381824899464846, 31308, 0, 65535, torch.int32)
2025-03-21T20:31:44.0346091Z             quantized_decomposed_dequantize_per_tensor_default_2283: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1681, 0.00039381824899464846, 31308, 0, 65535, torch.int32)
2025-03-21T20:31:44.0347010Z             quantized_decomposed_dequantize_per_tensor_default_2284: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1681, 0.00039381824899464846, 31308, 0, 65535, torch.int32)
2025-03-21T20:31:44.0347942Z             quantized_decomposed_dequantize_per_tensor_default_2285: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1681, 0.00039381824899464846, 31308, 0, 65535, torch.int32)
2025-03-21T20:31:44.0348861Z             quantized_decomposed_dequantize_per_tensor_default_2286: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1681, 0.00039381824899464846, 31308, 0, 65535, torch.int32)
2025-03-21T20:31:44.0350088Z             quantized_decomposed_dequantize_per_tensor_default_2287: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1681, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1681 = None
2025-03-21T20:31:44.0350177Z             
2025-03-21T20:31:44.0350862Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:346 in update, code: v_out = torch.ops.aten.index_put_(self.past_v_caches, [None, input_pos], v_val)
2025-03-21T20:31:44.0352140Z             aten_index_put_default_21: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_index_put_default(quantized_decomposed_dequantize_per_tensor_default_144, [None, attn_options_input_pos], quantized_decomposed_dequantize_per_tensor_default_2235);  quantized_decomposed_dequantize_per_tensor_default_144 = quantized_decomposed_dequantize_per_tensor_default_2235 = None
2025-03-21T20:31:44.0353091Z             quantized_decomposed_quantize_per_tensor_default_1682: "i32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_put_default_21, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_index_put_default_21 = None
2025-03-21T20:31:44.0353179Z             
2025-03-21T20:31:44.0353983Z              # File: <eval_with_key>.50:5845 in forward, code: dequantize_per_tensor_default_1841 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1841, 0.00021122458565514535, 31154, 0, 65535, torch.int32)
2025-03-21T20:31:44.0354913Z             quantized_decomposed_dequantize_per_tensor_default_2288: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1682, 0.00021122458565514535, 31154, 0, 65535, torch.int32)
2025-03-21T20:31:44.0355035Z             
2025-03-21T20:31:44.0355672Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.0356614Z             quantized_decomposed_dequantize_per_tensor_default_2289: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1682, 0.00021122458565514535, 31154, 0, 65535, torch.int32)
2025-03-21T20:31:44.0357535Z             quantized_decomposed_dequantize_per_tensor_default_2290: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1682, 0.00021122458565514535, 31154, 0, 65535, torch.int32)
2025-03-21T20:31:44.0358473Z             quantized_decomposed_dequantize_per_tensor_default_2291: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1682, 0.00021122458565514535, 31154, 0, 65535, torch.int32)
2025-03-21T20:31:44.0359397Z             quantized_decomposed_dequantize_per_tensor_default_2292: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1682, 0.00021122458565514535, 31154, 0, 65535, torch.int32)
2025-03-21T20:31:44.0360327Z             quantized_decomposed_dequantize_per_tensor_default_2293: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1682, 0.00021122458565514535, 31154, 0, 65535, torch.int32)
2025-03-21T20:31:44.0361268Z             quantized_decomposed_dequantize_per_tensor_default_2294: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1682, 0.00021122458565514535, 31154, 0, 65535, torch.int32)
2025-03-21T20:31:44.0362228Z             quantized_decomposed_dequantize_per_tensor_default_2295: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1682, 0.00021122458565514535, 31154, 0, 65535, torch.int32)
2025-03-21T20:31:44.0363152Z             quantized_decomposed_dequantize_per_tensor_default_2296: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1682, 0.00021122458565514535, 31154, 0, 65535, torch.int32)
2025-03-21T20:31:44.0364082Z             quantized_decomposed_dequantize_per_tensor_default_2297: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1682, 0.00021122458565514535, 31154, 0, 65535, torch.int32)
2025-03-21T20:31:44.0365028Z             quantized_decomposed_dequantize_per_tensor_default_2298: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1682, 0.00021122458565514535, 31154, 0, 65535, torch.int32)
2025-03-21T20:31:44.0365962Z             quantized_decomposed_dequantize_per_tensor_default_2299: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1682, 0.00021122458565514535, 31154, 0, 65535, torch.int32)
2025-03-21T20:31:44.0367128Z             quantized_decomposed_dequantize_per_tensor_default_2300: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1682, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1682 = None
2025-03-21T20:31:44.0367245Z             
2025-03-21T20:31:44.0367882Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.0368695Z             aten_permute_copy_default_417: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2287, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2287 = None
2025-03-21T20:31:44.0369722Z             quantized_decomposed_quantize_per_tensor_default_1683: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_417, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_permute_copy_default_417 = None
2025-03-21T20:31:44.0370882Z             quantized_decomposed_dequantize_per_tensor_default_2301: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1683, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1683 = None
2025-03-21T20:31:44.0371642Z             aten_select_copy_int_480: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2301, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2301 = None
2025-03-21T20:31:44.0372538Z             quantized_decomposed_quantize_per_tensor_default_1684: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_480, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_select_copy_int_480 = None
2025-03-21T20:31:44.0373743Z             quantized_decomposed_dequantize_per_tensor_default_2302: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1684, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1684 = None
2025-03-21T20:31:44.0374508Z             aten_select_copy_int_481: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2302, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2302 = None
2025-03-21T20:31:44.0375410Z             quantized_decomposed_quantize_per_tensor_default_1685: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_481, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_select_copy_int_481 = None
2025-03-21T20:31:44.0375498Z             
2025-03-21T20:31:44.0376455Z              # File: <eval_with_key>.50:5866 in forward, code: dequantize_per_tensor_default_1844 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1844, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantize_per_tensor_default_1844 = None
2025-03-21T20:31:44.0377633Z             quantized_decomposed_dequantize_per_tensor_default_2303: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1685, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1685 = None
2025-03-21T20:31:44.0377737Z             
2025-03-21T20:31:44.0378375Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.0379191Z             aten_permute_copy_default_418: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2286, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2286 = None
2025-03-21T20:31:44.0380166Z             quantized_decomposed_quantize_per_tensor_default_1686: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_418, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_permute_copy_default_418 = None
2025-03-21T20:31:44.0381334Z             quantized_decomposed_dequantize_per_tensor_default_2304: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1686, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1686 = None
2025-03-21T20:31:44.0382077Z             aten_select_copy_int_482: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2304, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2304 = None
2025-03-21T20:31:44.0382994Z             quantized_decomposed_quantize_per_tensor_default_1687: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_482, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_select_copy_int_482 = None
2025-03-21T20:31:44.0384152Z             quantized_decomposed_dequantize_per_tensor_default_2305: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1687, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1687 = None
2025-03-21T20:31:44.0384901Z             aten_select_copy_int_483: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2305, 0, 1);  quantized_decomposed_dequantize_per_tensor_default_2305 = None
2025-03-21T20:31:44.0385822Z             quantized_decomposed_quantize_per_tensor_default_1688: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_483, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_select_copy_int_483 = None
2025-03-21T20:31:44.0385949Z             
2025-03-21T20:31:44.0386890Z              # File: <eval_with_key>.50:5875 in forward, code: dequantize_per_tensor_default_1847 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1847, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantize_per_tensor_default_1847 = None
2025-03-21T20:31:44.0388046Z             quantized_decomposed_dequantize_per_tensor_default_2306: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1688, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1688 = None
2025-03-21T20:31:44.0388136Z             
2025-03-21T20:31:44.0388786Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.0389618Z             aten_permute_copy_default_419: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2285, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2285 = None
2025-03-21T20:31:44.0390573Z             quantized_decomposed_quantize_per_tensor_default_1689: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_419, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_permute_copy_default_419 = None
2025-03-21T20:31:44.0391729Z             quantized_decomposed_dequantize_per_tensor_default_2307: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1689, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1689 = None
2025-03-21T20:31:44.0392507Z             aten_select_copy_int_484: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2307, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2307 = None
2025-03-21T20:31:44.0393419Z             quantized_decomposed_quantize_per_tensor_default_1690: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_484, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_select_copy_int_484 = None
2025-03-21T20:31:44.0394575Z             quantized_decomposed_dequantize_per_tensor_default_2308: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1690, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1690 = None
2025-03-21T20:31:44.0395330Z             aten_select_copy_int_485: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2308, 0, 2);  quantized_decomposed_dequantize_per_tensor_default_2308 = None
2025-03-21T20:31:44.0396220Z             quantized_decomposed_quantize_per_tensor_default_1691: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_485, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_select_copy_int_485 = None
2025-03-21T20:31:44.0396323Z             
2025-03-21T20:31:44.0397261Z              # File: <eval_with_key>.50:5884 in forward, code: dequantize_per_tensor_default_1850 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1850, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantize_per_tensor_default_1850 = None
2025-03-21T20:31:44.0398482Z             quantized_decomposed_dequantize_per_tensor_default_2309: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1691, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1691 = None
2025-03-21T20:31:44.0398573Z             
2025-03-21T20:31:44.0399221Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.0400021Z             aten_permute_copy_default_420: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2284, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2284 = None
2025-03-21T20:31:44.0400979Z             quantized_decomposed_quantize_per_tensor_default_1692: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_420, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_permute_copy_default_420 = None
2025-03-21T20:31:44.0402156Z             quantized_decomposed_dequantize_per_tensor_default_2310: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1692, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1692 = None
2025-03-21T20:31:44.0402907Z             aten_select_copy_int_486: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2310, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2310 = None
2025-03-21T20:31:44.0403829Z             quantized_decomposed_quantize_per_tensor_default_1693: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_486, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_select_copy_int_486 = None
2025-03-21T20:31:44.0404996Z             quantized_decomposed_dequantize_per_tensor_default_2311: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1693, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1693 = None
2025-03-21T20:31:44.0405733Z             aten_select_copy_int_487: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2311, 0, 3);  quantized_decomposed_dequantize_per_tensor_default_2311 = None
2025-03-21T20:31:44.0406640Z             quantized_decomposed_quantize_per_tensor_default_1694: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_487, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_select_copy_int_487 = None
2025-03-21T20:31:44.0406728Z             
2025-03-21T20:31:44.0407685Z              # File: <eval_with_key>.50:5893 in forward, code: dequantize_per_tensor_default_1853 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1853, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantize_per_tensor_default_1853 = None
2025-03-21T20:31:44.0408830Z             quantized_decomposed_dequantize_per_tensor_default_2312: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1694, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1694 = None
2025-03-21T20:31:44.0408930Z             
2025-03-21T20:31:44.0409629Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.0410508Z             aten_permute_copy_default_421: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2283, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2283 = None
2025-03-21T20:31:44.0411455Z             quantized_decomposed_quantize_per_tensor_default_1695: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_421, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_permute_copy_default_421 = None
2025-03-21T20:31:44.0412619Z             quantized_decomposed_dequantize_per_tensor_default_2313: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1695, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1695 = None
2025-03-21T20:31:44.0413390Z             aten_select_copy_int_488: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2313, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2313 = None
2025-03-21T20:31:44.0414300Z             quantized_decomposed_quantize_per_tensor_default_1696: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_488, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_select_copy_int_488 = None
2025-03-21T20:31:44.0415447Z             quantized_decomposed_dequantize_per_tensor_default_2314: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1696, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1696 = None
2025-03-21T20:31:44.0416239Z             aten_select_copy_int_489: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2314, 0, 4);  quantized_decomposed_dequantize_per_tensor_default_2314 = None
2025-03-21T20:31:44.0417286Z             quantized_decomposed_quantize_per_tensor_default_1697: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_489, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_select_copy_int_489 = None
2025-03-21T20:31:44.0417376Z             
2025-03-21T20:31:44.0418316Z              # File: <eval_with_key>.50:5902 in forward, code: dequantize_per_tensor_default_1856 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1856, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantize_per_tensor_default_1856 = None
2025-03-21T20:31:44.0419483Z             quantized_decomposed_dequantize_per_tensor_default_2315: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1697, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1697 = None
2025-03-21T20:31:44.0419585Z             
2025-03-21T20:31:44.0420224Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.0421026Z             aten_permute_copy_default_422: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2282, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2282 = None
2025-03-21T20:31:44.0422010Z             quantized_decomposed_quantize_per_tensor_default_1698: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_422, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_permute_copy_default_422 = None
2025-03-21T20:31:44.0423199Z             quantized_decomposed_dequantize_per_tensor_default_2316: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1698, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1698 = None
2025-03-21T20:31:44.0423936Z             aten_select_copy_int_490: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2316, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2316 = None
2025-03-21T20:31:44.0424843Z             quantized_decomposed_quantize_per_tensor_default_1699: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_490, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_select_copy_int_490 = None
2025-03-21T20:31:44.0426016Z             quantized_decomposed_dequantize_per_tensor_default_2317: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1699, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1699 = None
2025-03-21T20:31:44.0426767Z             aten_select_copy_int_491: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2317, 0, 5);  quantized_decomposed_dequantize_per_tensor_default_2317 = None
2025-03-21T20:31:44.0427659Z             quantized_decomposed_quantize_per_tensor_default_1700: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_491, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_select_copy_int_491 = None
2025-03-21T20:31:44.0427784Z             
2025-03-21T20:31:44.0428726Z              # File: <eval_with_key>.50:5911 in forward, code: dequantize_per_tensor_default_1859 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1859, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantize_per_tensor_default_1859 = None
2025-03-21T20:31:44.0429885Z             quantized_decomposed_dequantize_per_tensor_default_2318: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1700, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1700 = None
2025-03-21T20:31:44.0429972Z             
2025-03-21T20:31:44.0430618Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.0431421Z             aten_permute_copy_default_423: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2281, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2281 = None
2025-03-21T20:31:44.0432565Z             quantized_decomposed_quantize_per_tensor_default_1701: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_423, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_permute_copy_default_423 = None
2025-03-21T20:31:44.0433722Z             quantized_decomposed_dequantize_per_tensor_default_2319: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1701, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1701 = None
2025-03-21T20:31:44.0434540Z             aten_select_copy_int_492: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2319, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2319 = None
2025-03-21T20:31:44.0435471Z             quantized_decomposed_quantize_per_tensor_default_1702: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_492, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_select_copy_int_492 = None
2025-03-21T20:31:44.0436633Z             quantized_decomposed_dequantize_per_tensor_default_2320: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1702, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1702 = None
2025-03-21T20:31:44.0437372Z             aten_select_copy_int_493: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2320, 0, 6);  quantized_decomposed_dequantize_per_tensor_default_2320 = None
2025-03-21T20:31:44.0438312Z             quantized_decomposed_quantize_per_tensor_default_1703: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_493, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_select_copy_int_493 = None
2025-03-21T20:31:44.0438402Z             
2025-03-21T20:31:44.0439361Z              # File: <eval_with_key>.50:5920 in forward, code: dequantize_per_tensor_default_1862 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1862, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantize_per_tensor_default_1862 = None
2025-03-21T20:31:44.0440548Z             quantized_decomposed_dequantize_per_tensor_default_2321: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1703, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1703 = None
2025-03-21T20:31:44.0440653Z             
2025-03-21T20:31:44.0441292Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.0442107Z             aten_permute_copy_default_424: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2280, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2280 = None
2025-03-21T20:31:44.0443051Z             quantized_decomposed_quantize_per_tensor_default_1704: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_424, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_permute_copy_default_424 = None
2025-03-21T20:31:44.0444218Z             quantized_decomposed_dequantize_per_tensor_default_2322: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1704, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1704 = None
2025-03-21T20:31:44.0444957Z             aten_select_copy_int_494: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2322, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2322 = None
2025-03-21T20:31:44.0445866Z             quantized_decomposed_quantize_per_tensor_default_1705: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_494, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_select_copy_int_494 = None
2025-03-21T20:31:44.0447059Z             quantized_decomposed_dequantize_per_tensor_default_2323: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1705, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1705 = None
2025-03-21T20:31:44.0447819Z             aten_select_copy_int_495: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2323, 0, 7);  quantized_decomposed_dequantize_per_tensor_default_2323 = None
2025-03-21T20:31:44.0448728Z             quantized_decomposed_quantize_per_tensor_default_1706: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_495, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_select_copy_int_495 = None
2025-03-21T20:31:44.0448818Z             
2025-03-21T20:31:44.0449832Z              # File: <eval_with_key>.50:5929 in forward, code: dequantize_per_tensor_default_1865 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1865, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantize_per_tensor_default_1865 = None
2025-03-21T20:31:44.0451011Z             quantized_decomposed_dequantize_per_tensor_default_2324: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1706, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1706 = None
2025-03-21T20:31:44.0451114Z             
2025-03-21T20:31:44.0451748Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.0452595Z             aten_permute_copy_default_425: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2279, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2279 = None
2025-03-21T20:31:44.0453538Z             quantized_decomposed_quantize_per_tensor_default_1707: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_425, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_permute_copy_default_425 = None
2025-03-21T20:31:44.0454703Z             quantized_decomposed_dequantize_per_tensor_default_2325: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1707, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1707 = None
2025-03-21T20:31:44.0455445Z             aten_select_copy_int_496: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2325, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2325 = None
2025-03-21T20:31:44.0456361Z             quantized_decomposed_quantize_per_tensor_default_1708: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_496, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_select_copy_int_496 = None
2025-03-21T20:31:44.0457513Z             quantized_decomposed_dequantize_per_tensor_default_2326: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1708, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1708 = None
2025-03-21T20:31:44.0458263Z             aten_select_copy_int_497: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2326, 0, 8);  quantized_decomposed_dequantize_per_tensor_default_2326 = None
2025-03-21T20:31:44.0459210Z             quantized_decomposed_quantize_per_tensor_default_1709: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_497, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_select_copy_int_497 = None
2025-03-21T20:31:44.0459314Z             
2025-03-21T20:31:44.0460254Z              # File: <eval_with_key>.50:5938 in forward, code: dequantize_per_tensor_default_1868 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1868, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantize_per_tensor_default_1868 = None
2025-03-21T20:31:44.0461417Z             quantized_decomposed_dequantize_per_tensor_default_2327: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1709, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1709 = None
2025-03-21T20:31:44.0461509Z             
2025-03-21T20:31:44.0462201Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.0463002Z             aten_permute_copy_default_426: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2278, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2278 = None
2025-03-21T20:31:44.0463961Z             quantized_decomposed_quantize_per_tensor_default_1710: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_426, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_permute_copy_default_426 = None
2025-03-21T20:31:44.0465142Z             quantized_decomposed_dequantize_per_tensor_default_2328: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1710, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1710 = None
2025-03-21T20:31:44.0465897Z             aten_select_copy_int_498: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2328, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2328 = None
2025-03-21T20:31:44.0466796Z             quantized_decomposed_quantize_per_tensor_default_1711: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_498, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_select_copy_int_498 = None
2025-03-21T20:31:44.0467964Z             quantized_decomposed_dequantize_per_tensor_default_2329: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1711, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1711 = None
2025-03-21T20:31:44.0468704Z             aten_select_copy_int_499: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2329, 0, 9);  quantized_decomposed_dequantize_per_tensor_default_2329 = None
2025-03-21T20:31:44.0469610Z             quantized_decomposed_quantize_per_tensor_default_1712: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_499, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_select_copy_int_499 = None
2025-03-21T20:31:44.0469705Z             
2025-03-21T20:31:44.0470687Z              # File: <eval_with_key>.50:5947 in forward, code: dequantize_per_tensor_default_1871 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1871, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantize_per_tensor_default_1871 = None
2025-03-21T20:31:44.0471876Z             quantized_decomposed_dequantize_per_tensor_default_2330: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1712, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1712 = None
2025-03-21T20:31:44.0471966Z             
2025-03-21T20:31:44.0472603Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.0473428Z             aten_permute_copy_default_427: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2277, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2277 = None
2025-03-21T20:31:44.0474398Z             quantized_decomposed_quantize_per_tensor_default_1713: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_427, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_permute_copy_default_427 = None
2025-03-21T20:31:44.0475565Z             quantized_decomposed_dequantize_per_tensor_default_2331: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1713, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1713 = None
2025-03-21T20:31:44.0476317Z             aten_select_copy_int_500: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2331, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2331 = None
2025-03-21T20:31:44.0477243Z             quantized_decomposed_quantize_per_tensor_default_1714: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_500, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_select_copy_int_500 = None
2025-03-21T20:31:44.0478407Z             quantized_decomposed_dequantize_per_tensor_default_2332: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1714, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1714 = None
2025-03-21T20:31:44.0479147Z             aten_select_copy_int_501: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2332, 0, 10);  quantized_decomposed_dequantize_per_tensor_default_2332 = None
2025-03-21T20:31:44.0480062Z             quantized_decomposed_quantize_per_tensor_default_1715: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_501, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_select_copy_int_501 = None
2025-03-21T20:31:44.0480153Z             
2025-03-21T20:31:44.0481105Z              # File: <eval_with_key>.50:5956 in forward, code: dequantize_per_tensor_default_1874 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1874, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantize_per_tensor_default_1874 = None
2025-03-21T20:31:44.0482252Z             quantized_decomposed_dequantize_per_tensor_default_2333: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1715, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1715 = None
2025-03-21T20:31:44.0482378Z             
2025-03-21T20:31:44.0483036Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.0483852Z             aten_permute_copy_default_428: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2276, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2276 = None
2025-03-21T20:31:44.0484791Z             quantized_decomposed_quantize_per_tensor_default_1716: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_428, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_permute_copy_default_428 = None
2025-03-21T20:31:44.0485963Z             quantized_decomposed_dequantize_per_tensor_default_2334: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1716, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1716 = None
2025-03-21T20:31:44.0486738Z             aten_select_copy_int_502: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2334, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2334 = None
2025-03-21T20:31:44.0487651Z             quantized_decomposed_quantize_per_tensor_default_1717: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_502, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_select_copy_int_502 = None
2025-03-21T20:31:44.0488858Z             quantized_decomposed_dequantize_per_tensor_default_2335: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1717, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1717 = None
2025-03-21T20:31:44.0489685Z             aten_select_copy_int_503: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2335, 0, 11);  quantized_decomposed_dequantize_per_tensor_default_2335 = None
2025-03-21T20:31:44.0490583Z             quantized_decomposed_quantize_per_tensor_default_1718: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_503, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_select_copy_int_503 = None
2025-03-21T20:31:44.0490691Z             
2025-03-21T20:31:44.0491634Z              # File: <eval_with_key>.50:5965 in forward, code: dequantize_per_tensor_default_1877 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1877, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantize_per_tensor_default_1877 = None
2025-03-21T20:31:44.0492808Z             quantized_decomposed_dequantize_per_tensor_default_2336: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1718, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1718 = None
2025-03-21T20:31:44.0492894Z             
2025-03-21T20:31:44.0493542Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.0499064Z             aten_cat_default_42: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_aten_cat_default([quantized_decomposed_dequantize_per_tensor_default_2303, quantized_decomposed_dequantize_per_tensor_default_2306, quantized_decomposed_dequantize_per_tensor_default_2309, quantized_decomposed_dequantize_per_tensor_default_2312, quantized_decomposed_dequantize_per_tensor_default_2315, quantized_decomposed_dequantize_per_tensor_default_2318, quantized_decomposed_dequantize_per_tensor_default_2321, quantized_decomposed_dequantize_per_tensor_default_2324, quantized_decomposed_dequantize_per_tensor_default_2327, quantized_decomposed_dequantize_per_tensor_default_2330, quantized_decomposed_dequantize_per_tensor_default_2333, quantized_decomposed_dequantize_per_tensor_default_2336]);  quantized_decomposed_dequantize_per_tensor_default_2303 = quantized_decomposed_dequantize_per_tensor_default_2306 = quantized_decomposed_dequantize_per_tensor_default_2309 = quantized_decomposed_dequantize_per_tensor_default_2312 = quantized_decomposed_dequantize_per_tensor_default_2315 = quantized_decomposed_dequantize_per_tensor_default_2318 = quantized_decomposed_dequantize_per_tensor_default_2321 = quantized_decomposed_dequantize_per_tensor_default_2324 = quantized_decomposed_dequantize_per_tensor_default_2327 = quantized_decomposed_dequantize_per_tensor_default_2330 = quantized_decomposed_dequantize_per_tensor_default_2333 = quantized_decomposed_dequantize_per_tensor_default_2336 = None
2025-03-21T20:31:44.0499990Z             quantized_decomposed_quantize_per_tensor_default_1719: "i32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_42, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_cat_default_42 = None
2025-03-21T20:31:44.0501156Z             quantized_decomposed_dequantize_per_tensor_default_2337: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1719, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1719 = None
2025-03-21T20:31:44.0501972Z             aten_view_copy_default_189: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_2337, [1, 12, 128, 64]);  quantized_decomposed_dequantize_per_tensor_default_2337 = None
2025-03-21T20:31:44.0502894Z             quantized_decomposed_quantize_per_tensor_default_1720: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_189, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_view_copy_default_189 = None
2025-03-21T20:31:44.0502994Z             
2025-03-21T20:31:44.0503569Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:44.0504733Z             quantized_decomposed_dequantize_per_tensor_default_2338: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1720, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1720 = None
2025-03-21T20:31:44.0504827Z             
2025-03-21T20:31:44.0505463Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.0506275Z             aten_permute_copy_default_429: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2300, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2300 = None
2025-03-21T20:31:44.0507218Z             quantized_decomposed_quantize_per_tensor_default_1721: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_429, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_permute_copy_default_429 = None
2025-03-21T20:31:44.0508528Z             quantized_decomposed_dequantize_per_tensor_default_2339: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1721, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1721 = None
2025-03-21T20:31:44.0509320Z             aten_select_copy_int_504: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2339, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2339 = None
2025-03-21T20:31:44.0510223Z             quantized_decomposed_quantize_per_tensor_default_1722: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_504, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_select_copy_int_504 = None
2025-03-21T20:31:44.0511386Z             quantized_decomposed_dequantize_per_tensor_default_2340: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1722, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1722 = None
2025-03-21T20:31:44.0512150Z             aten_select_copy_int_505: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2340, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2340 = None
2025-03-21T20:31:44.0513053Z             quantized_decomposed_quantize_per_tensor_default_1723: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_505, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_select_copy_int_505 = None
2025-03-21T20:31:44.0513169Z             
2025-03-21T20:31:44.0514124Z              # File: <eval_with_key>.50:5980 in forward, code: dequantize_per_tensor_default_1882 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1882, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantize_per_tensor_default_1882 = None
2025-03-21T20:31:44.0515276Z             quantized_decomposed_dequantize_per_tensor_default_2341: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1723, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1723 = None
2025-03-21T20:31:44.0515376Z             
2025-03-21T20:31:44.0516013Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.0516822Z             aten_permute_copy_default_430: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2299, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2299 = None
2025-03-21T20:31:44.0517771Z             quantized_decomposed_quantize_per_tensor_default_1724: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_430, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_permute_copy_default_430 = None
2025-03-21T20:31:44.0519196Z             quantized_decomposed_dequantize_per_tensor_default_2342: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1724, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1724 = None
2025-03-21T20:31:44.0519944Z             aten_select_copy_int_506: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2342, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2342 = None
2025-03-21T20:31:44.0520927Z             quantized_decomposed_quantize_per_tensor_default_1725: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_506, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_select_copy_int_506 = None
2025-03-21T20:31:44.0522080Z             quantized_decomposed_dequantize_per_tensor_default_2343: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1725, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1725 = None
2025-03-21T20:31:44.0522830Z             aten_select_copy_int_507: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2343, 0, 1);  quantized_decomposed_dequantize_per_tensor_default_2343 = None
2025-03-21T20:31:44.0523729Z             quantized_decomposed_quantize_per_tensor_default_1726: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_507, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_select_copy_int_507 = None
2025-03-21T20:31:44.0523859Z             
2025-03-21T20:31:44.0524802Z              # File: <eval_with_key>.50:5989 in forward, code: dequantize_per_tensor_default_1885 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1885, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantize_per_tensor_default_1885 = None
2025-03-21T20:31:44.0525970Z             quantized_decomposed_dequantize_per_tensor_default_2344: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1726, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1726 = None
2025-03-21T20:31:44.0526083Z             
2025-03-21T20:31:44.0526736Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.0527541Z             aten_permute_copy_default_431: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2298, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2298 = None
2025-03-21T20:31:44.0528497Z             quantized_decomposed_quantize_per_tensor_default_1727: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_431, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_permute_copy_default_431 = None
2025-03-21T20:31:44.0529739Z             quantized_decomposed_dequantize_per_tensor_default_2345: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1727, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1727 = None
2025-03-21T20:31:44.0530503Z             aten_select_copy_int_508: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2345, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2345 = None
2025-03-21T20:31:44.0531399Z             quantized_decomposed_quantize_per_tensor_default_1728: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_508, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_select_copy_int_508 = None
2025-03-21T20:31:44.0532795Z             quantized_decomposed_dequantize_per_tensor_default_2346: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1728, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1728 = None
2025-03-21T20:31:44.0533591Z             aten_select_copy_int_509: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2346, 0, 2);  quantized_decomposed_dequantize_per_tensor_default_2346 = None
2025-03-21T20:31:44.0534486Z             quantized_decomposed_quantize_per_tensor_default_1729: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_509, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_select_copy_int_509 = None
2025-03-21T20:31:44.0534589Z             
2025-03-21T20:31:44.0535530Z              # File: <eval_with_key>.50:5998 in forward, code: dequantize_per_tensor_default_1888 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1888, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantize_per_tensor_default_1888 = None
2025-03-21T20:31:44.0536729Z             quantized_decomposed_dequantize_per_tensor_default_2347: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1729, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1729 = None
2025-03-21T20:31:44.0536825Z             
2025-03-21T20:31:44.0537475Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.0538278Z             aten_permute_copy_default_432: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2297, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2297 = None
2025-03-21T20:31:44.0539268Z             quantized_decomposed_quantize_per_tensor_default_1730: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_432, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_permute_copy_default_432 = None
2025-03-21T20:31:44.0540422Z             quantized_decomposed_dequantize_per_tensor_default_2348: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1730, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1730 = None
2025-03-21T20:31:44.0541174Z             aten_select_copy_int_510: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2348, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2348 = None
2025-03-21T20:31:44.0542077Z             quantized_decomposed_quantize_per_tensor_default_1731: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_510, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_select_copy_int_510 = None
2025-03-21T20:31:44.0543250Z             quantized_decomposed_dequantize_per_tensor_default_2349: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1731, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1731 = None
2025-03-21T20:31:44.0543984Z             aten_select_copy_int_511: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2349, 0, 3);  quantized_decomposed_dequantize_per_tensor_default_2349 = None
2025-03-21T20:31:44.0544915Z             quantized_decomposed_quantize_per_tensor_default_1732: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_511, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_select_copy_int_511 = None
2025-03-21T20:31:44.0545026Z             
2025-03-21T20:31:44.0545980Z              # File: <eval_with_key>.50:6007 in forward, code: dequantize_per_tensor_default_1891 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1891, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantize_per_tensor_default_1891 = None
2025-03-21T20:31:44.0547127Z             quantized_decomposed_dequantize_per_tensor_default_2350: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1732, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1732 = None
2025-03-21T20:31:44.0547228Z             
2025-03-21T20:31:44.0547865Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.0548702Z             aten_permute_copy_default_433: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2296, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2296 = None
2025-03-21T20:31:44.0549650Z             quantized_decomposed_quantize_per_tensor_default_1733: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_433, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_permute_copy_default_433 = None
2025-03-21T20:31:44.0550812Z             quantized_decomposed_dequantize_per_tensor_default_2351: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1733, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1733 = None
2025-03-21T20:31:44.0551580Z             aten_select_copy_int_512: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2351, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2351 = None
2025-03-21T20:31:44.0552490Z             quantized_decomposed_quantize_per_tensor_default_1734: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_512, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_select_copy_int_512 = None
2025-03-21T20:31:44.0553639Z             quantized_decomposed_dequantize_per_tensor_default_2352: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1734, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1734 = None
2025-03-21T20:31:44.0554393Z             aten_select_copy_int_513: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2352, 0, 4);  quantized_decomposed_dequantize_per_tensor_default_2352 = None
2025-03-21T20:31:44.0555284Z             quantized_decomposed_quantize_per_tensor_default_1735: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_513, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_select_copy_int_513 = None
2025-03-21T20:31:44.0555384Z             
2025-03-21T20:31:44.0556322Z              # File: <eval_with_key>.50:6016 in forward, code: dequantize_per_tensor_default_1894 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1894, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantize_per_tensor_default_1894 = None
2025-03-21T20:31:44.0557520Z             quantized_decomposed_dequantize_per_tensor_default_2353: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1735, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1735 = None
2025-03-21T20:31:44.0557630Z             
2025-03-21T20:31:44.0558280Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.0559080Z             aten_permute_copy_default_434: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2295, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2295 = None
2025-03-21T20:31:44.0560035Z             quantized_decomposed_quantize_per_tensor_default_1736: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_434, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_permute_copy_default_434 = None
2025-03-21T20:31:44.0561230Z             quantized_decomposed_dequantize_per_tensor_default_2354: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1736, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1736 = None
2025-03-21T20:31:44.0561970Z             aten_select_copy_int_514: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2354, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2354 = None
2025-03-21T20:31:44.0562904Z             quantized_decomposed_quantize_per_tensor_default_1737: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_514, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_select_copy_int_514 = None
2025-03-21T20:31:44.0564054Z             quantized_decomposed_dequantize_per_tensor_default_2355: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1737, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1737 = None
2025-03-21T20:31:44.0564800Z             aten_select_copy_int_515: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2355, 0, 5);  quantized_decomposed_dequantize_per_tensor_default_2355 = None
2025-03-21T20:31:44.0565694Z             quantized_decomposed_quantize_per_tensor_default_1738: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_515, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_select_copy_int_515 = None
2025-03-21T20:31:44.0565798Z             
2025-03-21T20:31:44.0566741Z              # File: <eval_with_key>.50:6025 in forward, code: dequantize_per_tensor_default_1897 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1897, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantize_per_tensor_default_1897 = None
2025-03-21T20:31:44.0567901Z             quantized_decomposed_dequantize_per_tensor_default_2356: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1738, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1738 = None
2025-03-21T20:31:44.0567990Z             
2025-03-21T20:31:44.0568634Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.0569558Z             aten_permute_copy_default_435: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2294, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2294 = None
2025-03-21T20:31:44.0570518Z             quantized_decomposed_quantize_per_tensor_default_1739: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_435, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_permute_copy_default_435 = None
2025-03-21T20:31:44.0571669Z             quantized_decomposed_dequantize_per_tensor_default_2357: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1739, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1739 = None
2025-03-21T20:31:44.0572451Z             aten_select_copy_int_516: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2357, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2357 = None
2025-03-21T20:31:44.0573348Z             quantized_decomposed_quantize_per_tensor_default_1740: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_516, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_select_copy_int_516 = None
2025-03-21T20:31:44.0574507Z             quantized_decomposed_dequantize_per_tensor_default_2358: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1740, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1740 = None
2025-03-21T20:31:44.0575272Z             aten_select_copy_int_517: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2358, 0, 6);  quantized_decomposed_dequantize_per_tensor_default_2358 = None
2025-03-21T20:31:44.0576185Z             quantized_decomposed_quantize_per_tensor_default_1741: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_517, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_select_copy_int_517 = None
2025-03-21T20:31:44.0576272Z             
2025-03-21T20:31:44.0577224Z              # File: <eval_with_key>.50:6034 in forward, code: dequantize_per_tensor_default_1900 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1900, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantize_per_tensor_default_1900 = None
2025-03-21T20:31:44.0578377Z             quantized_decomposed_dequantize_per_tensor_default_2359: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1741, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1741 = None
2025-03-21T20:31:44.0578484Z             
2025-03-21T20:31:44.0579120Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.0579933Z             aten_permute_copy_default_436: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2293, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2293 = None
2025-03-21T20:31:44.0580898Z             quantized_decomposed_quantize_per_tensor_default_1742: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_436, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_permute_copy_default_436 = None
2025-03-21T20:31:44.0582091Z             quantized_decomposed_dequantize_per_tensor_default_2360: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1742, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1742 = None
2025-03-21T20:31:44.0582831Z             aten_select_copy_int_518: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2360, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2360 = None
2025-03-21T20:31:44.0583744Z             quantized_decomposed_quantize_per_tensor_default_1743: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_518, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_select_copy_int_518 = None
2025-03-21T20:31:44.0584938Z             quantized_decomposed_dequantize_per_tensor_default_2361: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1743, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1743 = None
2025-03-21T20:31:44.0585677Z             aten_select_copy_int_519: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2361, 0, 7);  quantized_decomposed_dequantize_per_tensor_default_2361 = None
2025-03-21T20:31:44.0586582Z             quantized_decomposed_quantize_per_tensor_default_1744: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_519, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_select_copy_int_519 = None
2025-03-21T20:31:44.0586699Z             
2025-03-21T20:31:44.0587663Z              # File: <eval_with_key>.50:6043 in forward, code: dequantize_per_tensor_default_1903 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1903, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantize_per_tensor_default_1903 = None
2025-03-21T20:31:44.0588814Z             quantized_decomposed_dequantize_per_tensor_default_2362: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1744, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1744 = None
2025-03-21T20:31:44.0588917Z             
2025-03-21T20:31:44.0589555Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.0590380Z             aten_permute_copy_default_437: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2292, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2292 = None
2025-03-21T20:31:44.0591325Z             quantized_decomposed_quantize_per_tensor_default_1745: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_437, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_permute_copy_default_437 = None
2025-03-21T20:31:44.0592492Z             quantized_decomposed_dequantize_per_tensor_default_2363: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1745, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1745 = None
2025-03-21T20:31:44.0593256Z             aten_select_copy_int_520: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2363, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2363 = None
2025-03-21T20:31:44.0594207Z             quantized_decomposed_quantize_per_tensor_default_1746: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_520, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_select_copy_int_520 = None
2025-03-21T20:31:44.0595358Z             quantized_decomposed_dequantize_per_tensor_default_2364: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1746, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1746 = None
2025-03-21T20:31:44.0596110Z             aten_select_copy_int_521: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2364, 0, 8);  quantized_decomposed_dequantize_per_tensor_default_2364 = None
2025-03-21T20:31:44.0597031Z             quantized_decomposed_quantize_per_tensor_default_1747: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_521, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_select_copy_int_521 = None
2025-03-21T20:31:44.0597136Z             
2025-03-21T20:31:44.0598074Z              # File: <eval_with_key>.50:6052 in forward, code: dequantize_per_tensor_default_1906 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1906, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantize_per_tensor_default_1906 = None
2025-03-21T20:31:44.0599273Z             quantized_decomposed_dequantize_per_tensor_default_2365: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1747, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1747 = None
2025-03-21T20:31:44.0599365Z             
2025-03-21T20:31:44.0600017Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.0600817Z             aten_permute_copy_default_438: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2291, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2291 = None
2025-03-21T20:31:44.0601771Z             quantized_decomposed_quantize_per_tensor_default_1748: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_438, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_permute_copy_default_438 = None
2025-03-21T20:31:44.0602933Z             quantized_decomposed_dequantize_per_tensor_default_2366: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1748, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1748 = None
2025-03-21T20:31:44.0603685Z             aten_select_copy_int_522: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2366, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2366 = None
2025-03-21T20:31:44.0604583Z             quantized_decomposed_quantize_per_tensor_default_1749: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_522, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_select_copy_int_522 = None
2025-03-21T20:31:44.0605782Z             quantized_decomposed_dequantize_per_tensor_default_2367: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1749, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1749 = None
2025-03-21T20:31:44.0606539Z             aten_select_copy_int_523: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2367, 0, 9);  quantized_decomposed_dequantize_per_tensor_default_2367 = None
2025-03-21T20:31:44.0607448Z             quantized_decomposed_quantize_per_tensor_default_1750: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_523, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_select_copy_int_523 = None
2025-03-21T20:31:44.0607540Z             
2025-03-21T20:31:44.0608496Z              # File: <eval_with_key>.50:6061 in forward, code: dequantize_per_tensor_default_1909 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1909, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantize_per_tensor_default_1909 = None
2025-03-21T20:31:44.0609746Z             quantized_decomposed_dequantize_per_tensor_default_2368: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1750, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1750 = None
2025-03-21T20:31:44.0609852Z             
2025-03-21T20:31:44.0610487Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.0611329Z             aten_permute_copy_default_439: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2290, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2290 = None
2025-03-21T20:31:44.0612275Z             quantized_decomposed_quantize_per_tensor_default_1751: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_439, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_permute_copy_default_439 = None
2025-03-21T20:31:44.0613445Z             quantized_decomposed_dequantize_per_tensor_default_2369: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1751, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1751 = None
2025-03-21T20:31:44.0614204Z             aten_select_copy_int_524: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2369, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2369 = None
2025-03-21T20:31:44.0615107Z             quantized_decomposed_quantize_per_tensor_default_1752: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_524, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_select_copy_int_524 = None
2025-03-21T20:31:44.0616269Z             quantized_decomposed_dequantize_per_tensor_default_2370: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1752, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1752 = None
2025-03-21T20:31:44.0617008Z             aten_select_copy_int_525: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2370, 0, 10);  quantized_decomposed_dequantize_per_tensor_default_2370 = None
2025-03-21T20:31:44.0617989Z             quantized_decomposed_quantize_per_tensor_default_1753: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_525, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_select_copy_int_525 = None
2025-03-21T20:31:44.0618078Z             
2025-03-21T20:31:44.0619029Z              # File: <eval_with_key>.50:6070 in forward, code: dequantize_per_tensor_default_1912 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1912, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantize_per_tensor_default_1912 = None
2025-03-21T20:31:44.0620294Z             quantized_decomposed_dequantize_per_tensor_default_2371: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1753, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1753 = None
2025-03-21T20:31:44.0620404Z             
2025-03-21T20:31:44.0621069Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.0621882Z             aten_permute_copy_default_440: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2289, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2289 = None
2025-03-21T20:31:44.0622825Z             quantized_decomposed_quantize_per_tensor_default_1754: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_440, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_permute_copy_default_440 = None
2025-03-21T20:31:44.0624016Z             quantized_decomposed_dequantize_per_tensor_default_2372: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1754, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1754 = None
2025-03-21T20:31:44.0624756Z             aten_select_copy_int_526: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2372, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2372 = None
2025-03-21T20:31:44.0625664Z             quantized_decomposed_quantize_per_tensor_default_1755: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_526, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_select_copy_int_526 = None
2025-03-21T20:31:44.0626821Z             quantized_decomposed_dequantize_per_tensor_default_2373: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1755, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1755 = None
2025-03-21T20:31:44.0627574Z             aten_select_copy_int_527: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2373, 0, 11);  quantized_decomposed_dequantize_per_tensor_default_2373 = None
2025-03-21T20:31:44.0628464Z             quantized_decomposed_quantize_per_tensor_default_1756: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_527, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_select_copy_int_527 = None
2025-03-21T20:31:44.0628564Z             
2025-03-21T20:31:44.0629525Z              # File: <eval_with_key>.50:6079 in forward, code: dequantize_per_tensor_default_1915 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1915, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantize_per_tensor_default_1915 = None
2025-03-21T20:31:44.0630713Z             quantized_decomposed_dequantize_per_tensor_default_2374: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1756, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1756 = None
2025-03-21T20:31:44.0630800Z             
2025-03-21T20:31:44.0631445Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.0637181Z             aten_cat_default_43: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_aten_cat_default([quantized_decomposed_dequantize_per_tensor_default_2341, quantized_decomposed_dequantize_per_tensor_default_2344, quantized_decomposed_dequantize_per_tensor_default_2347, quantized_decomposed_dequantize_per_tensor_default_2350, quantized_decomposed_dequantize_per_tensor_default_2353, quantized_decomposed_dequantize_per_tensor_default_2356, quantized_decomposed_dequantize_per_tensor_default_2359, quantized_decomposed_dequantize_per_tensor_default_2362, quantized_decomposed_dequantize_per_tensor_default_2365, quantized_decomposed_dequantize_per_tensor_default_2368, quantized_decomposed_dequantize_per_tensor_default_2371, quantized_decomposed_dequantize_per_tensor_default_2374]);  quantized_decomposed_dequantize_per_tensor_default_2341 = quantized_decomposed_dequantize_per_tensor_default_2344 = quantized_decomposed_dequantize_per_tensor_default_2347 = quantized_decomposed_dequantize_per_tensor_default_2350 = quantized_decomposed_dequantize_per_tensor_default_2353 = quantized_decomposed_dequantize_per_tensor_default_2356 = quantized_decomposed_dequantize_per_tensor_default_2359 = quantized_decomposed_dequantize_per_tensor_default_2362 = quantized_decomposed_dequantize_per_tensor_default_2365 = quantized_decomposed_dequantize_per_tensor_default_2368 = quantized_decomposed_dequantize_per_tensor_default_2371 = quantized_decomposed_dequantize_per_tensor_default_2374 = None
2025-03-21T20:31:44.0638095Z             quantized_decomposed_quantize_per_tensor_default_1757: "i32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_43, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_cat_default_43 = None
2025-03-21T20:31:44.0639259Z             quantized_decomposed_dequantize_per_tensor_default_2375: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1757, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1757 = None
2025-03-21T20:31:44.0640047Z             aten_view_copy_default_190: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_2375, [1, 12, 128, 64]);  quantized_decomposed_dequantize_per_tensor_default_2375 = None
2025-03-21T20:31:44.0640979Z             quantized_decomposed_quantize_per_tensor_default_1758: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_190, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  aten_view_copy_default_190 = None
2025-03-21T20:31:44.0641080Z             
2025-03-21T20:31:44.0642018Z              # File: <eval_with_key>.50:6085 in forward, code: dequantize_per_tensor_default_1917 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1917, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantize_per_tensor_default_1917 = None
2025-03-21T20:31:44.0643224Z             quantized_decomposed_dequantize_per_tensor_default_2376: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1758, 0.00021122458565514535, 31154, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1758 = None
2025-03-21T20:31:44.0643344Z             
2025-03-21T20:31:44.0644287Z              # File: <eval_with_key>.50:6086 in forward, code: quantize_per_tensor_default_1918 = torch.ops.quantized_decomposed.quantize_per_tensor.default(dequantize_per_tensor_default_1917, 0.00022162823006510735, 0, -32767, 32767, torch.int16);  dequantize_per_tensor_default_1917 = None
2025-03-21T20:31:44.0645456Z             quantized_decomposed_quantize_per_tensor_default_1759: "i16[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_2376, 0.00022162823006510735, 0, -32767, 32767, torch.int16);  quantized_decomposed_dequantize_per_tensor_default_2376 = None
2025-03-21T20:31:44.0645559Z             
2025-03-21T20:31:44.0646028Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:163 in forward, code: y = attn_weight @ v
2025-03-21T20:31:44.0647224Z             quantized_decomposed_dequantize_per_tensor_default_2377: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1759, 0.00022162823006510735, 0, -32767, 32767, torch.int16);  quantized_decomposed_quantize_per_tensor_default_1759 = None
2025-03-21T20:31:44.0647325Z             
2025-03-21T20:31:44.0647816Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:157 in forward, code: attn_mask = mask[input_pos]
2025-03-21T20:31:44.0648620Z             aten_index_tensor_12: "f32[1, 128]" = executorch_exir_dialects_edge__ops_aten_index_Tensor(quantized_decomposed_dequantize_per_tensor_default_145, [attn_options_input_pos]);  quantized_decomposed_dequantize_per_tensor_default_145 = None
2025-03-21T20:31:44.0649573Z             quantized_decomposed_quantize_per_tensor_default_1760: "i32[1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_tensor_12, 0.0038910505827516317, 65535, 0, 65535, torch.int32);  aten_index_tensor_12 = None
2025-03-21T20:31:44.0649679Z             
2025-03-21T20:31:44.0650164Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:161 in forward, code: attn_weight += attn_mask
2025-03-21T20:31:44.0651318Z             quantized_decomposed_dequantize_per_tensor_default_2378: "f32[1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1760, 0.0038910505827516317, 65535, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1760 = None
2025-03-21T20:31:44.0651408Z             
2025-03-21T20:31:44.0651996Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:44.0652804Z             aten_permute_copy_default_441: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2338, [0, 1, 3, 2]);  quantized_decomposed_dequantize_per_tensor_default_2338 = None
2025-03-21T20:31:44.0653757Z             quantized_decomposed_quantize_per_tensor_default_1761: "i32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_441, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  aten_permute_copy_default_441 = None
2025-03-21T20:31:44.0653845Z             
2025-03-21T20:31:44.0654796Z              # File: <eval_with_key>.50:6093 in forward, code: dequantize_per_tensor_default_1920 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1920, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantize_per_tensor_default_1920 = None
2025-03-21T20:31:44.0656017Z             quantized_decomposed_dequantize_per_tensor_default_2379: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1761, 0.00039381824899464846, 31308, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1761 = None
2025-03-21T20:31:44.0656117Z             
2025-03-21T20:31:44.0657048Z              # File: <eval_with_key>.50:6094 in forward, code: quantize_per_tensor_default_1921 = torch.ops.quantized_decomposed.quantize_per_tensor.default(dequantize_per_tensor_default_1920, 0.000411360728321597, 0, -32767, 32767, torch.int16);  dequantize_per_tensor_default_1920 = None
2025-03-21T20:31:44.0658206Z             quantized_decomposed_quantize_per_tensor_default_1762: "i16[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_2379, 0.000411360728321597, 0, -32767, 32767, torch.int16);  quantized_decomposed_dequantize_per_tensor_default_2379 = None
2025-03-21T20:31:44.0658295Z             
2025-03-21T20:31:44.0658901Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:44.0660049Z             quantized_decomposed_dequantize_per_tensor_default_2380: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1762, 0.000411360728321597, 0, -32767, 32767, torch.int16);  quantized_decomposed_quantize_per_tensor_default_1762 = None
2025-03-21T20:31:44.0660844Z             aten_expand_copy_default_40: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_2274, [1, 12, 1, 64]);  quantized_decomposed_dequantize_per_tensor_default_2274 = None
2025-03-21T20:31:44.0661430Z             aten_view_copy_default_191: "f32[12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_40, [12, 1, 64]);  aten_expand_copy_default_40 = None
2025-03-21T20:31:44.0662236Z             aten_expand_copy_default_41: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_2380, [1, 12, 64, 128]);  quantized_decomposed_dequantize_per_tensor_default_2380 = None
2025-03-21T20:31:44.0662803Z             aten_view_copy_default_192: "f32[12, 64, 128]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_41, [12, 64, 128]);  aten_expand_copy_default_41 = None
2025-03-21T20:31:44.0663470Z             aten_bmm_default_20: "f32[12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_bmm_default(aten_view_copy_default_191, aten_view_copy_default_192);  aten_view_copy_default_191 = aten_view_copy_default_192 = None
2025-03-21T20:31:44.0663994Z             aten_view_copy_default_193: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_bmm_default_20, [1, 12, 1, 128]);  aten_bmm_default_20 = None
2025-03-21T20:31:44.0664921Z             quantized_decomposed_quantize_per_tensor_default_1763: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_193, 0.0036731965374201536, 37823, 0, 65535, torch.int32);  aten_view_copy_default_193 = None
2025-03-21T20:31:44.0666066Z             quantized_decomposed_dequantize_per_tensor_default_2381: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1763, 0.0036731965374201536, 37823, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1763 = None
2025-03-21T20:31:44.0666954Z             quantized_decomposed_dequantize_per_tensor_default_2382: "f32[1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param159, 1.9073777366429567e-06, 0, 0, 65535, torch.int32);  b__frozen_param159 = None
2025-03-21T20:31:44.0668111Z             aten_mul_tensor_160: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2381, quantized_decomposed_dequantize_per_tensor_default_2382);  quantized_decomposed_dequantize_per_tensor_default_2381 = quantized_decomposed_dequantize_per_tensor_default_2382 = None
2025-03-21T20:31:44.0668986Z             quantized_decomposed_quantize_per_tensor_default_1764: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_160, 0.0004591495671775192, 37823, 0, 65535, torch.int32);  aten_mul_tensor_160 = None
2025-03-21T20:31:44.0669075Z             
2025-03-21T20:31:44.0669571Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:161 in forward, code: attn_weight += attn_mask
2025-03-21T20:31:44.0670748Z             quantized_decomposed_dequantize_per_tensor_default_2383: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1764, 0.0004591495671775192, 37823, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1764 = None
2025-03-21T20:31:44.0671892Z             aten_add_tensor_52: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_2383, quantized_decomposed_dequantize_per_tensor_default_2378);  quantized_decomposed_dequantize_per_tensor_default_2383 = quantized_decomposed_dequantize_per_tensor_default_2378 = None
2025-03-21T20:31:44.0672780Z             quantized_decomposed_quantize_per_tensor_default_1765: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_52, 0.004276345018297434, 62560, 0, 65535, torch.int32);  aten_add_tensor_52 = None
2025-03-21T20:31:44.0672872Z             
2025-03-21T20:31:44.0673438Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:162 in forward, code: attn_weight = torch.softmax(attn_weight, dim=-1)
2025-03-21T20:31:44.0674595Z             quantized_decomposed_dequantize_per_tensor_default_2384: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1765, 0.004276345018297434, 62560, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1765 = None
2025-03-21T20:31:44.0675371Z             aten__softmax_default_10: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten__softmax_default(quantized_decomposed_dequantize_per_tensor_default_2384, -1, False);  quantized_decomposed_dequantize_per_tensor_default_2384 = None
2025-03-21T20:31:44.0676275Z             quantized_decomposed_quantize_per_tensor_default_1766: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten__softmax_default_10, 1.5259021893143654e-05, 0, 0, 65535, torch.int32);  aten__softmax_default_10 = None
2025-03-21T20:31:44.0676364Z             
2025-03-21T20:31:44.0676835Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:163 in forward, code: y = attn_weight @ v
2025-03-21T20:31:44.0677969Z             quantized_decomposed_dequantize_per_tensor_default_2385: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1766, 1.5259021893143654e-05, 0, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1766 = None
2025-03-21T20:31:44.0678797Z             aten_expand_copy_default_42: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_2385, [1, 12, 1, 128]);  quantized_decomposed_dequantize_per_tensor_default_2385 = None
2025-03-21T20:31:44.0679383Z             aten_view_copy_default_194: "f32[12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_42, [12, 1, 128]);  aten_expand_copy_default_42 = None
2025-03-21T20:31:44.0680192Z             aten_expand_copy_default_43: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_2377, [1, 12, 128, 64]);  quantized_decomposed_dequantize_per_tensor_default_2377 = None
2025-03-21T20:31:44.0680769Z             aten_view_copy_default_195: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_43, [12, 128, 64]);  aten_expand_copy_default_43 = None
2025-03-21T20:31:44.0681423Z             aten_bmm_default_21: "f32[12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_bmm_default(aten_view_copy_default_194, aten_view_copy_default_195);  aten_view_copy_default_194 = aten_view_copy_default_195 = None
2025-03-21T20:31:44.0681994Z             aten_view_copy_default_196: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_bmm_default_21, [1, 12, 1, 64]);  aten_bmm_default_21 = None
2025-03-21T20:31:44.0682918Z             quantized_decomposed_quantize_per_tensor_default_1767: "i32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_196, 0.00014636466221418232, 32803, 0, 65535, torch.int32);  aten_view_copy_default_196 = None
2025-03-21T20:31:44.0683007Z             
2025-03-21T20:31:44.0683647Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:165 in forward, code: return y.transpose(1, 2).contiguous().view(bsz, seqlen, self.dim)
2025-03-21T20:31:44.0684822Z             quantized_decomposed_dequantize_per_tensor_default_2386: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1767, 0.00014636466221418232, 32803, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1767 = None
2025-03-21T20:31:44.0685627Z             aten_permute_copy_default_442: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2386, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2386 = None
2025-03-21T20:31:44.0686572Z             quantized_decomposed_quantize_per_tensor_default_1768: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_442, 0.00014636466221418232, 32803, 0, 65535, torch.int32);  aten_permute_copy_default_442 = None
2025-03-21T20:31:44.0687725Z             quantized_decomposed_dequantize_per_tensor_default_2387: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1768, 0.00014636466221418232, 32803, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1768 = None
2025-03-21T20:31:44.0688518Z             aten_view_copy_default_197: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_2387, [1, 1, 768]);  quantized_decomposed_dequantize_per_tensor_default_2387 = None
2025-03-21T20:31:44.0689493Z             quantized_decomposed_quantize_per_tensor_default_1769: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_197, 0.00014636466221418232, 32803, 0, 65535, torch.int32);  aten_view_copy_default_197 = None
2025-03-21T20:31:44.0689607Z             
2025-03-21T20:31:44.0690132Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:44.0691367Z             quantized_decomposed_dequantize_per_tensor_default_2388: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1769, 0.00014636466221418232, 32803, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1769 = None
2025-03-21T20:31:44.0692180Z             aten_unsqueeze_copy_default_117: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_2388, -1);  quantized_decomposed_dequantize_per_tensor_default_2388 = None
2025-03-21T20:31:44.0693150Z             quantized_decomposed_quantize_per_tensor_default_1770: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_117, 0.00014636466221418232, 32803, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_117 = None
2025-03-21T20:31:44.0693243Z             
2025-03-21T20:31:44.0693672Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:44.0694844Z             quantized_decomposed_dequantize_per_tensor_default_2389: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1770, 0.00014636466221418232, 32803, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1770 = None
2025-03-21T20:31:44.0695657Z             aten_permute_copy_default_443: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2389, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2389 = None
2025-03-21T20:31:44.0696622Z             quantized_decomposed_quantize_per_tensor_default_1771: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_443, 0.00014636466221418232, 32803, 0, 65535, torch.int32);  aten_permute_copy_default_443 = None
2025-03-21T20:31:44.0696724Z             
2025-03-21T20:31:44.0697089Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:44.0698249Z             quantized_decomposed_dequantize_per_tensor_default_2390: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1771, 0.00014636466221418232, 32803, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1771 = None
2025-03-21T20:31:44.0699519Z             aten_convolution_default_73: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_2390, quantized_decomposed_dequantize_per_tensor_default_95, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_2390 = quantized_decomposed_dequantize_per_tensor_default_95 = None
2025-03-21T20:31:44.0700467Z             quantized_decomposed_quantize_per_tensor_default_1772: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_73, 0.0002480327384546399, 28212, 0, 65535, torch.int32);  aten_convolution_default_73 = None
2025-03-21T20:31:44.0700554Z             
2025-03-21T20:31:44.0700992Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:44.0702137Z             quantized_decomposed_dequantize_per_tensor_default_2391: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1772, 0.0002480327384546399, 28212, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1772 = None
2025-03-21T20:31:44.0702994Z             aten_permute_copy_default_444: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2391, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2391 = None
2025-03-21T20:31:44.0703929Z             quantized_decomposed_quantize_per_tensor_default_1773: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_444, 0.0002480327384546399, 28212, 0, 65535, torch.int32);  aten_permute_copy_default_444 = None
2025-03-21T20:31:44.0704029Z             
2025-03-21T20:31:44.0704564Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:44.0705727Z             quantized_decomposed_dequantize_per_tensor_default_2392: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1773, 0.0002480327384546399, 28212, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1773 = None
2025-03-21T20:31:44.0706510Z             aten_squeeze_copy_dims_117: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_2392, [-1]);  quantized_decomposed_dequantize_per_tensor_default_2392 = None
2025-03-21T20:31:44.0707430Z             quantized_decomposed_quantize_per_tensor_default_1774: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_117, 0.0002480327384546399, 28212, 0, 65535, torch.int32);  aten_squeeze_copy_dims_117 = None
2025-03-21T20:31:44.0707544Z             
2025-03-21T20:31:44.0707931Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:111 in forward, code: h = x + h
2025-03-21T20:31:44.0709082Z             quantized_decomposed_dequantize_per_tensor_default_2393: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1774, 0.0002480327384546399, 28212, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1774 = None
2025-03-21T20:31:44.0710227Z             aten_add_tensor_53: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_2213, quantized_decomposed_dequantize_per_tensor_default_2393);  quantized_decomposed_dequantize_per_tensor_default_2213 = quantized_decomposed_dequantize_per_tensor_default_2393 = None
2025-03-21T20:31:44.0711177Z             quantized_decomposed_quantize_per_tensor_default_1775: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_53, 0.0027502242010086775, 9540, 0, 65535, torch.int32);  aten_add_tensor_53 = None
2025-03-21T20:31:44.0711286Z             
2025-03-21T20:31:44.0711799Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:115 in forward, code: out = h + self.feed_forward(self.ffn_norm(h))
2025-03-21T20:31:44.0712732Z             quantized_decomposed_dequantize_per_tensor_default_2394: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1775, 0.0027502242010086775, 9540, 0, 65535, torch.int32)
2025-03-21T20:31:44.0713872Z             quantized_decomposed_dequantize_per_tensor_default_2395: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1775, 0.0027502242010086775, 9540, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1775 = None
2025-03-21T20:31:44.0714401Z             aten_pow_tensor_scalar_21: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_pow_Tensor_Scalar(quantized_decomposed_dequantize_per_tensor_default_2395, 2)
2025-03-21T20:31:44.0714915Z             aten_mean_dim_21: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_mean_dim(aten_pow_tensor_scalar_21, [2], True);  aten_pow_tensor_scalar_21 = None
2025-03-21T20:31:44.0715375Z             aten_add_scalar_21: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_add_Scalar(aten_mean_dim_21, 9.999999747378752e-06);  aten_mean_dim_21 = None
2025-03-21T20:31:44.0715798Z             aten_rsqrt_default_21: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_rsqrt_default(aten_add_scalar_21);  aten_add_scalar_21 = None
2025-03-21T20:31:44.0716664Z             aten_mul_tensor_161: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2395, aten_rsqrt_default_21);  quantized_decomposed_dequantize_per_tensor_default_2395 = aten_rsqrt_default_21 = None
2025-03-21T20:31:44.0717480Z             aten_mul_tensor_162: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(aten_mul_tensor_161, quantized_decomposed_dequantize_per_tensor_default_96);  aten_mul_tensor_161 = quantized_decomposed_dequantize_per_tensor_default_96 = None
2025-03-21T20:31:44.0718372Z             quantized_decomposed_quantize_per_tensor_default_1776: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_162, 0.0005783338565379381, 21200, 0, 65535, torch.int32);  aten_mul_tensor_162 = None
2025-03-21T20:31:44.0718459Z             
2025-03-21T20:31:44.0718988Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:44.0725484Z             quantized_decomposed_dequantize_per_tensor_default_2396: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1776, 0.0005783338565379381, 21200, 0, 65535, torch.int32)
2025-03-21T20:31:44.0726879Z             quantized_decomposed_dequantize_per_tensor_default_2397: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1776, 0.0005783338565379381, 21200, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1776 = None
2025-03-21T20:31:44.0727711Z             aten_unsqueeze_copy_default_118: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_2397, -1);  quantized_decomposed_dequantize_per_tensor_default_2397 = None
2025-03-21T20:31:44.0728671Z             quantized_decomposed_quantize_per_tensor_default_1777: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_118, 0.0005783338565379381, 21200, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_118 = None
2025-03-21T20:31:44.0728785Z             
2025-03-21T20:31:44.0729206Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:44.0730464Z             quantized_decomposed_dequantize_per_tensor_default_2398: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1777, 0.0005783338565379381, 21200, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1777 = None
2025-03-21T20:31:44.0731279Z             aten_permute_copy_default_445: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2398, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2398 = None
2025-03-21T20:31:44.0732469Z             quantized_decomposed_quantize_per_tensor_default_1778: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_445, 0.0005783338565379381, 21200, 0, 65535, torch.int32);  aten_permute_copy_default_445 = None
2025-03-21T20:31:44.0732610Z             
2025-03-21T20:31:44.0732985Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:44.0734146Z             quantized_decomposed_dequantize_per_tensor_default_2399: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1778, 0.0005783338565379381, 21200, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1778 = None
2025-03-21T20:31:44.0735443Z             aten_convolution_default_74: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_2399, quantized_decomposed_dequantize_per_tensor_default_97, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_2399 = quantized_decomposed_dequantize_per_tensor_default_97 = None
2025-03-21T20:31:44.0736416Z             quantized_decomposed_quantize_per_tensor_default_1779: "i32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_74, 0.0002567260235082358, 25603, 0, 65535, torch.int32);  aten_convolution_default_74 = None
2025-03-21T20:31:44.0736519Z             
2025-03-21T20:31:44.0736943Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:44.0738113Z             quantized_decomposed_dequantize_per_tensor_default_2400: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1779, 0.0002567260235082358, 25603, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1779 = None
2025-03-21T20:31:44.0738957Z             aten_permute_copy_default_446: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2400, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2400 = None
2025-03-21T20:31:44.0739911Z             quantized_decomposed_quantize_per_tensor_default_1780: "i32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_446, 0.0002567260235082358, 25603, 0, 65535, torch.int32);  aten_permute_copy_default_446 = None
2025-03-21T20:31:44.0740004Z             
2025-03-21T20:31:44.0740557Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:44.0741713Z             quantized_decomposed_dequantize_per_tensor_default_2401: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1780, 0.0002567260235082358, 25603, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1780 = None
2025-03-21T20:31:44.0742493Z             aten_squeeze_copy_dims_118: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_2401, [-1]);  quantized_decomposed_dequantize_per_tensor_default_2401 = None
2025-03-21T20:31:44.0743410Z             quantized_decomposed_quantize_per_tensor_default_1781: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_118, 0.0002567260235082358, 25603, 0, 65535, torch.int32);  aten_squeeze_copy_dims_118 = None
2025-03-21T20:31:44.0743511Z             
2025-03-21T20:31:44.0744029Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:36 in forward, code: return self.w2(F.silu(self.w1(x)) * self.w3(x))
2025-03-21T20:31:44.0745029Z             quantized_decomposed_dequantize_per_tensor_default_2402: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1781, 0.0002567260235082358, 25603, 0, 65535, torch.int32)
2025-03-21T20:31:44.0746183Z             quantized_decomposed_dequantize_per_tensor_default_2403: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1781, 0.0002567260235082358, 25603, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1781 = None
2025-03-21T20:31:44.0746939Z             aten_sigmoid_default_10: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_sigmoid_default(quantized_decomposed_dequantize_per_tensor_default_2403);  quantized_decomposed_dequantize_per_tensor_default_2403 = None
2025-03-21T20:31:44.0747805Z             quantized_decomposed_quantize_per_tensor_default_1782: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_sigmoid_default_10, 1.52587890625e-05, 0, 0, 65535, torch.int32);  aten_sigmoid_default_10 = None
2025-03-21T20:31:44.0748959Z             quantized_decomposed_dequantize_per_tensor_default_2404: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1782, 1.52587890625e-05, 0, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1782 = None
2025-03-21T20:31:44.0750087Z             aten_mul_tensor_163: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2402, quantized_decomposed_dequantize_per_tensor_default_2404);  quantized_decomposed_dequantize_per_tensor_default_2402 = quantized_decomposed_dequantize_per_tensor_default_2404 = None
2025-03-21T20:31:44.0750983Z             quantized_decomposed_quantize_per_tensor_default_1783: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_163, 0.00016067380784079432, 1733, 0, 65535, torch.int32);  aten_mul_tensor_163 = None
2025-03-21T20:31:44.0752132Z             quantized_decomposed_dequantize_per_tensor_default_2405: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1783, 0.00016067380784079432, 1733, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1783 = None
2025-03-21T20:31:44.0752233Z             
2025-03-21T20:31:44.0752750Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:44.0753574Z             aten_unsqueeze_copy_default_119: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_2396, -1);  quantized_decomposed_dequantize_per_tensor_default_2396 = None
2025-03-21T20:31:44.0754535Z             quantized_decomposed_quantize_per_tensor_default_1784: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_119, 0.0005783338565379381, 21200, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_119 = None
2025-03-21T20:31:44.0754633Z             
2025-03-21T20:31:44.0755039Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:44.0756196Z             quantized_decomposed_dequantize_per_tensor_default_2406: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1784, 0.0005783338565379381, 21200, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1784 = None
2025-03-21T20:31:44.0757047Z             aten_permute_copy_default_447: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2406, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2406 = None
2025-03-21T20:31:44.0757992Z             quantized_decomposed_quantize_per_tensor_default_1785: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_447, 0.0005783338565379381, 21200, 0, 65535, torch.int32);  aten_permute_copy_default_447 = None
2025-03-21T20:31:44.0758079Z             
2025-03-21T20:31:44.0758458Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:44.0759606Z             quantized_decomposed_dequantize_per_tensor_default_2407: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1785, 0.0005783338565379381, 21200, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1785 = None
2025-03-21T20:31:44.0760919Z             aten_convolution_default_75: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_2407, quantized_decomposed_dequantize_per_tensor_default_98, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_2407 = quantized_decomposed_dequantize_per_tensor_default_98 = None
2025-03-21T20:31:44.0761858Z             quantized_decomposed_quantize_per_tensor_default_1786: "i32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_75, 0.00028021426987834275, 27530, 0, 65535, torch.int32);  aten_convolution_default_75 = None
2025-03-21T20:31:44.0761983Z             
2025-03-21T20:31:44.0762407Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:44.0763584Z             quantized_decomposed_dequantize_per_tensor_default_2408: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1786, 0.00028021426987834275, 27530, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1786 = None
2025-03-21T20:31:44.0764385Z             aten_permute_copy_default_448: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2408, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2408 = None
2025-03-21T20:31:44.0765342Z             quantized_decomposed_quantize_per_tensor_default_1787: "i32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_448, 0.00028021426987834275, 27530, 0, 65535, torch.int32);  aten_permute_copy_default_448 = None
2025-03-21T20:31:44.0765437Z             
2025-03-21T20:31:44.0765987Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:44.0767145Z             quantized_decomposed_dequantize_per_tensor_default_2409: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1787, 0.00028021426987834275, 27530, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1787 = None
2025-03-21T20:31:44.0767918Z             aten_squeeze_copy_dims_119: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_2409, [-1]);  quantized_decomposed_dequantize_per_tensor_default_2409 = None
2025-03-21T20:31:44.0768860Z             quantized_decomposed_quantize_per_tensor_default_1788: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_119, 0.00028021426987834275, 27530, 0, 65535, torch.int32);  aten_squeeze_copy_dims_119 = None
2025-03-21T20:31:44.0768988Z             
2025-03-21T20:31:44.0769575Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:36 in forward, code: return self.w2(F.silu(self.w1(x)) * self.w3(x))
2025-03-21T20:31:44.0770757Z             quantized_decomposed_dequantize_per_tensor_default_2410: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1788, 0.00028021426987834275, 27530, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1788 = None
2025-03-21T20:31:44.0771894Z             aten_mul_tensor_164: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2405, quantized_decomposed_dequantize_per_tensor_default_2410);  quantized_decomposed_dequantize_per_tensor_default_2405 = quantized_decomposed_dequantize_per_tensor_default_2410 = None
2025-03-21T20:31:44.0772799Z             quantized_decomposed_quantize_per_tensor_default_1789: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_164, 0.0008850086014717817, 31787, 0, 65535, torch.int32);  aten_mul_tensor_164 = None
2025-03-21T20:31:44.0772889Z             
2025-03-21T20:31:44.0773418Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:44.0774568Z             quantized_decomposed_dequantize_per_tensor_default_2411: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1789, 0.0008850086014717817, 31787, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1789 = None
2025-03-21T20:31:44.0775419Z             aten_unsqueeze_copy_default_120: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_2411, -1);  quantized_decomposed_dequantize_per_tensor_default_2411 = None
2025-03-21T20:31:44.0776375Z             quantized_decomposed_quantize_per_tensor_default_1790: "i32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_120, 0.0008850086014717817, 31787, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_120 = None
2025-03-21T20:31:44.0776477Z             
2025-03-21T20:31:44.0776882Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:44.0778050Z             quantized_decomposed_dequantize_per_tensor_default_2412: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1790, 0.0008850086014717817, 31787, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1790 = None
2025-03-21T20:31:44.0778853Z             aten_permute_copy_default_449: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2412, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2412 = None
2025-03-21T20:31:44.0779798Z             quantized_decomposed_quantize_per_tensor_default_1791: "i32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_449, 0.0008850086014717817, 31787, 0, 65535, torch.int32);  aten_permute_copy_default_449 = None
2025-03-21T20:31:44.0779889Z             
2025-03-21T20:31:44.0780264Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:44.0781465Z             quantized_decomposed_dequantize_per_tensor_default_2413: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1791, 0.0008850086014717817, 31787, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1791 = None
2025-03-21T20:31:44.0782755Z             aten_convolution_default_76: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_2413, quantized_decomposed_dequantize_per_tensor_default_99, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_2413 = quantized_decomposed_dequantize_per_tensor_default_99 = None
2025-03-21T20:31:44.0783687Z             quantized_decomposed_quantize_per_tensor_default_1792: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_76, 0.0007228487520478666, 44000, 0, 65535, torch.int32);  aten_convolution_default_76 = None
2025-03-21T20:31:44.0783790Z             
2025-03-21T20:31:44.0784232Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:44.0785393Z             quantized_decomposed_dequantize_per_tensor_default_2414: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1792, 0.0007228487520478666, 44000, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1792 = None
2025-03-21T20:31:44.0786187Z             aten_permute_copy_default_450: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2414, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2414 = None
2025-03-21T20:31:44.0787170Z             quantized_decomposed_quantize_per_tensor_default_1793: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_450, 0.0007228487520478666, 44000, 0, 65535, torch.int32);  aten_permute_copy_default_450 = None
2025-03-21T20:31:44.0787259Z             
2025-03-21T20:31:44.0787805Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:44.0788955Z             quantized_decomposed_dequantize_per_tensor_default_2415: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1793, 0.0007228487520478666, 44000, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1793 = None
2025-03-21T20:31:44.0789733Z             aten_squeeze_copy_dims_120: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_2415, [-1]);  quantized_decomposed_dequantize_per_tensor_default_2415 = None
2025-03-21T20:31:44.0790644Z             quantized_decomposed_quantize_per_tensor_default_1794: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_120, 0.0007228487520478666, 44000, 0, 65535, torch.int32);  aten_squeeze_copy_dims_120 = None
2025-03-21T20:31:44.0790743Z             
2025-03-21T20:31:44.0791250Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:115 in forward, code: out = h + self.feed_forward(self.ffn_norm(h))
2025-03-21T20:31:44.0792404Z             quantized_decomposed_dequantize_per_tensor_default_2416: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1794, 0.0007228487520478666, 44000, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1794 = None
2025-03-21T20:31:44.0793583Z             aten_add_tensor_54: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_2394, quantized_decomposed_dequantize_per_tensor_default_2416);  quantized_decomposed_dequantize_per_tensor_default_2394 = quantized_decomposed_dequantize_per_tensor_default_2416 = None
2025-03-21T20:31:44.0794447Z             quantized_decomposed_quantize_per_tensor_default_1795: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_54, 0.0024239460472017527, 13427, 0, 65535, torch.int32);  aten_add_tensor_54 = None
2025-03-21T20:31:44.0794534Z             
2025-03-21T20:31:44.0794916Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:111 in forward, code: h = x + h
2025-03-21T20:31:44.0795832Z             quantized_decomposed_dequantize_per_tensor_default_2417: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1795, 0.0024239460472017527, 13427, 0, 65535, torch.int32)
2025-03-21T20:31:44.0795931Z             
2025-03-21T20:31:44.0796517Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:108 in forward, code: self.attention_norm(x), freqs_cos, freqs_sin, **attn_options
2025-03-21T20:31:44.0797681Z             quantized_decomposed_dequantize_per_tensor_default_2418: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1795, 0.0024239460472017527, 13427, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1795 = None
2025-03-21T20:31:44.0798224Z             aten_pow_tensor_scalar_22: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_pow_Tensor_Scalar(quantized_decomposed_dequantize_per_tensor_default_2418, 2)
2025-03-21T20:31:44.0798700Z             aten_mean_dim_22: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_mean_dim(aten_pow_tensor_scalar_22, [2], True);  aten_pow_tensor_scalar_22 = None
2025-03-21T20:31:44.0799155Z             aten_add_scalar_22: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_add_Scalar(aten_mean_dim_22, 9.999999747378752e-06);  aten_mean_dim_22 = None
2025-03-21T20:31:44.0799595Z             aten_rsqrt_default_22: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_rsqrt_default(aten_add_scalar_22);  aten_add_scalar_22 = None
2025-03-21T20:31:44.0800455Z             aten_mul_tensor_165: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2418, aten_rsqrt_default_22);  quantized_decomposed_dequantize_per_tensor_default_2418 = aten_rsqrt_default_22 = None
2025-03-21T20:31:44.0801293Z             aten_mul_tensor_166: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(aten_mul_tensor_165, quantized_decomposed_dequantize_per_tensor_default_100);  aten_mul_tensor_165 = quantized_decomposed_dequantize_per_tensor_default_100 = None
2025-03-21T20:31:44.0802156Z             quantized_decomposed_quantize_per_tensor_default_1796: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_166, 0.0005588648491539061, 33862, 0, 65535, torch.int32);  aten_mul_tensor_166 = None
2025-03-21T20:31:44.0802258Z             
2025-03-21T20:31:44.0802783Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:44.0803715Z             quantized_decomposed_dequantize_per_tensor_default_2419: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1796, 0.0005588648491539061, 33862, 0, 65535, torch.int32)
2025-03-21T20:31:44.0804658Z             quantized_decomposed_dequantize_per_tensor_default_2420: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1796, 0.0005588648491539061, 33862, 0, 65535, torch.int32)
2025-03-21T20:31:44.0805842Z             quantized_decomposed_dequantize_per_tensor_default_2421: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1796, 0.0005588648491539061, 33862, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1796 = None
2025-03-21T20:31:44.0806646Z             aten_unsqueeze_copy_default_121: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_2421, -1);  quantized_decomposed_dequantize_per_tensor_default_2421 = None
2025-03-21T20:31:44.0807610Z             quantized_decomposed_quantize_per_tensor_default_1797: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_121, 0.0005588648491539061, 33862, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_121 = None
2025-03-21T20:31:44.0807724Z             
2025-03-21T20:31:44.0808142Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:44.0809370Z             quantized_decomposed_dequantize_per_tensor_default_2422: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1797, 0.0005588648491539061, 33862, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1797 = None
2025-03-21T20:31:44.0810227Z             aten_permute_copy_default_451: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2422, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2422 = None
2025-03-21T20:31:44.0811162Z             quantized_decomposed_quantize_per_tensor_default_1798: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_451, 0.0005588648491539061, 33862, 0, 65535, torch.int32);  aten_permute_copy_default_451 = None
2025-03-21T20:31:44.0811263Z             
2025-03-21T20:31:44.0811629Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:44.0812786Z             quantized_decomposed_dequantize_per_tensor_default_2423: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1798, 0.0005588648491539061, 33862, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1798 = None
2025-03-21T20:31:44.0814065Z             aten_convolution_default_77: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_2423, quantized_decomposed_dequantize_per_tensor_default_101, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_2423 = quantized_decomposed_dequantize_per_tensor_default_101 = None
2025-03-21T20:31:44.0815010Z             quantized_decomposed_quantize_per_tensor_default_1799: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_77, 0.00039327371632680297, 29965, 0, 65535, torch.int32);  aten_convolution_default_77 = None
2025-03-21T20:31:44.0815096Z             
2025-03-21T20:31:44.0815529Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:44.0816706Z             quantized_decomposed_dequantize_per_tensor_default_2424: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1799, 0.00039327371632680297, 29965, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1799 = None
2025-03-21T20:31:44.0817540Z             aten_permute_copy_default_452: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2424, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2424 = None
2025-03-21T20:31:44.0818476Z             quantized_decomposed_quantize_per_tensor_default_1800: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_452, 0.00039327371632680297, 29965, 0, 65535, torch.int32);  aten_permute_copy_default_452 = None
2025-03-21T20:31:44.0818576Z             
2025-03-21T20:31:44.0819116Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:44.0820299Z             quantized_decomposed_dequantize_per_tensor_default_2425: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1800, 0.00039327371632680297, 29965, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1800 = None
2025-03-21T20:31:44.0821060Z             aten_squeeze_copy_dims_121: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_2425, [-1]);  quantized_decomposed_dequantize_per_tensor_default_2425 = None
2025-03-21T20:31:44.0821979Z             quantized_decomposed_quantize_per_tensor_default_1801: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_121, 0.00039327371632680297, 29965, 0, 65535, torch.int32);  aten_squeeze_copy_dims_121 = None
2025-03-21T20:31:44.0822093Z             
2025-03-21T20:31:44.0822625Z              # File: /pytorch/executorch/examples/models/llama/attention.py:242 in forward, code: q = q.view(bsz, seqlen, self.n_local_heads, self.head_dim)
2025-03-21T20:31:44.0823923Z             quantized_decomposed_dequantize_per_tensor_default_2426: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1801, 0.00039327371632680297, 29965, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1801 = None
2025-03-21T20:31:44.0824026Z             
2025-03-21T20:31:44.0824543Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:44.0825369Z             aten_unsqueeze_copy_default_122: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_2420, -1);  quantized_decomposed_dequantize_per_tensor_default_2420 = None
2025-03-21T20:31:44.0826325Z             quantized_decomposed_quantize_per_tensor_default_1802: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_122, 0.0005588648491539061, 33862, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_122 = None
2025-03-21T20:31:44.0826430Z             
2025-03-21T20:31:44.0826837Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:44.0827997Z             quantized_decomposed_dequantize_per_tensor_default_2427: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1802, 0.0005588648491539061, 33862, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1802 = None
2025-03-21T20:31:44.0828852Z             aten_permute_copy_default_453: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2427, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2427 = None
2025-03-21T20:31:44.0829801Z             quantized_decomposed_quantize_per_tensor_default_1803: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_453, 0.0005588648491539061, 33862, 0, 65535, torch.int32);  aten_permute_copy_default_453 = None
2025-03-21T20:31:44.0829891Z             
2025-03-21T20:31:44.0830266Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:44.0831412Z             quantized_decomposed_dequantize_per_tensor_default_2428: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1803, 0.0005588648491539061, 33862, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1803 = None
2025-03-21T20:31:44.0832963Z             aten_convolution_default_78: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_2428, quantized_decomposed_dequantize_per_tensor_default_102, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_2428 = quantized_decomposed_dequantize_per_tensor_default_102 = None
2025-03-21T20:31:44.0833894Z             quantized_decomposed_quantize_per_tensor_default_1804: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_78, 0.0004171783511992544, 32679, 0, 65535, torch.int32);  aten_convolution_default_78 = None
2025-03-21T20:31:44.0834028Z             
2025-03-21T20:31:44.0834455Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:44.0835620Z             quantized_decomposed_dequantize_per_tensor_default_2429: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1804, 0.0004171783511992544, 32679, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1804 = None
2025-03-21T20:31:44.0836414Z             aten_permute_copy_default_454: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2429, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2429 = None
2025-03-21T20:31:44.0837357Z             quantized_decomposed_quantize_per_tensor_default_1805: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_454, 0.0004171783511992544, 32679, 0, 65535, torch.int32);  aten_permute_copy_default_454 = None
2025-03-21T20:31:44.0837450Z             
2025-03-21T20:31:44.0838002Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:44.0839151Z             quantized_decomposed_dequantize_per_tensor_default_2430: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1805, 0.0004171783511992544, 32679, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1805 = None
2025-03-21T20:31:44.0839923Z             aten_squeeze_copy_dims_122: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_2430, [-1]);  quantized_decomposed_dequantize_per_tensor_default_2430 = None
2025-03-21T20:31:44.0840874Z             quantized_decomposed_quantize_per_tensor_default_1806: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_122, 0.0004171783511992544, 32679, 0, 65535, torch.int32);  aten_squeeze_copy_dims_122 = None
2025-03-21T20:31:44.0841003Z             
2025-03-21T20:31:44.0841531Z              # File: /pytorch/executorch/examples/models/llama/attention.py:243 in forward, code: k = k.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:44.0842689Z             quantized_decomposed_dequantize_per_tensor_default_2431: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1806, 0.0004171783511992544, 32679, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1806 = None
2025-03-21T20:31:44.0842779Z             
2025-03-21T20:31:44.0843303Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:44.0844140Z             aten_unsqueeze_copy_default_123: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_2419, -1);  quantized_decomposed_dequantize_per_tensor_default_2419 = None
2025-03-21T20:31:44.0845108Z             quantized_decomposed_quantize_per_tensor_default_1807: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_123, 0.0005588648491539061, 33862, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_123 = None
2025-03-21T20:31:44.0845200Z             
2025-03-21T20:31:44.0845621Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:44.0846796Z             quantized_decomposed_dequantize_per_tensor_default_2432: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1807, 0.0005588648491539061, 33862, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1807 = None
2025-03-21T20:31:44.0847611Z             aten_permute_copy_default_455: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2432, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2432 = None
2025-03-21T20:31:44.0848547Z             quantized_decomposed_quantize_per_tensor_default_1808: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_455, 0.0005588648491539061, 33862, 0, 65535, torch.int32);  aten_permute_copy_default_455 = None
2025-03-21T20:31:44.0848653Z             
2025-03-21T20:31:44.0849019Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:44.0850255Z             quantized_decomposed_dequantize_per_tensor_default_2433: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1808, 0.0005588648491539061, 33862, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1808 = None
2025-03-21T20:31:44.0851537Z             aten_convolution_default_79: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_2433, quantized_decomposed_dequantize_per_tensor_default_103, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_2433 = quantized_decomposed_dequantize_per_tensor_default_103 = None
2025-03-21T20:31:44.0852517Z             quantized_decomposed_quantize_per_tensor_default_1809: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_79, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_convolution_default_79 = None
2025-03-21T20:31:44.0852632Z             
2025-03-21T20:31:44.0853071Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:44.0854227Z             quantized_decomposed_dequantize_per_tensor_default_2434: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1809, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1809 = None
2025-03-21T20:31:44.0855039Z             aten_permute_copy_default_456: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2434, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2434 = None
2025-03-21T20:31:44.0855979Z             quantized_decomposed_quantize_per_tensor_default_1810: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_456, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_permute_copy_default_456 = None
2025-03-21T20:31:44.0856109Z             
2025-03-21T20:31:44.0856648Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:44.0857808Z             quantized_decomposed_dequantize_per_tensor_default_2435: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1810, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1810 = None
2025-03-21T20:31:44.0858593Z             aten_squeeze_copy_dims_123: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_2435, [-1]);  quantized_decomposed_dequantize_per_tensor_default_2435 = None
2025-03-21T20:31:44.0859519Z             quantized_decomposed_quantize_per_tensor_default_1811: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_123, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_squeeze_copy_dims_123 = None
2025-03-21T20:31:44.0859609Z             
2025-03-21T20:31:44.0860152Z              # File: /pytorch/executorch/examples/models/llama/attention.py:244 in forward, code: v = v.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:44.0861294Z             quantized_decomposed_dequantize_per_tensor_default_2436: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1811, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1811 = None
2025-03-21T20:31:44.0861403Z             
2025-03-21T20:31:44.0861917Z              # File: /pytorch/executorch/examples/models/llama/attention.py:242 in forward, code: q = q.view(bsz, seqlen, self.n_local_heads, self.head_dim)
2025-03-21T20:31:44.0862702Z             aten_view_copy_default_198: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_2426, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_2426 = None
2025-03-21T20:31:44.0863613Z             quantized_decomposed_quantize_per_tensor_default_1812: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_198, 0.00039327371632680297, 29965, 0, 65535, torch.int32);  aten_view_copy_default_198 = None
2025-03-21T20:31:44.0863714Z             
2025-03-21T20:31:44.0864676Z              # File: <eval_with_key>.50:6253 in forward, code: dequantize_per_tensor_default_1972 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1972, 0.00039327371632680297, 29965, 0, 65535, torch.int32);  quantize_per_tensor_default_1972 = None
2025-03-21T20:31:44.0865865Z             quantized_decomposed_dequantize_per_tensor_default_2437: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1812, 0.00039327371632680297, 29965, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1812 = None
2025-03-21T20:31:44.0865954Z             
2025-03-21T20:31:44.0866475Z              # File: /pytorch/executorch/examples/models/llama/attention.py:243 in forward, code: k = k.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:44.0867261Z             aten_view_copy_default_199: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_2431, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_2431 = None
2025-03-21T20:31:44.0868193Z             quantized_decomposed_quantize_per_tensor_default_1813: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_199, 0.0004171783511992544, 32679, 0, 65535, torch.int32);  aten_view_copy_default_199 = None
2025-03-21T20:31:44.0868293Z             
2025-03-21T20:31:44.0869228Z              # File: <eval_with_key>.50:6256 in forward, code: dequantize_per_tensor_default_1973 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1973, 0.0004171783511992544, 32679, 0, 65535, torch.int32);  quantize_per_tensor_default_1973 = None
2025-03-21T20:31:44.0870384Z             quantized_decomposed_dequantize_per_tensor_default_2438: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1813, 0.0004171783511992544, 32679, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1813 = None
2025-03-21T20:31:44.0870503Z             
2025-03-21T20:31:44.0871036Z              # File: /pytorch/executorch/examples/models/llama/attention.py:244 in forward, code: v = v.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
2025-03-21T20:31:44.0871807Z             aten_view_copy_default_200: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_2436, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_2436 = None
2025-03-21T20:31:44.0872723Z             quantized_decomposed_quantize_per_tensor_default_1814: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_200, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_view_copy_default_200 = None
2025-03-21T20:31:44.0872811Z             
2025-03-21T20:31:44.0873494Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:346 in update, code: v_out = torch.ops.aten.index_put_(self.past_v_caches, [None, input_pos], v_val)
2025-03-21T20:31:44.0874644Z             quantized_decomposed_dequantize_per_tensor_default_2439: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1814, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1814 = None
2025-03-21T20:31:44.0874742Z             
2025-03-21T20:31:44.0875504Z              # File: <eval_with_key>.50:6261 in forward, code: quantize_per_tensor_default_1975 = torch.ops.quantized_decomposed.quantize_per_tensor.default(_to_copy_22, 0.00039327371632680297, 29965, 0, 65535, torch.int32);  _to_copy_22 = None
2025-03-21T20:31:44.0876683Z             quantized_decomposed_quantize_per_tensor_default_1815: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_2437, 0.00039327371632680297, 29965, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_2437 = None
2025-03-21T20:31:44.0876834Z             
2025-03-21T20:31:44.0877373Z              # File: /pytorch/executorch/examples/models/llama/rope.py:84 in apply_rotary_emb, code: xq_r, xq_i = xq.float().reshape(xq.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:44.0878518Z             quantized_decomposed_dequantize_per_tensor_default_2440: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1815, 0.00039327371632680297, 29965, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1815 = None
2025-03-21T20:31:44.0879309Z             aten_view_copy_default_201: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_2440, [1, 1, 12, -1, 2]);  quantized_decomposed_dequantize_per_tensor_default_2440 = None
2025-03-21T20:31:44.0880245Z             quantized_decomposed_quantize_per_tensor_default_1816: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_201, 0.00039327371632680297, 29965, 0, 65535, torch.int32);  aten_view_copy_default_201 = None
2025-03-21T20:31:44.0881408Z             quantized_decomposed_dequantize_per_tensor_default_2441: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1816, 0.00039327371632680297, 29965, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1816 = None
2025-03-21T20:31:44.0881969Z             aten_slice_copy_tensor_44: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_2441, 4, 0, 1)
2025-03-21T20:31:44.0882742Z             aten_slice_copy_tensor_45: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_2441, 4, 1, 2);  quantized_decomposed_dequantize_per_tensor_default_2441 = None
2025-03-21T20:31:44.0883266Z             aten_squeeze_copy_dims_124: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_44, [4]);  aten_slice_copy_tensor_44 = None
2025-03-21T20:31:44.0883801Z             aten_squeeze_copy_dims_125: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_45, [4]);  aten_slice_copy_tensor_45 = None
2025-03-21T20:31:44.0884709Z             quantized_decomposed_quantize_per_tensor_default_1817: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_124, 0.00039327371632680297, 29965, 0, 65535, torch.int32);  aten_squeeze_copy_dims_124 = None
2025-03-21T20:31:44.0884815Z             
2025-03-21T20:31:44.0885292Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:44.0886222Z             quantized_decomposed_dequantize_per_tensor_default_2442: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1817, 0.00039327371632680297, 29965, 0, 65535, torch.int32)
2025-03-21T20:31:44.0886310Z             
2025-03-21T20:31:44.0886796Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:44.0887968Z             quantized_decomposed_dequantize_per_tensor_default_2443: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1817, 0.00039327371632680297, 29965, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1817 = None
2025-03-21T20:31:44.0888095Z             
2025-03-21T20:31:44.0888614Z              # File: /pytorch/executorch/examples/models/llama/rope.py:84 in apply_rotary_emb, code: xq_r, xq_i = xq.float().reshape(xq.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:44.0889609Z             quantized_decomposed_quantize_per_tensor_default_1818: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_125, 0.000342332263244316, 30696, 0, 65535, torch.int32);  aten_squeeze_copy_dims_125 = None
2025-03-21T20:31:44.0889699Z             
2025-03-21T20:31:44.0890182Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:44.0891102Z             quantized_decomposed_dequantize_per_tensor_default_2444: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1818, 0.000342332263244316, 30696, 0, 65535, torch.int32)
2025-03-21T20:31:44.0891205Z             
2025-03-21T20:31:44.0891701Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:44.0892860Z             quantized_decomposed_dequantize_per_tensor_default_2445: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1818, 0.000342332263244316, 30696, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1818 = None
2025-03-21T20:31:44.0892949Z             
2025-03-21T20:31:44.0893739Z              # File: <eval_with_key>.50:6276 in forward, code: quantize_per_tensor_default_1979 = torch.ops.quantized_decomposed.quantize_per_tensor.default(_to_copy_23, 0.0004171783511992544, 32679, 0, 65535, torch.int32);  _to_copy_23 = None
2025-03-21T20:31:44.0894899Z             quantized_decomposed_quantize_per_tensor_default_1819: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_2438, 0.0004171783511992544, 32679, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_2438 = None
2025-03-21T20:31:44.0894999Z             
2025-03-21T20:31:44.0895517Z              # File: /pytorch/executorch/examples/models/llama/rope.py:85 in apply_rotary_emb, code: xk_r, xk_i = xk.float().reshape(xk.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:44.0896658Z             quantized_decomposed_dequantize_per_tensor_default_2446: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1819, 0.0004171783511992544, 32679, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1819 = None
2025-03-21T20:31:44.0897453Z             aten_view_copy_default_202: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_2446, [1, 1, 12, -1, 2]);  quantized_decomposed_dequantize_per_tensor_default_2446 = None
2025-03-21T20:31:44.0898373Z             quantized_decomposed_quantize_per_tensor_default_1820: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_202, 0.0004171783511992544, 32679, 0, 65535, torch.int32);  aten_view_copy_default_202 = None
2025-03-21T20:31:44.0899517Z             quantized_decomposed_dequantize_per_tensor_default_2447: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1820, 0.0004171783511992544, 32679, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1820 = None
2025-03-21T20:31:44.0900119Z             aten_slice_copy_tensor_46: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_2447, 4, 0, 1)
2025-03-21T20:31:44.0900878Z             aten_slice_copy_tensor_47: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_slice_copy_Tensor(quantized_decomposed_dequantize_per_tensor_default_2447, 4, 1, 2);  quantized_decomposed_dequantize_per_tensor_default_2447 = None
2025-03-21T20:31:44.0901418Z             aten_squeeze_copy_dims_126: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_46, [4]);  aten_slice_copy_tensor_46 = None
2025-03-21T20:31:44.0901941Z             aten_squeeze_copy_dims_127: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(aten_slice_copy_tensor_47, [4]);  aten_slice_copy_tensor_47 = None
2025-03-21T20:31:44.0902875Z             quantized_decomposed_quantize_per_tensor_default_1821: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_126, 0.00038696694537065923, 32773, 0, 65535, torch.int32);  aten_squeeze_copy_dims_126 = None
2025-03-21T20:31:44.0902992Z             
2025-03-21T20:31:44.0903486Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:44.0904405Z             quantized_decomposed_dequantize_per_tensor_default_2448: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1821, 0.00038696694537065923, 32773, 0, 65535, torch.int32)
2025-03-21T20:31:44.0904509Z             
2025-03-21T20:31:44.0905008Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:44.0906160Z             quantized_decomposed_dequantize_per_tensor_default_2449: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1821, 0.00038696694537065923, 32773, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1821 = None
2025-03-21T20:31:44.0906262Z             
2025-03-21T20:31:44.0906776Z              # File: /pytorch/executorch/examples/models/llama/rope.py:85 in apply_rotary_emb, code: xk_r, xk_i = xk.float().reshape(xk.shape[:-1] + (-1, 2)).unbind(-1)
2025-03-21T20:31:44.0907693Z             quantized_decomposed_quantize_per_tensor_default_1822: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_127, 0.0004171783511992544, 32679, 0, 65535, torch.int32);  aten_squeeze_copy_dims_127 = None
2025-03-21T20:31:44.0907784Z             
2025-03-21T20:31:44.0908266Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:44.0909189Z             quantized_decomposed_dequantize_per_tensor_default_2450: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1822, 0.0004171783511992544, 32679, 0, 65535, torch.int32)
2025-03-21T20:31:44.0909288Z             
2025-03-21T20:31:44.0909756Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:44.0910911Z             quantized_decomposed_dequantize_per_tensor_default_2451: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1822, 0.0004171783511992544, 32679, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1822 = None
2025-03-21T20:31:44.0911025Z             
2025-03-21T20:31:44.0911496Z              # File: /pytorch/executorch/examples/models/llama/rope.py:78 in reshape_for_broadcast, code: return freqs_cis.view(shape)
2025-03-21T20:31:44.0912256Z             aten_view_copy_default_203: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_151, [1, 1, 1, 32]);  quantized_decomposed_dequantize_per_tensor_default_151 = None
2025-03-21T20:31:44.0913171Z             quantized_decomposed_quantize_per_tensor_default_1823: "i32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_203, 3.051804378628731e-05, 32768, 0, 65535, torch.int32);  aten_view_copy_default_203 = None
2025-03-21T20:31:44.0913259Z             
2025-03-21T20:31:44.0913743Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:44.0914812Z             quantized_decomposed_dequantize_per_tensor_default_2452: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1823, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:44.0914915Z             
2025-03-21T20:31:44.0915385Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:44.0916293Z             quantized_decomposed_dequantize_per_tensor_default_2453: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1823, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:44.0916418Z             
2025-03-21T20:31:44.0916884Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:44.0917813Z             quantized_decomposed_dequantize_per_tensor_default_2454: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1823, 3.051804378628731e-05, 32768, 0, 65535, torch.int32)
2025-03-21T20:31:44.0917898Z             
2025-03-21T20:31:44.0918377Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:44.0919515Z             quantized_decomposed_dequantize_per_tensor_default_2455: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1823, 3.051804378628731e-05, 32768, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1823 = None
2025-03-21T20:31:44.0919616Z             
2025-03-21T20:31:44.0920051Z              # File: /pytorch/executorch/examples/models/llama/rope.py:78 in reshape_for_broadcast, code: return freqs_cis.view(shape)
2025-03-21T20:31:44.0920821Z             aten_view_copy_default_204: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_163, [1, 1, 1, 32]);  quantized_decomposed_dequantize_per_tensor_default_163 = None
2025-03-21T20:31:44.0921717Z             quantized_decomposed_quantize_per_tensor_default_1824: "i32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_204, 3.051786916330457e-05, 32767, 0, 65535, torch.int32);  aten_view_copy_default_204 = None
2025-03-21T20:31:44.0921816Z             
2025-03-21T20:31:44.0922285Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:44.0923242Z             quantized_decomposed_dequantize_per_tensor_default_2456: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1824, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:44.0923355Z             
2025-03-21T20:31:44.0923836Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:44.0924924Z             quantized_decomposed_dequantize_per_tensor_default_2457: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1824, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:44.0925077Z             
2025-03-21T20:31:44.0925576Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:44.0926501Z             quantized_decomposed_dequantize_per_tensor_default_2458: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1824, 3.051786916330457e-05, 32767, 0, 65535, torch.int32)
2025-03-21T20:31:44.0926649Z             
2025-03-21T20:31:44.0927118Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:44.0928272Z             quantized_decomposed_dequantize_per_tensor_default_2459: "f32[1, 1, 1, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1824, 3.051786916330457e-05, 32767, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1824 = None
2025-03-21T20:31:44.0928394Z             
2025-03-21T20:31:44.0928877Z              # File: /pytorch/executorch/examples/models/llama/rope.py:90 in apply_rotary_emb, code: xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
2025-03-21T20:31:44.0930087Z             aten_mul_tensor_167: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2443, quantized_decomposed_dequantize_per_tensor_default_2455);  quantized_decomposed_dequantize_per_tensor_default_2443 = quantized_decomposed_dequantize_per_tensor_default_2455 = None
2025-03-21T20:31:44.0930958Z             quantized_decomposed_quantize_per_tensor_default_1825: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_167, 0.0003908620565198362, 30132, 0, 65535, torch.int32);  aten_mul_tensor_167 = None
2025-03-21T20:31:44.0932100Z             quantized_decomposed_dequantize_per_tensor_default_2460: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1825, 0.0003908620565198362, 30132, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1825 = None
2025-03-21T20:31:44.0933472Z             aten_mul_tensor_168: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2444, quantized_decomposed_dequantize_per_tensor_default_2458);  quantized_decomposed_dequantize_per_tensor_default_2444 = quantized_decomposed_dequantize_per_tensor_default_2458 = None
2025-03-21T20:31:44.0934355Z             quantized_decomposed_quantize_per_tensor_default_1826: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_168, 0.00015990187239367515, 32711, 0, 65535, torch.int32);  aten_mul_tensor_168 = None
2025-03-21T20:31:44.0935572Z             quantized_decomposed_dequantize_per_tensor_default_2461: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1826, 0.00015990187239367515, 32711, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1826 = None
2025-03-21T20:31:44.0936746Z             aten_sub_tensor_22: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_sub_Tensor(quantized_decomposed_dequantize_per_tensor_default_2460, quantized_decomposed_dequantize_per_tensor_default_2461);  quantized_decomposed_dequantize_per_tensor_default_2460 = quantized_decomposed_dequantize_per_tensor_default_2461 = None
2025-03-21T20:31:44.0937597Z             quantized_decomposed_quantize_per_tensor_default_1827: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_sub_tensor_22, 0.0003872470697388053, 30395, 0, 65535, torch.int32);  aten_sub_tensor_22 = None
2025-03-21T20:31:44.0937702Z             
2025-03-21T20:31:44.0938644Z              # File: <eval_with_key>.50:6310 in forward, code: dequantize_per_tensor_default_1987 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1987, 0.0003872470697388053, 30395, 0, 65535, torch.int32);  quantize_per_tensor_default_1987 = None
2025-03-21T20:31:44.0939837Z             quantized_decomposed_dequantize_per_tensor_default_2462: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1827, 0.0003872470697388053, 30395, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1827 = None
2025-03-21T20:31:44.0939926Z             
2025-03-21T20:31:44.0940413Z              # File: /pytorch/executorch/examples/models/llama/rope.py:91 in apply_rotary_emb, code: xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
2025-03-21T20:31:44.0941549Z             aten_mul_tensor_169: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2442, quantized_decomposed_dequantize_per_tensor_default_2459);  quantized_decomposed_dequantize_per_tensor_default_2442 = quantized_decomposed_dequantize_per_tensor_default_2459 = None
2025-03-21T20:31:44.0942462Z             quantized_decomposed_quantize_per_tensor_default_1828: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_169, 0.00018527904467191547, 30845, 0, 65535, torch.int32);  aten_mul_tensor_169 = None
2025-03-21T20:31:44.0943613Z             quantized_decomposed_dequantize_per_tensor_default_2463: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1828, 0.00018527904467191547, 30845, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1828 = None
2025-03-21T20:31:44.0944751Z             aten_mul_tensor_170: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2445, quantized_decomposed_dequantize_per_tensor_default_2454);  quantized_decomposed_dequantize_per_tensor_default_2445 = quantized_decomposed_dequantize_per_tensor_default_2454 = None
2025-03-21T20:31:44.0945613Z             quantized_decomposed_quantize_per_tensor_default_1829: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_170, 0.00033935264218598604, 30930, 0, 65535, torch.int32);  aten_mul_tensor_170 = None
2025-03-21T20:31:44.0946768Z             quantized_decomposed_dequantize_per_tensor_default_2464: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1829, 0.00033935264218598604, 30930, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1829 = None
2025-03-21T20:31:44.0947915Z             aten_add_tensor_55: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_2463, quantized_decomposed_dequantize_per_tensor_default_2464);  quantized_decomposed_dequantize_per_tensor_default_2463 = quantized_decomposed_dequantize_per_tensor_default_2464 = None
2025-03-21T20:31:44.0948801Z             quantized_decomposed_quantize_per_tensor_default_1830: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_55, 0.0003357737441547215, 31113, 0, 65535, torch.int32);  aten_add_tensor_55 = None
2025-03-21T20:31:44.0948889Z             
2025-03-21T20:31:44.0949836Z              # File: <eval_with_key>.50:6319 in forward, code: dequantize_per_tensor_default_1990 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1990, 0.0003357737441547215, 31113, 0, 65535, torch.int32);  quantize_per_tensor_default_1990 = None
2025-03-21T20:31:44.0950982Z             quantized_decomposed_dequantize_per_tensor_default_2465: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1830, 0.0003357737441547215, 31113, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1830 = None
2025-03-21T20:31:44.0951087Z             
2025-03-21T20:31:44.0951583Z              # File: /pytorch/executorch/examples/models/llama/rope.py:92 in apply_rotary_emb, code: xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
2025-03-21T20:31:44.0952728Z             aten_mul_tensor_171: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2449, quantized_decomposed_dequantize_per_tensor_default_2453);  quantized_decomposed_dequantize_per_tensor_default_2449 = quantized_decomposed_dequantize_per_tensor_default_2453 = None
2025-03-21T20:31:44.0953583Z             quantized_decomposed_quantize_per_tensor_default_1831: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_171, 0.0003779088146984577, 32871, 0, 65535, torch.int32);  aten_mul_tensor_171 = None
2025-03-21T20:31:44.0954767Z             quantized_decomposed_dequantize_per_tensor_default_2466: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1831, 0.0003779088146984577, 32871, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1831 = None
2025-03-21T20:31:44.0955901Z             aten_mul_tensor_172: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2450, quantized_decomposed_dequantize_per_tensor_default_2456);  quantized_decomposed_dequantize_per_tensor_default_2450 = quantized_decomposed_dequantize_per_tensor_default_2456 = None
2025-03-21T20:31:44.0956759Z             quantized_decomposed_quantize_per_tensor_default_1832: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_172, 0.00018996265134774148, 34253, 0, 65535, torch.int32);  aten_mul_tensor_172 = None
2025-03-21T20:31:44.0957913Z             quantized_decomposed_dequantize_per_tensor_default_2467: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1832, 0.00018996265134774148, 34253, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1832 = None
2025-03-21T20:31:44.0959046Z             aten_sub_tensor_23: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_sub_Tensor(quantized_decomposed_dequantize_per_tensor_default_2466, quantized_decomposed_dequantize_per_tensor_default_2467);  quantized_decomposed_dequantize_per_tensor_default_2466 = quantized_decomposed_dequantize_per_tensor_default_2467 = None
2025-03-21T20:31:44.0959925Z             quantized_decomposed_quantize_per_tensor_default_1833: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_sub_tensor_23, 0.00038636886165477335, 32957, 0, 65535, torch.int32);  aten_sub_tensor_23 = None
2025-03-21T20:31:44.0960043Z             
2025-03-21T20:31:44.0960983Z              # File: <eval_with_key>.50:6328 in forward, code: dequantize_per_tensor_default_1993 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1993, 0.00038636886165477335, 32957, 0, 65535, torch.int32);  quantize_per_tensor_default_1993 = None
2025-03-21T20:31:44.0962134Z             quantized_decomposed_dequantize_per_tensor_default_2468: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1833, 0.00038636886165477335, 32957, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1833 = None
2025-03-21T20:31:44.0962222Z             
2025-03-21T20:31:44.0962703Z              # File: /pytorch/executorch/examples/models/llama/rope.py:93 in apply_rotary_emb, code: xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
2025-03-21T20:31:44.0963859Z             aten_mul_tensor_173: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2448, quantized_decomposed_dequantize_per_tensor_default_2457);  quantized_decomposed_dequantize_per_tensor_default_2448 = quantized_decomposed_dequantize_per_tensor_default_2457 = None
2025-03-21T20:31:44.0964737Z             quantized_decomposed_quantize_per_tensor_default_1834: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_173, 0.00015066901687532663, 31607, 0, 65535, torch.int32);  aten_mul_tensor_173 = None
2025-03-21T20:31:44.0965881Z             quantized_decomposed_dequantize_per_tensor_default_2469: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1834, 0.00015066901687532663, 31607, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1834 = None
2025-03-21T20:31:44.0967053Z             aten_mul_tensor_174: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2451, quantized_decomposed_dequantize_per_tensor_default_2452);  quantized_decomposed_dequantize_per_tensor_default_2451 = quantized_decomposed_dequantize_per_tensor_default_2452 = None
2025-03-21T20:31:44.0967907Z             quantized_decomposed_quantize_per_tensor_default_1835: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_174, 0.00040073951822705567, 32950, 0, 65535, torch.int32);  aten_mul_tensor_174 = None
2025-03-21T20:31:44.0969053Z             quantized_decomposed_dequantize_per_tensor_default_2470: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1835, 0.00040073951822705567, 32950, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1835 = None
2025-03-21T20:31:44.0970260Z             aten_add_tensor_56: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_2469, quantized_decomposed_dequantize_per_tensor_default_2470);  quantized_decomposed_dequantize_per_tensor_default_2469 = quantized_decomposed_dequantize_per_tensor_default_2470 = None
2025-03-21T20:31:44.0971107Z             quantized_decomposed_quantize_per_tensor_default_1836: "i32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_56, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_add_tensor_56 = None
2025-03-21T20:31:44.0971201Z             
2025-03-21T20:31:44.0972163Z              # File: <eval_with_key>.50:6337 in forward, code: dequantize_per_tensor_default_1996 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1996, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantize_per_tensor_default_1996 = None
2025-03-21T20:31:44.0973347Z             quantized_decomposed_dequantize_per_tensor_default_2471: "f32[1, 1, 12, 32]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1836, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1836 = None
2025-03-21T20:31:44.0973434Z             
2025-03-21T20:31:44.0973964Z              # File: /pytorch/executorch/examples/models/llama/rope.py:95 in apply_rotary_emb, code: xq_out = torch.stack([xq_out_r, xq_out_i], dim=-1).flatten(3)
2025-03-21T20:31:44.0974762Z             aten_unsqueeze_copy_default_124: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_2462, 4);  quantized_decomposed_dequantize_per_tensor_default_2462 = None
2025-03-21T20:31:44.0975571Z             aten_unsqueeze_copy_default_125: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_2465, 4);  quantized_decomposed_dequantize_per_tensor_default_2465 = None
2025-03-21T20:31:44.0976343Z             aten_cat_default_44: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_cat_default([aten_unsqueeze_copy_default_124, aten_unsqueeze_copy_default_125], -1);  aten_unsqueeze_copy_default_124 = aten_unsqueeze_copy_default_125 = None
2025-03-21T20:31:44.0977207Z             quantized_decomposed_quantize_per_tensor_default_1837: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_44, 0.0003872470697388053, 30395, 0, 65535, torch.int32);  aten_cat_default_44 = None
2025-03-21T20:31:44.0978372Z             quantized_decomposed_dequantize_per_tensor_default_2472: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1837, 0.0003872470697388053, 30395, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1837 = None
2025-03-21T20:31:44.0979148Z             aten_view_copy_default_205: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_2472, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_2472 = None
2025-03-21T20:31:44.0980050Z             quantized_decomposed_quantize_per_tensor_default_1838: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_205, 0.0003872470697388053, 30395, 0, 65535, torch.int32);  aten_view_copy_default_205 = None
2025-03-21T20:31:44.0980150Z             
2025-03-21T20:31:44.0981086Z              # File: <eval_with_key>.50:6343 in forward, code: dequantize_per_tensor_default_1998 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1998, 0.0003872470697388053, 30395, 0, 65535, torch.int32);  quantize_per_tensor_default_1998 = None
2025-03-21T20:31:44.0982242Z             quantized_decomposed_dequantize_per_tensor_default_2473: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1838, 0.0003872470697388053, 30395, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1838 = None
2025-03-21T20:31:44.0982324Z             
2025-03-21T20:31:44.0982855Z              # File: /pytorch/executorch/examples/models/llama/rope.py:96 in apply_rotary_emb, code: xk_out = torch.stack([xk_out_r, xk_out_i], dim=-1).flatten(3)
2025-03-21T20:31:44.0983653Z             aten_unsqueeze_copy_default_126: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_2468, 4);  quantized_decomposed_dequantize_per_tensor_default_2468 = None
2025-03-21T20:31:44.0984517Z             aten_unsqueeze_copy_default_127: "f32[1, 1, 12, 32, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_2471, 4);  quantized_decomposed_dequantize_per_tensor_default_2471 = None
2025-03-21T20:31:44.0985264Z             aten_cat_default_45: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_aten_cat_default([aten_unsqueeze_copy_default_126, aten_unsqueeze_copy_default_127], -1);  aten_unsqueeze_copy_default_126 = aten_unsqueeze_copy_default_127 = None
2025-03-21T20:31:44.0986131Z             quantized_decomposed_quantize_per_tensor_default_1839: "i32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_45, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_cat_default_45 = None
2025-03-21T20:31:44.0987274Z             quantized_decomposed_dequantize_per_tensor_default_2474: "f32[1, 1, 12, 32, 2]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1839, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1839 = None
2025-03-21T20:31:44.0988074Z             aten_view_copy_default_206: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_2474, [1, 1, 12, 64]);  quantized_decomposed_dequantize_per_tensor_default_2474 = None
2025-03-21T20:31:44.0988977Z             quantized_decomposed_quantize_per_tensor_default_1840: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_206, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_view_copy_default_206 = None
2025-03-21T20:31:44.0989101Z             
2025-03-21T20:31:44.0990029Z              # File: <eval_with_key>.50:6349 in forward, code: dequantize_per_tensor_default_2000 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_2000, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantize_per_tensor_default_2000 = None
2025-03-21T20:31:44.0991187Z             quantized_decomposed_dequantize_per_tensor_default_2475: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1840, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1840 = None
2025-03-21T20:31:44.0991269Z             
2025-03-21T20:31:44.0992034Z              # File: <eval_with_key>.50:6351 in forward, code: quantize_per_tensor_default_2001 = torch.ops.quantized_decomposed.quantize_per_tensor.default(type_as_22, 0.0003872470697388053, 30395, 0, 65535, torch.int32);  type_as_22 = None
2025-03-21T20:31:44.0993172Z             quantized_decomposed_quantize_per_tensor_default_1841: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_2473, 0.0003872470697388053, 30395, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_2473 = None
2025-03-21T20:31:44.0993273Z             
2025-03-21T20:31:44.0993792Z              # File: /pytorch/executorch/examples/models/llama/attention.py:249 in forward, code: q = q.transpose(1, 2)  # (bs, n_local_heads, seqlen, head_dim)
2025-03-21T20:31:44.0994950Z             quantized_decomposed_dequantize_per_tensor_default_2476: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1841, 0.0003872470697388053, 30395, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1841 = None
2025-03-21T20:31:44.0995034Z             
2025-03-21T20:31:44.0995820Z              # File: <eval_with_key>.50:6354 in forward, code: quantize_per_tensor_default_2002 = torch.ops.quantized_decomposed.quantize_per_tensor.default(type_as_23, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  type_as_23 = None
2025-03-21T20:31:44.0996984Z             quantized_decomposed_quantize_per_tensor_default_1842: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_2475, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_dequantize_per_tensor_default_2475 = None
2025-03-21T20:31:44.0997081Z             
2025-03-21T20:31:44.0997744Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:345 in update, code: k_out = torch.ops.aten.index_put_(self.past_k_caches, [None, input_pos], k_val)
2025-03-21T20:31:44.0998900Z             quantized_decomposed_dequantize_per_tensor_default_2477: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1842, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1842 = None
2025-03-21T20:31:44.0998985Z             
2025-03-21T20:31:44.0999535Z              # File: /pytorch/executorch/examples/models/llama/attention.py:249 in forward, code: q = q.transpose(1, 2)  # (bs, n_local_heads, seqlen, head_dim)
2025-03-21T20:31:44.1000328Z             aten_permute_copy_default_457: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2476, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2476 = None
2025-03-21T20:31:44.1001263Z             quantized_decomposed_quantize_per_tensor_default_1843: "i32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_457, 0.0003872470697388053, 30395, 0, 65535, torch.int32);  aten_permute_copy_default_457 = None
2025-03-21T20:31:44.1001370Z             
2025-03-21T20:31:44.1001950Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:44.1003094Z             quantized_decomposed_dequantize_per_tensor_default_2478: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1843, 0.0003872470697388053, 30395, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1843 = None
2025-03-21T20:31:44.1003186Z             
2025-03-21T20:31:44.1003850Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:345 in update, code: k_out = torch.ops.aten.index_put_(self.past_k_caches, [None, input_pos], k_val)
2025-03-21T20:31:44.1005149Z             aten_index_put_default_22: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_index_put_default(quantized_decomposed_dequantize_per_tensor_default_146, [None, attn_options_input_pos], quantized_decomposed_dequantize_per_tensor_default_2477);  quantized_decomposed_dequantize_per_tensor_default_146 = quantized_decomposed_dequantize_per_tensor_default_2477 = None
2025-03-21T20:31:44.1006060Z             quantized_decomposed_quantize_per_tensor_default_1844: "i32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_put_default_22, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_index_put_default_22 = None
2025-03-21T20:31:44.1006155Z             
2025-03-21T20:31:44.1006944Z              # File: <eval_with_key>.50:6361 in forward, code: dequantize_per_tensor_default_2004 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_2004, 0.0004016910679638386, 33587, 0, 65535, torch.int32)
2025-03-21T20:31:44.1007900Z             quantized_decomposed_dequantize_per_tensor_default_2479: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1844, 0.0004016910679638386, 33587, 0, 65535, torch.int32)
2025-03-21T20:31:44.1008014Z             
2025-03-21T20:31:44.1008652Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.1009639Z             quantized_decomposed_dequantize_per_tensor_default_2480: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1844, 0.0004016910679638386, 33587, 0, 65535, torch.int32)
2025-03-21T20:31:44.1010568Z             quantized_decomposed_dequantize_per_tensor_default_2481: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1844, 0.0004016910679638386, 33587, 0, 65535, torch.int32)
2025-03-21T20:31:44.1011531Z             quantized_decomposed_dequantize_per_tensor_default_2482: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1844, 0.0004016910679638386, 33587, 0, 65535, torch.int32)
2025-03-21T20:31:44.1012456Z             quantized_decomposed_dequantize_per_tensor_default_2483: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1844, 0.0004016910679638386, 33587, 0, 65535, torch.int32)
2025-03-21T20:31:44.1013371Z             quantized_decomposed_dequantize_per_tensor_default_2484: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1844, 0.0004016910679638386, 33587, 0, 65535, torch.int32)
2025-03-21T20:31:44.1014323Z             quantized_decomposed_dequantize_per_tensor_default_2485: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1844, 0.0004016910679638386, 33587, 0, 65535, torch.int32)
2025-03-21T20:31:44.1015242Z             quantized_decomposed_dequantize_per_tensor_default_2486: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1844, 0.0004016910679638386, 33587, 0, 65535, torch.int32)
2025-03-21T20:31:44.1016158Z             quantized_decomposed_dequantize_per_tensor_default_2487: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1844, 0.0004016910679638386, 33587, 0, 65535, torch.int32)
2025-03-21T20:31:44.1017072Z             quantized_decomposed_dequantize_per_tensor_default_2488: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1844, 0.0004016910679638386, 33587, 0, 65535, torch.int32)
2025-03-21T20:31:44.1017995Z             quantized_decomposed_dequantize_per_tensor_default_2489: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1844, 0.0004016910679638386, 33587, 0, 65535, torch.int32)
2025-03-21T20:31:44.1018909Z             quantized_decomposed_dequantize_per_tensor_default_2490: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1844, 0.0004016910679638386, 33587, 0, 65535, torch.int32)
2025-03-21T20:31:44.1020086Z             quantized_decomposed_dequantize_per_tensor_default_2491: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1844, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1844 = None
2025-03-21T20:31:44.1020196Z             
2025-03-21T20:31:44.1020866Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:346 in update, code: v_out = torch.ops.aten.index_put_(self.past_v_caches, [None, input_pos], v_val)
2025-03-21T20:31:44.1022147Z             aten_index_put_default_23: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_index_put_default(quantized_decomposed_dequantize_per_tensor_default_147, [None, attn_options_input_pos], quantized_decomposed_dequantize_per_tensor_default_2439);  quantized_decomposed_dequantize_per_tensor_default_147 = quantized_decomposed_dequantize_per_tensor_default_2439 = None
2025-03-21T20:31:44.1023061Z             quantized_decomposed_quantize_per_tensor_default_1845: "i32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_put_default_23, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_index_put_default_23 = None
2025-03-21T20:31:44.1023149Z             
2025-03-21T20:31:44.1023972Z              # File: <eval_with_key>.50:6376 in forward, code: dequantize_per_tensor_default_2005 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_2005, 0.0001868398830993101, 34146, 0, 65535, torch.int32)
2025-03-21T20:31:44.1024895Z             quantized_decomposed_dequantize_per_tensor_default_2492: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1845, 0.0001868398830993101, 34146, 0, 65535, torch.int32)
2025-03-21T20:31:44.1025012Z             
2025-03-21T20:31:44.1025645Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.1026702Z             quantized_decomposed_dequantize_per_tensor_default_2493: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1845, 0.0001868398830993101, 34146, 0, 65535, torch.int32)
2025-03-21T20:31:44.1027624Z             quantized_decomposed_dequantize_per_tensor_default_2494: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1845, 0.0001868398830993101, 34146, 0, 65535, torch.int32)
2025-03-21T20:31:44.1028551Z             quantized_decomposed_dequantize_per_tensor_default_2495: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1845, 0.0001868398830993101, 34146, 0, 65535, torch.int32)
2025-03-21T20:31:44.1029470Z             quantized_decomposed_dequantize_per_tensor_default_2496: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1845, 0.0001868398830993101, 34146, 0, 65535, torch.int32)
2025-03-21T20:31:44.1030397Z             quantized_decomposed_dequantize_per_tensor_default_2497: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1845, 0.0001868398830993101, 34146, 0, 65535, torch.int32)
2025-03-21T20:31:44.1031311Z             quantized_decomposed_dequantize_per_tensor_default_2498: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1845, 0.0001868398830993101, 34146, 0, 65535, torch.int32)
2025-03-21T20:31:44.1032458Z             quantized_decomposed_dequantize_per_tensor_default_2499: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1845, 0.0001868398830993101, 34146, 0, 65535, torch.int32)
2025-03-21T20:31:44.1033432Z             quantized_decomposed_dequantize_per_tensor_default_2500: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1845, 0.0001868398830993101, 34146, 0, 65535, torch.int32)
2025-03-21T20:31:44.1034348Z             quantized_decomposed_dequantize_per_tensor_default_2501: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1845, 0.0001868398830993101, 34146, 0, 65535, torch.int32)
2025-03-21T20:31:44.1035277Z             quantized_decomposed_dequantize_per_tensor_default_2502: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1845, 0.0001868398830993101, 34146, 0, 65535, torch.int32)
2025-03-21T20:31:44.1036228Z             quantized_decomposed_dequantize_per_tensor_default_2503: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1845, 0.0001868398830993101, 34146, 0, 65535, torch.int32)
2025-03-21T20:31:44.1037392Z             quantized_decomposed_dequantize_per_tensor_default_2504: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1845, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1845 = None
2025-03-21T20:31:44.1037510Z             
2025-03-21T20:31:44.1038150Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.1038957Z             aten_permute_copy_default_458: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2491, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2491 = None
2025-03-21T20:31:44.1039903Z             quantized_decomposed_quantize_per_tensor_default_1846: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_458, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_permute_copy_default_458 = None
2025-03-21T20:31:44.1041051Z             quantized_decomposed_dequantize_per_tensor_default_2505: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1846, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1846 = None
2025-03-21T20:31:44.1041803Z             aten_select_copy_int_528: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2505, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2505 = None
2025-03-21T20:31:44.1042693Z             quantized_decomposed_quantize_per_tensor_default_1847: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_528, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_select_copy_int_528 = None
2025-03-21T20:31:44.1043851Z             quantized_decomposed_dequantize_per_tensor_default_2506: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1847, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1847 = None
2025-03-21T20:31:44.1044616Z             aten_select_copy_int_529: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2506, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2506 = None
2025-03-21T20:31:44.1045547Z             quantized_decomposed_quantize_per_tensor_default_1848: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_529, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_select_copy_int_529 = None
2025-03-21T20:31:44.1045633Z             
2025-03-21T20:31:44.1046575Z              # File: <eval_with_key>.50:6397 in forward, code: dequantize_per_tensor_default_2008 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_2008, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantize_per_tensor_default_2008 = None
2025-03-21T20:31:44.1047719Z             quantized_decomposed_dequantize_per_tensor_default_2507: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1848, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1848 = None
2025-03-21T20:31:44.1047841Z             
2025-03-21T20:31:44.1048477Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.1049341Z             aten_permute_copy_default_459: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2490, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2490 = None
2025-03-21T20:31:44.1050319Z             quantized_decomposed_quantize_per_tensor_default_1849: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_459, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_permute_copy_default_459 = None
2025-03-21T20:31:44.1051480Z             quantized_decomposed_dequantize_per_tensor_default_2508: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1849, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1849 = None
2025-03-21T20:31:44.1052220Z             aten_select_copy_int_530: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2508, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2508 = None
2025-03-21T20:31:44.1053121Z             quantized_decomposed_quantize_per_tensor_default_1850: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_530, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_select_copy_int_530 = None
2025-03-21T20:31:44.1054280Z             quantized_decomposed_dequantize_per_tensor_default_2509: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1850, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1850 = None
2025-03-21T20:31:44.1055015Z             aten_select_copy_int_531: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2509, 0, 1);  quantized_decomposed_dequantize_per_tensor_default_2509 = None
2025-03-21T20:31:44.1055909Z             quantized_decomposed_quantize_per_tensor_default_1851: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_531, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_select_copy_int_531 = None
2025-03-21T20:31:44.1055999Z             
2025-03-21T20:31:44.1057253Z              # File: <eval_with_key>.50:6406 in forward, code: dequantize_per_tensor_default_2011 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_2011, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantize_per_tensor_default_2011 = None
2025-03-21T20:31:44.1058395Z             quantized_decomposed_dequantize_per_tensor_default_2510: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1851, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1851 = None
2025-03-21T20:31:44.1058489Z             
2025-03-21T20:31:44.1059125Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.1059937Z             aten_permute_copy_default_460: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2489, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2489 = None
2025-03-21T20:31:44.1060902Z             quantized_decomposed_quantize_per_tensor_default_1852: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_460, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_permute_copy_default_460 = None
2025-03-21T20:31:44.1062061Z             quantized_decomposed_dequantize_per_tensor_default_2511: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1852, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1852 = None
2025-03-21T20:31:44.1062824Z             aten_select_copy_int_532: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2511, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2511 = None
2025-03-21T20:31:44.1063727Z             quantized_decomposed_quantize_per_tensor_default_1853: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_532, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_select_copy_int_532 = None
2025-03-21T20:31:44.1064872Z             quantized_decomposed_dequantize_per_tensor_default_2512: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1853, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1853 = None
2025-03-21T20:31:44.1065619Z             aten_select_copy_int_533: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2512, 0, 2);  quantized_decomposed_dequantize_per_tensor_default_2512 = None
2025-03-21T20:31:44.1066509Z             quantized_decomposed_quantize_per_tensor_default_1854: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_533, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_select_copy_int_533 = None
2025-03-21T20:31:44.1066603Z             
2025-03-21T20:31:44.1067534Z              # File: <eval_with_key>.50:6415 in forward, code: dequantize_per_tensor_default_2014 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_2014, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantize_per_tensor_default_2014 = None
2025-03-21T20:31:44.1068730Z             quantized_decomposed_dequantize_per_tensor_default_2513: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1854, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1854 = None
2025-03-21T20:31:44.1068842Z             
2025-03-21T20:31:44.1069482Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.1070284Z             aten_permute_copy_default_461: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2488, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2488 = None
2025-03-21T20:31:44.1071228Z             quantized_decomposed_quantize_per_tensor_default_1855: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_461, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_permute_copy_default_461 = None
2025-03-21T20:31:44.1072401Z             quantized_decomposed_dequantize_per_tensor_default_2514: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1855, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1855 = None
2025-03-21T20:31:44.1073141Z             aten_select_copy_int_534: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2514, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2514 = None
2025-03-21T20:31:44.1074028Z             quantized_decomposed_quantize_per_tensor_default_1856: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_534, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_select_copy_int_534 = None
2025-03-21T20:31:44.1075205Z             quantized_decomposed_dequantize_per_tensor_default_2515: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1856, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1856 = None
2025-03-21T20:31:44.1075943Z             aten_select_copy_int_535: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2515, 0, 3);  quantized_decomposed_dequantize_per_tensor_default_2515 = None
2025-03-21T20:31:44.1076836Z             quantized_decomposed_quantize_per_tensor_default_1857: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_535, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_select_copy_int_535 = None
2025-03-21T20:31:44.1076920Z             
2025-03-21T20:31:44.1077859Z              # File: <eval_with_key>.50:6424 in forward, code: dequantize_per_tensor_default_2017 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_2017, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantize_per_tensor_default_2017 = None
2025-03-21T20:31:44.1079002Z             quantized_decomposed_dequantize_per_tensor_default_2516: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1857, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1857 = None
2025-03-21T20:31:44.1079094Z             
2025-03-21T20:31:44.1079727Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.1080559Z             aten_permute_copy_default_462: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2487, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2487 = None
2025-03-21T20:31:44.1081521Z             quantized_decomposed_quantize_per_tensor_default_1858: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_462, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_permute_copy_default_462 = None
2025-03-21T20:31:44.1082669Z             quantized_decomposed_dequantize_per_tensor_default_2517: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1858, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1858 = None
2025-03-21T20:31:44.1083417Z             aten_select_copy_int_536: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2517, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2517 = None
2025-03-21T20:31:44.1084329Z             quantized_decomposed_quantize_per_tensor_default_1859: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_536, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_select_copy_int_536 = None
2025-03-21T20:31:44.1085476Z             quantized_decomposed_dequantize_per_tensor_default_2518: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1859, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1859 = None
2025-03-21T20:31:44.1086205Z             aten_select_copy_int_537: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2518, 0, 4);  quantized_decomposed_dequantize_per_tensor_default_2518 = None
2025-03-21T20:31:44.1087125Z             quantized_decomposed_quantize_per_tensor_default_1860: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_537, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_select_copy_int_537 = None
2025-03-21T20:31:44.1087209Z             
2025-03-21T20:31:44.1088146Z              # File: <eval_with_key>.50:6433 in forward, code: dequantize_per_tensor_default_2020 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_2020, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantize_per_tensor_default_2020 = None
2025-03-21T20:31:44.1089353Z             quantized_decomposed_dequantize_per_tensor_default_2519: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1860, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1860 = None
2025-03-21T20:31:44.1089463Z             
2025-03-21T20:31:44.1090101Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.1090914Z             aten_permute_copy_default_463: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2486, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2486 = None
2025-03-21T20:31:44.1091852Z             quantized_decomposed_quantize_per_tensor_default_1861: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_463, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_permute_copy_default_463 = None
2025-03-21T20:31:44.1093041Z             quantized_decomposed_dequantize_per_tensor_default_2520: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1861, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1861 = None
2025-03-21T20:31:44.1093805Z             aten_select_copy_int_538: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2520, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2520 = None
2025-03-21T20:31:44.1094704Z             quantized_decomposed_quantize_per_tensor_default_1862: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_538, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_select_copy_int_538 = None
2025-03-21T20:31:44.1095853Z             quantized_decomposed_dequantize_per_tensor_default_2521: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1862, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1862 = None
2025-03-21T20:31:44.1096622Z             aten_select_copy_int_539: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2521, 0, 5);  quantized_decomposed_dequantize_per_tensor_default_2521 = None
2025-03-21T20:31:44.1097510Z             quantized_decomposed_quantize_per_tensor_default_1863: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_539, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_select_copy_int_539 = None
2025-03-21T20:31:44.1097603Z             
2025-03-21T20:31:44.1098560Z              # File: <eval_with_key>.50:6442 in forward, code: dequantize_per_tensor_default_2023 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_2023, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantize_per_tensor_default_2023 = None
2025-03-21T20:31:44.1099712Z             quantized_decomposed_dequantize_per_tensor_default_2522: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1863, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1863 = None
2025-03-21T20:31:44.1099800Z             
2025-03-21T20:31:44.1100443Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.1101244Z             aten_permute_copy_default_464: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2485, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2485 = None
2025-03-21T20:31:44.1102196Z             quantized_decomposed_quantize_per_tensor_default_1864: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_464, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_permute_copy_default_464 = None
2025-03-21T20:31:44.1103341Z             quantized_decomposed_dequantize_per_tensor_default_2523: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1864, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1864 = None
2025-03-21T20:31:44.1104087Z             aten_select_copy_int_540: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2523, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2523 = None
2025-03-21T20:31:44.1105020Z             quantized_decomposed_quantize_per_tensor_default_1865: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_540, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_select_copy_int_540 = None
2025-03-21T20:31:44.1106193Z             quantized_decomposed_dequantize_per_tensor_default_2524: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1865, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1865 = None
2025-03-21T20:31:44.1106936Z             aten_select_copy_int_541: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2524, 0, 6);  quantized_decomposed_dequantize_per_tensor_default_2524 = None
2025-03-21T20:31:44.1107828Z             quantized_decomposed_quantize_per_tensor_default_1866: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_541, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_select_copy_int_541 = None
2025-03-21T20:31:44.1107928Z             
2025-03-21T20:31:44.1108884Z              # File: <eval_with_key>.50:6451 in forward, code: dequantize_per_tensor_default_2026 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_2026, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantize_per_tensor_default_2026 = None
2025-03-21T20:31:44.1110034Z             quantized_decomposed_dequantize_per_tensor_default_2525: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1866, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1866 = None
2025-03-21T20:31:44.1110180Z             
2025-03-21T20:31:44.1110817Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.1111633Z             aten_permute_copy_default_465: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2484, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2484 = None
2025-03-21T20:31:44.1112584Z             quantized_decomposed_quantize_per_tensor_default_1867: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_465, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_permute_copy_default_465 = None
2025-03-21T20:31:44.1113734Z             quantized_decomposed_dequantize_per_tensor_default_2526: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1867, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1867 = None
2025-03-21T20:31:44.1114482Z             aten_select_copy_int_542: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2526, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2526 = None
2025-03-21T20:31:44.1115372Z             quantized_decomposed_quantize_per_tensor_default_1868: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_542, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_select_copy_int_542 = None
2025-03-21T20:31:44.1116554Z             quantized_decomposed_dequantize_per_tensor_default_2527: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1868, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1868 = None
2025-03-21T20:31:44.1117424Z             aten_select_copy_int_543: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2527, 0, 7);  quantized_decomposed_dequantize_per_tensor_default_2527 = None
2025-03-21T20:31:44.1118324Z             quantized_decomposed_quantize_per_tensor_default_1869: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_543, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_select_copy_int_543 = None
2025-03-21T20:31:44.1118413Z             
2025-03-21T20:31:44.1119353Z              # File: <eval_with_key>.50:6460 in forward, code: dequantize_per_tensor_default_2029 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_2029, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantize_per_tensor_default_2029 = None
2025-03-21T20:31:44.1120532Z             quantized_decomposed_dequantize_per_tensor_default_2528: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1869, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1869 = None
2025-03-21T20:31:44.1120626Z             
2025-03-21T20:31:44.1121265Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.1122077Z             aten_permute_copy_default_466: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2483, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2483 = None
2025-03-21T20:31:44.1123043Z             quantized_decomposed_quantize_per_tensor_default_1870: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_466, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_permute_copy_default_466 = None
2025-03-21T20:31:44.1124195Z             quantized_decomposed_dequantize_per_tensor_default_2529: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1870, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1870 = None
2025-03-21T20:31:44.1124936Z             aten_select_copy_int_544: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2529, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2529 = None
2025-03-21T20:31:44.1125834Z             quantized_decomposed_quantize_per_tensor_default_1871: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_544, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_select_copy_int_544 = None
2025-03-21T20:31:44.1126978Z             quantized_decomposed_dequantize_per_tensor_default_2530: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1871, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1871 = None
2025-03-21T20:31:44.1127754Z             aten_select_copy_int_545: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2530, 0, 8);  quantized_decomposed_dequantize_per_tensor_default_2530 = None
2025-03-21T20:31:44.1128893Z             quantized_decomposed_quantize_per_tensor_default_1872: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_545, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_select_copy_int_545 = None
2025-03-21T20:31:44.1129016Z             
2025-03-21T20:31:44.1130032Z              # File: <eval_with_key>.50:6469 in forward, code: dequantize_per_tensor_default_2032 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_2032, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantize_per_tensor_default_2032 = None
2025-03-21T20:31:44.1131184Z             quantized_decomposed_dequantize_per_tensor_default_2531: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1872, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1872 = None
2025-03-21T20:31:44.1131275Z             
2025-03-21T20:31:44.1131925Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.1132956Z             aten_permute_copy_default_467: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2482, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2482 = None
2025-03-21T20:31:44.1133915Z             quantized_decomposed_quantize_per_tensor_default_1873: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_467, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_permute_copy_default_467 = None
2025-03-21T20:31:44.1135064Z             quantized_decomposed_dequantize_per_tensor_default_2532: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1873, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1873 = None
2025-03-21T20:31:44.1135852Z             aten_select_copy_int_546: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2532, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2532 = None
2025-03-21T20:31:44.1136753Z             quantized_decomposed_quantize_per_tensor_default_1874: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_546, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_select_copy_int_546 = None
2025-03-21T20:31:44.1137897Z             quantized_decomposed_dequantize_per_tensor_default_2533: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1874, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1874 = None
2025-03-21T20:31:44.1138645Z             aten_select_copy_int_547: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2533, 0, 9);  quantized_decomposed_dequantize_per_tensor_default_2533 = None
2025-03-21T20:31:44.1139538Z             quantized_decomposed_quantize_per_tensor_default_1875: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_547, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_select_copy_int_547 = None
2025-03-21T20:31:44.1139626Z             
2025-03-21T20:31:44.1140559Z              # File: <eval_with_key>.50:6478 in forward, code: dequantize_per_tensor_default_2035 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_2035, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantize_per_tensor_default_2035 = None
2025-03-21T20:31:44.1141739Z             quantized_decomposed_dequantize_per_tensor_default_2534: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1875, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1875 = None
2025-03-21T20:31:44.1141856Z             
2025-03-21T20:31:44.1142498Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.1143297Z             aten_permute_copy_default_468: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2481, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2481 = None
2025-03-21T20:31:44.1144241Z             quantized_decomposed_quantize_per_tensor_default_1876: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_468, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_permute_copy_default_468 = None
2025-03-21T20:31:44.1145410Z             quantized_decomposed_dequantize_per_tensor_default_2535: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1876, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1876 = None
2025-03-21T20:31:44.1146157Z             aten_select_copy_int_548: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2535, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2535 = None
2025-03-21T20:31:44.1147051Z             quantized_decomposed_quantize_per_tensor_default_1877: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_548, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_select_copy_int_548 = None
2025-03-21T20:31:44.1148245Z             quantized_decomposed_dequantize_per_tensor_default_2536: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1877, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1877 = None
2025-03-21T20:31:44.1148984Z             aten_select_copy_int_549: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2536, 0, 10);  quantized_decomposed_dequantize_per_tensor_default_2536 = None
2025-03-21T20:31:44.1149875Z             quantized_decomposed_quantize_per_tensor_default_1878: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_549, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_select_copy_int_549 = None
2025-03-21T20:31:44.1149963Z             
2025-03-21T20:31:44.1150904Z              # File: <eval_with_key>.50:6487 in forward, code: dequantize_per_tensor_default_2038 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_2038, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantize_per_tensor_default_2038 = None
2025-03-21T20:31:44.1152046Z             quantized_decomposed_dequantize_per_tensor_default_2537: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1878, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1878 = None
2025-03-21T20:31:44.1152138Z             
2025-03-21T20:31:44.1152765Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.1153601Z             aten_permute_copy_default_469: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2480, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2480 = None
2025-03-21T20:31:44.1154557Z             quantized_decomposed_quantize_per_tensor_default_1879: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_469, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_permute_copy_default_469 = None
2025-03-21T20:31:44.1155709Z             quantized_decomposed_dequantize_per_tensor_default_2538: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1879, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1879 = None
2025-03-21T20:31:44.1156448Z             aten_select_copy_int_550: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2538, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2538 = None
2025-03-21T20:31:44.1157378Z             quantized_decomposed_quantize_per_tensor_default_1880: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_550, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_select_copy_int_550 = None
2025-03-21T20:31:44.1158527Z             quantized_decomposed_dequantize_per_tensor_default_2539: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1880, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1880 = None
2025-03-21T20:31:44.1159296Z             aten_select_copy_int_551: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2539, 0, 11);  quantized_decomposed_dequantize_per_tensor_default_2539 = None
2025-03-21T20:31:44.1160200Z             quantized_decomposed_quantize_per_tensor_default_1881: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_551, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_select_copy_int_551 = None
2025-03-21T20:31:44.1160284Z             
2025-03-21T20:31:44.1161210Z              # File: <eval_with_key>.50:6496 in forward, code: dequantize_per_tensor_default_2041 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_2041, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantize_per_tensor_default_2041 = None
2025-03-21T20:31:44.1162362Z             quantized_decomposed_dequantize_per_tensor_default_2540: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1881, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1881 = None
2025-03-21T20:31:44.1162446Z             
2025-03-21T20:31:44.1163092Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.1168587Z             aten_cat_default_46: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_aten_cat_default([quantized_decomposed_dequantize_per_tensor_default_2507, quantized_decomposed_dequantize_per_tensor_default_2510, quantized_decomposed_dequantize_per_tensor_default_2513, quantized_decomposed_dequantize_per_tensor_default_2516, quantized_decomposed_dequantize_per_tensor_default_2519, quantized_decomposed_dequantize_per_tensor_default_2522, quantized_decomposed_dequantize_per_tensor_default_2525, quantized_decomposed_dequantize_per_tensor_default_2528, quantized_decomposed_dequantize_per_tensor_default_2531, quantized_decomposed_dequantize_per_tensor_default_2534, quantized_decomposed_dequantize_per_tensor_default_2537, quantized_decomposed_dequantize_per_tensor_default_2540]);  quantized_decomposed_dequantize_per_tensor_default_2507 = quantized_decomposed_dequantize_per_tensor_default_2510 = quantized_decomposed_dequantize_per_tensor_default_2513 = quantized_decomposed_dequantize_per_tensor_default_2516 = quantized_decomposed_dequantize_per_tensor_default_2519 = quantized_decomposed_dequantize_per_tensor_default_2522 = quantized_decomposed_dequantize_per_tensor_default_2525 = quantized_decomposed_dequantize_per_tensor_default_2528 = quantized_decomposed_dequantize_per_tensor_default_2531 = quantized_decomposed_dequantize_per_tensor_default_2534 = quantized_decomposed_dequantize_per_tensor_default_2537 = quantized_decomposed_dequantize_per_tensor_default_2540 = None
2025-03-21T20:31:44.1169555Z             quantized_decomposed_quantize_per_tensor_default_1882: "i32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_46, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_cat_default_46 = None
2025-03-21T20:31:44.1170737Z             quantized_decomposed_dequantize_per_tensor_default_2541: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1882, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1882 = None
2025-03-21T20:31:44.1171523Z             aten_view_copy_default_207: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_2541, [1, 12, 128, 64]);  quantized_decomposed_dequantize_per_tensor_default_2541 = None
2025-03-21T20:31:44.1172461Z             quantized_decomposed_quantize_per_tensor_default_1883: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_207, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_view_copy_default_207 = None
2025-03-21T20:31:44.1172563Z             
2025-03-21T20:31:44.1173139Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:44.1174305Z             quantized_decomposed_dequantize_per_tensor_default_2542: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1883, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1883 = None
2025-03-21T20:31:44.1174393Z             
2025-03-21T20:31:44.1175036Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.1175845Z             aten_permute_copy_default_470: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2504, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2504 = None
2025-03-21T20:31:44.1176787Z             quantized_decomposed_quantize_per_tensor_default_1884: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_470, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_permute_copy_default_470 = None
2025-03-21T20:31:44.1177930Z             quantized_decomposed_dequantize_per_tensor_default_2543: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1884, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1884 = None
2025-03-21T20:31:44.1178733Z             aten_select_copy_int_552: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2543, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2543 = None
2025-03-21T20:31:44.1179629Z             quantized_decomposed_quantize_per_tensor_default_1885: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_552, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_select_copy_int_552 = None
2025-03-21T20:31:44.1180779Z             quantized_decomposed_dequantize_per_tensor_default_2544: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1885, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1885 = None
2025-03-21T20:31:44.1181518Z             aten_select_copy_int_553: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2544, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2544 = None
2025-03-21T20:31:44.1182434Z             quantized_decomposed_quantize_per_tensor_default_1886: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_553, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_select_copy_int_553 = None
2025-03-21T20:31:44.1182522Z             
2025-03-21T20:31:44.1183462Z              # File: <eval_with_key>.50:6511 in forward, code: dequantize_per_tensor_default_2046 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_2046, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantize_per_tensor_default_2046 = None
2025-03-21T20:31:44.1184631Z             quantized_decomposed_dequantize_per_tensor_default_2545: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1886, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1886 = None
2025-03-21T20:31:44.1184726Z             
2025-03-21T20:31:44.1185365Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.1186176Z             aten_permute_copy_default_471: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2503, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2503 = None
2025-03-21T20:31:44.1187113Z             quantized_decomposed_quantize_per_tensor_default_1887: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_471, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_permute_copy_default_471 = None
2025-03-21T20:31:44.1188268Z             quantized_decomposed_dequantize_per_tensor_default_2546: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1887, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1887 = None
2025-03-21T20:31:44.1189004Z             aten_select_copy_int_554: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2546, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2546 = None
2025-03-21T20:31:44.1189906Z             quantized_decomposed_quantize_per_tensor_default_1888: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_554, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_select_copy_int_554 = None
2025-03-21T20:31:44.1191101Z             quantized_decomposed_dequantize_per_tensor_default_2547: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1888, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1888 = None
2025-03-21T20:31:44.1191838Z             aten_select_copy_int_555: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2547, 0, 1);  quantized_decomposed_dequantize_per_tensor_default_2547 = None
2025-03-21T20:31:44.1192733Z             quantized_decomposed_quantize_per_tensor_default_1889: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_555, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_select_copy_int_555 = None
2025-03-21T20:31:44.1192822Z             
2025-03-21T20:31:44.1193797Z              # File: <eval_with_key>.50:6520 in forward, code: dequantize_per_tensor_default_2049 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_2049, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantize_per_tensor_default_2049 = None
2025-03-21T20:31:44.1194944Z             quantized_decomposed_dequantize_per_tensor_default_2548: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1889, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1889 = None
2025-03-21T20:31:44.1195028Z             
2025-03-21T20:31:44.1195666Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.1196492Z             aten_permute_copy_default_472: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2502, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2502 = None
2025-03-21T20:31:44.1197435Z             quantized_decomposed_quantize_per_tensor_default_1890: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_472, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_permute_copy_default_472 = None
2025-03-21T20:31:44.1198588Z             quantized_decomposed_dequantize_per_tensor_default_2549: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1890, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1890 = None
2025-03-21T20:31:44.1199328Z             aten_select_copy_int_556: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2549, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2549 = None
2025-03-21T20:31:44.1200227Z             quantized_decomposed_quantize_per_tensor_default_1891: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_556, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_select_copy_int_556 = None
2025-03-21T20:31:44.1201369Z             quantized_decomposed_dequantize_per_tensor_default_2550: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1891, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1891 = None
2025-03-21T20:31:44.1202136Z             aten_select_copy_int_557: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2550, 0, 2);  quantized_decomposed_dequantize_per_tensor_default_2550 = None
2025-03-21T20:31:44.1203047Z             quantized_decomposed_quantize_per_tensor_default_1892: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_557, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_select_copy_int_557 = None
2025-03-21T20:31:44.1203144Z             
2025-03-21T20:31:44.1204072Z              # File: <eval_with_key>.50:6529 in forward, code: dequantize_per_tensor_default_2052 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_2052, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantize_per_tensor_default_2052 = None
2025-03-21T20:31:44.1205219Z             quantized_decomposed_dequantize_per_tensor_default_2551: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1892, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1892 = None
2025-03-21T20:31:44.1205309Z             
2025-03-21T20:31:44.1205971Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.1206770Z             aten_permute_copy_default_473: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2501, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2501 = None
2025-03-21T20:31:44.1207709Z             quantized_decomposed_quantize_per_tensor_default_1893: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_473, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_permute_copy_default_473 = None
2025-03-21T20:31:44.1208878Z             quantized_decomposed_dequantize_per_tensor_default_2552: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1893, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1893 = None
2025-03-21T20:31:44.1209682Z             aten_select_copy_int_558: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2552, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2552 = None
2025-03-21T20:31:44.1210573Z             quantized_decomposed_quantize_per_tensor_default_1894: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_558, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_select_copy_int_558 = None
2025-03-21T20:31:44.1211723Z             quantized_decomposed_dequantize_per_tensor_default_2553: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1894, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1894 = None
2025-03-21T20:31:44.1212460Z             aten_select_copy_int_559: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2553, 0, 3);  quantized_decomposed_dequantize_per_tensor_default_2553 = None
2025-03-21T20:31:44.1213361Z             quantized_decomposed_quantize_per_tensor_default_1895: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_559, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_select_copy_int_559 = None
2025-03-21T20:31:44.1213453Z             
2025-03-21T20:31:44.1214432Z              # File: <eval_with_key>.50:6538 in forward, code: dequantize_per_tensor_default_2055 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_2055, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantize_per_tensor_default_2055 = None
2025-03-21T20:31:44.1215604Z             quantized_decomposed_dequantize_per_tensor_default_2554: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1895, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1895 = None
2025-03-21T20:31:44.1215703Z             
2025-03-21T20:31:44.1216339Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.1217155Z             aten_permute_copy_default_474: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2500, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2500 = None
2025-03-21T20:31:44.1218118Z             quantized_decomposed_quantize_per_tensor_default_1896: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_474, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_permute_copy_default_474 = None
2025-03-21T20:31:44.1219282Z             quantized_decomposed_dequantize_per_tensor_default_2555: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1896, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1896 = None
2025-03-21T20:31:44.1220044Z             aten_select_copy_int_560: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2555, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2555 = None
2025-03-21T20:31:44.1220942Z             quantized_decomposed_quantize_per_tensor_default_1897: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_560, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_select_copy_int_560 = None
2025-03-21T20:31:44.1222090Z             quantized_decomposed_dequantize_per_tensor_default_2556: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1897, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1897 = None
2025-03-21T20:31:44.1222823Z             aten_select_copy_int_561: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2556, 0, 4);  quantized_decomposed_dequantize_per_tensor_default_2556 = None
2025-03-21T20:31:44.1223721Z             quantized_decomposed_quantize_per_tensor_default_1898: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_561, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_select_copy_int_561 = None
2025-03-21T20:31:44.1223806Z             
2025-03-21T20:31:44.1224743Z              # File: <eval_with_key>.50:6547 in forward, code: dequantize_per_tensor_default_2058 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_2058, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantize_per_tensor_default_2058 = None
2025-03-21T20:31:44.1225885Z             quantized_decomposed_dequantize_per_tensor_default_2557: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1898, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1898 = None
2025-03-21T20:31:44.1226007Z             
2025-03-21T20:31:44.1226658Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.1227475Z             aten_permute_copy_default_475: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2499, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2499 = None
2025-03-21T20:31:44.1228413Z             quantized_decomposed_quantize_per_tensor_default_1899: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_475, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_permute_copy_default_475 = None
2025-03-21T20:31:44.1229648Z             quantized_decomposed_dequantize_per_tensor_default_2558: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1899, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1899 = None
2025-03-21T20:31:44.1230479Z             aten_select_copy_int_562: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2558, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2558 = None
2025-03-21T20:31:44.1231390Z             quantized_decomposed_quantize_per_tensor_default_1900: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_562, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_select_copy_int_562 = None
2025-03-21T20:31:44.1232735Z             quantized_decomposed_dequantize_per_tensor_default_2559: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1900, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1900 = None
2025-03-21T20:31:44.1233493Z             aten_select_copy_int_563: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2559, 0, 5);  quantized_decomposed_dequantize_per_tensor_default_2559 = None
2025-03-21T20:31:44.1234387Z             quantized_decomposed_quantize_per_tensor_default_1901: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_563, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_select_copy_int_563 = None
2025-03-21T20:31:44.1234485Z             
2025-03-21T20:31:44.1235427Z              # File: <eval_with_key>.50:6556 in forward, code: dequantize_per_tensor_default_2061 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_2061, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantize_per_tensor_default_2061 = None
2025-03-21T20:31:44.1236597Z             quantized_decomposed_dequantize_per_tensor_default_2560: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1901, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1901 = None
2025-03-21T20:31:44.1236687Z             
2025-03-21T20:31:44.1237333Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.1238142Z             aten_permute_copy_default_476: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2498, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2498 = None
2025-03-21T20:31:44.1239166Z             quantized_decomposed_quantize_per_tensor_default_1902: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_476, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_permute_copy_default_476 = None
2025-03-21T20:31:44.1240354Z             quantized_decomposed_dequantize_per_tensor_default_2561: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1902, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1902 = None
2025-03-21T20:31:44.1241108Z             aten_select_copy_int_564: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2561, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2561 = None
2025-03-21T20:31:44.1242006Z             quantized_decomposed_quantize_per_tensor_default_1903: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_564, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_select_copy_int_564 = None
2025-03-21T20:31:44.1243196Z             quantized_decomposed_dequantize_per_tensor_default_2562: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1903, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1903 = None
2025-03-21T20:31:44.1243953Z             aten_select_copy_int_565: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2562, 0, 6);  quantized_decomposed_dequantize_per_tensor_default_2562 = None
2025-03-21T20:31:44.1244878Z             quantized_decomposed_quantize_per_tensor_default_1904: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_565, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_select_copy_int_565 = None
2025-03-21T20:31:44.1244967Z             
2025-03-21T20:31:44.1245915Z              # File: <eval_with_key>.50:6565 in forward, code: dequantize_per_tensor_default_2064 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_2064, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantize_per_tensor_default_2064 = None
2025-03-21T20:31:44.1247072Z             quantized_decomposed_dequantize_per_tensor_default_2563: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1904, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1904 = None
2025-03-21T20:31:44.1247164Z             
2025-03-21T20:31:44.1247803Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.1248621Z             aten_permute_copy_default_477: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2497, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2497 = None
2025-03-21T20:31:44.1249614Z             quantized_decomposed_quantize_per_tensor_default_1905: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_477, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_permute_copy_default_477 = None
2025-03-21T20:31:44.1250800Z             quantized_decomposed_dequantize_per_tensor_default_2564: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1905, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1905 = None
2025-03-21T20:31:44.1251580Z             aten_select_copy_int_566: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2564, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2564 = None
2025-03-21T20:31:44.1252469Z             quantized_decomposed_quantize_per_tensor_default_1906: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_566, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_select_copy_int_566 = None
2025-03-21T20:31:44.1253633Z             quantized_decomposed_dequantize_per_tensor_default_2565: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1906, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1906 = None
2025-03-21T20:31:44.1254400Z             aten_select_copy_int_567: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2565, 0, 7);  quantized_decomposed_dequantize_per_tensor_default_2565 = None
2025-03-21T20:31:44.1255300Z             quantized_decomposed_quantize_per_tensor_default_1907: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_567, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_select_copy_int_567 = None
2025-03-21T20:31:44.1255388Z             
2025-03-21T20:31:44.1256337Z              # File: <eval_with_key>.50:6574 in forward, code: dequantize_per_tensor_default_2067 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_2067, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantize_per_tensor_default_2067 = None
2025-03-21T20:31:44.1257531Z             quantized_decomposed_dequantize_per_tensor_default_2566: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1907, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1907 = None
2025-03-21T20:31:44.1257632Z             
2025-03-21T20:31:44.1258267Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.1259079Z             aten_permute_copy_default_478: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2496, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2496 = None
2025-03-21T20:31:44.1260017Z             quantized_decomposed_quantize_per_tensor_default_1908: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_478, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_permute_copy_default_478 = None
2025-03-21T20:31:44.1261183Z             quantized_decomposed_dequantize_per_tensor_default_2567: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1908, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1908 = None
2025-03-21T20:31:44.1261919Z             aten_select_copy_int_568: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2567, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2567 = None
2025-03-21T20:31:44.1262850Z             quantized_decomposed_quantize_per_tensor_default_1909: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_568, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_select_copy_int_568 = None
2025-03-21T20:31:44.1264024Z             quantized_decomposed_dequantize_per_tensor_default_2568: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1909, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1909 = None
2025-03-21T20:31:44.1264771Z             aten_select_copy_int_569: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2568, 0, 8);  quantized_decomposed_dequantize_per_tensor_default_2568 = None
2025-03-21T20:31:44.1265656Z             quantized_decomposed_quantize_per_tensor_default_1910: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_569, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_select_copy_int_569 = None
2025-03-21T20:31:44.1265755Z             
2025-03-21T20:31:44.1266712Z              # File: <eval_with_key>.50:6583 in forward, code: dequantize_per_tensor_default_2070 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_2070, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantize_per_tensor_default_2070 = None
2025-03-21T20:31:44.1267863Z             quantized_decomposed_dequantize_per_tensor_default_2569: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1910, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1910 = None
2025-03-21T20:31:44.1267972Z             
2025-03-21T20:31:44.1268619Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.1269423Z             aten_permute_copy_default_479: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2495, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2495 = None
2025-03-21T20:31:44.1270371Z             quantized_decomposed_quantize_per_tensor_default_1911: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_479, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_permute_copy_default_479 = None
2025-03-21T20:31:44.1271520Z             quantized_decomposed_dequantize_per_tensor_default_2570: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1911, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1911 = None
2025-03-21T20:31:44.1272276Z             aten_select_copy_int_570: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2570, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2570 = None
2025-03-21T20:31:44.1273170Z             quantized_decomposed_quantize_per_tensor_default_1912: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_570, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_select_copy_int_570 = None
2025-03-21T20:31:44.1274320Z             quantized_decomposed_dequantize_per_tensor_default_2571: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1912, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1912 = None
2025-03-21T20:31:44.1275090Z             aten_select_copy_int_571: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2571, 0, 9);  quantized_decomposed_dequantize_per_tensor_default_2571 = None
2025-03-21T20:31:44.1276005Z             quantized_decomposed_quantize_per_tensor_default_1913: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_571, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_select_copy_int_571 = None
2025-03-21T20:31:44.1276104Z             
2025-03-21T20:31:44.1277042Z              # File: <eval_with_key>.50:6592 in forward, code: dequantize_per_tensor_default_2073 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_2073, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantize_per_tensor_default_2073 = None
2025-03-21T20:31:44.1278200Z             quantized_decomposed_dequantize_per_tensor_default_2572: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1913, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1913 = None
2025-03-21T20:31:44.1278313Z             
2025-03-21T20:31:44.1278955Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.1279755Z             aten_permute_copy_default_480: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2494, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2494 = None
2025-03-21T20:31:44.1280725Z             quantized_decomposed_quantize_per_tensor_default_1914: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_480, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_permute_copy_default_480 = None
2025-03-21T20:31:44.1281874Z             quantized_decomposed_dequantize_per_tensor_default_2573: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1914, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1914 = None
2025-03-21T20:31:44.1282623Z             aten_select_copy_int_572: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2573, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2573 = None
2025-03-21T20:31:44.1283512Z             quantized_decomposed_quantize_per_tensor_default_1915: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_572, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_select_copy_int_572 = None
2025-03-21T20:31:44.1284672Z             quantized_decomposed_dequantize_per_tensor_default_2574: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1915, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1915 = None
2025-03-21T20:31:44.1285410Z             aten_select_copy_int_573: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2574, 0, 10);  quantized_decomposed_dequantize_per_tensor_default_2574 = None
2025-03-21T20:31:44.1286305Z             quantized_decomposed_quantize_per_tensor_default_1916: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_573, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_select_copy_int_573 = None
2025-03-21T20:31:44.1286395Z             
2025-03-21T20:31:44.1287397Z              # File: <eval_with_key>.50:6601 in forward, code: dequantize_per_tensor_default_2076 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_2076, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantize_per_tensor_default_2076 = None
2025-03-21T20:31:44.1288540Z             quantized_decomposed_dequantize_per_tensor_default_2575: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1916, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1916 = None
2025-03-21T20:31:44.1288635Z             
2025-03-21T20:31:44.1289329Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.1290151Z             aten_permute_copy_default_481: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2493, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2493 = None
2025-03-21T20:31:44.1291121Z             quantized_decomposed_quantize_per_tensor_default_1917: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_481, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_permute_copy_default_481 = None
2025-03-21T20:31:44.1292275Z             quantized_decomposed_dequantize_per_tensor_default_2576: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1917, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1917 = None
2025-03-21T20:31:44.1293044Z             aten_select_copy_int_574: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2576, 0, 0);  quantized_decomposed_dequantize_per_tensor_default_2576 = None
2025-03-21T20:31:44.1293957Z             quantized_decomposed_quantize_per_tensor_default_1918: "i32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_574, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_select_copy_int_574 = None
2025-03-21T20:31:44.1295103Z             quantized_decomposed_dequantize_per_tensor_default_2577: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1918, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1918 = None
2025-03-21T20:31:44.1295858Z             aten_select_copy_int_575: "f32[128, 64]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2577, 0, 11);  quantized_decomposed_dequantize_per_tensor_default_2577 = None
2025-03-21T20:31:44.1296754Z             quantized_decomposed_quantize_per_tensor_default_1919: "i32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_575, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_select_copy_int_575 = None
2025-03-21T20:31:44.1296854Z             
2025-03-21T20:31:44.1297790Z              # File: <eval_with_key>.50:6610 in forward, code: dequantize_per_tensor_default_2079 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_2079, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantize_per_tensor_default_2079 = None
2025-03-21T20:31:44.1298970Z             quantized_decomposed_dequantize_per_tensor_default_2578: "f32[128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1919, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1919 = None
2025-03-21T20:31:44.1299082Z             
2025-03-21T20:31:44.1299726Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:128 in repeat_kv, code: return torch.cat(new_kv, 0).reshape(batch, n_heads, seqlen, head_dim)
2025-03-21T20:31:44.1305239Z             aten_cat_default_47: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_aten_cat_default([quantized_decomposed_dequantize_per_tensor_default_2545, quantized_decomposed_dequantize_per_tensor_default_2548, quantized_decomposed_dequantize_per_tensor_default_2551, quantized_decomposed_dequantize_per_tensor_default_2554, quantized_decomposed_dequantize_per_tensor_default_2557, quantized_decomposed_dequantize_per_tensor_default_2560, quantized_decomposed_dequantize_per_tensor_default_2563, quantized_decomposed_dequantize_per_tensor_default_2566, quantized_decomposed_dequantize_per_tensor_default_2569, quantized_decomposed_dequantize_per_tensor_default_2572, quantized_decomposed_dequantize_per_tensor_default_2575, quantized_decomposed_dequantize_per_tensor_default_2578]);  quantized_decomposed_dequantize_per_tensor_default_2545 = quantized_decomposed_dequantize_per_tensor_default_2548 = quantized_decomposed_dequantize_per_tensor_default_2551 = quantized_decomposed_dequantize_per_tensor_default_2554 = quantized_decomposed_dequantize_per_tensor_default_2557 = quantized_decomposed_dequantize_per_tensor_default_2560 = quantized_decomposed_dequantize_per_tensor_default_2563 = quantized_decomposed_dequantize_per_tensor_default_2566 = quantized_decomposed_dequantize_per_tensor_default_2569 = quantized_decomposed_dequantize_per_tensor_default_2572 = quantized_decomposed_dequantize_per_tensor_default_2575 = quantized_decomposed_dequantize_per_tensor_default_2578 = None
2025-03-21T20:31:44.1306153Z             quantized_decomposed_quantize_per_tensor_default_1920: "i32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_cat_default_47, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_cat_default_47 = None
2025-03-21T20:31:44.1307301Z             quantized_decomposed_dequantize_per_tensor_default_2579: "f32[1536, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1920, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1920 = None
2025-03-21T20:31:44.1308096Z             aten_view_copy_default_208: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_2579, [1, 12, 128, 64]);  quantized_decomposed_dequantize_per_tensor_default_2579 = None
2025-03-21T20:31:44.1309005Z             quantized_decomposed_quantize_per_tensor_default_1921: "i32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_208, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  aten_view_copy_default_208 = None
2025-03-21T20:31:44.1309107Z             
2025-03-21T20:31:44.1310044Z              # File: <eval_with_key>.50:6616 in forward, code: dequantize_per_tensor_default_2081 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_2081, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantize_per_tensor_default_2081 = None
2025-03-21T20:31:44.1311201Z             quantized_decomposed_dequantize_per_tensor_default_2580: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1921, 0.0001868398830993101, 34146, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1921 = None
2025-03-21T20:31:44.1311287Z             
2025-03-21T20:31:44.1312261Z              # File: <eval_with_key>.50:6617 in forward, code: quantize_per_tensor_default_2082 = torch.ops.quantized_decomposed.quantize_per_tensor.default(dequantize_per_tensor_default_2081, 0.00019470337429083884, 0, -32767, 32767, torch.int16);  dequantize_per_tensor_default_2081 = None
2025-03-21T20:31:44.1313442Z             quantized_decomposed_quantize_per_tensor_default_1922: "i16[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_2580, 0.00019470337429083884, 0, -32767, 32767, torch.int16);  quantized_decomposed_dequantize_per_tensor_default_2580 = None
2025-03-21T20:31:44.1313541Z             
2025-03-21T20:31:44.1314003Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:163 in forward, code: y = attn_weight @ v
2025-03-21T20:31:44.1315171Z             quantized_decomposed_dequantize_per_tensor_default_2581: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1922, 0.00019470337429083884, 0, -32767, 32767, torch.int16);  quantized_decomposed_quantize_per_tensor_default_1922 = None
2025-03-21T20:31:44.1315257Z             
2025-03-21T20:31:44.1315780Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:157 in forward, code: attn_mask = mask[input_pos]
2025-03-21T20:31:44.1316668Z             aten_index_tensor_13: "f32[1, 128]" = executorch_exir_dialects_edge__ops_aten_index_Tensor(quantized_decomposed_dequantize_per_tensor_default_148, [attn_options_input_pos]);  quantized_decomposed_dequantize_per_tensor_default_148 = attn_options_input_pos = None
2025-03-21T20:31:44.1317545Z             quantized_decomposed_quantize_per_tensor_default_1923: "i32[1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_index_tensor_13, 0.0038910505827516317, 65535, 0, 65535, torch.int32);  aten_index_tensor_13 = None
2025-03-21T20:31:44.1317658Z             
2025-03-21T20:31:44.1318144Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:161 in forward, code: attn_weight += attn_mask
2025-03-21T20:31:44.1319297Z             quantized_decomposed_dequantize_per_tensor_default_2582: "f32[1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1923, 0.0038910505827516317, 65535, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1923 = None
2025-03-21T20:31:44.1319390Z             
2025-03-21T20:31:44.1319975Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:44.1320882Z             aten_permute_copy_default_482: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2542, [0, 1, 3, 2]);  quantized_decomposed_dequantize_per_tensor_default_2542 = None
2025-03-21T20:31:44.1321849Z             quantized_decomposed_quantize_per_tensor_default_1924: "i32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_482, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  aten_permute_copy_default_482 = None
2025-03-21T20:31:44.1321940Z             
2025-03-21T20:31:44.1322883Z              # File: <eval_with_key>.50:6624 in forward, code: dequantize_per_tensor_default_2084 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_2084, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantize_per_tensor_default_2084 = None
2025-03-21T20:31:44.1324064Z             quantized_decomposed_dequantize_per_tensor_default_2583: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1924, 0.0004016910679638386, 33587, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1924 = None
2025-03-21T20:31:44.1324192Z             
2025-03-21T20:31:44.1325130Z              # File: <eval_with_key>.50:6625 in forward, code: quantize_per_tensor_default_2085 = torch.ops.quantized_decomposed.quantize_per_tensor.default(dequantize_per_tensor_default_2084, 0.00041174760553985834, 0, -32767, 32767, torch.int16);  dequantize_per_tensor_default_2084 = None
2025-03-21T20:31:44.1326292Z             quantized_decomposed_quantize_per_tensor_default_1925: "i16[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(quantized_decomposed_dequantize_per_tensor_default_2583, 0.00041174760553985834, 0, -32767, 32767, torch.int16);  quantized_decomposed_dequantize_per_tensor_default_2583 = None
2025-03-21T20:31:44.1326381Z             
2025-03-21T20:31:44.1326966Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:160 in forward, code: attn_weight = q @ k.transpose(-2, -1) * scale_factor
2025-03-21T20:31:44.1328152Z             quantized_decomposed_dequantize_per_tensor_default_2584: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1925, 0.00041174760553985834, 0, -32767, 32767, torch.int16);  quantized_decomposed_quantize_per_tensor_default_1925 = None
2025-03-21T20:31:44.1328947Z             aten_expand_copy_default_44: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_2478, [1, 12, 1, 64]);  quantized_decomposed_dequantize_per_tensor_default_2478 = None
2025-03-21T20:31:44.1329558Z             aten_view_copy_default_209: "f32[12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_44, [12, 1, 64]);  aten_expand_copy_default_44 = None
2025-03-21T20:31:44.1330405Z             aten_expand_copy_default_45: "f32[1, 12, 64, 128]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_2584, [1, 12, 64, 128]);  quantized_decomposed_dequantize_per_tensor_default_2584 = None
2025-03-21T20:31:44.1331040Z             aten_view_copy_default_210: "f32[12, 64, 128]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_45, [12, 64, 128]);  aten_expand_copy_default_45 = None
2025-03-21T20:31:44.1331877Z             aten_bmm_default_22: "f32[12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_bmm_default(aten_view_copy_default_209, aten_view_copy_default_210);  aten_view_copy_default_209 = aten_view_copy_default_210 = None
2025-03-21T20:31:44.1332563Z             aten_view_copy_default_211: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_bmm_default_22, [1, 12, 1, 128]);  aten_bmm_default_22 = None
2025-03-21T20:31:44.1333498Z             quantized_decomposed_quantize_per_tensor_default_1926: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_211, 0.0039060052949935198, 34370, 0, 65535, torch.int32);  aten_view_copy_default_211 = None
2025-03-21T20:31:44.1334652Z             quantized_decomposed_dequantize_per_tensor_default_2585: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1926, 0.0039060052949935198, 34370, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1926 = None
2025-03-21T20:31:44.1335515Z             quantized_decomposed_dequantize_per_tensor_default_2586: "f32[1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(b__frozen_param160, 1.9073777366429567e-06, 0, 0, 65535, torch.int32);  b__frozen_param160 = None
2025-03-21T20:31:44.1336745Z             aten_mul_tensor_175: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2585, quantized_decomposed_dequantize_per_tensor_default_2586);  quantized_decomposed_dequantize_per_tensor_default_2585 = quantized_decomposed_dequantize_per_tensor_default_2586 = None
2025-03-21T20:31:44.1337650Z             quantized_decomposed_quantize_per_tensor_default_1927: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_175, 0.00048825066187418997, 34370, 0, 65535, torch.int32);  aten_mul_tensor_175 = None
2025-03-21T20:31:44.1337753Z             
2025-03-21T20:31:44.1338236Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:161 in forward, code: attn_weight += attn_mask
2025-03-21T20:31:44.1339399Z             quantized_decomposed_dequantize_per_tensor_default_2587: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1927, 0.00048825066187418997, 34370, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1927 = None
2025-03-21T20:31:44.1340564Z             aten_add_tensor_57: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_2587, quantized_decomposed_dequantize_per_tensor_default_2582);  quantized_decomposed_dequantize_per_tensor_default_2587 = quantized_decomposed_dequantize_per_tensor_default_2582 = None
2025-03-21T20:31:44.1341431Z             quantized_decomposed_quantize_per_tensor_default_1928: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_57, 0.0042822156101465225, 61982, 0, 65535, torch.int32);  aten_add_tensor_57 = None
2025-03-21T20:31:44.1341516Z             
2025-03-21T20:31:44.1342130Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:162 in forward, code: attn_weight = torch.softmax(attn_weight, dim=-1)
2025-03-21T20:31:44.1343281Z             quantized_decomposed_dequantize_per_tensor_default_2588: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1928, 0.0042822156101465225, 61982, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1928 = None
2025-03-21T20:31:44.1344070Z             aten__softmax_default_11: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten__softmax_default(quantized_decomposed_dequantize_per_tensor_default_2588, -1, False);  quantized_decomposed_dequantize_per_tensor_default_2588 = None
2025-03-21T20:31:44.1344959Z             quantized_decomposed_quantize_per_tensor_default_1929: "i32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten__softmax_default_11, 1.5259021893143654e-05, 0, 0, 65535, torch.int32);  aten__softmax_default_11 = None
2025-03-21T20:31:44.1345059Z             
2025-03-21T20:31:44.1345518Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:163 in forward, code: y = attn_weight @ v
2025-03-21T20:31:44.1346665Z             quantized_decomposed_dequantize_per_tensor_default_2589: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1929, 1.5259021893143654e-05, 0, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1929 = None
2025-03-21T20:31:44.1347452Z             aten_expand_copy_default_46: "f32[1, 12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_2589, [1, 12, 1, 128]);  quantized_decomposed_dequantize_per_tensor_default_2589 = None
2025-03-21T20:31:44.1348025Z             aten_view_copy_default_212: "f32[12, 1, 128]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_46, [12, 1, 128]);  aten_expand_copy_default_46 = None
2025-03-21T20:31:44.1348865Z             aten_expand_copy_default_47: "f32[1, 12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_expand_copy_default(quantized_decomposed_dequantize_per_tensor_default_2581, [1, 12, 128, 64]);  quantized_decomposed_dequantize_per_tensor_default_2581 = None
2025-03-21T20:31:44.1349447Z             aten_view_copy_default_213: "f32[12, 128, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_expand_copy_default_47, [12, 128, 64]);  aten_expand_copy_default_47 = None
2025-03-21T20:31:44.1350098Z             aten_bmm_default_23: "f32[12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_bmm_default(aten_view_copy_default_212, aten_view_copy_default_213);  aten_view_copy_default_212 = aten_view_copy_default_213 = None
2025-03-21T20:31:44.1350618Z             aten_view_copy_default_214: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_bmm_default_23, [1, 12, 1, 64]);  aten_bmm_default_23 = None
2025-03-21T20:31:44.1351556Z             quantized_decomposed_quantize_per_tensor_default_1930: "i32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_214, 0.00014522179844789207, 27770, 0, 65535, torch.int32);  aten_view_copy_default_214 = None
2025-03-21T20:31:44.1351660Z             
2025-03-21T20:31:44.1352282Z              # File: /pytorch/executorch/examples/models/llama/source_transformation/sdpa.py:165 in forward, code: return y.transpose(1, 2).contiguous().view(bsz, seqlen, self.dim)
2025-03-21T20:31:44.1353440Z             quantized_decomposed_dequantize_per_tensor_default_2590: "f32[1, 12, 1, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1930, 0.00014522179844789207, 27770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1930 = None
2025-03-21T20:31:44.1354256Z             aten_permute_copy_default_483: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2590, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2590 = None
2025-03-21T20:31:44.1355203Z             quantized_decomposed_quantize_per_tensor_default_1931: "i32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_483, 0.00014522179844789207, 27770, 0, 65535, torch.int32);  aten_permute_copy_default_483 = None
2025-03-21T20:31:44.1356345Z             quantized_decomposed_dequantize_per_tensor_default_2591: "f32[1, 1, 12, 64]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1931, 0.00014522179844789207, 27770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1931 = None
2025-03-21T20:31:44.1357125Z             aten_view_copy_default_215: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_2591, [1, 1, 768]);  quantized_decomposed_dequantize_per_tensor_default_2591 = None
2025-03-21T20:31:44.1358036Z             quantized_decomposed_quantize_per_tensor_default_1932: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_215, 0.00014522179844789207, 27770, 0, 65535, torch.int32);  aten_view_copy_default_215 = None
2025-03-21T20:31:44.1358132Z             
2025-03-21T20:31:44.1358656Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:44.1359820Z             quantized_decomposed_dequantize_per_tensor_default_2592: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1932, 0.00014522179844789207, 27770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1932 = None
2025-03-21T20:31:44.1360681Z             aten_unsqueeze_copy_default_128: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_2592, -1);  quantized_decomposed_dequantize_per_tensor_default_2592 = None
2025-03-21T20:31:44.1361649Z             quantized_decomposed_quantize_per_tensor_default_1933: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_128, 0.00014522179844789207, 27770, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_128 = None
2025-03-21T20:31:44.1361737Z             
2025-03-21T20:31:44.1362153Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:44.1363309Z             quantized_decomposed_dequantize_per_tensor_default_2593: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1933, 0.00014522179844789207, 27770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1933 = None
2025-03-21T20:31:44.1364147Z             aten_permute_copy_default_484: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2593, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2593 = None
2025-03-21T20:31:44.1365087Z             quantized_decomposed_quantize_per_tensor_default_1934: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_484, 0.00014522179844789207, 27770, 0, 65535, torch.int32);  aten_permute_copy_default_484 = None
2025-03-21T20:31:44.1365266Z             
2025-03-21T20:31:44.1365642Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:44.1366875Z             quantized_decomposed_dequantize_per_tensor_default_2594: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1934, 0.00014522179844789207, 27770, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1934 = None
2025-03-21T20:31:44.1368181Z             aten_convolution_default_80: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_2594, quantized_decomposed_dequantize_per_tensor_default_104, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_2594 = quantized_decomposed_dequantize_per_tensor_default_104 = None
2025-03-21T20:31:44.1369149Z             quantized_decomposed_quantize_per_tensor_default_1935: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_80, 0.0005083726719021797, 47465, 0, 65535, torch.int32);  aten_convolution_default_80 = None
2025-03-21T20:31:44.1369318Z             
2025-03-21T20:31:44.1369761Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:44.1370930Z             quantized_decomposed_dequantize_per_tensor_default_2595: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1935, 0.0005083726719021797, 47465, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1935 = None
2025-03-21T20:31:44.1371723Z             aten_permute_copy_default_485: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2595, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2595 = None
2025-03-21T20:31:44.1372708Z             quantized_decomposed_quantize_per_tensor_default_1936: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_485, 0.0005083726719021797, 47465, 0, 65535, torch.int32);  aten_permute_copy_default_485 = None
2025-03-21T20:31:44.1372820Z             
2025-03-21T20:31:44.1373374Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:44.1374520Z             quantized_decomposed_dequantize_per_tensor_default_2596: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1936, 0.0005083726719021797, 47465, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1936 = None
2025-03-21T20:31:44.1375295Z             aten_squeeze_copy_dims_128: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_2596, [-1]);  quantized_decomposed_dequantize_per_tensor_default_2596 = None
2025-03-21T20:31:44.1376239Z             quantized_decomposed_quantize_per_tensor_default_1937: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_128, 0.0005083726719021797, 47465, 0, 65535, torch.int32);  aten_squeeze_copy_dims_128 = None
2025-03-21T20:31:44.1376342Z             
2025-03-21T20:31:44.1376713Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:111 in forward, code: h = x + h
2025-03-21T20:31:44.1377875Z             quantized_decomposed_dequantize_per_tensor_default_2597: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1937, 0.0005083726719021797, 47465, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1937 = None
2025-03-21T20:31:44.1379028Z             aten_add_tensor_58: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_2417, quantized_decomposed_dequantize_per_tensor_default_2597);  quantized_decomposed_dequantize_per_tensor_default_2417 = quantized_decomposed_dequantize_per_tensor_default_2597 = None
2025-03-21T20:31:44.1379891Z             quantized_decomposed_quantize_per_tensor_default_1938: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_58, 0.0023697831202298403, 14969, 0, 65535, torch.int32);  aten_add_tensor_58 = None
2025-03-21T20:31:44.1379976Z             
2025-03-21T20:31:44.1380496Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:115 in forward, code: out = h + self.feed_forward(self.ffn_norm(h))
2025-03-21T20:31:44.1381413Z             quantized_decomposed_dequantize_per_tensor_default_2598: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1938, 0.0023697831202298403, 14969, 0, 65535, torch.int32)
2025-03-21T20:31:44.1382570Z             quantized_decomposed_dequantize_per_tensor_default_2599: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1938, 0.0023697831202298403, 14969, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1938 = None
2025-03-21T20:31:44.1383083Z             aten_pow_tensor_scalar_23: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_pow_Tensor_Scalar(quantized_decomposed_dequantize_per_tensor_default_2599, 2)
2025-03-21T20:31:44.1383554Z             aten_mean_dim_23: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_mean_dim(aten_pow_tensor_scalar_23, [2], True);  aten_pow_tensor_scalar_23 = None
2025-03-21T20:31:44.1384025Z             aten_add_scalar_23: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_add_Scalar(aten_mean_dim_23, 9.999999747378752e-06);  aten_mean_dim_23 = None
2025-03-21T20:31:44.1384481Z             aten_rsqrt_default_23: "f32[1, 1, 1]" = executorch_exir_dialects_edge__ops_aten_rsqrt_default(aten_add_scalar_23);  aten_add_scalar_23 = None
2025-03-21T20:31:44.1385332Z             aten_mul_tensor_176: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2599, aten_rsqrt_default_23);  quantized_decomposed_dequantize_per_tensor_default_2599 = aten_rsqrt_default_23 = None
2025-03-21T20:31:44.1386165Z             aten_mul_tensor_177: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(aten_mul_tensor_176, quantized_decomposed_dequantize_per_tensor_default_105);  aten_mul_tensor_176 = quantized_decomposed_dequantize_per_tensor_default_105 = None
2025-03-21T20:31:44.1387019Z             quantized_decomposed_quantize_per_tensor_default_1939: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_177, 0.0006559237372130156, 27360, 0, 65535, torch.int32);  aten_mul_tensor_177 = None
2025-03-21T20:31:44.1387118Z             
2025-03-21T20:31:44.1387661Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:44.1388592Z             quantized_decomposed_dequantize_per_tensor_default_2600: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1939, 0.0006559237372130156, 27360, 0, 65535, torch.int32)
2025-03-21T20:31:44.1389735Z             quantized_decomposed_dequantize_per_tensor_default_2601: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1939, 0.0006559237372130156, 27360, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1939 = None
2025-03-21T20:31:44.1390585Z             aten_unsqueeze_copy_default_129: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_2601, -1);  quantized_decomposed_dequantize_per_tensor_default_2601 = None
2025-03-21T20:31:44.1391532Z             quantized_decomposed_quantize_per_tensor_default_1940: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_129, 0.0006559237372130156, 27360, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_129 = None
2025-03-21T20:31:44.1391629Z             
2025-03-21T20:31:44.1392036Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:44.1393195Z             quantized_decomposed_dequantize_per_tensor_default_2602: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1940, 0.0006559237372130156, 27360, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1940 = None
2025-03-21T20:31:44.1393996Z             aten_permute_copy_default_486: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2602, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2602 = None
2025-03-21T20:31:44.1394938Z             quantized_decomposed_quantize_per_tensor_default_1941: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_486, 0.0006559237372130156, 27360, 0, 65535, torch.int32);  aten_permute_copy_default_486 = None
2025-03-21T20:31:44.1395026Z             
2025-03-21T20:31:44.1395399Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:44.1396610Z             quantized_decomposed_dequantize_per_tensor_default_2603: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1941, 0.0006559237372130156, 27360, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1941 = None
2025-03-21T20:31:44.1397911Z             aten_convolution_default_81: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_2603, quantized_decomposed_dequantize_per_tensor_default_106, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_2603 = quantized_decomposed_dequantize_per_tensor_default_106 = None
2025-03-21T20:31:44.1398848Z             quantized_decomposed_quantize_per_tensor_default_1942: "i32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_81, 0.0002535042294766754, 28878, 0, 65535, torch.int32);  aten_convolution_default_81 = None
2025-03-21T20:31:44.1398947Z             
2025-03-21T20:31:44.1399389Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:44.1400552Z             quantized_decomposed_dequantize_per_tensor_default_2604: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1942, 0.0002535042294766754, 28878, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1942 = None
2025-03-21T20:31:44.1401355Z             aten_permute_copy_default_487: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2604, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2604 = None
2025-03-21T20:31:44.1402331Z             quantized_decomposed_quantize_per_tensor_default_1943: "i32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_487, 0.0002535042294766754, 28878, 0, 65535, torch.int32);  aten_permute_copy_default_487 = None
2025-03-21T20:31:44.1402420Z             
2025-03-21T20:31:44.1402964Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:44.1404115Z             quantized_decomposed_dequantize_per_tensor_default_2605: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1943, 0.0002535042294766754, 28878, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1943 = None
2025-03-21T20:31:44.1404888Z             aten_squeeze_copy_dims_129: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_2605, [-1]);  quantized_decomposed_dequantize_per_tensor_default_2605 = None
2025-03-21T20:31:44.1405805Z             quantized_decomposed_quantize_per_tensor_default_1944: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_129, 0.0002535042294766754, 28878, 0, 65535, torch.int32);  aten_squeeze_copy_dims_129 = None
2025-03-21T20:31:44.1405902Z             
2025-03-21T20:31:44.1406417Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:36 in forward, code: return self.w2(F.silu(self.w1(x)) * self.w3(x))
2025-03-21T20:31:44.1407350Z             quantized_decomposed_dequantize_per_tensor_default_2606: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1944, 0.0002535042294766754, 28878, 0, 65535, torch.int32)
2025-03-21T20:31:44.1408527Z             quantized_decomposed_dequantize_per_tensor_default_2607: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1944, 0.0002535042294766754, 28878, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1944 = None
2025-03-21T20:31:44.1409397Z             aten_sigmoid_default_11: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_sigmoid_default(quantized_decomposed_dequantize_per_tensor_default_2607);  quantized_decomposed_dequantize_per_tensor_default_2607 = None
2025-03-21T20:31:44.1410259Z             quantized_decomposed_quantize_per_tensor_default_1945: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_sigmoid_default_11, 1.52587890625e-05, 0, 0, 65535, torch.int32);  aten_sigmoid_default_11 = None
2025-03-21T20:31:44.1411382Z             quantized_decomposed_dequantize_per_tensor_default_2608: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1945, 1.52587890625e-05, 0, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1945 = None
2025-03-21T20:31:44.1412543Z             aten_mul_tensor_178: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2606, quantized_decomposed_dequantize_per_tensor_default_2608);  quantized_decomposed_dequantize_per_tensor_default_2606 = quantized_decomposed_dequantize_per_tensor_default_2608 = None
2025-03-21T20:31:44.1413420Z             quantized_decomposed_quantize_per_tensor_default_1946: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_178, 0.00014603332965634763, 1907, 0, 65535, torch.int32);  aten_mul_tensor_178 = None
2025-03-21T20:31:44.1414596Z             quantized_decomposed_dequantize_per_tensor_default_2609: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1946, 0.00014603332965634763, 1907, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1946 = None
2025-03-21T20:31:44.1414696Z             
2025-03-21T20:31:44.1415215Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:44.1416038Z             aten_unsqueeze_copy_default_130: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_2600, -1);  quantized_decomposed_dequantize_per_tensor_default_2600 = None
2025-03-21T20:31:44.1416988Z             quantized_decomposed_quantize_per_tensor_default_1947: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_130, 0.0006559237372130156, 27360, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_130 = None
2025-03-21T20:31:44.1417091Z             
2025-03-21T20:31:44.1417498Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:44.1418654Z             quantized_decomposed_dequantize_per_tensor_default_2610: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1947, 0.0006559237372130156, 27360, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1947 = None
2025-03-21T20:31:44.1419456Z             aten_permute_copy_default_488: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2610, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2610 = None
2025-03-21T20:31:44.1420435Z             quantized_decomposed_quantize_per_tensor_default_1948: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_488, 0.0006559237372130156, 27360, 0, 65535, torch.int32);  aten_permute_copy_default_488 = None
2025-03-21T20:31:44.1420563Z             
2025-03-21T20:31:44.1420944Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:44.1422094Z             quantized_decomposed_dequantize_per_tensor_default_2611: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1948, 0.0006559237372130156, 27360, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1948 = None
2025-03-21T20:31:44.1423400Z             aten_convolution_default_82: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_2611, quantized_decomposed_dequantize_per_tensor_default_107, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_2611 = quantized_decomposed_dequantize_per_tensor_default_107 = None
2025-03-21T20:31:44.1424365Z             quantized_decomposed_quantize_per_tensor_default_1949: "i32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_82, 0.00044822643394581974, 39750, 0, 65535, torch.int32);  aten_convolution_default_82 = None
2025-03-21T20:31:44.1424470Z             
2025-03-21T20:31:44.1424892Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:44.1426065Z             quantized_decomposed_dequantize_per_tensor_default_2612: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1949, 0.00044822643394581974, 39750, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1949 = None
2025-03-21T20:31:44.1426893Z             aten_permute_copy_default_489: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2612, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2612 = None
2025-03-21T20:31:44.1427850Z             quantized_decomposed_quantize_per_tensor_default_1950: "i32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_489, 0.00044822643394581974, 39750, 0, 65535, torch.int32);  aten_permute_copy_default_489 = None
2025-03-21T20:31:44.1427934Z             
2025-03-21T20:31:44.1428481Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:44.1429635Z             quantized_decomposed_dequantize_per_tensor_default_2613: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1950, 0.00044822643394581974, 39750, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1950 = None
2025-03-21T20:31:44.1430409Z             aten_squeeze_copy_dims_130: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_2613, [-1]);  quantized_decomposed_dequantize_per_tensor_default_2613 = None
2025-03-21T20:31:44.1431325Z             quantized_decomposed_quantize_per_tensor_default_1951: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_130, 0.00044822643394581974, 39750, 0, 65535, torch.int32);  aten_squeeze_copy_dims_130 = None
2025-03-21T20:31:44.1431423Z             
2025-03-21T20:31:44.1431957Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:36 in forward, code: return self.w2(F.silu(self.w1(x)) * self.w3(x))
2025-03-21T20:31:44.1433452Z             quantized_decomposed_dequantize_per_tensor_default_2614: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1951, 0.00044822643394581974, 39750, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1951 = None
2025-03-21T20:31:44.1434593Z             aten_mul_tensor_179: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2609, quantized_decomposed_dequantize_per_tensor_default_2614);  quantized_decomposed_dequantize_per_tensor_default_2609 = quantized_decomposed_dequantize_per_tensor_default_2614 = None
2025-03-21T20:31:44.1435465Z             quantized_decomposed_quantize_per_tensor_default_1952: "i32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_179, 0.002697124844416976, 47690, 0, 65535, torch.int32);  aten_mul_tensor_179 = None
2025-03-21T20:31:44.1435554Z             
2025-03-21T20:31:44.1436150Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:44.1437294Z             quantized_decomposed_dequantize_per_tensor_default_2615: "f32[1, 1, 2048]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1952, 0.002697124844416976, 47690, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1952 = None
2025-03-21T20:31:44.1438117Z             aten_unsqueeze_copy_default_131: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_aten_unsqueeze_copy_default(quantized_decomposed_dequantize_per_tensor_default_2615, -1);  quantized_decomposed_dequantize_per_tensor_default_2615 = None
2025-03-21T20:31:44.1439109Z             quantized_decomposed_quantize_per_tensor_default_1953: "i32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_unsqueeze_copy_default_131, 0.002697124844416976, 47690, 0, 65535, torch.int32);  aten_unsqueeze_copy_default_131 = None
2025-03-21T20:31:44.1439206Z             
2025-03-21T20:31:44.1439613Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:44.1440776Z             quantized_decomposed_dequantize_per_tensor_default_2616: "f32[1, 1, 2048, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1953, 0.002697124844416976, 47690, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1953 = None
2025-03-21T20:31:44.1441678Z             aten_permute_copy_default_490: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2616, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2616 = None
2025-03-21T20:31:44.1442646Z             quantized_decomposed_quantize_per_tensor_default_1954: "i32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_490, 0.002697124844416976, 47690, 0, 65535, torch.int32);  aten_permute_copy_default_490 = None
2025-03-21T20:31:44.1442789Z             
2025-03-21T20:31:44.1443167Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:44.1444334Z             quantized_decomposed_dequantize_per_tensor_default_2617: "f32[1, 2048, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1954, 0.002697124844416976, 47690, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1954 = None
2025-03-21T20:31:44.1445709Z             aten_convolution_default_83: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_2617, quantized_decomposed_dequantize_per_tensor_default_108, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_2617 = quantized_decomposed_dequantize_per_tensor_default_108 = None
2025-03-21T20:31:44.1446652Z             quantized_decomposed_quantize_per_tensor_default_1955: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_83, 0.002150162821635604, 55113, 0, 65535, torch.int32);  aten_convolution_default_83 = None
2025-03-21T20:31:44.1446739Z             
2025-03-21T20:31:44.1447175Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:44.1448377Z             quantized_decomposed_dequantize_per_tensor_default_2618: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1955, 0.002150162821635604, 55113, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1955 = None
2025-03-21T20:31:44.1449192Z             aten_permute_copy_default_491: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2618, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2618 = None
2025-03-21T20:31:44.1450189Z             quantized_decomposed_quantize_per_tensor_default_1956: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_491, 0.002150162821635604, 55113, 0, 65535, torch.int32);  aten_permute_copy_default_491 = None
2025-03-21T20:31:44.1450323Z             
2025-03-21T20:31:44.1450866Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:44.1452426Z             quantized_decomposed_dequantize_per_tensor_default_2619: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1956, 0.002150162821635604, 55113, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1956 = None
2025-03-21T20:31:44.1453191Z             aten_squeeze_copy_dims_131: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_squeeze_copy_dims(quantized_decomposed_dequantize_per_tensor_default_2619, [-1]);  quantized_decomposed_dequantize_per_tensor_default_2619 = None
2025-03-21T20:31:44.1454115Z             quantized_decomposed_quantize_per_tensor_default_1957: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_squeeze_copy_dims_131, 0.002150162821635604, 55113, 0, 65535, torch.int32);  aten_squeeze_copy_dims_131 = None
2025-03-21T20:31:44.1454207Z             
2025-03-21T20:31:44.1454731Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:115 in forward, code: out = h + self.feed_forward(self.ffn_norm(h))
2025-03-21T20:31:44.1455871Z             quantized_decomposed_dequantize_per_tensor_default_2620: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1957, 0.002150162821635604, 55113, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1957 = None
2025-03-21T20:31:44.1457517Z             aten_add_tensor_59: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_aten_add_Tensor(quantized_decomposed_dequantize_per_tensor_default_2598, quantized_decomposed_dequantize_per_tensor_default_2620);  quantized_decomposed_dequantize_per_tensor_default_2598 = quantized_decomposed_dequantize_per_tensor_default_2620 = None
2025-03-21T20:31:44.1458946Z             quantized_decomposed_quantize_per_tensor_default_1958: "i32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_add_tensor_59, 0.003176590660586953, 40851, 0, 65535, torch.int32);  aten_add_tensor_59 = None
2025-03-21T20:31:44.1459100Z             
2025-03-21T20:31:44.1459797Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:180 in forward, code: h = h[:, -1, :]
2025-03-21T20:31:44.1461742Z             quantized_decomposed_dequantize_per_tensor_default_2621: "f32[1, 1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1958, 0.003176590660586953, 40851, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1958 = None
2025-03-21T20:31:44.1462903Z             aten_select_copy_int_576: "f32[1, 768]" = executorch_exir_dialects_edge__ops_aten_select_copy_int(quantized_decomposed_dequantize_per_tensor_default_2621, 1, -1);  quantized_decomposed_dequantize_per_tensor_default_2621 = None
2025-03-21T20:31:44.1464601Z             quantized_decomposed_quantize_per_tensor_default_1959: "i32[1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_select_copy_int_576, 0.003176590660586953, 40851, 0, 65535, torch.int32);  aten_select_copy_int_576 = None
2025-03-21T20:31:44.1464757Z             
2025-03-21T20:31:44.1465517Z              # File: /pytorch/executorch/examples/models/llama/llama_transformer.py:182 in forward, code: h = self.norm(h)
2025-03-21T20:31:44.1467646Z             quantized_decomposed_dequantize_per_tensor_default_2622: "f32[1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1959, 0.003176590660586953, 40851, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1959 = None
2025-03-21T20:31:44.1468669Z             aten_pow_tensor_scalar_24: "f32[1, 768]" = executorch_exir_dialects_edge__ops_aten_pow_Tensor_Scalar(quantized_decomposed_dequantize_per_tensor_default_2622, 2)
2025-03-21T20:31:44.1469525Z             aten_mean_dim_24: "f32[1, 1]" = executorch_exir_dialects_edge__ops_aten_mean_dim(aten_pow_tensor_scalar_24, [1], True);  aten_pow_tensor_scalar_24 = None
2025-03-21T20:31:44.1470370Z             aten_add_scalar_24: "f32[1, 1]" = executorch_exir_dialects_edge__ops_aten_add_Scalar(aten_mean_dim_24, 9.999999747378752e-06);  aten_mean_dim_24 = None
2025-03-21T20:31:44.1471109Z             aten_rsqrt_default_24: "f32[1, 1]" = executorch_exir_dialects_edge__ops_aten_rsqrt_default(aten_add_scalar_24);  aten_add_scalar_24 = None
2025-03-21T20:31:44.1472781Z             aten_mul_tensor_180: "f32[1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(quantized_decomposed_dequantize_per_tensor_default_2622, aten_rsqrt_default_24);  quantized_decomposed_dequantize_per_tensor_default_2622 = aten_rsqrt_default_24 = None
2025-03-21T20:31:44.1474445Z             aten_mul_tensor_181: "f32[1, 768]" = executorch_exir_dialects_edge__ops_aten_mul_Tensor(aten_mul_tensor_180, quantized_decomposed_dequantize_per_tensor_default_109);  aten_mul_tensor_180 = quantized_decomposed_dequantize_per_tensor_default_109 = None
2025-03-21T20:31:44.1476113Z             quantized_decomposed_quantize_per_tensor_default_1960: "i32[1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_mul_tensor_181, 0.0029369546100497246, 33824, 0, 65535, torch.int32);  aten_mul_tensor_181 = None
2025-03-21T20:31:44.1476264Z             
2025-03-21T20:31:44.1477255Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:190 in forward, code: x = x.unsqueeze(-1) if rank == 3 else x.reshape(1, *x.shape, 1)
2025-03-21T20:31:44.1479606Z             quantized_decomposed_dequantize_per_tensor_default_2623: "f32[1, 768]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1960, 0.0029369546100497246, 33824, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1960 = None
2025-03-21T20:31:44.1481123Z             aten_view_copy_default_216: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_2623, [1, 1, 768, 1]);  quantized_decomposed_dequantize_per_tensor_default_2623 = None
2025-03-21T20:31:44.1482811Z             quantized_decomposed_quantize_per_tensor_default_1961: "i32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_216, 0.0029369546100497246, 33824, 0, 65535, torch.int32);  aten_view_copy_default_216 = None
2025-03-21T20:31:44.1482994Z             
2025-03-21T20:31:44.1483761Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:191 in forward, code: x = torch.transpose(x, 1, 2)
2025-03-21T20:31:44.1486083Z             quantized_decomposed_dequantize_per_tensor_default_2624: "f32[1, 1, 768, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1961, 0.0029369546100497246, 33824, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1961 = None
2025-03-21T20:31:44.1487650Z             aten_permute_copy_default_492: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2624, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2624 = None
2025-03-21T20:31:44.1489603Z             quantized_decomposed_quantize_per_tensor_default_1962: "i32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_492, 0.0029369546100497246, 33824, 0, 65535, torch.int32);  aten_permute_copy_default_492 = None
2025-03-21T20:31:44.1489813Z             
2025-03-21T20:31:44.1490522Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:192 in forward, code: res = self.conv(x)
2025-03-21T20:31:44.1492642Z             quantized_decomposed_dequantize_per_tensor_default_2625: "f32[1, 768, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1962, 0.0029369546100497246, 33824, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1962 = None
2025-03-21T20:31:44.1495022Z             aten_convolution_default_84: "f32[1, 32000, 1, 1]" = executorch_exir_dialects_edge__ops_aten_convolution_default(quantized_decomposed_dequantize_per_tensor_default_2625, quantized_decomposed_dequantize_per_tensor_default_110, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1);  quantized_decomposed_dequantize_per_tensor_default_2625 = quantized_decomposed_dequantize_per_tensor_default_110 = None
2025-03-21T20:31:44.1496837Z             quantized_decomposed_quantize_per_tensor_default_1963: "i32[1, 32000, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_convolution_default_84, 0.0006781866541132331, 24939, 0, 65535, torch.int32);  aten_convolution_default_84 = None
2025-03-21T20:31:44.1497010Z             
2025-03-21T20:31:44.1497824Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:193 in forward, code: res = torch.transpose(res, 1, 2)
2025-03-21T20:31:44.1500052Z             quantized_decomposed_dequantize_per_tensor_default_2626: "f32[1, 32000, 1, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1963, 0.0006781866541132331, 24939, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1963 = None
2025-03-21T20:31:44.1501608Z             aten_permute_copy_default_493: "f32[1, 1, 32000, 1]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(quantized_decomposed_dequantize_per_tensor_default_2626, [0, 2, 1, 3]);  quantized_decomposed_dequantize_per_tensor_default_2626 = None
2025-03-21T20:31:44.1503112Z             quantized_decomposed_quantize_per_tensor_default_1964: "i32[1, 1, 32000, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_permute_copy_default_493, 0.0006781866541132331, 24939, 0, 65535, torch.int32);  aten_permute_copy_default_493 = None
2025-03-21T20:31:44.1503212Z             
2025-03-21T20:31:44.1503774Z              # File: /pytorch/executorch/backends/qualcomm/utils/utils.py:194 in forward, code: res = res.squeeze(-1) if rank == 3 else res.reshape(*res.shape[1:3])
2025-03-21T20:31:44.1504942Z             quantized_decomposed_dequantize_per_tensor_default_2627: "f32[1, 1, 32000, 1]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1964, 0.0006781866541132331, 24939, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1964 = None
2025-03-21T20:31:44.1505798Z             aten_view_copy_default_217: "f32[1, 32000]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(quantized_decomposed_dequantize_per_tensor_default_2627, [1, 32000]);  quantized_decomposed_dequantize_per_tensor_default_2627 = None
2025-03-21T20:31:44.1506791Z             quantized_decomposed_quantize_per_tensor_default_1965: "i32[1, 32000]" = executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default(aten_view_copy_default_217, 0.0006781866541132331, 24939, 0, 65535, torch.int32);  aten_view_copy_default_217 = None
2025-03-21T20:31:44.1506932Z             
2025-03-21T20:31:44.1508067Z              # File: <eval_with_key>.50:6757 in forward, code: dequantize_per_tensor_default_2128 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_2128, 0.0006781866541132331, 24939, 0, 65535, torch.int32);  quantize_per_tensor_default_2128 = None
2025-03-21T20:31:44.1509297Z             quantized_decomposed_dequantize_per_tensor_default_2628: "f32[1, 32000]" = executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default(quantized_decomposed_quantize_per_tensor_default_1965, 0.0006781866541132331, 24939, 0, 65535, torch.int32);  quantized_decomposed_quantize_per_tensor_default_1965 = None
2025-03-21T20:31:44.1509388Z             
2025-03-21T20:31:44.1510313Z              # File: <eval_with_key>.50:6758 in forward, code: copy__default = torch.ops.aten.copy_.default(layers_0_attention_kv_cache_past_k_caches, dequantize_per_tensor_default_200);  layers_0_attention_kv_cache_past_k_caches = dequantize_per_tensor_default_200 = copy__default = None
2025-03-21T20:31:44.1511331Z             aten_copy_default: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_copy_default(b_layers_0_attention_kv_cache_past_k_caches, quantized_decomposed_dequantize_per_tensor_default_235);  b_layers_0_attention_kv_cache_past_k_caches = quantized_decomposed_dequantize_per_tensor_default_235 = None
2025-03-21T20:31:44.1511439Z             
2025-03-21T20:31:44.1512360Z              # File: <eval_with_key>.50:6759 in forward, code: copy__default_1 = torch.ops.aten.copy_.default(layers_0_attention_kv_cache_past_v_caches, dequantize_per_tensor_default_201);  layers_0_attention_kv_cache_past_v_caches = dequantize_per_tensor_default_201 = copy__default_1 = None
2025-03-21T20:31:44.1513391Z             aten_copy_default_1: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_copy_default(b_layers_0_attention_kv_cache_past_v_caches, quantized_decomposed_dequantize_per_tensor_default_248);  b_layers_0_attention_kv_cache_past_v_caches = quantized_decomposed_dequantize_per_tensor_default_248 = None
2025-03-21T20:31:44.1513480Z             
2025-03-21T20:31:44.1514447Z              # File: <eval_with_key>.50:6760 in forward, code: copy__default_2 = torch.ops.aten.copy_.default(layers_1_attention_kv_cache_past_k_caches, dequantize_per_tensor_default_364);  layers_1_attention_kv_cache_past_k_caches = dequantize_per_tensor_default_364 = copy__default_2 = None
2025-03-21T20:31:44.1515492Z             aten_copy_default_2: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_copy_default(b_layers_1_attention_kv_cache_past_k_caches, quantized_decomposed_dequantize_per_tensor_default_439);  b_layers_1_attention_kv_cache_past_k_caches = quantized_decomposed_dequantize_per_tensor_default_439 = None
2025-03-21T20:31:44.1515592Z             
2025-03-21T20:31:44.1516510Z              # File: <eval_with_key>.50:6761 in forward, code: copy__default_3 = torch.ops.aten.copy_.default(layers_1_attention_kv_cache_past_v_caches, dequantize_per_tensor_default_365);  layers_1_attention_kv_cache_past_v_caches = dequantize_per_tensor_default_365 = copy__default_3 = None
2025-03-21T20:31:44.1517535Z             aten_copy_default_3: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_copy_default(b_layers_1_attention_kv_cache_past_v_caches, quantized_decomposed_dequantize_per_tensor_default_452);  b_layers_1_attention_kv_cache_past_v_caches = quantized_decomposed_dequantize_per_tensor_default_452 = None
2025-03-21T20:31:44.1517624Z             
2025-03-21T20:31:44.1518583Z              # File: <eval_with_key>.50:6762 in forward, code: copy__default_4 = torch.ops.aten.copy_.default(layers_2_attention_kv_cache_past_k_caches, dequantize_per_tensor_default_528);  layers_2_attention_kv_cache_past_k_caches = dequantize_per_tensor_default_528 = copy__default_4 = None
2025-03-21T20:31:44.1519597Z             aten_copy_default_4: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_copy_default(b_layers_2_attention_kv_cache_past_k_caches, quantized_decomposed_dequantize_per_tensor_default_643);  b_layers_2_attention_kv_cache_past_k_caches = quantized_decomposed_dequantize_per_tensor_default_643 = None
2025-03-21T20:31:44.1519724Z             
2025-03-21T20:31:44.1520647Z              # File: <eval_with_key>.50:6763 in forward, code: copy__default_5 = torch.ops.aten.copy_.default(layers_2_attention_kv_cache_past_v_caches, dequantize_per_tensor_default_529);  layers_2_attention_kv_cache_past_v_caches = dequantize_per_tensor_default_529 = copy__default_5 = None
2025-03-21T20:31:44.1521676Z             aten_copy_default_5: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_copy_default(b_layers_2_attention_kv_cache_past_v_caches, quantized_decomposed_dequantize_per_tensor_default_656);  b_layers_2_attention_kv_cache_past_v_caches = quantized_decomposed_dequantize_per_tensor_default_656 = None
2025-03-21T20:31:44.1521763Z             
2025-03-21T20:31:44.1522690Z              # File: <eval_with_key>.50:6764 in forward, code: copy__default_6 = torch.ops.aten.copy_.default(layers_3_attention_kv_cache_past_k_caches, dequantize_per_tensor_default_692);  layers_3_attention_kv_cache_past_k_caches = dequantize_per_tensor_default_692 = copy__default_6 = None
2025-03-21T20:31:44.1523819Z             aten_copy_default_6: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_copy_default(b_layers_3_attention_kv_cache_past_k_caches, quantized_decomposed_dequantize_per_tensor_default_847);  b_layers_3_attention_kv_cache_past_k_caches = quantized_decomposed_dequantize_per_tensor_default_847 = None
2025-03-21T20:31:44.1523925Z             
2025-03-21T20:31:44.1524844Z              # File: <eval_with_key>.50:6765 in forward, code: copy__default_7 = torch.ops.aten.copy_.default(layers_3_attention_kv_cache_past_v_caches, dequantize_per_tensor_default_693);  layers_3_attention_kv_cache_past_v_caches = dequantize_per_tensor_default_693 = copy__default_7 = None
2025-03-21T20:31:44.1525870Z             aten_copy_default_7: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_copy_default(b_layers_3_attention_kv_cache_past_v_caches, quantized_decomposed_dequantize_per_tensor_default_860);  b_layers_3_attention_kv_cache_past_v_caches = quantized_decomposed_dequantize_per_tensor_default_860 = None
2025-03-21T20:31:44.1525959Z             
2025-03-21T20:31:44.1526923Z              # File: <eval_with_key>.50:6766 in forward, code: copy__default_8 = torch.ops.aten.copy_.default(layers_4_attention_kv_cache_past_k_caches, dequantize_per_tensor_default_856);  layers_4_attention_kv_cache_past_k_caches = dequantize_per_tensor_default_856 = copy__default_8 = None
2025-03-21T20:31:44.1527969Z             aten_copy_default_8: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_copy_default(b_layers_4_attention_kv_cache_past_k_caches, quantized_decomposed_dequantize_per_tensor_default_1051);  b_layers_4_attention_kv_cache_past_k_caches = quantized_decomposed_dequantize_per_tensor_default_1051 = None
2025-03-21T20:31:44.1528069Z             
2025-03-21T20:31:44.1528989Z              # File: <eval_with_key>.50:6767 in forward, code: copy__default_9 = torch.ops.aten.copy_.default(layers_4_attention_kv_cache_past_v_caches, dequantize_per_tensor_default_857);  layers_4_attention_kv_cache_past_v_caches = dequantize_per_tensor_default_857 = copy__default_9 = None
2025-03-21T20:31:44.1530124Z             aten_copy_default_9: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_copy_default(b_layers_4_attention_kv_cache_past_v_caches, quantized_decomposed_dequantize_per_tensor_default_1064);  b_layers_4_attention_kv_cache_past_v_caches = quantized_decomposed_dequantize_per_tensor_default_1064 = None
2025-03-21T20:31:44.1530219Z             
2025-03-21T20:31:44.1531168Z              # File: <eval_with_key>.50:6768 in forward, code: copy__default_10 = torch.ops.aten.copy_.default(layers_5_attention_kv_cache_past_k_caches, dequantize_per_tensor_default_1020);  layers_5_attention_kv_cache_past_k_caches = dequantize_per_tensor_default_1020 = copy__default_10 = None
2025-03-21T20:31:44.1532192Z             aten_copy_default_10: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_copy_default(b_layers_5_attention_kv_cache_past_k_caches, quantized_decomposed_dequantize_per_tensor_default_1255);  b_layers_5_attention_kv_cache_past_k_caches = quantized_decomposed_dequantize_per_tensor_default_1255 = None
2025-03-21T20:31:44.1532488Z             
2025-03-21T20:31:44.1533429Z              # File: <eval_with_key>.50:6769 in forward, code: copy__default_11 = torch.ops.aten.copy_.default(layers_5_attention_kv_cache_past_v_caches, dequantize_per_tensor_default_1021);  layers_5_attention_kv_cache_past_v_caches = dequantize_per_tensor_default_1021 = copy__default_11 = None
2025-03-21T20:31:44.1534712Z             aten_copy_default_11: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_copy_default(b_layers_5_attention_kv_cache_past_v_caches, quantized_decomposed_dequantize_per_tensor_default_1268);  b_layers_5_attention_kv_cache_past_v_caches = quantized_decomposed_dequantize_per_tensor_default_1268 = None
2025-03-21T20:31:44.1534818Z             
2025-03-21T20:31:44.1535774Z              # File: <eval_with_key>.50:6770 in forward, code: copy__default_12 = torch.ops.aten.copy_.default(layers_6_attention_kv_cache_past_k_caches, dequantize_per_tensor_default_1184);  layers_6_attention_kv_cache_past_k_caches = dequantize_per_tensor_default_1184 = copy__default_12 = None
2025-03-21T20:31:44.1536800Z             aten_copy_default_12: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_copy_default(b_layers_6_attention_kv_cache_past_k_caches, quantized_decomposed_dequantize_per_tensor_default_1459);  b_layers_6_attention_kv_cache_past_k_caches = quantized_decomposed_dequantize_per_tensor_default_1459 = None
2025-03-21T20:31:44.1536901Z             
2025-03-21T20:31:44.1537832Z              # File: <eval_with_key>.50:6771 in forward, code: copy__default_13 = torch.ops.aten.copy_.default(layers_6_attention_kv_cache_past_v_caches, dequantize_per_tensor_default_1185);  layers_6_attention_kv_cache_past_v_caches = dequantize_per_tensor_default_1185 = copy__default_13 = None
2025-03-21T20:31:44.1538947Z             aten_copy_default_13: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_copy_default(b_layers_6_attention_kv_cache_past_v_caches, quantized_decomposed_dequantize_per_tensor_default_1472);  b_layers_6_attention_kv_cache_past_v_caches = quantized_decomposed_dequantize_per_tensor_default_1472 = None
2025-03-21T20:31:44.1539070Z             
2025-03-21T20:31:44.1540019Z              # File: <eval_with_key>.50:6772 in forward, code: copy__default_14 = torch.ops.aten.copy_.default(layers_7_attention_kv_cache_past_k_caches, dequantize_per_tensor_default_1348);  layers_7_attention_kv_cache_past_k_caches = dequantize_per_tensor_default_1348 = copy__default_14 = None
2025-03-21T20:31:44.1541047Z             aten_copy_default_14: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_copy_default(b_layers_7_attention_kv_cache_past_k_caches, quantized_decomposed_dequantize_per_tensor_default_1663);  b_layers_7_attention_kv_cache_past_k_caches = quantized_decomposed_dequantize_per_tensor_default_1663 = None
2025-03-21T20:31:44.1541151Z             
2025-03-21T20:31:44.1542085Z              # File: <eval_with_key>.50:6773 in forward, code: copy__default_15 = torch.ops.aten.copy_.default(layers_7_attention_kv_cache_past_v_caches, dequantize_per_tensor_default_1349);  layers_7_attention_kv_cache_past_v_caches = dequantize_per_tensor_default_1349 = copy__default_15 = None
2025-03-21T20:31:44.1543160Z             aten_copy_default_15: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_copy_default(b_layers_7_attention_kv_cache_past_v_caches, quantized_decomposed_dequantize_per_tensor_default_1676);  b_layers_7_attention_kv_cache_past_v_caches = quantized_decomposed_dequantize_per_tensor_default_1676 = None
2025-03-21T20:31:44.1543248Z             
2025-03-21T20:31:44.1544192Z              # File: <eval_with_key>.50:6774 in forward, code: copy__default_16 = torch.ops.aten.copy_.default(layers_8_attention_kv_cache_past_k_caches, dequantize_per_tensor_default_1512);  layers_8_attention_kv_cache_past_k_caches = dequantize_per_tensor_default_1512 = copy__default_16 = None
2025-03-21T20:31:44.1545249Z             aten_copy_default_16: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_copy_default(b_layers_8_attention_kv_cache_past_k_caches, quantized_decomposed_dequantize_per_tensor_default_1867);  b_layers_8_attention_kv_cache_past_k_caches = quantized_decomposed_dequantize_per_tensor_default_1867 = None
2025-03-21T20:31:44.1545354Z             
2025-03-21T20:31:44.1546288Z              # File: <eval_with_key>.50:6775 in forward, code: copy__default_17 = torch.ops.aten.copy_.default(layers_8_attention_kv_cache_past_v_caches, dequantize_per_tensor_default_1513);  layers_8_attention_kv_cache_past_v_caches = dequantize_per_tensor_default_1513 = copy__default_17 = None
2025-03-21T20:31:44.1547328Z             aten_copy_default_17: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_copy_default(b_layers_8_attention_kv_cache_past_v_caches, quantized_decomposed_dequantize_per_tensor_default_1880);  b_layers_8_attention_kv_cache_past_v_caches = quantized_decomposed_dequantize_per_tensor_default_1880 = None
2025-03-21T20:31:44.1547422Z             
2025-03-21T20:31:44.1548377Z              # File: <eval_with_key>.50:6776 in forward, code: copy__default_18 = torch.ops.aten.copy_.default(layers_9_attention_kv_cache_past_k_caches, dequantize_per_tensor_default_1676);  layers_9_attention_kv_cache_past_k_caches = dequantize_per_tensor_default_1676 = copy__default_18 = None
2025-03-21T20:31:44.1549403Z             aten_copy_default_18: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_copy_default(b_layers_9_attention_kv_cache_past_k_caches, quantized_decomposed_dequantize_per_tensor_default_2071);  b_layers_9_attention_kv_cache_past_k_caches = quantized_decomposed_dequantize_per_tensor_default_2071 = None
2025-03-21T20:31:44.1549510Z             
2025-03-21T20:31:44.1550446Z              # File: <eval_with_key>.50:6777 in forward, code: copy__default_19 = torch.ops.aten.copy_.default(layers_9_attention_kv_cache_past_v_caches, dequantize_per_tensor_default_1677);  layers_9_attention_kv_cache_past_v_caches = dequantize_per_tensor_default_1677 = copy__default_19 = None
2025-03-21T20:31:44.1551539Z             aten_copy_default_19: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_copy_default(b_layers_9_attention_kv_cache_past_v_caches, quantized_decomposed_dequantize_per_tensor_default_2084);  b_layers_9_attention_kv_cache_past_v_caches = quantized_decomposed_dequantize_per_tensor_default_2084 = None
2025-03-21T20:31:44.1551631Z             
2025-03-21T20:31:44.1552582Z              # File: <eval_with_key>.50:6778 in forward, code: copy__default_20 = torch.ops.aten.copy_.default(layers_10_attention_kv_cache_past_k_caches, dequantize_per_tensor_default_1840);  layers_10_attention_kv_cache_past_k_caches = dequantize_per_tensor_default_1840 = copy__default_20 = None
2025-03-21T20:31:44.1553611Z             aten_copy_default_20: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_copy_default(b_layers_10_attention_kv_cache_past_k_caches, quantized_decomposed_dequantize_per_tensor_default_2275);  b_layers_10_attention_kv_cache_past_k_caches = quantized_decomposed_dequantize_per_tensor_default_2275 = None
2025-03-21T20:31:44.1553713Z             
2025-03-21T20:31:44.1554669Z              # File: <eval_with_key>.50:6779 in forward, code: copy__default_21 = torch.ops.aten.copy_.default(layers_10_attention_kv_cache_past_v_caches, dequantize_per_tensor_default_1841);  layers_10_attention_kv_cache_past_v_caches = dequantize_per_tensor_default_1841 = copy__default_21 = None
2025-03-21T20:31:44.1555709Z             aten_copy_default_21: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_copy_default(b_layers_10_attention_kv_cache_past_v_caches, quantized_decomposed_dequantize_per_tensor_default_2288);  b_layers_10_attention_kv_cache_past_v_caches = quantized_decomposed_dequantize_per_tensor_default_2288 = None
2025-03-21T20:31:44.1555820Z             
2025-03-21T20:31:44.1556766Z              # File: <eval_with_key>.50:6780 in forward, code: copy__default_22 = torch.ops.aten.copy_.default(layers_11_attention_kv_cache_past_k_caches, dequantize_per_tensor_default_2004);  layers_11_attention_kv_cache_past_k_caches = dequantize_per_tensor_default_2004 = copy__default_22 = None
2025-03-21T20:31:44.1557797Z             aten_copy_default_22: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_copy_default(b_layers_11_attention_kv_cache_past_k_caches, quantized_decomposed_dequantize_per_tensor_default_2479);  b_layers_11_attention_kv_cache_past_k_caches = quantized_decomposed_dequantize_per_tensor_default_2479 = None
2025-03-21T20:31:44.1557898Z             
2025-03-21T20:31:44.1558832Z              # File: <eval_with_key>.50:6781 in forward, code: copy__default_23 = torch.ops.aten.copy_.default(layers_11_attention_kv_cache_past_v_caches, dequantize_per_tensor_default_2005);  layers_11_attention_kv_cache_past_v_caches = dequantize_per_tensor_default_2005 = copy__default_23 = None
2025-03-21T20:31:44.1559872Z             aten_copy_default_23: "f32[1, 128, 12, 64]" = executorch_exir_dialects_edge__ops_aten_copy_default(b_layers_11_attention_kv_cache_past_v_caches, quantized_decomposed_dequantize_per_tensor_default_2492);  b_layers_11_attention_kv_cache_past_v_caches = quantized_decomposed_dequantize_per_tensor_default_2492 = None
2025-03-21T20:31:44.1562161Z             return (aten_copy_default, aten_copy_default_1, aten_copy_default_2, aten_copy_default_3, aten_copy_default_4, aten_copy_default_5, aten_copy_default_6, aten_copy_default_7, aten_copy_default_8, aten_copy_default_9, aten_copy_default_10, aten_copy_default_11, aten_copy_default_12, aten_copy_default_13, aten_copy_default_14, aten_copy_default_15, aten_copy_default_16, aten_copy_default_17, aten_copy_default_18, aten_copy_default_19, aten_copy_default_20, aten_copy_default_21, aten_copy_default_22, aten_copy_default_23, quantized_decomposed_dequantize_per_tensor_default_2628)
2025-03-21T20:31:44.1562272Z             
2025-03-21T20:31:44.1667421Z Graph signature: ExportGraphSignature(input_specs=[InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param0'), target='_frozen_param0', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param1'), target='_frozen_param1', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param2'), target='_frozen_param2', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param3'), target='_frozen_param3', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param4'), target='_frozen_param4', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param5'), target='_frozen_param5', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param6'), target='_frozen_param6', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param7'), target='_frozen_param7', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param8'), target='_frozen_param8', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param9'), target='_frozen_param9', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param10'), target='_frozen_param10', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param11'), target='_frozen_param11', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param12'), target='_frozen_param12', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param13'), target='_frozen_param13', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param14'), target='_frozen_param14', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param15'), target='_frozen_param15', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param16'), target='_frozen_param16', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param17'), target='_frozen_param17', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param18'), target='_frozen_param18', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param19'), target='_frozen_param19', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param20'), target='_frozen_param20', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param21'), target='_frozen_param21', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param22'), target='_frozen_param22', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param23'), target='_frozen_param23', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param24'), target='_frozen_param24', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param25'), target='_frozen_param25', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param26'), target='_frozen_param26', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param27'), target='_frozen_param27', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param28'), target='_frozen_param28', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param29'), target='_frozen_param29', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param30'), target='_frozen_param30', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param31'), target='_frozen_param31', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param32'), target='_frozen_param32', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param33'), target='_frozen_param33', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param34'), target='_frozen_param34', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param35'), target='_frozen_param35', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param36'), target='_frozen_param36', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param37'), target='_frozen_param37', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param38'), target='_frozen_param38', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param39'), target='_frozen_param39', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param40'), target='_frozen_param40', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param41'), target='_frozen_param41', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param42'), target='_frozen_param42', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param43'), target='_frozen_param43', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param44'), target='_frozen_param44', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param45'), target='_frozen_param45', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param46'), target='_frozen_param46', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param47'), target='_frozen_param47', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param48'), target='_frozen_param48', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param49'), target='_frozen_param49', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param50'), target='_frozen_param50', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param51'), target='_frozen_param51', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param52'), target='_frozen_param52', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param53'), target='_frozen_param53', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param54'), target='_frozen_param54', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param55'), target='_frozen_param55', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param56'), target='_frozen_param56', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param57'), target='_frozen_param57', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param58'), target='_frozen_param58', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param59'), target='_frozen_param59', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param60'), target='_frozen_param60', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param61'), target='_frozen_param61', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param62'), target='_frozen_param62', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param63'), target='_frozen_param63', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param64'), target='_frozen_param64', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param65'), target='_frozen_param65', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param66'), target='_frozen_param66', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param67'), target='_frozen_param67', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param68'), target='_frozen_param68', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param69'), target='_frozen_param69', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param70'), target='_frozen_param70', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param71'), target='_frozen_param71', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param72'), target='_frozen_param72', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param73'), target='_frozen_param73', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param74'), target='_frozen_param74', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param75'), target='_frozen_param75', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param76'), target='_frozen_param76', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param77'), target='_frozen_param77', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param78'), target='_frozen_param78', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param79'), target='_frozen_param79', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param80'), target='_frozen_param80', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param81'), target='_frozen_param81', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param82'), target='_frozen_param82', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param83'), target='_frozen_param83', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param84'), target='_frozen_param84', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param85'), target='_frozen_param85', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param86'), target='_frozen_param86', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param87'), target='_frozen_param87', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param88'), target='_frozen_param88', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param89'), target='_frozen_param89', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param90'), target='_frozen_param90', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param91'), target='_frozen_param91', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param92'), target='_frozen_param92', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param93'), target='_frozen_param93', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param94'), target='_frozen_param94', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param95'), target='_frozen_param95', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param96'), target='_frozen_param96', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param97'), target='_frozen_param97', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param98'), target='_frozen_param98', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param99'), target='_frozen_param99', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param100'), target='_frozen_param100', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param101'), target='_frozen_param101', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param102'), target='_frozen_param102', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param103'), target='_frozen_param103', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param104'), target='_frozen_param104', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param105'), target='_frozen_param105', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param106'), target='_frozen_param106', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param107'), target='_frozen_param107', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param108'), target='_frozen_param108', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param109'), target='_frozen_param109', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param110'), target='_frozen_param110', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param111'), target='_frozen_param111', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param112'), target='_frozen_param112', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param113'), target='_frozen_param113', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param114'), target='_frozen_param114', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param115'), target='_frozen_param115', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param116'), target='_frozen_param116', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param117'), target='_frozen_param117', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param118'), target='_frozen_param118', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param119'), target='_frozen_param119', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param120'), target='_frozen_param120', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param121'), target='_frozen_param121', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param122'), target='_frozen_param122', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param123'), target='_frozen_param123', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param124'), target='_frozen_param124', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param125'), target='_frozen_param125', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param126'), target='_frozen_param126', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param127'), target='_frozen_param127', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param128'), target='_frozen_param128', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param129'), target='_frozen_param129', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param130'), target='_frozen_param130', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param131'), target='_frozen_param131', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param132'), target='_frozen_param132', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param133'), target='_frozen_param133', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param134'), target='_frozen_param134', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param135'), target='_frozen_param135', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param136'), target='_frozen_param136', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param137'), target='_frozen_param137', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param138'), target='_frozen_param138', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param139'), target='_frozen_param139', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param140'), target='_frozen_param140', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param141'), target='_frozen_param141', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param142'), target='_frozen_param142', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param143'), target='_frozen_param143', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param144'), target='_frozen_param144', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param145'), target='_frozen_param145', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param146'), target='_frozen_param146', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param147'), target='_frozen_param147', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param148'), target='_frozen_param148', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param149'), target='_frozen_param149', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param150'), target='_frozen_param150', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param151'), target='_frozen_param151', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param152'), target='_frozen_param152', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param153'), target='_frozen_param153', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param154'), target='_frozen_param154', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param155'), target='_frozen_param155', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param156'), target='_frozen_param156', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param157'), target='_frozen_param157', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param158'), target='_frozen_param158', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param159'), target='_frozen_param159', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b__frozen_param160'), target='_frozen_param160', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b_layers_0_attention_kv_cache_past_k_caches'), target='layers.0.attention.kv_cache.past_k_caches', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b_layers_0_attention_kv_cache_past_v_caches'), target='layers.0.attention.kv_cache.past_v_caches', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b_layers_1_attention_kv_cache_past_k_caches'), target='layers.1.attention.kv_cache.past_k_caches', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b_layers_1_attention_kv_cache_past_v_caches'), target='layers.1.attention.kv_cache.past_v_caches', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b_layers_2_attention_kv_cache_past_k_caches'), target='layers.2.attention.kv_cache.past_k_caches', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b_layers_2_attention_kv_cache_past_v_caches'), target='layers.2.attention.kv_cache.past_v_caches', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b_layers_3_attention_kv_cache_past_k_caches'), target='layers.3.attention.kv_cache.past_k_caches', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b_layers_3_attention_kv_cache_past_v_caches'), target='layers.3.attention.kv_cache.past_v_caches', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b_layers_4_attention_kv_cache_past_k_caches'), target='layers.4.attention.kv_cache.past_k_caches', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b_layers_4_attention_kv_cache_past_v_caches'), target='layers.4.attention.kv_cache.past_v_caches', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b_layers_5_attention_kv_cache_past_k_caches'), target='layers.5.attention.kv_cache.past_k_caches', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b_layers_5_attention_kv_cache_past_v_caches'), target='layers.5.attention.kv_cache.past_v_caches', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b_layers_6_attention_kv_cache_past_k_caches'), target='layers.6.attention.kv_cache.past_k_caches', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b_layers_6_attention_kv_cache_past_v_caches'), target='layers.6.attention.kv_cache.past_v_caches', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b_layers_7_attention_kv_cache_past_k_caches'), target='layers.7.attention.kv_cache.past_k_caches', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b_layers_7_attention_kv_cache_past_v_caches'), target='layers.7.attention.kv_cache.past_v_caches', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b_layers_8_attention_kv_cache_past_k_caches'), target='layers.8.attention.kv_cache.past_k_caches', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b_layers_8_attention_kv_cache_past_v_caches'), target='layers.8.attention.kv_cache.past_v_caches', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b_layers_9_attention_kv_cache_past_k_caches'), target='layers.9.attention.kv_cache.past_k_caches', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b_layers_9_attention_kv_cache_past_v_caches'), target='layers.9.attention.kv_cache.past_v_caches', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b_layers_10_attention_kv_cache_past_k_caches'), target='layers.10.attention.kv_cache.past_k_caches', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b_layers_10_attention_kv_cache_past_v_caches'), target='layers.10.attention.kv_cache.past_v_caches', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b_layers_11_attention_kv_cache_past_k_caches'), target='layers.11.attention.kv_cache.past_k_caches', persistent=True), InputSpec(kind=<InputKind.BUFFER: 3>, arg=TensorArgument(name='b_layers_11_attention_kv_cache_past_v_caches'), target='layers.11.attention.kv_cache.past_v_caches', persistent=True), InputSpec(kind=<InputKind.USER_INPUT: 1>, arg=TensorArgument(name='tokens'), target=None, persistent=None), InputSpec(kind=<InputKind.USER_INPUT: 1>, arg=TensorArgument(name='attn_options_input_pos'), target=None, persistent=None)], output_specs=[OutputSpec(kind=<OutputKind.BUFFER_MUTATION: 3>, arg=TensorArgument(name='aten_copy_default'), target='layers.0.attention.kv_cache.past_k_caches'), OutputSpec(kind=<OutputKind.BUFFER_MUTATION: 3>, arg=TensorArgument(name='aten_copy_default_1'), target='layers.0.attention.kv_cache.past_v_caches'), OutputSpec(kind=<OutputKind.BUFFER_MUTATION: 3>, arg=TensorArgument(name='aten_copy_default_2'), target='layers.1.attention.kv_cache.past_k_caches'), OutputSpec(kind=<OutputKind.BUFFER_MUTATION: 3>, arg=TensorArgument(name='aten_copy_default_3'), target='layers.1.attention.kv_cache.past_v_caches'), OutputSpec(kind=<OutputKind.BUFFER_MUTATION: 3>, arg=TensorArgument(name='aten_copy_default_4'), target='layers.2.attention.kv_cache.past_k_caches'), OutputSpec(kind=<OutputKind.BUFFER_MUTATION: 3>, arg=TensorArgument(name='aten_copy_default_5'), target='layers.2.attention.kv_cache.past_v_caches'), OutputSpec(kind=<OutputKind.BUFFER_MUTATION: 3>, arg=TensorArgument(name='aten_copy_default_6'), target='layers.3.attention.kv_cache.past_k_caches'), OutputSpec(kind=<OutputKind.BUFFER_MUTATION: 3>, arg=TensorArgument(name='aten_copy_default_7'), target='layers.3.attention.kv_cache.past_v_caches'), OutputSpec(kind=<OutputKind.BUFFER_MUTATION: 3>, arg=TensorArgument(name='aten_copy_default_8'), target='layers.4.attention.kv_cache.past_k_caches'), OutputSpec(kind=<OutputKind.BUFFER_MUTATION: 3>, arg=TensorArgument(name='aten_copy_default_9'), target='layers.4.attention.kv_cache.past_v_caches'), OutputSpec(kind=<OutputKind.BUFFER_MUTATION: 3>, arg=TensorArgument(name='aten_copy_default_10'), target='layers.5.attention.kv_cache.past_k_caches'), OutputSpec(kind=<OutputKind.BUFFER_MUTATION: 3>, arg=TensorArgument(name='aten_copy_default_11'), target='layers.5.attention.kv_cache.past_v_caches'), OutputSpec(kind=<OutputKind.BUFFER_MUTATION: 3>, arg=TensorArgument(name='aten_copy_default_12'), target='layers.6.attention.kv_cache.past_k_caches'), OutputSpec(kind=<OutputKind.BUFFER_MUTATION: 3>, arg=TensorArgument(name='aten_copy_default_13'), target='layers.6.attention.kv_cache.past_v_caches'), OutputSpec(kind=<OutputKind.BUFFER_MUTATION: 3>, arg=TensorArgument(name='aten_copy_default_14'), target='layers.7.attention.kv_cache.past_k_caches'), OutputSpec(kind=<OutputKind.BUFFER_MUTATION: 3>, arg=TensorArgument(name='aten_copy_default_15'), target='layers.7.attention.kv_cache.past_v_caches'), OutputSpec(kind=<OutputKind.BUFFER_MUTATION: 3>, arg=TensorArgument(name='aten_copy_default_16'), target='layers.8.attention.kv_cache.past_k_caches'), OutputSpec(kind=<OutputKind.BUFFER_MUTATION: 3>, arg=TensorArgument(name='aten_copy_default_17'), target='layers.8.attention.kv_cache.past_v_caches'), OutputSpec(kind=<OutputKind.BUFFER_MUTATION: 3>, arg=TensorArgument(name='aten_copy_default_18'), target='layers.9.attention.kv_cache.past_k_caches'), OutputSpec(kind=<OutputKind.BUFFER_MUTATION: 3>, arg=TensorArgument(name='aten_copy_default_19'), target='layers.9.attention.kv_cache.past_v_caches'), OutputSpec(kind=<OutputKind.BUFFER_MUTATION: 3>, arg=TensorArgument(name='aten_copy_default_20'), target='layers.10.attention.kv_cache.past_k_caches'), OutputSpec(kind=<OutputKind.BUFFER_MUTATION: 3>, arg=TensorArgument(name='aten_copy_default_21'), target='layers.10.attention.kv_cache.past_v_caches'), OutputSpec(kind=<OutputKind.BUFFER_MUTATION: 3>, arg=TensorArgument(name='aten_copy_default_22'), target='layers.11.attention.kv_cache.past_k_caches'), OutputSpec(kind=<OutputKind.BUFFER_MUTATION: 3>, arg=TensorArgument(name='aten_copy_default_23'), target='layers.11.attention.kv_cache.past_v_caches'), OutputSpec(kind=<OutputKind.USER_OUTPUT: 1>, arg=TensorArgument(name='quantized_decomposed_dequantize_per_tensor_default_2628'), target=None)])
2025-03-21T20:31:56.6286112Z Range constraints: {}
2025-03-21T20:31:56.6286366Z 
2025-03-21T20:31:56.6286696Z [INFO 2025-03-21 20:31:55,946 export_llama_lib.py:813] Lowering model using following partitioner(s): 
2025-03-21T20:31:56.6287333Z [INFO 2025-03-21 20:31:55,946 export_llama_lib.py:815] --> QnnPartitioner
2025-03-21T20:31:56.6287820Z [INFO] [Qnn ExecuTorch]: create QNN Logger with log_level 2
2025-03-21T20:31:56.6288299Z [WARNING] [Qnn ExecuTorch]: QnnDsp <W> Initializing HtpProvider
2025-03-21T20:31:56.6288617Z 
2025-03-21T20:31:56.6288917Z [INFO] [Qnn ExecuTorch]: Initialize Qnn backend parameters for Qnn executorch backend type 2
2025-03-21T20:31:56.6289565Z [INFO] [Qnn ExecuTorch]: Caching: Caching is in SAVE MODE.
2025-03-21T20:31:56.6290090Z [WARNING] [Qnn ExecuTorch]: QnnDsp <W> Performance Estimates unsupported
2025-03-21T20:31:56.6290439Z 
2025-03-21T20:31:56.6291104Z [WARNING] [Qnn ExecuTorch]: QnnDsp <W> Arch 68 set by custom config is different from arch associated with SoC 57, will overwrite it to 75
2025-03-21T20:31:56.6291660Z 
2025-03-21T20:31:56.6291832Z [INFO] [Qnn ExecuTorch]: Running level=3 optimization.
2025-03-21T20:31:56.6292447Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:56.6292933Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6293419Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:56.6293910Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6294389Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:56.6294940Z [QNN Partitioner Op Support]: aten.rms_norm.default | True
2025-03-21T20:31:56.6295406Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6295843Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:56.6296294Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:56.6296780Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6297272Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:56.6297762Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6298262Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:56.6298714Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:56.6299157Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:56.6299637Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6300131Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:56.6300623Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6301112Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:56.6301579Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:56.6302019Z [QNN Partitioner Op Support]: aten.sigmoid.default | True
2025-03-21T20:31:56.6302484Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:56.6302962Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6303457Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:56.6303987Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6304573Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:56.6305061Z [QNN Partitioner Op Support]: aten.rms_norm.default | True
2025-03-21T20:31:56.6305505Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:56.6305950Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:56.6306429Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6307116Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:56.6307620Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6308126Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:56.6308608Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:56.6309096Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6309571Z [QNN Partitioner Op Support]: aten.matmul.default | True
2025-03-21T20:31:56.6310032Z [QNN Partitioner Op Support]: aten._softmax.default | True
2025-03-21T20:31:56.6310482Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:56.6310893Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:56.6311337Z [QNN Partitioner Op Support]: aten.matmul.default | True
2025-03-21T20:31:56.6311816Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6312347Z [QNN Partitioner Op Support]: aten.index.Tensor | True
2025-03-21T20:31:56.6312881Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:56.6313320Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:56.6313807Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6314263Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6314734Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6315205Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6315660Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6316119Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6316595Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6317078Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6317546Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6318020Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6318459Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6318929Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6319401Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6319855Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6320360Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6320940Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6321379Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6321848Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6322323Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6322779Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6323252Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6323725Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6324179Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6324652Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6325122Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6325574Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6326047Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6326514Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6326964Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6327434Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6327912Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6328367Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6328915Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6329460Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6329918Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6330399Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6330886Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:56.6331377Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:56.6331900Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6332556Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6333035Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6333521Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6333981Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6334438Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6334917Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6335367Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6335920Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6336396Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6336834Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6337305Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6337779Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6338229Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6338703Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6339221Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6339659Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6340129Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6340602Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6341051Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6341527Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6341985Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6342473Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6343064Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6343537Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6343988Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6344462Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6344927Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6345382Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6345857Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6346331Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6346786Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6347242Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6347714Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6348166Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.6355539Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6356172Z [QNN Partitioner Op Support]: aten.index_put.default | True
2025-03-21T20:31:56.6356649Z [QNN Partitioner Op Support]: aten.index_put.default | True
2025-03-21T20:31:56.6357152Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.6357627Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:56.6358202Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:56.6358730Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:56.7773430Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:56.7774136Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:56.7774600Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:56.7775076Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:56.7775621Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:56.7776092Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:56.7776516Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:56.7776930Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:56.7777338Z [QNN Partitioner Op Support]: aten.sub.Tensor | True
2025-03-21T20:31:56.7777754Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:56.7778182Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:56.7778599Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:56.7779019Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:56.7779556Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:56.7779978Z [QNN Partitioner Op Support]: aten.sub.Tensor | True
2025-03-21T20:31:56.7780394Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:56.7780856Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:56.7781438Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:56.7781936Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:56.7782406Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:56.7782954Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:56.7783422Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:56.7783899Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:56.7784370Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:56.7784823Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:56.7785294Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:56.7785761Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:56.7786226Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:56.7786692Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:56.7787148Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:56.7787618Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:56.7788087Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:56.7788550Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:56.7789029Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.7789533Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:56.7790102Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.7790692Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:56.7791185Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:56.7791664Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.7792153Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:56.7792635Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.7793141Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:56.7793638Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:56.7794122Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.7794615Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:56.7795236Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.7795729Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:56.7796221Z [QNN Partitioner Op Support]: aten.rms_norm.default | True
2025-03-21T20:31:56.7796664Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:56.7797106Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:56.7797586Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.7798068Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:56.7798560Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.7799061Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:56.7799534Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:56.7799980Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:56.7800454Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.7801098Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:56.7801597Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.7802206Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:56.7802683Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:56.7803122Z [QNN Partitioner Op Support]: aten.sigmoid.default | True
2025-03-21T20:31:56.7803574Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:56.7804057Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.7804553Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:56.7805082Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.7805582Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:56.7806055Z [QNN Partitioner Op Support]: aten.rms_norm.default | True
2025-03-21T20:31:56.7806501Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:56.7806950Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:56.7807441Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.7807938Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:56.7808433Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.7808924Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:56.7809503Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:56.7810107Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.7810634Z [QNN Partitioner Op Support]: aten.matmul.default | True
2025-03-21T20:31:56.7811100Z [QNN Partitioner Op Support]: aten._softmax.default | True
2025-03-21T20:31:56.7811591Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:56.7812067Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:56.7812500Z [QNN Partitioner Op Support]: aten.matmul.default | True
2025-03-21T20:31:56.7813017Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.7813501Z [QNN Partitioner Op Support]: aten.index.Tensor | True
2025-03-21T20:31:56.7813996Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:56.7814489Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:56.7814936Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.7815450Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.7815978Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.7816457Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.7816963Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.7817503Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.7818072Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.7818615Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.7819182Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.7819673Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.7820155Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.7820677Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.7821150Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.7821663Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.7822192Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.7822657Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.7823172Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.7823706Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.7824187Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.7824703Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.7825258Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.7825734Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.7826245Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.7826768Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.7827239Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.7827750Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.7828272Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.7828778Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.7829320Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.7829905Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.7830389Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.7830829Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.7831300Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.7831777Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.7832387Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.7832888Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.7833379Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:56.7833823Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:56.7834271Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.7834726Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.7835202Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.7835684Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.7836127Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.7836607Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.7837083Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.7837537Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.7838014Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.7838512Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.7839080Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.7839611Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.7840145Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.7840603Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.9312746Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.9313351Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.9313816Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.9314303Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.9314766Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.9315221Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.9315697Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.9316172Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.9316629Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.9317111Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.9317574Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.9318029Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.9318519Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.9318991Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.9319510Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.9319978Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.9320500Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.9320954Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.9321423Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.9321894Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.9322351Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.9322855Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.9323355Z [QNN Partitioner Op Support]: aten.index_put.default | True
2025-03-21T20:31:56.9323837Z [QNN Partitioner Op Support]: aten.index_put.default | True
2025-03-21T20:31:56.9324324Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.9324812Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:56.9325272Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:56.9325736Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:56.9326257Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:56.9326760Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:56.9327218Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:56.9327693Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:56.9328197Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:56.9328672Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:56.9329096Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:56.9329615Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:56.9330033Z [QNN Partitioner Op Support]: aten.sub.Tensor | True
2025-03-21T20:31:56.9330458Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:56.9330861Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:56.9331351Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:56.9331769Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:56.9332182Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:56.9332769Z [QNN Partitioner Op Support]: aten.sub.Tensor | True
2025-03-21T20:31:56.9333173Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:56.9333589Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:56.9334037Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:56.9334510Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:56.9335110Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:56.9335567Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:56.9336038Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:56.9336503Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:56.9336971Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:56.9337436Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:56.9337905Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:56.9338366Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:56.9338836Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:56.9339307Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:56.9339776Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:56.9340250Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:56.9340769Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:56.9341237Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:56.9341761Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.9342258Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:56.9342758Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.9343264Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:56.9343746Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:56.9344232Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.9344727Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:56.9345264Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.9345801Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:56.9346300Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:56.9346786Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.9347272Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:56.9347778Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.9348281Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:56.9348767Z [QNN Partitioner Op Support]: aten.rms_norm.default | True
2025-03-21T20:31:56.9349208Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:56.9349737Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:56.9350215Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.9350709Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:56.9351199Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.9351705Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:56.9352170Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:56.9352604Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:56.9353091Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.9353587Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:56.9354077Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.9354577Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:56.9355031Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:56.9355470Z [QNN Partitioner Op Support]: aten.sigmoid.default | True
2025-03-21T20:31:56.9355932Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:56.9356412Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.9356902Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:56.9357455Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.9357960Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:56.9358453Z [QNN Partitioner Op Support]: aten.rms_norm.default | True
2025-03-21T20:31:56.9358895Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:56.9359340Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:56.9359823Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.9360359Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:56.9360946Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.9361455Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:56.9361956Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:56.9362441Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.9362907Z [QNN Partitioner Op Support]: aten.matmul.default | True
2025-03-21T20:31:56.9363372Z [QNN Partitioner Op Support]: aten._softmax.default | True
2025-03-21T20:31:56.9363853Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:56.9364339Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:56.9364775Z [QNN Partitioner Op Support]: aten.matmul.default | True
2025-03-21T20:31:56.9365246Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.9365702Z [QNN Partitioner Op Support]: aten.index.Tensor | True
2025-03-21T20:31:56.9366165Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:56.9366621Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:56.9367101Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.9367560Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.9368025Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.9368510Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.9368966Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.9369587Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.9370070Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.9370514Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.9370991Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.9371472Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.9371930Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.9372406Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.9372885Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.9373326Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.9373799Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.9374287Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.9374741Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.9375216Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.9375677Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.9376128Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.9376600Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:56.9377071Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.9377520Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:56.9377997Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.0839748Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.0840616Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.0841798Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.0842584Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.0843409Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.0844285Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.0845173Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.0846022Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.0846915Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.0847786Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.0848621Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.0849459Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.0850370Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.0851185Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:57.0852012Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.0852869Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.0853908Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.0854725Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.0855541Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.0856419Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.0857241Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.0858059Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.0858950Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.0859918Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.0860816Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.0861722Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.0862563Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.0863429Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.0864287Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.0865024Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.0865759Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.0866602Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.0867461Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.0868201Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.0869041Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.0869897Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.0870691Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.0871581Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.0872477Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.0873212Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.0874098Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.0874992Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.0875766Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.0876512Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.0877381Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.0878198Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.0879054Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.0879900Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.0880859Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.0881637Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.0882503Z [QNN Partitioner Op Support]: aten.index_put.default | True
2025-03-21T20:31:57.0883371Z [QNN Partitioner Op Support]: aten.index_put.default | True
2025-03-21T20:31:57.0884206Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.0885117Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.0885912Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:57.0886716Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.0887685Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.0888587Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.0889526Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:57.0890394Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.0891304Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.0892180Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:57.0893054Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.0893810Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.0894598Z [QNN Partitioner Op Support]: aten.sub.Tensor | True
2025-03-21T20:31:57.0895362Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.0896090Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.0896864Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:57.0897646Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.0898479Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.0899241Z [QNN Partitioner Op Support]: aten.sub.Tensor | True
2025-03-21T20:31:57.0899999Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.0900735Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.0901572Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.0902445Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.0903314Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.0904198Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.0905017Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:57.0905896Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:57.0906785Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.0907618Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.0908516Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.0909369Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:57.0910226Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:57.0911117Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.0911970Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.0912842Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.0913720Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.0914554Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.0915457Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.0916367Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:57.0917279Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.0918237Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.0919119Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.0920028Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.0921103Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:57.0922039Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.0922967Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.0923846Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.0924747Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.0925652Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:57.0926585Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.0927519Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.0928398Z [QNN Partitioner Op Support]: aten.rms_norm.default | True
2025-03-21T20:31:57.0929228Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:57.0930113Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.0931026Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.0931953Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:57.0933133Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.0934083Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.0934957Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.0935766Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.0936678Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.0937534Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:57.0938461Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.0939499Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.0940346Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.0941177Z [QNN Partitioner Op Support]: aten.sigmoid.default | True
2025-03-21T20:31:57.0942036Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.0942787Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.0943603Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:57.0944516Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.0945439Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.0946305Z [QNN Partitioner Op Support]: aten.rms_norm.default | True
2025-03-21T20:31:57.0947076Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:57.0947876Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.0948651Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.0949542Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:57.0950456Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.0951342Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.0952277Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.0953134Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.0953991Z [QNN Partitioner Op Support]: aten.matmul.default | True
2025-03-21T20:31:57.0954851Z [QNN Partitioner Op Support]: aten._softmax.default | True
2025-03-21T20:31:57.0955657Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:57.0956425Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.0957236Z [QNN Partitioner Op Support]: aten.matmul.default | True
2025-03-21T20:31:57.2398384Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.2399304Z [QNN Partitioner Op Support]: aten.index.Tensor | True
2025-03-21T20:31:57.2400128Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.2400948Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:57.2402058Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2402887Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2403754Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.2404622Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2405470Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2406308Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.2407144Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2407997Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2408830Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.2409835Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2410685Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2411518Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.2412411Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2413245Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2414244Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.2415148Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2415948Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2416685Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.2417535Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2418360Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2419333Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.2420186Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2420988Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2421874Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.2422642Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2423440Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2424298Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.2425135Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2425994Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2426893Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.2427670Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2428521Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2429414Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.2430272Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2431132Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2431990Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.2432967Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.2433787Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:57.2434584Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2435394Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2436252Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.2437086Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2437917Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2438683Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.2439518Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2440337Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2441376Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.2442272Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2443117Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2443835Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.2444591Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2445304Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2446130Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.2446888Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2447601Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2448404Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.2449344Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2450166Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2450956Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.2451690Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2452628Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2453494Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.2454331Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2455146Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2455997Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.2456855Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2457590Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2458552Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.2459413Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2460274Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2461169Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.2462052Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2462814Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.2463657Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.2464582Z [QNN Partitioner Op Support]: aten.index_put.default | True
2025-03-21T20:31:57.2465389Z [QNN Partitioner Op Support]: aten.index_put.default | True
2025-03-21T20:31:57.2466141Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.2466958Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.2467701Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:57.2468445Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.2469261Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.2470132Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.2470947Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:57.2471796Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.2472689Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.2473561Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:57.2474341Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.2475118Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.2475899Z [QNN Partitioner Op Support]: aten.sub.Tensor | True
2025-03-21T20:31:57.2476659Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.2477369Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.2478029Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:57.2478680Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.2479567Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.2480240Z [QNN Partitioner Op Support]: aten.sub.Tensor | True
2025-03-21T20:31:57.2480894Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.2481532Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.2482250Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.2483063Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.2483829Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.2484585Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.2485407Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:57.2486267Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:57.2487141Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.2488037Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.2488900Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.2489870Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:57.2490776Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:57.2491662Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.2492500Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.2493232Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.2493971Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.2494780Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.2495682Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.2496466Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:57.2497309Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.2498235Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.2499127Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.2499887Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.2500648Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:57.2501507Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.2502424Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.2503291Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.2504160Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.2505046Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:57.2505940Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.2506767Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.2507627Z [QNN Partitioner Op Support]: aten.rms_norm.default | True
2025-03-21T20:31:57.2508434Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:57.2509216Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.2510124Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.2511044Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:57.2511802Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.3989664Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.3990556Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.3991371Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.3992279Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.3993079Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:57.3994228Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.3995298Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.3996175Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.3997013Z [QNN Partitioner Op Support]: aten.sigmoid.default | True
2025-03-21T20:31:57.3997784Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.3998674Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.3999606Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:57.4000493Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.4001445Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.4002331Z [QNN Partitioner Op Support]: aten.rms_norm.default | True
2025-03-21T20:31:57.4003018Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:57.4003755Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.4004658Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.4005549Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:57.4006597Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.4007514Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.4008409Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.4009205Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.4010123Z [QNN Partitioner Op Support]: aten.matmul.default | True
2025-03-21T20:31:57.4010952Z [QNN Partitioner Op Support]: aten._softmax.default | True
2025-03-21T20:31:57.4011730Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:57.4012632Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.4013443Z [QNN Partitioner Op Support]: aten.matmul.default | True
2025-03-21T20:31:57.4014216Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.4015089Z [QNN Partitioner Op Support]: aten.index.Tensor | True
2025-03-21T20:31:57.4015936Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.4016734Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:57.4017417Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4018221Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4019078Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.4019935Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4020740Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4021572Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.4022461Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4023219Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4024034Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.4024895Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4025690Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4026557Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.4027445Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4028231Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4029050Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.4029936Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4030750Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4031481Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.4032520Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4033341Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4034418Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.4035252Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4036062Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4036924Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.4037709Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4038495Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4039338Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.4040177Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4041022Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4041914Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.4042701Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4043566Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4044437Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.4045392Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4046139Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4046993Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.4047873Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.4048654Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:57.4049574Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4050388Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4051378Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.4052145Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4052960Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4053829Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.4054655Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4055511Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4056368Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.4057166Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4057993Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4058877Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.4059641Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4060398Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4061269Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.4062121Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4062932Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4063784Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.4064654Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4065410Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4066207Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.4067050Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4067859Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4068712Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.4069608Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4070424Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4071239Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.4072126Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4073702Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4074595Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.4075396Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4076110Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4076954Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.4077821Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4078615Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.4079457Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.4080328Z [QNN Partitioner Op Support]: aten.index_put.default | True
2025-03-21T20:31:57.4081174Z [QNN Partitioner Op Support]: aten.index_put.default | True
2025-03-21T20:31:57.4081958Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.4082826Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.4083654Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:57.4084483Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.4085549Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.4086422Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.4087096Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:57.4087840Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.4088718Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.4089575Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:57.4090358Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.4091002Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.4091713Z [QNN Partitioner Op Support]: aten.sub.Tensor | True
2025-03-21T20:31:57.4092463Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.4093224Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.4093895Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:57.4094552Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.4095247Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.4095996Z [QNN Partitioner Op Support]: aten.sub.Tensor | True
2025-03-21T20:31:57.4096749Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.4097476Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.4098249Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.4099087Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.4099951Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.4100717Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.4101547Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:57.4102380Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:57.4103259Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.4104144Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.4105020Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.5666644Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:57.5667546Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:57.5668395Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.5669271Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.5670046Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.5670918Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.5671750Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.5672914Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5673856Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:57.5674781Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5675640Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.5676562Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.5677429Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5678364Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:57.5679308Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5680202Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.5681140Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.5682028Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5682969Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:57.5683915Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5684912Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.5685744Z [QNN Partitioner Op Support]: aten.rms_norm.default | True
2025-03-21T20:31:57.5686552Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:57.5687331Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.5688194Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5689086Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:57.5690049Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5691107Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.5691843Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.5692632Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.5693510Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5694388Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:57.5695320Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5696257Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.5697033Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.5697855Z [QNN Partitioner Op Support]: aten.sigmoid.default | True
2025-03-21T20:31:57.5698731Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.5699607Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5700556Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:57.5701418Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5702222Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.5703137Z [QNN Partitioner Op Support]: aten.rms_norm.default | True
2025-03-21T20:31:57.5703928Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:57.5704734Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.5705602Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5706474Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:57.5707398Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5708226Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.5709088Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.5709958Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5710787Z [QNN Partitioner Op Support]: aten.matmul.default | True
2025-03-21T20:31:57.5711645Z [QNN Partitioner Op Support]: aten._softmax.default | True
2025-03-21T20:31:57.5712634Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:57.5713333Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.5714131Z [QNN Partitioner Op Support]: aten.matmul.default | True
2025-03-21T20:31:57.5715013Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5715860Z [QNN Partitioner Op Support]: aten.index.Tensor | True
2025-03-21T20:31:57.5716700Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.5717538Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:57.5718230Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5719010Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5719866Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5720726Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5721523Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5722372Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5723231Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5724135Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5724907Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5725749Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5726576Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5727396Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5728283Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5729103Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5730054Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5730938Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5731780Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5732765Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5733549Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5734378Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5735236Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5736078Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5736885Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5737741Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5738586Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5739327Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5740162Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5741021Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5741957Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5742912Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5744141Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5745128Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5746097Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5747120Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5760666Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5761558Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5762409Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.5763264Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:57.5764065Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5764827Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5765924Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5766824Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5767641Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5768517Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5769492Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5770209Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5770993Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5771862Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5772675Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5773512Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5774358Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5775171Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5776039Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5776950Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5777733Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5778588Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5779421Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5780271Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5781162Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5781953Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5782893Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5783766Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5784629Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5785491Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5786330Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5787062Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5787886Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5788752Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5789578Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5790381Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5791209Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5792083Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5792863Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.5793640Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.5794520Z [QNN Partitioner Op Support]: aten.index_put.default | True
2025-03-21T20:31:57.5795370Z [QNN Partitioner Op Support]: aten.index_put.default | True
2025-03-21T20:31:57.5796220Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.7334872Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.7335800Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:57.7336655Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.7337586Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.7338386Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.7339184Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:57.7340069Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.7340959Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.7341827Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:57.7342890Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.7343670Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.7344448Z [QNN Partitioner Op Support]: aten.sub.Tensor | True
2025-03-21T20:31:57.7345195Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.7345962Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.7346737Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:57.7347488Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.7348130Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.7348784Z [QNN Partitioner Op Support]: aten.sub.Tensor | True
2025-03-21T20:31:57.7349511Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.7350277Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.7351061Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.7351909Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.7352737Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.7353742Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.7354553Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:57.7355341Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:57.7356193Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.7357035Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.7357878Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.7358752Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:57.7359705Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:57.7360578Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.7361448Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.7362308Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.7363176Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.7364067Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.7364846Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.7365636Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:57.7366527Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.7367429Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.7368287Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.7369147Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.7370134Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:57.7371046Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.7371897Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.7372741Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.7373625Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.7374503Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:57.7375432Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.7376370Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.7377120Z [QNN Partitioner Op Support]: aten.rms_norm.default | True
2025-03-21T20:31:57.7377811Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:57.7378535Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.7379379Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.7380164Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:57.7381152Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.7382036Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.7382898Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.7383698Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.7384433Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.7385256Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:57.7386153Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.7387044Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.7387873Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.7388660Z [QNN Partitioner Op Support]: aten.sigmoid.default | True
2025-03-21T20:31:57.7389503Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.7390379Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.7391187Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:57.7392068Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.7393111Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.7393990Z [QNN Partitioner Op Support]: aten.rms_norm.default | True
2025-03-21T20:31:57.7394816Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:57.7395599Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.7396435Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.7397371Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:57.7398273Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.7399309Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.7400231Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.7400989Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.7401739Z [QNN Partitioner Op Support]: aten.matmul.default | True
2025-03-21T20:31:57.7402571Z [QNN Partitioner Op Support]: aten._softmax.default | True
2025-03-21T20:31:57.7403353Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:57.7404108Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.7404861Z [QNN Partitioner Op Support]: aten.matmul.default | True
2025-03-21T20:31:57.7405698Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.7406555Z [QNN Partitioner Op Support]: aten.index.Tensor | True
2025-03-21T20:31:57.7407361Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.7408101Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:57.7408886Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.7409786Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.7410624Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.7411510Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.7412354Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.7413154Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.7414023Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.7414865Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.7415722Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.7416611Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.7417429Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.7418167Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.7418930Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.7419904Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.7420751Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.7421584Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.7422398Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.7423250Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.7424115Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.7424850Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.7425685Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.7426558Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.7427339Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.7428223Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.7429116Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.7429822Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.7430568Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.7431444Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.7432428Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.7433195Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.7433948Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.7434704Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.7435552Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.7436446Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.7437304Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.7438060Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.7438923Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.7439731Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:57.7440531Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.7441338Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.7442187Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.7443066Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.7443809Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.7444601Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.7445462Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.7446282Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.7447148Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.7448032Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.7448860Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.9039684Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.9040617Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.9041431Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.9042357Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.9043176Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.9043912Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.9044758Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.9045633Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.9046429Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.9047321Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.9048174Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.9049366Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.9050252Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.9051123Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.9051971Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.9052866Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.9053627Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.9054324Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.9055165Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.9056013Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.9056848Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.9057693Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.9058535Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.9059366Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.9060360Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.9061149Z [QNN Partitioner Op Support]: aten.index_put.default | True
2025-03-21T20:31:57.9061984Z [QNN Partitioner Op Support]: aten.index_put.default | True
2025-03-21T20:31:57.9062861Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.9063708Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.9064556Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:57.9065422Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.9066341Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.9067114Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.9067880Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:57.9068679Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.9069513Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.9070279Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:57.9071016Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.9071766Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.9072512Z [QNN Partitioner Op Support]: aten.sub.Tensor | True
2025-03-21T20:31:57.9073148Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.9073803Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.9074545Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:57.9075281Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.9076025Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.9076749Z [QNN Partitioner Op Support]: aten.sub.Tensor | True
2025-03-21T20:31:57.9077501Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.9078234Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.9079069Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.9079853Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.9080638Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.9081481Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.9082331Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:57.9083168Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:57.9084038Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.9084881Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.9085698Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.9086701Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:57.9087610Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:57.9088474Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.9089448Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.9090202Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.9090912Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.9091747Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.9092617Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.9093494Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:57.9094371Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.9095287Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.9096201Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.9097059Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.9097859Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:57.9098870Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.9099748Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.9100673Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.9101576Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.9102404Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:57.9103321Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.9104272Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.9105274Z [QNN Partitioner Op Support]: aten.rms_norm.default | True
2025-03-21T20:31:57.9106108Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:57.9106920Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.9107638Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.9108449Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:57.9109355Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.9110253Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.9111082Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.9111871Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.9112716Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.9113646Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:57.9114468Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.9115347Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.9116195Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.9116956Z [QNN Partitioner Op Support]: aten.sigmoid.default | True
2025-03-21T20:31:57.9117816Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.9118725Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.9119544Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:57.9120305Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.9121104Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.9121940Z [QNN Partitioner Op Support]: aten.rms_norm.default | True
2025-03-21T20:31:57.9122654Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:57.9123348Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:57.9124158Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.9125040Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:57.9126096Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.9126873Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:57.9127691Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.9128573Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.9129517Z [QNN Partitioner Op Support]: aten.matmul.default | True
2025-03-21T20:31:57.9130318Z [QNN Partitioner Op Support]: aten._softmax.default | True
2025-03-21T20:31:57.9131097Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:57.9131838Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:57.9132856Z [QNN Partitioner Op Support]: aten.matmul.default | True
2025-03-21T20:31:57.9133724Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.9134466Z [QNN Partitioner Op Support]: aten.index.Tensor | True
2025-03-21T20:31:57.9135253Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:57.9136097Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:57.9136858Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.9137855Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.9138745Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.9139537Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.9140380Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.9141263Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.9142132Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.9142984Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.9143903Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.9144626Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.9145402Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.9146256Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.9147106Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.9147895Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.9148718Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.9149562Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.9150406Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.9151183Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:57.9151990Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.9152815Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:57.9153633Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.0761313Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.0762202Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.0763052Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.0763951Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.0764825Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.0765601Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.0766441Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.0767251Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.0768079Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.0768966Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.0769920Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.0770712Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.0771909Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.0772708Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.0773600Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.0774534Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.0775311Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:58.0776143Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.0776981Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.0777875Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.0778774Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.0779636Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.0780536Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.0781406Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.0782153Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.0783037Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.0784024Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.0784880Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.0785758Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.0786661Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.0787429Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.0788159Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.0789003Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.0789945Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.0790768Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.0791618Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.0792434Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.0793279Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.0794182Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.0794937Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.0795692Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.0796529Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.0797365Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.0798185Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.0799078Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.0799908Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.0800702Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.0801593Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.0802437Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.0803304Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.0804187Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.0804992Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.0805869Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.0806781Z [QNN Partitioner Op Support]: aten.index_put.default | True
2025-03-21T20:31:58.0807636Z [QNN Partitioner Op Support]: aten.index_put.default | True
2025-03-21T20:31:58.0808546Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.0809537Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.0810257Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:58.0811153Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.0812131Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.0813014Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.0813802Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:58.0814644Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.0815567Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.0816445Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:58.0817178Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.0817833Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.0818553Z [QNN Partitioner Op Support]: aten.sub.Tensor | True
2025-03-21T20:31:58.0819311Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.0820036Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.0820821Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:58.0821602Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.0822342Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.0823060Z [QNN Partitioner Op Support]: aten.sub.Tensor | True
2025-03-21T20:31:58.0823730Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.0824389Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.0825149Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.0825891Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.0826633Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.0827404Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.0828352Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:58.0829210Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:58.0829952Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.0830666Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.0831501Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.0832549Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:58.0833378Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:58.0834209Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.0835026Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.0835851Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.0836734Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.0837549Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.0838322Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.0839187Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:58.0840116Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.0841075Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.0842011Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.0842926Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.0843857Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:58.0844719Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.0845575Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.0846506Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.0847384Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.0848333Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:58.0849329Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.0850463Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.0851329Z [QNN Partitioner Op Support]: aten.rms_norm.default | True
2025-03-21T20:31:58.0852164Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:58.0852941Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.0853785Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.0854699Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:58.0855577Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.0856531Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.0857415Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.0858226Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.0859126Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.0860034Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:58.0860804Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.0861625Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.0862641Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.0863420Z [QNN Partitioner Op Support]: aten.sigmoid.default | True
2025-03-21T20:31:58.0864228Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.0865085Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.0866017Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:58.0866864Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.0867804Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.0868679Z [QNN Partitioner Op Support]: aten.rms_norm.default | True
2025-03-21T20:31:58.0869479Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:58.0870270Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.0871176Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.0872066Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:58.0872905Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.0873859Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.0874753Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.0875495Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.0876358Z [QNN Partitioner Op Support]: aten.matmul.default | True
2025-03-21T20:31:58.0877188Z [QNN Partitioner Op Support]: aten._softmax.default | True
2025-03-21T20:31:58.2452914Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:58.2453714Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.2454521Z [QNN Partitioner Op Support]: aten.matmul.default | True
2025-03-21T20:31:58.2455383Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.2456246Z [QNN Partitioner Op Support]: aten.index.Tensor | True
2025-03-21T20:31:58.2457015Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.2457826Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:58.2458618Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2459453Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2460273Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.2461173Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2461977Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2462709Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.2463454Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2464518Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2465295Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.2466057Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2466789Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2467629Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.2468481Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2469264Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2469996Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.2470794Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2471606Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2472457Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.2473272Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2474083Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2474915Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.2475937Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2476738Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2477491Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.2478307Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2479124Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2479952Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.2480848Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2481816Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2482571Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.2483477Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2484321Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2485179Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.2486069Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2486890Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2487632Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.2488455Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.2489331Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:58.2490130Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2490936Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2491755Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.2492590Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2493431Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2494279Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.2495083Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2495841Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2496703Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.2497532Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2498381Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2499274Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.2500093Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2500935Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2501824Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.2502849Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2503713Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2504578Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.2505408Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2506260Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2507114Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.2508014Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2508870Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2509642Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.2510427Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2511248Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2512083Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.2512927Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2513725Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2514646Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.2515500Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2516354Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2517141Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.2517929Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2518728Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.2519594Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.2520554Z [QNN Partitioner Op Support]: aten.index_put.default | True
2025-03-21T20:31:58.2521437Z [QNN Partitioner Op Support]: aten.index_put.default | True
2025-03-21T20:31:58.2522294Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.2523158Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.2523993Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:58.2524852Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.2525827Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.2526753Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.2527476Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:58.2528252Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.2529170Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.2530113Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:58.2530850Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.2531587Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.2532532Z [QNN Partitioner Op Support]: aten.sub.Tensor | True
2025-03-21T20:31:58.2533283Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.2534060Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.2534784Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:58.2535436Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.2536152Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.2536889Z [QNN Partitioner Op Support]: aten.sub.Tensor | True
2025-03-21T20:31:58.2537614Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.2538372Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.2539214Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.2540063Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.2540765Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.2541744Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.2542563Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:58.2543334Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:58.2544084Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.2544822Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.2545640Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.2546488Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:58.2547314Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:58.2548038Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.2548820Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.2549639Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.2550491Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.2551330Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.2552184Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.2553218Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:58.2554142Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.2555048Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.2555851Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.2556696Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.2557609Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:58.2558540Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.2559600Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.2560513Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.2561305Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.2562233Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:58.2563155Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.2563924Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.2564711Z [QNN Partitioner Op Support]: aten.rms_norm.default | True
2025-03-21T20:31:58.2565477Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:58.2566185Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.2566941Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.4169702Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:58.4170646Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.4171551Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.4172398Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.4173218Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.4174091Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.4174932Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:58.4175861Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.4176782Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.4177616Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.4178442Z [QNN Partitioner Op Support]: aten.sigmoid.default | True
2025-03-21T20:31:58.4179323Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.4180129Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.4181068Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:58.4182002Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.4183278Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.4184209Z [QNN Partitioner Op Support]: aten.rms_norm.default | True
2025-03-21T20:31:58.4184921Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:58.4185635Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.4186508Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.4187400Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:58.4188265Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.4189154Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.4190015Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.4190886Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.4191769Z [QNN Partitioner Op Support]: aten.matmul.default | True
2025-03-21T20:31:58.4192603Z [QNN Partitioner Op Support]: aten._softmax.default | True
2025-03-21T20:31:58.4193328Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:58.4194046Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.4194968Z [QNN Partitioner Op Support]: aten.matmul.default | True
2025-03-21T20:31:58.4195803Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.4196682Z [QNN Partitioner Op Support]: aten.index.Tensor | True
2025-03-21T20:31:58.4197530Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.4198278Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:58.4199090Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4200039Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4200905Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.4201791Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4202641Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4203381Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.4204137Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4204946Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4205797Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.4206632Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4207429Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4208254Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.4209090Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4210043Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4210870Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.4211666Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4212441Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4213301Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.4214143Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4214993Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4215881Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.4216681Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4217515Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4218413Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.4219275Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4220131Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4221016Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.4221951Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4222711Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4223564Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.4224429Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4225216Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4226058Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.4226876Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4227677Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4228568Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.4229407Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.4230136Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:58.4230902Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4231742Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4232910Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.4233936Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4234747Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4235525Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.4236406Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4237247Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4238004Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.4238809Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4239736Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4240584Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.4241427Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4242225Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4243060Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.4243904Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4244742Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4245610Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.4246391Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4247183Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4248053Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.4248882Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4249847Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4250734Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.4251506Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4252351Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4253231Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.4254043Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4254776Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4255611Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.4256477Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4257264Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4258079Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.4258922Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4259709Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.4260815Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.4261637Z [QNN Partitioner Op Support]: aten.index_put.default | True
2025-03-21T20:31:58.4262385Z [QNN Partitioner Op Support]: aten.index_put.default | True
2025-03-21T20:31:58.4263246Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.4264135Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.4264917Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:58.4265803Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.4266726Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.4267554Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.4268406Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:58.4269278Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.4270076Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.4270913Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:58.4271638Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.4272475Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.4273210Z [QNN Partitioner Op Support]: aten.sub.Tensor | True
2025-03-21T20:31:58.4273940Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.4274670Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.4275384Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:58.4276157Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.4276888Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.4277650Z [QNN Partitioner Op Support]: aten.sub.Tensor | True
2025-03-21T20:31:58.4278360Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.4279112Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.4279914Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.4280753Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.4281648Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.4282486Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.4283297Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:58.4284162Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:58.4285032Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.5972138Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.5973023Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.5973914Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:58.5974735Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:58.5975548Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.5976404Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.5977306Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.5978179Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.5979029Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.5979849Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.5980710Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:58.5981621Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.5982486Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.5983411Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.5984338Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.5985120Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:58.5986295Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.5987175Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.5987980Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.5988747Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.5989556Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:58.5990603Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.5991526Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.5992291Z [QNN Partitioner Op Support]: aten.rms_norm.default | True
2025-03-21T20:31:58.5992976Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:58.5993786Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.5994679Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.5995569Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:58.5996440Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.5997496Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.5998338Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.5999171Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.6000020Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.6000847Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:58.6001696Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.6002619Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.6003578Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.6004399Z [QNN Partitioner Op Support]: aten.sigmoid.default | True
2025-03-21T20:31:58.6005274Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.6006079Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.6006995Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:58.6007933Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.6008758Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.6009655Z [QNN Partitioner Op Support]: aten.rms_norm.default | True
2025-03-21T20:31:58.6010613Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:58.6011481Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.6012620Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.6013668Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:58.6014626Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.6015757Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.6028079Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.6028976Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.6029868Z [QNN Partitioner Op Support]: aten.matmul.default | True
2025-03-21T20:31:58.6030687Z [QNN Partitioner Op Support]: aten._softmax.default | True
2025-03-21T20:31:58.6031362Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:58.6032047Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.6033002Z [QNN Partitioner Op Support]: aten.matmul.default | True
2025-03-21T20:31:58.6033857Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.6034657Z [QNN Partitioner Op Support]: aten.index.Tensor | True
2025-03-21T20:31:58.6035472Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.6036268Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:58.6037042Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6038129Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6038952Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.6039753Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6040538Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6041405Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.6042233Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6043061Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6043952Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.6044760Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6045589Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6046479Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.6047361Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6048196Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6049091Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.6050136Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6050921Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6051782Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.6052605Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6053393Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6054235Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.6055196Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6056015Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6056908Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.6057729Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6058453Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6059290Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.6060159Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6060951Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6061827Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.6062720Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6063471Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6064358Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.6065249Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6066070Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6066958Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.6067831Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.6068521Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:58.6069298Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6070122Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6070935Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.6071762Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6072556Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6073387Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.6074248Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6075094Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6075931Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.6076914Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6077732Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6078602Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.6079447Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6080286Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6081132Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.6081932Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6082778Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6083661Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.6084401Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6085182Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6086036Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.6086890Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6087684Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6088617Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.6089529Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6090350Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6091234Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.6092053Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6092769Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6093583Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.6094564Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6095346Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6096249Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.6097132Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6097896Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.6098764Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.6099674Z [QNN Partitioner Op Support]: aten.index_put.default | True
2025-03-21T20:31:58.7800347Z [QNN Partitioner Op Support]: aten.index_put.default | True
2025-03-21T20:31:58.7801219Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.7801712Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.7802174Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:58.7802658Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.7803173Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.7803666Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.7804134Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:58.7804605Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.7805123Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.7805575Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:58.7805995Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.7806412Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.7806828Z [QNN Partitioner Op Support]: aten.sub.Tensor | True
2025-03-21T20:31:58.7807242Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.7807648Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.7808069Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:58.7808491Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.7808995Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.7809686Z [QNN Partitioner Op Support]: aten.sub.Tensor | True
2025-03-21T20:31:58.7810095Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.7810580Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.7811028Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.7811559Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.7812032Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.7812487Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.7812954Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:58.7813417Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:58.7813885Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.7814350Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.7814822Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.7815279Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:58.7815749Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:58.7816279Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.7816752Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.7817226Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.7817687Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.7818209Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.7818681Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.7819261Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:58.7819764Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.7820272Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.7820774Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.7821245Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.7821745Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:58.7822240Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.7822745Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.7823234Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.7823781Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.7824343Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:58.7824842Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.7825345Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.7825834Z [QNN Partitioner Op Support]: aten.rms_norm.default | True
2025-03-21T20:31:58.7826284Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:58.7826716Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.7827202Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.7827695Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:58.7828184Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.7828684Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.7829149Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.7829579Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.7830058Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.7830551Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:58.7831044Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.7831589Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.7832078Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.7832740Z [QNN Partitioner Op Support]: aten.sigmoid.default | True
2025-03-21T20:31:58.7833212Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.7833702Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.7834200Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:58.7834793Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.7835288Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.7835835Z [QNN Partitioner Op Support]: aten.rms_norm.default | True
2025-03-21T20:31:58.7836298Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:58.7836748Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:58.7837231Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.7837718Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:58.7838217Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.7838795Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:58.7839290Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.7839780Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.7840244Z [QNN Partitioner Op Support]: aten.matmul.default | True
2025-03-21T20:31:58.7840703Z [QNN Partitioner Op Support]: aten._softmax.default | True
2025-03-21T20:31:58.7841151Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:58.7841575Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:58.7842050Z [QNN Partitioner Op Support]: aten.matmul.default | True
2025-03-21T20:31:58.7842525Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.7842979Z [QNN Partitioner Op Support]: aten.index.Tensor | True
2025-03-21T20:31:58.7843436Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.7843896Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:58.7844342Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.7844795Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.7845276Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.7845861Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.7846362Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.7846831Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.7847304Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.7847761Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.7848218Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.7848696Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.7849145Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.7849703Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.7850175Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.7850617Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.7851087Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.7851562Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.7852019Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.7852495Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.7852960Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.7853416Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.7853886Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.7854474Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.7854930Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.7855403Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.7855867Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.7856319Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.7856790Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.7857266Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.7857718Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.7858189Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.7858758Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.7859265Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.7859744Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.7860223Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.7860674Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.7861166Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.7861646Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:58.7862097Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:58.7862541Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.7862993Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.7863452Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.7863958Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.7864409Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.7864879Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:58.7865355Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.7865810Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:58.7866272Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:59.4470866Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:59.4471735Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:59.4472224Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:59.4472709Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:59.4473165Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:59.4473637Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:59.4474137Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:59.4474574Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:59.4475057Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:59.4475540Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:59.4475992Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:59.4476471Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:59.4476929Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:59.4477385Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:59.4477858Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:59.4478331Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:59.4478784Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:59.4479257Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:59.4479719Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:59.4480170Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:59.4480915Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:59.4481395Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:59.4481849Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:59.4482310Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:59.4482782Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:59.4483233Z [QNN Partitioner Op Support]: aten.select_copy.int | True
2025-03-21T20:31:59.4483703Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:59.4484188Z [QNN Partitioner Op Support]: aten.index_put.default | True
2025-03-21T20:31:59.4484657Z [QNN Partitioner Op Support]: aten.index_put.default | True
2025-03-21T20:31:59.4485130Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:59.4485610Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:59.4486063Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:59.4486546Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:59.4487058Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:59.4487588Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:59.4488041Z [QNN Partitioner Op Support]: aten.cat.default | True
2025-03-21T20:31:59.4488519Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:59.4489031Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:59.4489590Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:59.4489999Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:59.4490423Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:59.4490922Z [QNN Partitioner Op Support]: aten.sub.Tensor | True
2025-03-21T20:31:59.4491339Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:59.4491766Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:59.4492188Z [QNN Partitioner Op Support]: aten.add.Tensor | True
2025-03-21T20:31:59.4492594Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:59.4493015Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:59.4493431Z [QNN Partitioner Op Support]: aten.sub.Tensor | True
2025-03-21T20:31:59.4493847Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:59.4494270Z [QNN Partitioner Op Support]: aten.mul.Tensor | True
2025-03-21T20:31:59.4494701Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:59.4495173Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:59.4495639Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:59.4496110Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:59.4496577Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:59.4497042Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:59.4497512Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:59.4497982Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:59.4498451Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:59.4498915Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:59.4499383Z [QNN Partitioner Op Support]: aten.slice_copy.Tensor | True
2025-03-21T20:31:59.4499837Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:59.4500307Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:59.4500774Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:59.4501245Z [QNN Partitioner Op Support]: aten.view_copy.default | True
2025-03-21T20:31:59.4501713Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:59.4502186Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:59.4502763Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:59.4503263Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:59.4503773Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:59.4504262Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:59.4504744Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:59.4505224Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:59.4505719Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:59.4506222Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:59.4506710Z [QNN Partitioner Op Support]: aten.squeeze_copy.dims | True
2025-03-21T20:31:59.4507192Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:59.4507673Z [QNN Partitioner Op Support]: aten.convolution.default | True
2025-03-21T20:31:59.4508169Z [QNN Partitioner Op Support]: aten.permute_copy.default | True
2025-03-21T20:31:59.4508671Z [QNN Partitioner Op Support]: aten.unsqueeze_copy.default | True
2025-03-21T20:31:59.4509191Z [QNN Partitioner Op Support]: aten.rms_norm.default | True
2025-03-21T20:31:59.4509644Z [QNN Partitioner Op Support]: aten.index.Tensor | True
2025-03-21T20:31:59.4510078Z [QNN Partitioner Op Support]: aten.index.Tensor | True
2025-03-21T20:31:59.4510527Z [QNN Partitioner Op Support]: aten.embedding.default | True
2025-03-21T20:31:59.4510997Z [QNN Partitioner Op Support]: aten._to_copy.default | True
2025-03-21T20:31:59.4511458Z [QNN Partitioner Op Support]: aten._to_copy.default | True
2025-03-21T20:31:59.4512046Z [INFO 2025-03-21 20:31:58,935 utils.py:363] The buffer node is a mutated buffer node, which is not constant.
2025-03-21T20:31:59.4512786Z [INFO 2025-03-21 20:31:58,935 utils.py:363] The buffer node is a mutated buffer node, which is not constant.
2025-03-21T20:31:59.4513481Z [INFO 2025-03-21 20:31:58,935 utils.py:363] The buffer node is a mutated buffer node, which is not constant.
2025-03-21T20:31:59.4514185Z [INFO 2025-03-21 20:31:58,936 utils.py:363] The buffer node is a mutated buffer node, which is not constant.
2025-03-21T20:31:59.4514881Z [INFO 2025-03-21 20:31:58,936 utils.py:363] The buffer node is a mutated buffer node, which is not constant.
2025-03-21T20:31:59.4515579Z [INFO 2025-03-21 20:31:58,936 utils.py:363] The buffer node is a mutated buffer node, which is not constant.
2025-03-21T20:31:59.4516392Z [INFO 2025-03-21 20:31:58,936 utils.py:363] The buffer node is a mutated buffer node, which is not constant.
2025-03-21T20:31:59.4517094Z [INFO 2025-03-21 20:31:58,936 utils.py:363] The buffer node is a mutated buffer node, which is not constant.
2025-03-21T20:31:59.4517956Z [INFO 2025-03-21 20:31:58,936 utils.py:363] The buffer node is a mutated buffer node, which is not constant.
2025-03-21T20:31:59.4518641Z [INFO 2025-03-21 20:31:58,937 utils.py:363] The buffer node is a mutated buffer node, which is not constant.
2025-03-21T20:31:59.4519358Z [INFO 2025-03-21 20:31:58,937 utils.py:363] The buffer node is a mutated buffer node, which is not constant.
2025-03-21T20:31:59.4520065Z [INFO 2025-03-21 20:31:58,937 utils.py:363] The buffer node is a mutated buffer node, which is not constant.
2025-03-21T20:31:59.4520760Z [INFO 2025-03-21 20:31:58,937 utils.py:363] The buffer node is a mutated buffer node, which is not constant.
2025-03-21T20:31:59.4521454Z [INFO 2025-03-21 20:31:58,937 utils.py:363] The buffer node is a mutated buffer node, which is not constant.
2025-03-21T20:31:59.4522150Z [INFO 2025-03-21 20:31:58,937 utils.py:363] The buffer node is a mutated buffer node, which is not constant.
2025-03-21T20:31:59.4522843Z [INFO 2025-03-21 20:31:58,938 utils.py:363] The buffer node is a mutated buffer node, which is not constant.
2025-03-21T20:31:59.4523532Z [INFO 2025-03-21 20:31:58,938 utils.py:363] The buffer node is a mutated buffer node, which is not constant.
2025-03-21T20:31:59.4524320Z [INFO 2025-03-21 20:31:58,938 utils.py:363] The buffer node is a mutated buffer node, which is not constant.
2025-03-21T20:31:59.4525025Z [INFO 2025-03-21 20:31:58,938 utils.py:363] The buffer node is a mutated buffer node, which is not constant.
2025-03-21T20:31:59.4525730Z [INFO 2025-03-21 20:31:58,938 utils.py:363] The buffer node is a mutated buffer node, which is not constant.
2025-03-21T20:31:59.4526435Z [INFO 2025-03-21 20:31:58,938 utils.py:363] The buffer node is a mutated buffer node, which is not constant.
2025-03-21T20:31:59.4527135Z [INFO 2025-03-21 20:31:58,938 utils.py:363] The buffer node is a mutated buffer node, which is not constant.
2025-03-21T20:31:59.4527825Z [INFO 2025-03-21 20:31:58,939 utils.py:363] The buffer node is a mutated buffer node, which is not constant.
2025-03-21T20:31:59.4528803Z [INFO 2025-03-21 20:31:58,939 utils.py:363] The buffer node is a mutated buffer node, which is not constant.
2025-03-21T20:31:59.4529438Z [INFO] [Qnn ExecuTorch]: Destroy Qnn backend parameters
2025-03-21T20:31:59.4529855Z [INFO] [Qnn ExecuTorch]: Destroy Qnn context
2025-03-21T20:31:59.4530234Z [INFO] [Qnn ExecuTorch]: Destroy Qnn device
2025-03-21T20:31:59.4530597Z [INFO] [Qnn ExecuTorch]: Destroy Qnn backend
2025-03-21T20:31:59.4531056Z [INFO] [Qnn ExecuTorch]: create QNN Logger with log_level 2
2025-03-21T20:31:59.4531621Z [INFO] [Qnn ExecuTorch]: Initialize Qnn backend parameters for Qnn executorch backend type 2
2025-03-21T20:31:59.4532204Z [INFO] [Qnn ExecuTorch]: Caching: Caching is in SAVE MODE.
2025-03-21T20:32:00.3896674Z [WARNING] [Qnn ExecuTorch]: QnnDsp <W> Performance Estimates unsupported
2025-03-21T20:32:00.3897346Z 
2025-03-21T20:32:00.3898110Z [WARNING] [Qnn ExecuTorch]: QnnDsp <W> Arch 68 set by custom config is different from arch associated with SoC 57, will overwrite it to 75
2025-03-21T20:32:00.3899311Z 
2025-03-21T20:32:00.3899577Z [INFO] [Qnn ExecuTorch]: Running level=3 optimization.
2025-03-21T20:32:00.3900601Z [INFO 2025-03-21 20:32:00,227 qnn_preprocess.py:69] Visiting: aten__to_copy_default, aten._to_copy.default
2025-03-21T20:32:00.3901921Z [INFO 2025-03-21 20:32:00,228 qnn_preprocess.py:69] Visiting: aten__to_copy_default_1, aten._to_copy.default
2025-03-21T20:32:00.3903091Z [INFO 2025-03-21 20:32:00,229 qnn_preprocess.py:69] Visiting: aten_embedding_default, aten.embedding.default
2025-03-21T20:32:00.3904352Z [INFO 2025-03-21 20:32:00,334 qnn_preprocess.py:69] Visiting: aten_index_tensor, aten.index.Tensor
2025-03-21T20:32:00.3905593Z [INFO 2025-03-21 20:32:00,336 qnn_preprocess.py:69] Visiting: aten_index_tensor_1, aten.index.Tensor
2025-03-21T20:32:00.3906638Z [INFO 2025-03-21 20:32:00,337 qnn_preprocess.py:69] Visiting: aten_index_tensor_2, aten.index.Tensor
2025-03-21T20:32:00.3907795Z [INFO 2025-03-21 20:32:00,339 qnn_preprocess.py:69] Visiting: aten_index_tensor_3, aten.index.Tensor
2025-03-21T20:32:00.3908898Z [INFO 2025-03-21 20:32:00,340 qnn_preprocess.py:69] Visiting: aten_index_tensor_4, aten.index.Tensor
2025-03-21T20:32:00.3910022Z [INFO 2025-03-21 20:32:00,341 qnn_preprocess.py:69] Visiting: aten_index_tensor_5, aten.index.Tensor
2025-03-21T20:32:00.3911255Z [INFO 2025-03-21 20:32:00,342 qnn_preprocess.py:69] Visiting: aten_index_tensor_6, aten.index.Tensor
2025-03-21T20:32:00.3912434Z [INFO 2025-03-21 20:32:00,344 qnn_preprocess.py:69] Visiting: aten_index_tensor_7, aten.index.Tensor
2025-03-21T20:32:00.3913489Z [INFO 2025-03-21 20:32:00,345 qnn_preprocess.py:69] Visiting: aten_index_tensor_8, aten.index.Tensor
2025-03-21T20:32:00.3914887Z [INFO 2025-03-21 20:32:00,346 qnn_preprocess.py:69] Visiting: aten_index_tensor_9, aten.index.Tensor
2025-03-21T20:32:00.3916047Z [INFO 2025-03-21 20:32:00,348 qnn_preprocess.py:69] Visiting: aten_index_tensor_10, aten.index.Tensor
2025-03-21T20:32:00.3917119Z [INFO 2025-03-21 20:32:00,349 qnn_preprocess.py:69] Visiting: aten_index_tensor_11, aten.index.Tensor
2025-03-21T20:32:00.3918289Z [INFO 2025-03-21 20:32:00,350 qnn_preprocess.py:69] Visiting: aten_index_tensor_12, aten.index.Tensor
2025-03-21T20:32:00.3919734Z [INFO 2025-03-21 20:32:00,351 qnn_preprocess.py:69] Visiting: aten_index_tensor_13, aten.index.Tensor
2025-03-21T20:32:00.3920965Z [INFO 2025-03-21 20:32:00,353 qnn_preprocess.py:69] Visiting: aten_rms_norm_default, aten.rms_norm.default
2025-03-21T20:32:00.3922289Z [INFO 2025-03-21 20:32:00,354 qnn_preprocess.py:69] Visiting: aten_view_copy_default_5, aten.view_copy.default
2025-03-21T20:32:00.3923465Z [INFO 2025-03-21 20:32:00,355 qnn_preprocess.py:69] Visiting: aten_view_copy_default_23, aten.view_copy.default
2025-03-21T20:32:00.3924801Z [INFO 2025-03-21 20:32:00,355 qnn_preprocess.py:69] Visiting: aten_view_copy_default_41, aten.view_copy.default
2025-03-21T20:32:00.3926116Z [INFO 2025-03-21 20:32:00,355 qnn_preprocess.py:69] Visiting: aten_view_copy_default_59, aten.view_copy.default
2025-03-21T20:32:00.3927310Z [INFO 2025-03-21 20:32:00,356 qnn_preprocess.py:69] Visiting: aten_view_copy_default_77, aten.view_copy.default
2025-03-21T20:32:00.3928582Z [INFO 2025-03-21 20:32:00,356 qnn_preprocess.py:69] Visiting: aten_view_copy_default_95, aten.view_copy.default
2025-03-21T20:32:00.3929874Z [INFO 2025-03-21 20:32:00,356 qnn_preprocess.py:69] Visiting: aten_view_copy_default_113, aten.view_copy.default
2025-03-21T20:32:00.3931367Z [INFO 2025-03-21 20:32:00,357 qnn_preprocess.py:69] Visiting: aten_view_copy_default_131, aten.view_copy.default
2025-03-21T20:32:00.3932944Z [INFO 2025-03-21 20:32:00,357 qnn_preprocess.py:69] Visiting: aten_view_copy_default_149, aten.view_copy.default
2025-03-21T20:32:00.3934134Z [INFO 2025-03-21 20:32:00,357 qnn_preprocess.py:69] Visiting: aten_view_copy_default_167, aten.view_copy.default
2025-03-21T20:32:00.3935514Z [INFO 2025-03-21 20:32:00,358 qnn_preprocess.py:69] Visiting: aten_view_copy_default_185, aten.view_copy.default
2025-03-21T20:32:00.3936938Z [INFO 2025-03-21 20:32:00,358 qnn_preprocess.py:69] Visiting: aten_view_copy_default_203, aten.view_copy.default
2025-03-21T20:32:00.3938148Z [INFO 2025-03-21 20:32:00,358 qnn_preprocess.py:69] Visiting: aten_view_copy_default_6, aten.view_copy.default
2025-03-21T20:32:00.3939396Z [INFO 2025-03-21 20:32:00,359 qnn_preprocess.py:69] Visiting: aten_view_copy_default_24, aten.view_copy.default
2025-03-21T20:32:00.3940604Z [INFO 2025-03-21 20:32:00,359 qnn_preprocess.py:69] Visiting: aten_view_copy_default_42, aten.view_copy.default
2025-03-21T20:32:00.3941960Z [INFO 2025-03-21 20:32:00,359 qnn_preprocess.py:69] Visiting: aten_view_copy_default_60, aten.view_copy.default
2025-03-21T20:32:00.3943249Z [INFO 2025-03-21 20:32:00,360 qnn_preprocess.py:69] Visiting: aten_view_copy_default_78, aten.view_copy.default
2025-03-21T20:32:00.3944449Z [INFO 2025-03-21 20:32:00,360 qnn_preprocess.py:69] Visiting: aten_view_copy_default_96, aten.view_copy.default
2025-03-21T20:32:00.3945848Z [INFO 2025-03-21 20:32:00,360 qnn_preprocess.py:69] Visiting: aten_view_copy_default_114, aten.view_copy.default
2025-03-21T20:32:00.3947118Z [INFO 2025-03-21 20:32:00,361 qnn_preprocess.py:69] Visiting: aten_view_copy_default_132, aten.view_copy.default
2025-03-21T20:32:00.3948349Z [INFO 2025-03-21 20:32:00,361 qnn_preprocess.py:69] Visiting: aten_view_copy_default_150, aten.view_copy.default
2025-03-21T20:32:00.3949597Z [INFO 2025-03-21 20:32:00,362 qnn_preprocess.py:69] Visiting: aten_view_copy_default_168, aten.view_copy.default
2025-03-21T20:32:00.3950822Z [INFO 2025-03-21 20:32:00,362 qnn_preprocess.py:69] Visiting: aten_view_copy_default_186, aten.view_copy.default
2025-03-21T20:32:00.3952195Z [INFO 2025-03-21 20:32:00,362 qnn_preprocess.py:69] Visiting: aten_view_copy_default_204, aten.view_copy.default
2025-03-21T20:32:00.3953517Z [INFO 2025-03-21 20:32:00,363 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default, aten.unsqueeze_copy.default
2025-03-21T20:32:00.3954893Z [INFO 2025-03-21 20:32:00,363 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_664, aten.permute_copy.default
2025-03-21T20:32:00.3956432Z [INFO 2025-03-21 20:32:00,365 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_1, aten.unsqueeze_copy.default
2025-03-21T20:32:00.3957972Z [INFO 2025-03-21 20:32:00,365 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_665, aten.permute_copy.default
2025-03-21T20:32:00.3959363Z [INFO 2025-03-21 20:32:00,366 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_2, aten.unsqueeze_copy.default
2025-03-21T20:32:00.3960651Z [INFO 2025-03-21 20:32:00,366 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_666, aten.permute_copy.default
2025-03-21T20:32:00.3962062Z [INFO 2025-03-21 20:32:00,367 qnn_preprocess.py:69] Visiting: aten_convolution_default, aten.convolution.default
2025-03-21T20:32:00.3963436Z [INFO 2025-03-21 20:32:00,371 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_667, aten.permute_copy.default
2025-03-21T20:32:00.3964728Z [INFO 2025-03-21 20:32:00,372 qnn_preprocess.py:69] Visiting: aten_convolution_default_1, aten.convolution.default
2025-03-21T20:32:00.3966223Z [INFO 2025-03-21 20:32:00,376 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_668, aten.permute_copy.default
2025-03-21T20:32:00.3967492Z [INFO 2025-03-21 20:32:00,377 qnn_preprocess.py:69] Visiting: aten_convolution_default_2, aten.convolution.default
2025-03-21T20:32:00.3968980Z [INFO 2025-03-21 20:32:00,379 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_669, aten.permute_copy.default
2025-03-21T20:32:00.3970316Z [INFO 2025-03-21 20:32:00,380 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims, aten.squeeze_copy.dims
2025-03-21T20:32:00.3971532Z [INFO 2025-03-21 20:32:00,381 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_1, aten.squeeze_copy.dims
2025-03-21T20:32:00.3972902Z [INFO 2025-03-21 20:32:00,381 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_2, aten.squeeze_copy.dims
2025-03-21T20:32:00.3974097Z [INFO 2025-03-21 20:32:00,382 qnn_preprocess.py:69] Visiting: aten_view_copy_default, aten.view_copy.default
2025-03-21T20:32:00.3975478Z [INFO 2025-03-21 20:32:00,382 qnn_preprocess.py:69] Visiting: aten_view_copy_default_1, aten.view_copy.default
2025-03-21T20:32:00.3976857Z [INFO 2025-03-21 20:32:00,382 qnn_preprocess.py:69] Visiting: aten_view_copy_default_2, aten.view_copy.default
2025-03-21T20:32:00.3978254Z [INFO 2025-03-21 20:32:00,382 qnn_preprocess.py:69] Visiting: aten_view_copy_default_3, aten.view_copy.default
2025-03-21T20:32:00.3979624Z [INFO 2025-03-21 20:32:00,383 qnn_preprocess.py:69] Visiting: aten_view_copy_default_4, aten.view_copy.default
2025-03-21T20:32:00.3981026Z [INFO 2025-03-21 20:32:00,383 qnn_preprocess.py:69] Visiting: aten_index_put_default_1, aten.index_put.default
2025-03-21T20:32:00.3982218Z [INFO 2025-03-21 20:32:00,384 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor, aten.slice_copy.Tensor
2025-03-21T20:32:00.3983585Z [INFO 2025-03-21 20:32:00,385 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_1, aten.slice_copy.Tensor
2025-03-21T20:32:00.3984976Z [INFO 2025-03-21 20:32:00,385 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_2, aten.slice_copy.Tensor
2025-03-21T20:32:00.3986381Z [INFO 2025-03-21 20:32:00,386 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_3, aten.slice_copy.Tensor
2025-03-21T20:32:00.3987810Z [INFO 2025-03-21 20:32:00,386 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_19, aten.permute_copy.default
2025-03-21T20:32:00.3989207Z [INFO 2025-03-21 20:32:00,387 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_20, aten.permute_copy.default
2025-03-21T20:32:00.3990620Z [INFO 2025-03-21 20:32:00,387 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_21, aten.permute_copy.default
2025-03-21T20:32:00.3992102Z [INFO 2025-03-21 20:32:00,388 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_22, aten.permute_copy.default
2025-03-21T20:32:00.4339761Z [INFO 2025-03-21 20:32:00,389 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_23, aten.permute_copy.default
2025-03-21T20:32:00.4341339Z [INFO 2025-03-21 20:32:00,390 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_24, aten.permute_copy.default
2025-03-21T20:32:00.4343003Z [INFO 2025-03-21 20:32:00,391 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_25, aten.permute_copy.default
2025-03-21T20:32:00.4344337Z [INFO 2025-03-21 20:32:00,392 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_26, aten.permute_copy.default
2025-03-21T20:32:00.4345775Z [INFO 2025-03-21 20:32:00,393 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_27, aten.permute_copy.default
2025-03-21T20:32:00.4347264Z [INFO 2025-03-21 20:32:00,394 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_28, aten.permute_copy.default
2025-03-21T20:32:00.4348758Z [INFO 2025-03-21 20:32:00,395 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_29, aten.permute_copy.default
2025-03-21T20:32:00.4350263Z [INFO 2025-03-21 20:32:00,396 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_30, aten.permute_copy.default
2025-03-21T20:32:00.4351587Z [INFO 2025-03-21 20:32:00,397 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_3, aten.squeeze_copy.dims
2025-03-21T20:32:00.4352883Z [INFO 2025-03-21 20:32:00,398 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_4, aten.squeeze_copy.dims
2025-03-21T20:32:00.4354295Z [INFO 2025-03-21 20:32:00,398 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_5, aten.squeeze_copy.dims
2025-03-21T20:32:00.4355796Z [INFO 2025-03-21 20:32:00,399 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_6, aten.squeeze_copy.dims
2025-03-21T20:32:00.4357163Z [INFO 2025-03-21 20:32:00,399 qnn_preprocess.py:69] Visiting: aten_select_copy_int_24, aten.select_copy.int
2025-03-21T20:32:00.4358539Z [INFO 2025-03-21 20:32:00,400 qnn_preprocess.py:69] Visiting: aten_select_copy_int_26, aten.select_copy.int
2025-03-21T20:32:00.4359702Z [INFO 2025-03-21 20:32:00,400 qnn_preprocess.py:69] Visiting: aten_select_copy_int_28, aten.select_copy.int
2025-03-21T20:32:00.4360963Z [INFO 2025-03-21 20:32:00,401 qnn_preprocess.py:69] Visiting: aten_select_copy_int_30, aten.select_copy.int
2025-03-21T20:32:00.4362432Z [INFO 2025-03-21 20:32:00,401 qnn_preprocess.py:69] Visiting: aten_select_copy_int_32, aten.select_copy.int
2025-03-21T20:32:00.4363816Z [INFO 2025-03-21 20:32:00,402 qnn_preprocess.py:69] Visiting: aten_select_copy_int_34, aten.select_copy.int
2025-03-21T20:32:00.4365145Z [INFO 2025-03-21 20:32:00,402 qnn_preprocess.py:69] Visiting: aten_select_copy_int_36, aten.select_copy.int
2025-03-21T20:32:00.4366487Z [INFO 2025-03-21 20:32:00,403 qnn_preprocess.py:69] Visiting: aten_select_copy_int_38, aten.select_copy.int
2025-03-21T20:32:00.4367626Z [INFO 2025-03-21 20:32:00,403 qnn_preprocess.py:69] Visiting: aten_select_copy_int_40, aten.select_copy.int
2025-03-21T20:32:00.4368944Z [INFO 2025-03-21 20:32:00,404 qnn_preprocess.py:69] Visiting: aten_select_copy_int_42, aten.select_copy.int
2025-03-21T20:32:00.4370366Z [INFO 2025-03-21 20:32:00,404 qnn_preprocess.py:69] Visiting: aten_select_copy_int_44, aten.select_copy.int
2025-03-21T20:32:00.4371749Z [INFO 2025-03-21 20:32:00,405 qnn_preprocess.py:69] Visiting: aten_select_copy_int_46, aten.select_copy.int
2025-03-21T20:32:00.4373011Z [INFO 2025-03-21 20:32:00,405 qnn_preprocess.py:69] Visiting: aten_mul_tensor_2, aten.mul.Tensor
2025-03-21T20:32:00.4374243Z [INFO 2025-03-21 20:32:00,406 qnn_preprocess.py:69] Visiting: aten_mul_tensor_4, aten.mul.Tensor
2025-03-21T20:32:00.4375286Z [INFO 2025-03-21 20:32:00,406 qnn_preprocess.py:69] Visiting: aten_mul_tensor_3, aten.mul.Tensor
2025-03-21T20:32:00.4376434Z [INFO 2025-03-21 20:32:00,407 qnn_preprocess.py:69] Visiting: aten_mul_tensor_5, aten.mul.Tensor
2025-03-21T20:32:00.4377673Z [INFO 2025-03-21 20:32:00,407 qnn_preprocess.py:69] Visiting: aten_mul_tensor_6, aten.mul.Tensor
2025-03-21T20:32:00.4378886Z [INFO 2025-03-21 20:32:00,408 qnn_preprocess.py:69] Visiting: aten_mul_tensor_8, aten.mul.Tensor
2025-03-21T20:32:00.4380086Z [INFO 2025-03-21 20:32:00,408 qnn_preprocess.py:69] Visiting: aten_mul_tensor_7, aten.mul.Tensor
2025-03-21T20:32:00.4381312Z [INFO 2025-03-21 20:32:00,409 qnn_preprocess.py:69] Visiting: aten_mul_tensor_9, aten.mul.Tensor
2025-03-21T20:32:00.4382480Z [INFO 2025-03-21 20:32:00,409 qnn_preprocess.py:69] Visiting: aten_select_copy_int_25, aten.select_copy.int
2025-03-21T20:32:00.4384047Z [INFO 2025-03-21 20:32:00,410 qnn_preprocess.py:69] Visiting: aten_select_copy_int_27, aten.select_copy.int
2025-03-21T20:32:00.4385400Z [INFO 2025-03-21 20:32:00,410 qnn_preprocess.py:69] Visiting: aten_select_copy_int_29, aten.select_copy.int
2025-03-21T20:32:00.4386751Z [INFO 2025-03-21 20:32:00,411 qnn_preprocess.py:69] Visiting: aten_select_copy_int_31, aten.select_copy.int
2025-03-21T20:32:00.4388087Z [INFO 2025-03-21 20:32:00,411 qnn_preprocess.py:69] Visiting: aten_select_copy_int_33, aten.select_copy.int
2025-03-21T20:32:00.4389439Z [INFO 2025-03-21 20:32:00,412 qnn_preprocess.py:69] Visiting: aten_select_copy_int_35, aten.select_copy.int
2025-03-21T20:32:00.4390594Z [INFO 2025-03-21 20:32:00,412 qnn_preprocess.py:69] Visiting: aten_select_copy_int_37, aten.select_copy.int
2025-03-21T20:32:00.4391848Z [INFO 2025-03-21 20:32:00,413 qnn_preprocess.py:69] Visiting: aten_select_copy_int_39, aten.select_copy.int
2025-03-21T20:32:00.4393204Z [INFO 2025-03-21 20:32:00,413 qnn_preprocess.py:69] Visiting: aten_select_copy_int_41, aten.select_copy.int
2025-03-21T20:32:00.4394653Z [INFO 2025-03-21 20:32:00,413 qnn_preprocess.py:69] Visiting: aten_select_copy_int_43, aten.select_copy.int
2025-03-21T20:32:00.4395991Z [INFO 2025-03-21 20:32:00,414 qnn_preprocess.py:69] Visiting: aten_select_copy_int_45, aten.select_copy.int
2025-03-21T20:32:00.4397351Z [INFO 2025-03-21 20:32:00,414 qnn_preprocess.py:69] Visiting: aten_select_copy_int_47, aten.select_copy.int
2025-03-21T20:32:00.4398440Z [INFO 2025-03-21 20:32:00,415 qnn_preprocess.py:69] Visiting: aten_sub_tensor, aten.sub.Tensor
2025-03-21T20:32:00.4399572Z [INFO 2025-03-21 20:32:00,415 qnn_preprocess.py:69] Visiting: aten_add_tensor, aten.add.Tensor
2025-03-21T20:32:00.4400886Z [INFO 2025-03-21 20:32:00,416 qnn_preprocess.py:69] Visiting: aten_sub_tensor_1, aten.sub.Tensor
2025-03-21T20:32:00.4402117Z [INFO 2025-03-21 20:32:00,416 qnn_preprocess.py:69] Visiting: aten_add_tensor_1, aten.add.Tensor
2025-03-21T20:32:00.4403343Z [INFO 2025-03-21 20:32:00,417 qnn_preprocess.py:69] Visiting: aten_cat_default_3, aten.cat.default
2025-03-21T20:32:00.4404769Z [INFO 2025-03-21 20:32:00,418 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_3, aten.unsqueeze_copy.default
2025-03-21T20:32:00.4406123Z [INFO 2025-03-21 20:32:00,419 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_4, aten.unsqueeze_copy.default
2025-03-21T20:32:00.4407566Z [INFO 2025-03-21 20:32:00,419 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_5, aten.unsqueeze_copy.default
2025-03-21T20:32:00.4409101Z [INFO 2025-03-21 20:32:00,420 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_6, aten.unsqueeze_copy.default
2025-03-21T20:32:00.4410673Z [INFO 2025-03-21 20:32:00,420 qnn_preprocess.py:69] Visiting: aten_view_copy_default_10, aten.view_copy.default
2025-03-21T20:32:00.4412055Z [INFO 2025-03-21 20:32:00,420 qnn_preprocess.py:69] Visiting: aten__to_copy_default_2, aten._to_copy.default
2025-03-21T20:32:00.4413293Z [INFO 2025-03-21 20:32:00,421 qnn_preprocess.py:69] Visiting: aten_cat_default, aten.cat.default
2025-03-21T20:32:00.4414361Z [INFO 2025-03-21 20:32:00,422 qnn_preprocess.py:69] Visiting: aten_cat_default_1, aten.cat.default
2025-03-21T20:32:00.4415682Z [INFO 2025-03-21 20:32:00,422 qnn_preprocess.py:69] Visiting: aten_view_copy_default_7, aten.view_copy.default
2025-03-21T20:32:00.4417069Z [INFO 2025-03-21 20:32:00,422 qnn_preprocess.py:69] Visiting: aten_view_copy_default_8, aten.view_copy.default
2025-03-21T20:32:00.4418510Z [INFO 2025-03-21 20:32:00,423 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_6, aten.permute_copy.default
2025-03-21T20:32:00.4419965Z [INFO 2025-03-21 20:32:00,423 qnn_preprocess.py:69] Visiting: aten_index_put_default, aten.index_put.default
2025-03-21T20:32:00.4421256Z [INFO 2025-03-21 20:32:00,425 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_7, aten.permute_copy.default
2025-03-21T20:32:00.4422735Z [INFO 2025-03-21 20:32:00,425 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_8, aten.permute_copy.default
2025-03-21T20:32:00.4424247Z [INFO 2025-03-21 20:32:00,426 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_9, aten.permute_copy.default
2025-03-21T20:32:00.4425749Z [INFO 2025-03-21 20:32:00,427 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_10, aten.permute_copy.default
2025-03-21T20:32:00.4427237Z [INFO 2025-03-21 20:32:00,427 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_11, aten.permute_copy.default
2025-03-21T20:32:00.4428635Z [INFO 2025-03-21 20:32:00,428 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_12, aten.permute_copy.default
2025-03-21T20:32:00.4429959Z [INFO 2025-03-21 20:32:00,429 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_13, aten.permute_copy.default
2025-03-21T20:32:00.4431455Z [INFO 2025-03-21 20:32:00,429 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_14, aten.permute_copy.default
2025-03-21T20:32:00.4433133Z [INFO 2025-03-21 20:32:00,430 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_15, aten.permute_copy.default
2025-03-21T20:32:00.4434597Z [INFO 2025-03-21 20:32:00,431 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_16, aten.permute_copy.default
2025-03-21T20:32:00.4436206Z [INFO 2025-03-21 20:32:00,431 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_17, aten.permute_copy.default
2025-03-21T20:32:00.4437463Z [INFO 2025-03-21 20:32:00,432 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_18, aten.permute_copy.default
2025-03-21T20:32:00.4438849Z [INFO 2025-03-21 20:32:00,433 qnn_preprocess.py:69] Visiting: aten_select_copy_int, aten.select_copy.int
2025-03-21T20:32:00.5106294Z [INFO 2025-03-21 20:32:00,433 qnn_preprocess.py:69] Visiting: aten_select_copy_int_2, aten.select_copy.int
2025-03-21T20:32:00.5108055Z [INFO 2025-03-21 20:32:00,434 qnn_preprocess.py:69] Visiting: aten_select_copy_int_4, aten.select_copy.int
2025-03-21T20:32:00.5109218Z [INFO 2025-03-21 20:32:00,435 qnn_preprocess.py:69] Visiting: aten_select_copy_int_6, aten.select_copy.int
2025-03-21T20:32:00.5110517Z [INFO 2025-03-21 20:32:00,435 qnn_preprocess.py:69] Visiting: aten_select_copy_int_8, aten.select_copy.int
2025-03-21T20:32:00.5111834Z [INFO 2025-03-21 20:32:00,436 qnn_preprocess.py:69] Visiting: aten_select_copy_int_10, aten.select_copy.int
2025-03-21T20:32:00.5113207Z [INFO 2025-03-21 20:32:00,437 qnn_preprocess.py:69] Visiting: aten_select_copy_int_12, aten.select_copy.int
2025-03-21T20:32:00.5114530Z [INFO 2025-03-21 20:32:00,438 qnn_preprocess.py:69] Visiting: aten_select_copy_int_14, aten.select_copy.int
2025-03-21T20:32:00.5115889Z [INFO 2025-03-21 20:32:00,439 qnn_preprocess.py:69] Visiting: aten_select_copy_int_16, aten.select_copy.int
2025-03-21T20:32:00.5117099Z [INFO 2025-03-21 20:32:00,439 qnn_preprocess.py:69] Visiting: aten_select_copy_int_18, aten.select_copy.int
2025-03-21T20:32:00.5118463Z [INFO 2025-03-21 20:32:00,440 qnn_preprocess.py:69] Visiting: aten_select_copy_int_20, aten.select_copy.int
2025-03-21T20:32:00.5119821Z [INFO 2025-03-21 20:32:00,441 qnn_preprocess.py:69] Visiting: aten_select_copy_int_22, aten.select_copy.int
2025-03-21T20:32:00.5121180Z [INFO 2025-03-21 20:32:00,442 qnn_preprocess.py:69] Visiting: aten_select_copy_int_1, aten.select_copy.int
2025-03-21T20:32:00.5122526Z [INFO 2025-03-21 20:32:00,442 qnn_preprocess.py:69] Visiting: aten_select_copy_int_3, aten.select_copy.int
2025-03-21T20:32:00.5123773Z [INFO 2025-03-21 20:32:00,443 qnn_preprocess.py:69] Visiting: aten_select_copy_int_5, aten.select_copy.int
2025-03-21T20:32:00.5125002Z [INFO 2025-03-21 20:32:00,444 qnn_preprocess.py:69] Visiting: aten_select_copy_int_7, aten.select_copy.int
2025-03-21T20:32:00.5126343Z [INFO 2025-03-21 20:32:00,444 qnn_preprocess.py:69] Visiting: aten_select_copy_int_9, aten.select_copy.int
2025-03-21T20:32:00.5127667Z [INFO 2025-03-21 20:32:00,445 qnn_preprocess.py:69] Visiting: aten_select_copy_int_11, aten.select_copy.int
2025-03-21T20:32:00.5128999Z [INFO 2025-03-21 20:32:00,445 qnn_preprocess.py:69] Visiting: aten_select_copy_int_13, aten.select_copy.int
2025-03-21T20:32:00.5130669Z [INFO 2025-03-21 20:32:00,446 qnn_preprocess.py:69] Visiting: aten_select_copy_int_15, aten.select_copy.int
2025-03-21T20:32:00.5132043Z [INFO 2025-03-21 20:32:00,446 qnn_preprocess.py:69] Visiting: aten_select_copy_int_17, aten.select_copy.int
2025-03-21T20:32:00.5133594Z [INFO 2025-03-21 20:32:00,446 qnn_preprocess.py:69] Visiting: aten_select_copy_int_19, aten.select_copy.int
2025-03-21T20:32:00.5134882Z [INFO 2025-03-21 20:32:00,447 qnn_preprocess.py:69] Visiting: aten_select_copy_int_21, aten.select_copy.int
2025-03-21T20:32:00.5136087Z [INFO 2025-03-21 20:32:00,447 qnn_preprocess.py:69] Visiting: aten_select_copy_int_23, aten.select_copy.int
2025-03-21T20:32:00.5137381Z [INFO 2025-03-21 20:32:00,448 qnn_preprocess.py:69] Visiting: aten_cat_default_2, aten.cat.default
2025-03-21T20:32:00.5138691Z [INFO 2025-03-21 20:32:00,449 qnn_preprocess.py:69] Visiting: aten_view_copy_default_9, aten.view_copy.default
2025-03-21T20:32:00.5140143Z [INFO 2025-03-21 20:32:00,450 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_31, aten.permute_copy.default
2025-03-21T20:32:00.5141426Z [INFO 2025-03-21 20:32:00,450 qnn_preprocess.py:69] Visiting: aten__to_copy_default_3, aten._to_copy.default
2025-03-21T20:32:00.5142940Z [INFO 2025-03-21 20:32:00,451 qnn_preprocess.py:69] Visiting: aten_matmul_default, aten.matmul.default
2025-03-21T20:32:00.5144192Z [INFO 2025-03-21 20:32:00,451 qnn_preprocess.py:69] Visiting: aten_mul_tensor_10, aten.mul.Tensor
2025-03-21T20:32:00.5145422Z [INFO 2025-03-21 20:32:00,453 qnn_preprocess.py:69] Visiting: aten_add_tensor_2, aten.add.Tensor
2025-03-21T20:32:00.5146529Z [INFO 2025-03-21 20:32:00,453 qnn_preprocess.py:69] Visiting: aten__softmax_default, aten._softmax.default
2025-03-21T20:32:00.5147994Z [INFO 2025-03-21 20:32:00,454 qnn_preprocess.py:69] Visiting: aten_matmul_default_1, aten.matmul.default
2025-03-21T20:32:00.5149378Z [INFO 2025-03-21 20:32:00,454 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_32, aten.permute_copy.default
2025-03-21T20:32:00.5150837Z [INFO 2025-03-21 20:32:00,455 qnn_preprocess.py:69] Visiting: aten_view_copy_default_17, aten.view_copy.default
2025-03-21T20:32:00.5152138Z [INFO 2025-03-21 20:32:00,455 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_7, aten.unsqueeze_copy.default
2025-03-21T20:32:00.5153673Z [INFO 2025-03-21 20:32:00,455 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_670, aten.permute_copy.default
2025-03-21T20:32:00.5155164Z [INFO 2025-03-21 20:32:00,456 qnn_preprocess.py:69] Visiting: aten_convolution_default_3, aten.convolution.default
2025-03-21T20:32:00.5156628Z [INFO 2025-03-21 20:32:00,459 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_671, aten.permute_copy.default
2025-03-21T20:32:00.5158085Z [INFO 2025-03-21 20:32:00,460 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_7, aten.squeeze_copy.dims
2025-03-21T20:32:00.5159353Z [INFO 2025-03-21 20:32:00,461 qnn_preprocess.py:69] Visiting: aten_add_tensor_3, aten.add.Tensor
2025-03-21T20:32:00.5160639Z [INFO 2025-03-21 20:32:00,461 qnn_preprocess.py:69] Visiting: aten_rms_norm_default_1, aten.rms_norm.default
2025-03-21T20:32:00.5161811Z [INFO 2025-03-21 20:32:00,463 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_8, aten.unsqueeze_copy.default
2025-03-21T20:32:00.5163150Z [INFO 2025-03-21 20:32:00,463 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_672, aten.permute_copy.default
2025-03-21T20:32:00.5164419Z [INFO 2025-03-21 20:32:00,464 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_9, aten.unsqueeze_copy.default
2025-03-21T20:32:00.5165786Z [INFO 2025-03-21 20:32:00,464 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_673, aten.permute_copy.default
2025-03-21T20:32:00.5167072Z [INFO 2025-03-21 20:32:00,465 qnn_preprocess.py:69] Visiting: aten_convolution_default_4, aten.convolution.default
2025-03-21T20:32:00.5168481Z [INFO 2025-03-21 20:32:00,471 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_674, aten.permute_copy.default
2025-03-21T20:32:00.5170305Z [INFO 2025-03-21 20:32:00,472 qnn_preprocess.py:69] Visiting: aten_convolution_default_5, aten.convolution.default
2025-03-21T20:32:00.5171785Z [INFO 2025-03-21 20:32:00,480 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_675, aten.permute_copy.default
2025-03-21T20:32:00.5173006Z [INFO 2025-03-21 20:32:00,481 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_8, aten.squeeze_copy.dims
2025-03-21T20:32:00.5174287Z [INFO 2025-03-21 20:32:00,482 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_9, aten.squeeze_copy.dims
2025-03-21T20:32:00.5175644Z [INFO 2025-03-21 20:32:00,482 qnn_preprocess.py:69] Visiting: aten_sigmoid_default, aten.sigmoid.default
2025-03-21T20:32:00.5176953Z [INFO 2025-03-21 20:32:00,483 qnn_preprocess.py:69] Visiting: aten_mul_tensor_13, aten.mul.Tensor
2025-03-21T20:32:00.5178183Z [INFO 2025-03-21 20:32:00,483 qnn_preprocess.py:69] Visiting: aten_mul_tensor_14, aten.mul.Tensor
2025-03-21T20:32:00.5179612Z [INFO 2025-03-21 20:32:00,484 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_10, aten.unsqueeze_copy.default
2025-03-21T20:32:00.5180932Z [INFO 2025-03-21 20:32:00,484 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_676, aten.permute_copy.default
2025-03-21T20:32:00.5182475Z [INFO 2025-03-21 20:32:00,485 qnn_preprocess.py:69] Visiting: aten_convolution_default_6, aten.convolution.default
2025-03-21T20:32:00.5183948Z [INFO 2025-03-21 20:32:00,491 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_677, aten.permute_copy.default
2025-03-21T20:32:00.5185420Z [INFO 2025-03-21 20:32:00,492 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_10, aten.squeeze_copy.dims
2025-03-21T20:32:00.5186729Z [INFO 2025-03-21 20:32:00,493 qnn_preprocess.py:69] Visiting: aten_add_tensor_4, aten.add.Tensor
2025-03-21T20:32:00.5188009Z [INFO 2025-03-21 20:32:00,494 qnn_preprocess.py:69] Visiting: aten_rms_norm_default_2, aten.rms_norm.default
2025-03-21T20:32:00.5189312Z [INFO 2025-03-21 20:32:00,495 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_11, aten.unsqueeze_copy.default
2025-03-21T20:32:00.5190854Z [INFO 2025-03-21 20:32:00,495 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_678, aten.permute_copy.default
2025-03-21T20:32:00.5192399Z [INFO 2025-03-21 20:32:00,496 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_12, aten.unsqueeze_copy.default
2025-03-21T20:32:00.5193897Z [INFO 2025-03-21 20:32:00,497 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_679, aten.permute_copy.default
2025-03-21T20:32:00.5195427Z [INFO 2025-03-21 20:32:00,497 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_13, aten.unsqueeze_copy.default
2025-03-21T20:32:00.5196755Z [INFO 2025-03-21 20:32:00,498 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_680, aten.permute_copy.default
2025-03-21T20:32:00.5198263Z [INFO 2025-03-21 20:32:00,498 qnn_preprocess.py:69] Visiting: aten_convolution_default_7, aten.convolution.default
2025-03-21T20:32:00.5199760Z [INFO 2025-03-21 20:32:00,501 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_681, aten.permute_copy.default
2025-03-21T20:32:00.5201243Z [INFO 2025-03-21 20:32:00,502 qnn_preprocess.py:69] Visiting: aten_convolution_default_8, aten.convolution.default
2025-03-21T20:32:00.5202766Z [INFO 2025-03-21 20:32:00,505 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_682, aten.permute_copy.default
2025-03-21T20:32:00.5204045Z [INFO 2025-03-21 20:32:00,506 qnn_preprocess.py:69] Visiting: aten_convolution_default_9, aten.convolution.default
2025-03-21T20:32:00.5205490Z [INFO 2025-03-21 20:32:00,509 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_683, aten.permute_copy.default
2025-03-21T20:32:00.5523594Z [INFO 2025-03-21 20:32:00,510 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_11, aten.squeeze_copy.dims
2025-03-21T20:32:00.5525042Z [INFO 2025-03-21 20:32:00,510 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_12, aten.squeeze_copy.dims
2025-03-21T20:32:00.5526424Z [INFO 2025-03-21 20:32:00,511 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_13, aten.squeeze_copy.dims
2025-03-21T20:32:00.5528258Z [INFO 2025-03-21 20:32:00,512 qnn_preprocess.py:69] Visiting: aten_view_copy_default_18, aten.view_copy.default
2025-03-21T20:32:00.5529779Z [INFO 2025-03-21 20:32:00,512 qnn_preprocess.py:69] Visiting: aten_view_copy_default_19, aten.view_copy.default
2025-03-21T20:32:00.5531058Z [INFO 2025-03-21 20:32:00,513 qnn_preprocess.py:69] Visiting: aten_view_copy_default_20, aten.view_copy.default
2025-03-21T20:32:00.5532854Z [INFO 2025-03-21 20:32:00,514 qnn_preprocess.py:69] Visiting: aten_view_copy_default_21, aten.view_copy.default
2025-03-21T20:32:00.5534189Z [INFO 2025-03-21 20:32:00,514 qnn_preprocess.py:69] Visiting: aten_view_copy_default_22, aten.view_copy.default
2025-03-21T20:32:00.5535352Z [INFO 2025-03-21 20:32:00,515 qnn_preprocess.py:69] Visiting: aten_index_put_default_3, aten.index_put.default
2025-03-21T20:32:00.5536624Z [INFO 2025-03-21 20:32:00,517 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_4, aten.slice_copy.Tensor
2025-03-21T20:32:00.5537822Z [INFO 2025-03-21 20:32:00,518 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_5, aten.slice_copy.Tensor
2025-03-21T20:32:00.5539219Z [INFO 2025-03-21 20:32:00,518 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_6, aten.slice_copy.Tensor
2025-03-21T20:32:00.5540583Z [INFO 2025-03-21 20:32:00,519 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_7, aten.slice_copy.Tensor
2025-03-21T20:32:00.5541781Z [INFO 2025-03-21 20:32:00,520 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_60, aten.permute_copy.default
2025-03-21T20:32:00.5543733Z [INFO 2025-03-21 20:32:00,521 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_61, aten.permute_copy.default
2025-03-21T20:32:00.5545218Z [INFO 2025-03-21 20:32:00,521 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_62, aten.permute_copy.default
2025-03-21T20:32:00.5546875Z [INFO 2025-03-21 20:32:00,522 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_63, aten.permute_copy.default
2025-03-21T20:32:00.5548383Z [INFO 2025-03-21 20:32:00,523 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_64, aten.permute_copy.default
2025-03-21T20:32:00.5549793Z [INFO 2025-03-21 20:32:00,523 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_65, aten.permute_copy.default
2025-03-21T20:32:00.5551200Z [INFO 2025-03-21 20:32:00,524 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_66, aten.permute_copy.default
2025-03-21T20:32:00.5552401Z [INFO 2025-03-21 20:32:00,525 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_67, aten.permute_copy.default
2025-03-21T20:32:00.5553710Z [INFO 2025-03-21 20:32:00,525 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_68, aten.permute_copy.default
2025-03-21T20:32:00.5554960Z [INFO 2025-03-21 20:32:00,526 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_69, aten.permute_copy.default
2025-03-21T20:32:00.5556310Z [INFO 2025-03-21 20:32:00,527 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_70, aten.permute_copy.default
2025-03-21T20:32:00.5557663Z [INFO 2025-03-21 20:32:00,527 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_71, aten.permute_copy.default
2025-03-21T20:32:00.5559056Z [INFO 2025-03-21 20:32:00,528 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_14, aten.squeeze_copy.dims
2025-03-21T20:32:00.5560459Z [INFO 2025-03-21 20:32:00,528 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_15, aten.squeeze_copy.dims
2025-03-21T20:32:00.5561864Z [INFO 2025-03-21 20:32:00,529 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_16, aten.squeeze_copy.dims
2025-03-21T20:32:00.5563052Z [INFO 2025-03-21 20:32:00,529 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_17, aten.squeeze_copy.dims
2025-03-21T20:32:00.5564731Z [INFO 2025-03-21 20:32:00,530 qnn_preprocess.py:69] Visiting: aten_select_copy_int_72, aten.select_copy.int
2025-03-21T20:32:00.5565979Z [INFO 2025-03-21 20:32:00,530 qnn_preprocess.py:69] Visiting: aten_select_copy_int_74, aten.select_copy.int
2025-03-21T20:32:00.5567368Z [INFO 2025-03-21 20:32:00,530 qnn_preprocess.py:69] Visiting: aten_select_copy_int_76, aten.select_copy.int
2025-03-21T20:32:00.5568593Z [INFO 2025-03-21 20:32:00,531 qnn_preprocess.py:69] Visiting: aten_select_copy_int_78, aten.select_copy.int
2025-03-21T20:32:00.5569854Z [INFO 2025-03-21 20:32:00,531 qnn_preprocess.py:69] Visiting: aten_select_copy_int_80, aten.select_copy.int
2025-03-21T20:32:00.5571136Z [INFO 2025-03-21 20:32:00,532 qnn_preprocess.py:69] Visiting: aten_select_copy_int_82, aten.select_copy.int
2025-03-21T20:32:00.5572434Z [INFO 2025-03-21 20:32:00,532 qnn_preprocess.py:69] Visiting: aten_select_copy_int_84, aten.select_copy.int
2025-03-21T20:32:00.5573566Z [INFO 2025-03-21 20:32:00,533 qnn_preprocess.py:69] Visiting: aten_select_copy_int_86, aten.select_copy.int
2025-03-21T20:32:00.5574929Z [INFO 2025-03-21 20:32:00,533 qnn_preprocess.py:69] Visiting: aten_select_copy_int_88, aten.select_copy.int
2025-03-21T20:32:00.5576188Z [INFO 2025-03-21 20:32:00,534 qnn_preprocess.py:69] Visiting: aten_select_copy_int_90, aten.select_copy.int
2025-03-21T20:32:00.5577344Z [INFO 2025-03-21 20:32:00,534 qnn_preprocess.py:69] Visiting: aten_select_copy_int_92, aten.select_copy.int
2025-03-21T20:32:00.5578670Z [INFO 2025-03-21 20:32:00,534 qnn_preprocess.py:69] Visiting: aten_select_copy_int_94, aten.select_copy.int
2025-03-21T20:32:00.5579771Z [INFO 2025-03-21 20:32:00,535 qnn_preprocess.py:69] Visiting: aten_mul_tensor_17, aten.mul.Tensor
2025-03-21T20:32:00.5580891Z [INFO 2025-03-21 20:32:00,535 qnn_preprocess.py:69] Visiting: aten_mul_tensor_19, aten.mul.Tensor
2025-03-21T20:32:00.5582109Z [INFO 2025-03-21 20:32:00,536 qnn_preprocess.py:69] Visiting: aten_mul_tensor_18, aten.mul.Tensor
2025-03-21T20:32:00.5583181Z [INFO 2025-03-21 20:32:00,536 qnn_preprocess.py:69] Visiting: aten_mul_tensor_20, aten.mul.Tensor
2025-03-21T20:32:00.5584405Z [INFO 2025-03-21 20:32:00,537 qnn_preprocess.py:69] Visiting: aten_mul_tensor_21, aten.mul.Tensor
2025-03-21T20:32:00.5585636Z [INFO 2025-03-21 20:32:00,537 qnn_preprocess.py:69] Visiting: aten_mul_tensor_23, aten.mul.Tensor
2025-03-21T20:32:00.5586726Z [INFO 2025-03-21 20:32:00,538 qnn_preprocess.py:69] Visiting: aten_mul_tensor_22, aten.mul.Tensor
2025-03-21T20:32:00.5587771Z [INFO 2025-03-21 20:32:00,538 qnn_preprocess.py:69] Visiting: aten_mul_tensor_24, aten.mul.Tensor
2025-03-21T20:32:00.5588931Z [INFO 2025-03-21 20:32:00,539 qnn_preprocess.py:69] Visiting: aten_select_copy_int_73, aten.select_copy.int
2025-03-21T20:32:00.5590089Z [INFO 2025-03-21 20:32:00,539 qnn_preprocess.py:69] Visiting: aten_select_copy_int_75, aten.select_copy.int
2025-03-21T20:32:00.5591365Z [INFO 2025-03-21 20:32:00,540 qnn_preprocess.py:69] Visiting: aten_select_copy_int_77, aten.select_copy.int
2025-03-21T20:32:00.5592677Z [INFO 2025-03-21 20:32:00,540 qnn_preprocess.py:69] Visiting: aten_select_copy_int_79, aten.select_copy.int
2025-03-21T20:32:00.5593826Z [INFO 2025-03-21 20:32:00,541 qnn_preprocess.py:69] Visiting: aten_select_copy_int_81, aten.select_copy.int
2025-03-21T20:32:00.5595130Z [INFO 2025-03-21 20:32:00,541 qnn_preprocess.py:69] Visiting: aten_select_copy_int_83, aten.select_copy.int
2025-03-21T20:32:00.5596393Z [INFO 2025-03-21 20:32:00,541 qnn_preprocess.py:69] Visiting: aten_select_copy_int_85, aten.select_copy.int
2025-03-21T20:32:00.5597536Z [INFO 2025-03-21 20:32:00,542 qnn_preprocess.py:69] Visiting: aten_select_copy_int_87, aten.select_copy.int
2025-03-21T20:32:00.5598750Z [INFO 2025-03-21 20:32:00,542 qnn_preprocess.py:69] Visiting: aten_select_copy_int_89, aten.select_copy.int
2025-03-21T20:32:00.5599902Z [INFO 2025-03-21 20:32:00,543 qnn_preprocess.py:69] Visiting: aten_select_copy_int_91, aten.select_copy.int
2025-03-21T20:32:00.5601138Z [INFO 2025-03-21 20:32:00,543 qnn_preprocess.py:69] Visiting: aten_select_copy_int_93, aten.select_copy.int
2025-03-21T20:32:00.5602465Z [INFO 2025-03-21 20:32:00,544 qnn_preprocess.py:69] Visiting: aten_select_copy_int_95, aten.select_copy.int
2025-03-21T20:32:00.5603539Z [INFO 2025-03-21 20:32:00,544 qnn_preprocess.py:69] Visiting: aten_sub_tensor_2, aten.sub.Tensor
2025-03-21T20:32:00.5604861Z [INFO 2025-03-21 20:32:00,545 qnn_preprocess.py:69] Visiting: aten_add_tensor_5, aten.add.Tensor
2025-03-21T20:32:00.5606086Z [INFO 2025-03-21 20:32:00,545 qnn_preprocess.py:69] Visiting: aten_sub_tensor_3, aten.sub.Tensor
2025-03-21T20:32:00.5607078Z [INFO 2025-03-21 20:32:00,546 qnn_preprocess.py:69] Visiting: aten_add_tensor_6, aten.add.Tensor
2025-03-21T20:32:00.5608179Z [INFO 2025-03-21 20:32:00,546 qnn_preprocess.py:69] Visiting: aten_cat_default_7, aten.cat.default
2025-03-21T20:32:00.5609502Z [INFO 2025-03-21 20:32:00,548 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_14, aten.unsqueeze_copy.default
2025-03-21T20:32:00.5610848Z [INFO 2025-03-21 20:32:00,548 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_15, aten.unsqueeze_copy.default
2025-03-21T20:32:00.5612383Z [INFO 2025-03-21 20:32:00,549 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_16, aten.unsqueeze_copy.default
2025-03-21T20:32:00.5613734Z [INFO 2025-03-21 20:32:00,549 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_17, aten.unsqueeze_copy.default
2025-03-21T20:32:00.5615227Z [INFO 2025-03-21 20:32:00,549 qnn_preprocess.py:69] Visiting: aten_view_copy_default_28, aten.view_copy.default
2025-03-21T20:32:00.5616535Z [INFO 2025-03-21 20:32:00,550 qnn_preprocess.py:69] Visiting: aten__to_copy_default_4, aten._to_copy.default
2025-03-21T20:32:00.5617632Z [INFO 2025-03-21 20:32:00,550 qnn_preprocess.py:69] Visiting: aten_cat_default_4, aten.cat.default
2025-03-21T20:32:00.5618781Z [INFO 2025-03-21 20:32:00,551 qnn_preprocess.py:69] Visiting: aten_cat_default_5, aten.cat.default
2025-03-21T20:32:00.6126163Z [INFO 2025-03-21 20:32:00,552 qnn_preprocess.py:69] Visiting: aten_view_copy_default_25, aten.view_copy.default
2025-03-21T20:32:00.6128051Z [INFO 2025-03-21 20:32:00,552 qnn_preprocess.py:69] Visiting: aten_view_copy_default_26, aten.view_copy.default
2025-03-21T20:32:00.6129356Z [INFO 2025-03-21 20:32:00,553 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_47, aten.permute_copy.default
2025-03-21T20:32:00.6130661Z [INFO 2025-03-21 20:32:00,554 qnn_preprocess.py:69] Visiting: aten_index_put_default_2, aten.index_put.default
2025-03-21T20:32:00.6131909Z [INFO 2025-03-21 20:32:00,556 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_48, aten.permute_copy.default
2025-03-21T20:32:00.6133511Z [INFO 2025-03-21 20:32:00,557 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_49, aten.permute_copy.default
2025-03-21T20:32:00.6134992Z [INFO 2025-03-21 20:32:00,558 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_50, aten.permute_copy.default
2025-03-21T20:32:00.6136514Z [INFO 2025-03-21 20:32:00,559 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_51, aten.permute_copy.default
2025-03-21T20:32:00.6137922Z [INFO 2025-03-21 20:32:00,560 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_52, aten.permute_copy.default
2025-03-21T20:32:00.6139388Z [INFO 2025-03-21 20:32:00,561 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_53, aten.permute_copy.default
2025-03-21T20:32:00.6141062Z [INFO 2025-03-21 20:32:00,562 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_54, aten.permute_copy.default
2025-03-21T20:32:00.6142726Z [INFO 2025-03-21 20:32:00,562 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_55, aten.permute_copy.default
2025-03-21T20:32:00.6144403Z [INFO 2025-03-21 20:32:00,563 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_56, aten.permute_copy.default
2025-03-21T20:32:00.6146013Z [INFO 2025-03-21 20:32:00,564 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_57, aten.permute_copy.default
2025-03-21T20:32:00.6147711Z [INFO 2025-03-21 20:32:00,564 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_58, aten.permute_copy.default
2025-03-21T20:32:00.6149412Z [INFO 2025-03-21 20:32:00,565 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_59, aten.permute_copy.default
2025-03-21T20:32:00.6151252Z [INFO 2025-03-21 20:32:00,566 qnn_preprocess.py:69] Visiting: aten_select_copy_int_48, aten.select_copy.int
2025-03-21T20:32:00.6152886Z [INFO 2025-03-21 20:32:00,566 qnn_preprocess.py:69] Visiting: aten_select_copy_int_50, aten.select_copy.int
2025-03-21T20:32:00.6154272Z [INFO 2025-03-21 20:32:00,566 qnn_preprocess.py:69] Visiting: aten_select_copy_int_52, aten.select_copy.int
2025-03-21T20:32:00.6155545Z [INFO 2025-03-21 20:32:00,567 qnn_preprocess.py:69] Visiting: aten_select_copy_int_54, aten.select_copy.int
2025-03-21T20:32:00.6156814Z [INFO 2025-03-21 20:32:00,567 qnn_preprocess.py:69] Visiting: aten_select_copy_int_56, aten.select_copy.int
2025-03-21T20:32:00.6158078Z [INFO 2025-03-21 20:32:00,568 qnn_preprocess.py:69] Visiting: aten_select_copy_int_58, aten.select_copy.int
2025-03-21T20:32:00.6159234Z [INFO 2025-03-21 20:32:00,568 qnn_preprocess.py:69] Visiting: aten_select_copy_int_60, aten.select_copy.int
2025-03-21T20:32:00.6160522Z [INFO 2025-03-21 20:32:00,568 qnn_preprocess.py:69] Visiting: aten_select_copy_int_62, aten.select_copy.int
2025-03-21T20:32:00.6161902Z [INFO 2025-03-21 20:32:00,569 qnn_preprocess.py:69] Visiting: aten_select_copy_int_64, aten.select_copy.int
2025-03-21T20:32:00.6163356Z [INFO 2025-03-21 20:32:00,569 qnn_preprocess.py:69] Visiting: aten_select_copy_int_66, aten.select_copy.int
2025-03-21T20:32:00.6164450Z [INFO 2025-03-21 20:32:00,570 qnn_preprocess.py:69] Visiting: aten_select_copy_int_68, aten.select_copy.int
2025-03-21T20:32:00.6165669Z [INFO 2025-03-21 20:32:00,570 qnn_preprocess.py:69] Visiting: aten_select_copy_int_70, aten.select_copy.int
2025-03-21T20:32:00.6167066Z [INFO 2025-03-21 20:32:00,571 qnn_preprocess.py:69] Visiting: aten_select_copy_int_49, aten.select_copy.int
2025-03-21T20:32:00.6168500Z [INFO 2025-03-21 20:32:00,571 qnn_preprocess.py:69] Visiting: aten_select_copy_int_51, aten.select_copy.int
2025-03-21T20:32:00.6170216Z [INFO 2025-03-21 20:32:00,572 qnn_preprocess.py:69] Visiting: aten_select_copy_int_53, aten.select_copy.int
2025-03-21T20:32:00.6171710Z [INFO 2025-03-21 20:32:00,572 qnn_preprocess.py:69] Visiting: aten_select_copy_int_55, aten.select_copy.int
2025-03-21T20:32:00.6173287Z [INFO 2025-03-21 20:32:00,573 qnn_preprocess.py:69] Visiting: aten_select_copy_int_57, aten.select_copy.int
2025-03-21T20:32:00.6174623Z [INFO 2025-03-21 20:32:00,573 qnn_preprocess.py:69] Visiting: aten_select_copy_int_59, aten.select_copy.int
2025-03-21T20:32:00.6175948Z [INFO 2025-03-21 20:32:00,573 qnn_preprocess.py:69] Visiting: aten_select_copy_int_61, aten.select_copy.int
2025-03-21T20:32:00.6177202Z [INFO 2025-03-21 20:32:00,574 qnn_preprocess.py:69] Visiting: aten_select_copy_int_63, aten.select_copy.int
2025-03-21T20:32:00.6178754Z [INFO 2025-03-21 20:32:00,574 qnn_preprocess.py:69] Visiting: aten_select_copy_int_65, aten.select_copy.int
2025-03-21T20:32:00.6180296Z [INFO 2025-03-21 20:32:00,575 qnn_preprocess.py:69] Visiting: aten_select_copy_int_67, aten.select_copy.int
2025-03-21T20:32:00.6181728Z [INFO 2025-03-21 20:32:00,575 qnn_preprocess.py:69] Visiting: aten_select_copy_int_69, aten.select_copy.int
2025-03-21T20:32:00.6183221Z [INFO 2025-03-21 20:32:00,576 qnn_preprocess.py:69] Visiting: aten_select_copy_int_71, aten.select_copy.int
2025-03-21T20:32:00.6184397Z [INFO 2025-03-21 20:32:00,576 qnn_preprocess.py:69] Visiting: aten_cat_default_6, aten.cat.default
2025-03-21T20:32:00.6185699Z [INFO 2025-03-21 20:32:00,578 qnn_preprocess.py:69] Visiting: aten_view_copy_default_27, aten.view_copy.default
2025-03-21T20:32:00.6187130Z [INFO 2025-03-21 20:32:00,578 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_72, aten.permute_copy.default
2025-03-21T20:32:00.6188454Z [INFO 2025-03-21 20:32:00,579 qnn_preprocess.py:69] Visiting: aten__to_copy_default_5, aten._to_copy.default
2025-03-21T20:32:00.6189882Z [INFO 2025-03-21 20:32:00,579 qnn_preprocess.py:69] Visiting: aten_matmul_default_2, aten.matmul.default
2025-03-21T20:32:00.6191284Z [INFO 2025-03-21 20:32:00,580 qnn_preprocess.py:69] Visiting: aten_mul_tensor_25, aten.mul.Tensor
2025-03-21T20:32:00.6192280Z [INFO 2025-03-21 20:32:00,581 qnn_preprocess.py:69] Visiting: aten_add_tensor_7, aten.add.Tensor
2025-03-21T20:32:00.6193516Z [INFO 2025-03-21 20:32:00,582 qnn_preprocess.py:69] Visiting: aten__softmax_default_1, aten._softmax.default
2025-03-21T20:32:00.6194776Z [INFO 2025-03-21 20:32:00,582 qnn_preprocess.py:69] Visiting: aten_matmul_default_3, aten.matmul.default
2025-03-21T20:32:00.6196126Z [INFO 2025-03-21 20:32:00,583 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_73, aten.permute_copy.default
2025-03-21T20:32:00.6197293Z [INFO 2025-03-21 20:32:00,583 qnn_preprocess.py:69] Visiting: aten_view_copy_default_35, aten.view_copy.default
2025-03-21T20:32:00.6198609Z [INFO 2025-03-21 20:32:00,584 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_18, aten.unsqueeze_copy.default
2025-03-21T20:32:00.6199905Z [INFO 2025-03-21 20:32:00,584 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_684, aten.permute_copy.default
2025-03-21T20:32:00.6201187Z [INFO 2025-03-21 20:32:00,585 qnn_preprocess.py:69] Visiting: aten_convolution_default_10, aten.convolution.default
2025-03-21T20:32:00.6202573Z [INFO 2025-03-21 20:32:00,588 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_685, aten.permute_copy.default
2025-03-21T20:32:00.6203948Z [INFO 2025-03-21 20:32:00,589 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_18, aten.squeeze_copy.dims
2025-03-21T20:32:00.6205198Z [INFO 2025-03-21 20:32:00,589 qnn_preprocess.py:69] Visiting: aten_add_tensor_8, aten.add.Tensor
2025-03-21T20:32:00.6206447Z [INFO 2025-03-21 20:32:00,590 qnn_preprocess.py:69] Visiting: aten_rms_norm_default_3, aten.rms_norm.default
2025-03-21T20:32:00.6207655Z [INFO 2025-03-21 20:32:00,591 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_19, aten.unsqueeze_copy.default
2025-03-21T20:32:00.6209086Z [INFO 2025-03-21 20:32:00,592 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_686, aten.permute_copy.default
2025-03-21T20:32:00.6210792Z [INFO 2025-03-21 20:32:00,592 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_20, aten.unsqueeze_copy.default
2025-03-21T20:32:00.6212346Z [INFO 2025-03-21 20:32:00,593 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_687, aten.permute_copy.default
2025-03-21T20:32:00.6213851Z [INFO 2025-03-21 20:32:00,593 qnn_preprocess.py:69] Visiting: aten_convolution_default_11, aten.convolution.default
2025-03-21T20:32:00.6215211Z [INFO 2025-03-21 20:32:00,599 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_688, aten.permute_copy.default
2025-03-21T20:32:00.6216571Z [INFO 2025-03-21 20:32:00,600 qnn_preprocess.py:69] Visiting: aten_convolution_default_12, aten.convolution.default
2025-03-21T20:32:00.6218038Z [INFO 2025-03-21 20:32:00,607 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_689, aten.permute_copy.default
2025-03-21T20:32:00.6219512Z [INFO 2025-03-21 20:32:00,608 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_19, aten.squeeze_copy.dims
2025-03-21T20:32:00.6220849Z [INFO 2025-03-21 20:32:00,609 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_20, aten.squeeze_copy.dims
2025-03-21T20:32:00.6222264Z [INFO 2025-03-21 20:32:00,609 qnn_preprocess.py:69] Visiting: aten_sigmoid_default_1, aten.sigmoid.default
2025-03-21T20:32:00.6223570Z [INFO 2025-03-21 20:32:00,610 qnn_preprocess.py:69] Visiting: aten_mul_tensor_28, aten.mul.Tensor
2025-03-21T20:32:00.6224755Z [INFO 2025-03-21 20:32:00,610 qnn_preprocess.py:69] Visiting: aten_mul_tensor_29, aten.mul.Tensor
2025-03-21T20:32:00.6226045Z [INFO 2025-03-21 20:32:00,611 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_21, aten.unsqueeze_copy.default
2025-03-21T20:32:00.6227565Z [INFO 2025-03-21 20:32:00,611 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_690, aten.permute_copy.default
2025-03-21T20:32:00.6675089Z [INFO 2025-03-21 20:32:00,612 qnn_preprocess.py:69] Visiting: aten_convolution_default_13, aten.convolution.default
2025-03-21T20:32:00.6676633Z [INFO 2025-03-21 20:32:00,619 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_691, aten.permute_copy.default
2025-03-21T20:32:00.6678279Z [INFO 2025-03-21 20:32:00,620 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_21, aten.squeeze_copy.dims
2025-03-21T20:32:00.6679555Z [INFO 2025-03-21 20:32:00,621 qnn_preprocess.py:69] Visiting: aten_add_tensor_9, aten.add.Tensor
2025-03-21T20:32:00.6681286Z [INFO 2025-03-21 20:32:00,622 qnn_preprocess.py:69] Visiting: aten_rms_norm_default_4, aten.rms_norm.default
2025-03-21T20:32:00.6682755Z [INFO 2025-03-21 20:32:00,624 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_22, aten.unsqueeze_copy.default
2025-03-21T20:32:00.6684269Z [INFO 2025-03-21 20:32:00,624 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_692, aten.permute_copy.default
2025-03-21T20:32:00.6685770Z [INFO 2025-03-21 20:32:00,625 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_23, aten.unsqueeze_copy.default
2025-03-21T20:32:00.6687072Z [INFO 2025-03-21 20:32:00,625 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_693, aten.permute_copy.default
2025-03-21T20:32:00.6688974Z [INFO 2025-03-21 20:32:00,626 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_24, aten.unsqueeze_copy.default
2025-03-21T20:32:00.6690627Z [INFO 2025-03-21 20:32:00,626 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_694, aten.permute_copy.default
2025-03-21T20:32:00.6692268Z [INFO 2025-03-21 20:32:00,627 qnn_preprocess.py:69] Visiting: aten_convolution_default_14, aten.convolution.default
2025-03-21T20:32:00.6693705Z [INFO 2025-03-21 20:32:00,630 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_695, aten.permute_copy.default
2025-03-21T20:32:00.6694975Z [INFO 2025-03-21 20:32:00,631 qnn_preprocess.py:69] Visiting: aten_convolution_default_15, aten.convolution.default
2025-03-21T20:32:00.6696840Z [INFO 2025-03-21 20:32:00,634 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_696, aten.permute_copy.default
2025-03-21T20:32:00.6698514Z [INFO 2025-03-21 20:32:00,635 qnn_preprocess.py:69] Visiting: aten_convolution_default_16, aten.convolution.default
2025-03-21T20:32:00.6700005Z [INFO 2025-03-21 20:32:00,637 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_697, aten.permute_copy.default
2025-03-21T20:32:00.6701431Z [INFO 2025-03-21 20:32:00,638 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_22, aten.squeeze_copy.dims
2025-03-21T20:32:00.6702624Z [INFO 2025-03-21 20:32:00,639 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_23, aten.squeeze_copy.dims
2025-03-21T20:32:00.6704545Z [INFO 2025-03-21 20:32:00,639 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_24, aten.squeeze_copy.dims
2025-03-21T20:32:00.6705953Z [INFO 2025-03-21 20:32:00,640 qnn_preprocess.py:69] Visiting: aten_view_copy_default_36, aten.view_copy.default
2025-03-21T20:32:00.6707327Z [INFO 2025-03-21 20:32:00,640 qnn_preprocess.py:69] Visiting: aten_view_copy_default_37, aten.view_copy.default
2025-03-21T20:32:00.6708757Z [INFO 2025-03-21 20:32:00,640 qnn_preprocess.py:69] Visiting: aten_view_copy_default_38, aten.view_copy.default
2025-03-21T20:32:00.6709952Z [INFO 2025-03-21 20:32:00,641 qnn_preprocess.py:69] Visiting: aten_view_copy_default_39, aten.view_copy.default
2025-03-21T20:32:00.6711628Z [INFO 2025-03-21 20:32:00,641 qnn_preprocess.py:69] Visiting: aten_view_copy_default_40, aten.view_copy.default
2025-03-21T20:32:00.6713012Z [INFO 2025-03-21 20:32:00,641 qnn_preprocess.py:69] Visiting: aten_index_put_default_5, aten.index_put.default
2025-03-21T20:32:00.6714426Z [INFO 2025-03-21 20:32:00,642 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_8, aten.slice_copy.Tensor
2025-03-21T20:32:00.6715727Z [INFO 2025-03-21 20:32:00,643 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_9, aten.slice_copy.Tensor
2025-03-21T20:32:00.6717125Z [INFO 2025-03-21 20:32:00,643 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_10, aten.slice_copy.Tensor
2025-03-21T20:32:00.6718536Z [INFO 2025-03-21 20:32:00,644 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_11, aten.slice_copy.Tensor
2025-03-21T20:32:00.6719886Z [INFO 2025-03-21 20:32:00,644 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_101, aten.permute_copy.default
2025-03-21T20:32:00.6721965Z [INFO 2025-03-21 20:32:00,645 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_102, aten.permute_copy.default
2025-03-21T20:32:00.6723454Z [INFO 2025-03-21 20:32:00,645 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_103, aten.permute_copy.default
2025-03-21T20:32:00.6724858Z [INFO 2025-03-21 20:32:00,646 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_104, aten.permute_copy.default
2025-03-21T20:32:00.6726380Z [INFO 2025-03-21 20:32:00,647 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_105, aten.permute_copy.default
2025-03-21T20:32:00.6727873Z [INFO 2025-03-21 20:32:00,647 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_106, aten.permute_copy.default
2025-03-21T20:32:00.6729392Z [INFO 2025-03-21 20:32:00,648 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_107, aten.permute_copy.default
2025-03-21T20:32:00.6731230Z [INFO 2025-03-21 20:32:00,649 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_108, aten.permute_copy.default
2025-03-21T20:32:00.6732883Z [INFO 2025-03-21 20:32:00,649 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_109, aten.permute_copy.default
2025-03-21T20:32:00.6734495Z [INFO 2025-03-21 20:32:00,650 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_110, aten.permute_copy.default
2025-03-21T20:32:00.6736016Z [INFO 2025-03-21 20:32:00,651 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_111, aten.permute_copy.default
2025-03-21T20:32:00.6737516Z [INFO 2025-03-21 20:32:00,651 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_112, aten.permute_copy.default
2025-03-21T20:32:00.6738910Z [INFO 2025-03-21 20:32:00,652 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_25, aten.squeeze_copy.dims
2025-03-21T20:32:00.6740264Z [INFO 2025-03-21 20:32:00,653 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_26, aten.squeeze_copy.dims
2025-03-21T20:32:00.6741763Z [INFO 2025-03-21 20:32:00,653 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_27, aten.squeeze_copy.dims
2025-03-21T20:32:00.6743198Z [INFO 2025-03-21 20:32:00,654 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_28, aten.squeeze_copy.dims
2025-03-21T20:32:00.6744506Z [INFO 2025-03-21 20:32:00,654 qnn_preprocess.py:69] Visiting: aten_select_copy_int_120, aten.select_copy.int
2025-03-21T20:32:00.6745888Z [INFO 2025-03-21 20:32:00,654 qnn_preprocess.py:69] Visiting: aten_select_copy_int_122, aten.select_copy.int
2025-03-21T20:32:00.6747235Z [INFO 2025-03-21 20:32:00,655 qnn_preprocess.py:69] Visiting: aten_select_copy_int_124, aten.select_copy.int
2025-03-21T20:32:00.6748527Z [INFO 2025-03-21 20:32:00,655 qnn_preprocess.py:69] Visiting: aten_select_copy_int_126, aten.select_copy.int
2025-03-21T20:32:00.6749803Z [INFO 2025-03-21 20:32:00,656 qnn_preprocess.py:69] Visiting: aten_select_copy_int_128, aten.select_copy.int
2025-03-21T20:32:00.6751166Z [INFO 2025-03-21 20:32:00,656 qnn_preprocess.py:69] Visiting: aten_select_copy_int_130, aten.select_copy.int
2025-03-21T20:32:00.6752554Z [INFO 2025-03-21 20:32:00,657 qnn_preprocess.py:69] Visiting: aten_select_copy_int_132, aten.select_copy.int
2025-03-21T20:32:00.6753913Z [INFO 2025-03-21 20:32:00,657 qnn_preprocess.py:69] Visiting: aten_select_copy_int_134, aten.select_copy.int
2025-03-21T20:32:00.6755281Z [INFO 2025-03-21 20:32:00,658 qnn_preprocess.py:69] Visiting: aten_select_copy_int_136, aten.select_copy.int
2025-03-21T20:32:00.6756643Z [INFO 2025-03-21 20:32:00,658 qnn_preprocess.py:69] Visiting: aten_select_copy_int_138, aten.select_copy.int
2025-03-21T20:32:00.6758007Z [INFO 2025-03-21 20:32:00,658 qnn_preprocess.py:69] Visiting: aten_select_copy_int_140, aten.select_copy.int
2025-03-21T20:32:00.6759365Z [INFO 2025-03-21 20:32:00,659 qnn_preprocess.py:69] Visiting: aten_select_copy_int_142, aten.select_copy.int
2025-03-21T20:32:00.6760688Z [INFO 2025-03-21 20:32:00,659 qnn_preprocess.py:69] Visiting: aten_mul_tensor_32, aten.mul.Tensor
2025-03-21T20:32:00.6761928Z [INFO 2025-03-21 20:32:00,660 qnn_preprocess.py:69] Visiting: aten_mul_tensor_34, aten.mul.Tensor
2025-03-21T20:32:00.6763384Z [INFO 2025-03-21 20:32:00,660 qnn_preprocess.py:69] Visiting: aten_mul_tensor_33, aten.mul.Tensor
2025-03-21T20:32:00.6764646Z [INFO 2025-03-21 20:32:00,661 qnn_preprocess.py:69] Visiting: aten_mul_tensor_35, aten.mul.Tensor
2025-03-21T20:32:00.6765865Z [INFO 2025-03-21 20:32:00,661 qnn_preprocess.py:69] Visiting: aten_mul_tensor_36, aten.mul.Tensor
2025-03-21T20:32:00.6767109Z [INFO 2025-03-21 20:32:00,662 qnn_preprocess.py:69] Visiting: aten_mul_tensor_38, aten.mul.Tensor
2025-03-21T20:32:00.6768359Z [INFO 2025-03-21 20:32:00,662 qnn_preprocess.py:69] Visiting: aten_mul_tensor_37, aten.mul.Tensor
2025-03-21T20:32:00.6769687Z [INFO 2025-03-21 20:32:00,663 qnn_preprocess.py:69] Visiting: aten_mul_tensor_39, aten.mul.Tensor
2025-03-21T20:32:00.6771009Z [INFO 2025-03-21 20:32:00,664 qnn_preprocess.py:69] Visiting: aten_select_copy_int_121, aten.select_copy.int
2025-03-21T20:32:00.6772400Z [INFO 2025-03-21 20:32:00,664 qnn_preprocess.py:69] Visiting: aten_select_copy_int_123, aten.select_copy.int
2025-03-21T20:32:00.6773763Z [INFO 2025-03-21 20:32:00,664 qnn_preprocess.py:69] Visiting: aten_select_copy_int_125, aten.select_copy.int
2025-03-21T20:32:00.6775174Z [INFO 2025-03-21 20:32:00,665 qnn_preprocess.py:69] Visiting: aten_select_copy_int_127, aten.select_copy.int
2025-03-21T20:32:00.6776557Z [INFO 2025-03-21 20:32:00,665 qnn_preprocess.py:69] Visiting: aten_select_copy_int_129, aten.select_copy.int
2025-03-21T20:32:00.6789817Z [INFO 2025-03-21 20:32:00,666 qnn_preprocess.py:69] Visiting: aten_select_copy_int_131, aten.select_copy.int
2025-03-21T20:32:00.6791419Z [INFO 2025-03-21 20:32:00,666 qnn_preprocess.py:69] Visiting: aten_select_copy_int_133, aten.select_copy.int
2025-03-21T20:32:00.7161949Z [INFO 2025-03-21 20:32:00,667 qnn_preprocess.py:69] Visiting: aten_select_copy_int_135, aten.select_copy.int
2025-03-21T20:32:00.7163495Z [INFO 2025-03-21 20:32:00,667 qnn_preprocess.py:69] Visiting: aten_select_copy_int_137, aten.select_copy.int
2025-03-21T20:32:00.7164831Z [INFO 2025-03-21 20:32:00,668 qnn_preprocess.py:69] Visiting: aten_select_copy_int_139, aten.select_copy.int
2025-03-21T20:32:00.7166012Z [INFO 2025-03-21 20:32:00,669 qnn_preprocess.py:69] Visiting: aten_select_copy_int_141, aten.select_copy.int
2025-03-21T20:32:00.7167366Z [INFO 2025-03-21 20:32:00,670 qnn_preprocess.py:69] Visiting: aten_select_copy_int_143, aten.select_copy.int
2025-03-21T20:32:00.7168636Z [INFO 2025-03-21 20:32:00,670 qnn_preprocess.py:69] Visiting: aten_sub_tensor_4, aten.sub.Tensor
2025-03-21T20:32:00.7169985Z [INFO 2025-03-21 20:32:00,671 qnn_preprocess.py:69] Visiting: aten_add_tensor_10, aten.add.Tensor
2025-03-21T20:32:00.7171134Z [INFO 2025-03-21 20:32:00,672 qnn_preprocess.py:69] Visiting: aten_sub_tensor_5, aten.sub.Tensor
2025-03-21T20:32:00.7172379Z [INFO 2025-03-21 20:32:00,673 qnn_preprocess.py:69] Visiting: aten_add_tensor_11, aten.add.Tensor
2025-03-21T20:32:00.7173618Z [INFO 2025-03-21 20:32:00,674 qnn_preprocess.py:69] Visiting: aten_cat_default_11, aten.cat.default
2025-03-21T20:32:00.7175004Z [INFO 2025-03-21 20:32:00,677 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_25, aten.unsqueeze_copy.default
2025-03-21T20:32:00.7176478Z [INFO 2025-03-21 20:32:00,678 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_26, aten.unsqueeze_copy.default
2025-03-21T20:32:00.7178017Z [INFO 2025-03-21 20:32:00,679 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_27, aten.unsqueeze_copy.default
2025-03-21T20:32:00.7179594Z [INFO 2025-03-21 20:32:00,679 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_28, aten.unsqueeze_copy.default
2025-03-21T20:32:00.7181090Z [INFO 2025-03-21 20:32:00,680 qnn_preprocess.py:69] Visiting: aten_view_copy_default_46, aten.view_copy.default
2025-03-21T20:32:00.7182438Z [INFO 2025-03-21 20:32:00,680 qnn_preprocess.py:69] Visiting: aten__to_copy_default_6, aten._to_copy.default
2025-03-21T20:32:00.7183771Z [INFO 2025-03-21 20:32:00,681 qnn_preprocess.py:69] Visiting: aten_cat_default_8, aten.cat.default
2025-03-21T20:32:00.7185260Z [INFO 2025-03-21 20:32:00,681 qnn_preprocess.py:69] Visiting: aten_cat_default_9, aten.cat.default
2025-03-21T20:32:00.7186613Z [INFO 2025-03-21 20:32:00,682 qnn_preprocess.py:69] Visiting: aten_view_copy_default_43, aten.view_copy.default
2025-03-21T20:32:00.7187812Z [INFO 2025-03-21 20:32:00,682 qnn_preprocess.py:69] Visiting: aten_view_copy_default_44, aten.view_copy.default
2025-03-21T20:32:00.7189203Z [INFO 2025-03-21 20:32:00,682 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_88, aten.permute_copy.default
2025-03-21T20:32:00.7190858Z [INFO 2025-03-21 20:32:00,683 qnn_preprocess.py:69] Visiting: aten_index_put_default_4, aten.index_put.default
2025-03-21T20:32:00.7192328Z [INFO 2025-03-21 20:32:00,684 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_89, aten.permute_copy.default
2025-03-21T20:32:00.7194075Z [INFO 2025-03-21 20:32:00,685 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_90, aten.permute_copy.default
2025-03-21T20:32:00.7195780Z [INFO 2025-03-21 20:32:00,686 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_91, aten.permute_copy.default
2025-03-21T20:32:00.7197675Z [INFO 2025-03-21 20:32:00,686 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_92, aten.permute_copy.default
2025-03-21T20:32:00.7199222Z [INFO 2025-03-21 20:32:00,687 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_93, aten.permute_copy.default
2025-03-21T20:32:00.7200681Z [INFO 2025-03-21 20:32:00,688 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_94, aten.permute_copy.default
2025-03-21T20:32:00.7202151Z [INFO 2025-03-21 20:32:00,688 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_95, aten.permute_copy.default
2025-03-21T20:32:00.7203619Z [INFO 2025-03-21 20:32:00,689 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_96, aten.permute_copy.default
2025-03-21T20:32:00.7205237Z [INFO 2025-03-21 20:32:00,690 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_97, aten.permute_copy.default
2025-03-21T20:32:00.7206567Z [INFO 2025-03-21 20:32:00,690 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_98, aten.permute_copy.default
2025-03-21T20:32:00.7208016Z [INFO 2025-03-21 20:32:00,691 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_99, aten.permute_copy.default
2025-03-21T20:32:00.7209481Z [INFO 2025-03-21 20:32:00,692 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_100, aten.permute_copy.default
2025-03-21T20:32:00.7210708Z [INFO 2025-03-21 20:32:00,692 qnn_preprocess.py:69] Visiting: aten_select_copy_int_96, aten.select_copy.int
2025-03-21T20:32:00.7211922Z [INFO 2025-03-21 20:32:00,693 qnn_preprocess.py:69] Visiting: aten_select_copy_int_98, aten.select_copy.int
2025-03-21T20:32:00.7213068Z [INFO 2025-03-21 20:32:00,693 qnn_preprocess.py:69] Visiting: aten_select_copy_int_100, aten.select_copy.int
2025-03-21T20:32:00.7214368Z [INFO 2025-03-21 20:32:00,694 qnn_preprocess.py:69] Visiting: aten_select_copy_int_102, aten.select_copy.int
2025-03-21T20:32:00.7215701Z [INFO 2025-03-21 20:32:00,694 qnn_preprocess.py:69] Visiting: aten_select_copy_int_104, aten.select_copy.int
2025-03-21T20:32:00.7216847Z [INFO 2025-03-21 20:32:00,694 qnn_preprocess.py:69] Visiting: aten_select_copy_int_106, aten.select_copy.int
2025-03-21T20:32:00.7218147Z [INFO 2025-03-21 20:32:00,695 qnn_preprocess.py:69] Visiting: aten_select_copy_int_108, aten.select_copy.int
2025-03-21T20:32:00.7219491Z [INFO 2025-03-21 20:32:00,695 qnn_preprocess.py:69] Visiting: aten_select_copy_int_110, aten.select_copy.int
2025-03-21T20:32:00.7220882Z [INFO 2025-03-21 20:32:00,696 qnn_preprocess.py:69] Visiting: aten_select_copy_int_112, aten.select_copy.int
2025-03-21T20:32:00.7222202Z [INFO 2025-03-21 20:32:00,696 qnn_preprocess.py:69] Visiting: aten_select_copy_int_114, aten.select_copy.int
2025-03-21T20:32:00.7223554Z [INFO 2025-03-21 20:32:00,697 qnn_preprocess.py:69] Visiting: aten_select_copy_int_116, aten.select_copy.int
2025-03-21T20:32:00.7224742Z [INFO 2025-03-21 20:32:00,697 qnn_preprocess.py:69] Visiting: aten_select_copy_int_118, aten.select_copy.int
2025-03-21T20:32:00.7226269Z [INFO 2025-03-21 20:32:00,698 qnn_preprocess.py:69] Visiting: aten_select_copy_int_97, aten.select_copy.int
2025-03-21T20:32:00.7227467Z [INFO 2025-03-21 20:32:00,698 qnn_preprocess.py:69] Visiting: aten_select_copy_int_99, aten.select_copy.int
2025-03-21T20:32:00.7228656Z [INFO 2025-03-21 20:32:00,698 qnn_preprocess.py:69] Visiting: aten_select_copy_int_101, aten.select_copy.int
2025-03-21T20:32:00.7229857Z [INFO 2025-03-21 20:32:00,699 qnn_preprocess.py:69] Visiting: aten_select_copy_int_103, aten.select_copy.int
2025-03-21T20:32:00.7230998Z [INFO 2025-03-21 20:32:00,699 qnn_preprocess.py:69] Visiting: aten_select_copy_int_105, aten.select_copy.int
2025-03-21T20:32:00.7232554Z [INFO 2025-03-21 20:32:00,700 qnn_preprocess.py:69] Visiting: aten_select_copy_int_107, aten.select_copy.int
2025-03-21T20:32:00.7233821Z [INFO 2025-03-21 20:32:00,700 qnn_preprocess.py:69] Visiting: aten_select_copy_int_109, aten.select_copy.int
2025-03-21T20:32:00.7234994Z [INFO 2025-03-21 20:32:00,701 qnn_preprocess.py:69] Visiting: aten_select_copy_int_111, aten.select_copy.int
2025-03-21T20:32:00.7236346Z [INFO 2025-03-21 20:32:00,701 qnn_preprocess.py:69] Visiting: aten_select_copy_int_113, aten.select_copy.int
2025-03-21T20:32:00.7237864Z [INFO 2025-03-21 20:32:00,702 qnn_preprocess.py:69] Visiting: aten_select_copy_int_115, aten.select_copy.int
2025-03-21T20:32:00.7239226Z [INFO 2025-03-21 20:32:00,702 qnn_preprocess.py:69] Visiting: aten_select_copy_int_117, aten.select_copy.int
2025-03-21T20:32:00.7240551Z [INFO 2025-03-21 20:32:00,702 qnn_preprocess.py:69] Visiting: aten_select_copy_int_119, aten.select_copy.int
2025-03-21T20:32:00.7241817Z [INFO 2025-03-21 20:32:00,703 qnn_preprocess.py:69] Visiting: aten_cat_default_10, aten.cat.default
2025-03-21T20:32:00.7243035Z [INFO 2025-03-21 20:32:00,705 qnn_preprocess.py:69] Visiting: aten_view_copy_default_45, aten.view_copy.default
2025-03-21T20:32:00.7244505Z [INFO 2025-03-21 20:32:00,705 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_113, aten.permute_copy.default
2025-03-21T20:32:00.7245740Z [INFO 2025-03-21 20:32:00,706 qnn_preprocess.py:69] Visiting: aten__to_copy_default_7, aten._to_copy.default
2025-03-21T20:32:00.7247010Z [INFO 2025-03-21 20:32:00,706 qnn_preprocess.py:69] Visiting: aten_matmul_default_4, aten.matmul.default
2025-03-21T20:32:00.7248289Z [INFO 2025-03-21 20:32:00,707 qnn_preprocess.py:69] Visiting: aten_mul_tensor_40, aten.mul.Tensor
2025-03-21T20:32:00.7249633Z [INFO 2025-03-21 20:32:00,708 qnn_preprocess.py:69] Visiting: aten_add_tensor_12, aten.add.Tensor
2025-03-21T20:32:00.7250893Z [INFO 2025-03-21 20:32:00,708 qnn_preprocess.py:69] Visiting: aten__softmax_default_2, aten._softmax.default
2025-03-21T20:32:00.7252204Z [INFO 2025-03-21 20:32:00,709 qnn_preprocess.py:69] Visiting: aten_matmul_default_5, aten.matmul.default
2025-03-21T20:32:00.7253762Z [INFO 2025-03-21 20:32:00,709 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_114, aten.permute_copy.default
2025-03-21T20:32:00.7255406Z [INFO 2025-03-21 20:32:00,710 qnn_preprocess.py:69] Visiting: aten_view_copy_default_53, aten.view_copy.default
2025-03-21T20:32:00.7257056Z [INFO 2025-03-21 20:32:00,710 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_29, aten.unsqueeze_copy.default
2025-03-21T20:32:00.7258763Z [INFO 2025-03-21 20:32:00,711 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_698, aten.permute_copy.default
2025-03-21T20:32:00.7260422Z [INFO 2025-03-21 20:32:00,712 qnn_preprocess.py:69] Visiting: aten_convolution_default_17, aten.convolution.default
2025-03-21T20:32:00.7262039Z [INFO 2025-03-21 20:32:00,714 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_699, aten.permute_copy.default
2025-03-21T20:32:00.7865629Z [INFO 2025-03-21 20:32:00,715 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_29, aten.squeeze_copy.dims
2025-03-21T20:32:00.7867067Z [INFO 2025-03-21 20:32:00,716 qnn_preprocess.py:69] Visiting: aten_add_tensor_13, aten.add.Tensor
2025-03-21T20:32:00.7868688Z [INFO 2025-03-21 20:32:00,717 qnn_preprocess.py:69] Visiting: aten_rms_norm_default_5, aten.rms_norm.default
2025-03-21T20:32:00.7870089Z [INFO 2025-03-21 20:32:00,719 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_30, aten.unsqueeze_copy.default
2025-03-21T20:32:00.7871686Z [INFO 2025-03-21 20:32:00,720 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_700, aten.permute_copy.default
2025-03-21T20:32:00.7873293Z [INFO 2025-03-21 20:32:00,721 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_31, aten.unsqueeze_copy.default
2025-03-21T20:32:00.7874887Z [INFO 2025-03-21 20:32:00,722 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_701, aten.permute_copy.default
2025-03-21T20:32:00.7876462Z [INFO 2025-03-21 20:32:00,723 qnn_preprocess.py:69] Visiting: aten_convolution_default_18, aten.convolution.default
2025-03-21T20:32:00.7877833Z [INFO 2025-03-21 20:32:00,729 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_702, aten.permute_copy.default
2025-03-21T20:32:00.7879403Z [INFO 2025-03-21 20:32:00,730 qnn_preprocess.py:69] Visiting: aten_convolution_default_19, aten.convolution.default
2025-03-21T20:32:00.7880961Z [INFO 2025-03-21 20:32:00,737 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_703, aten.permute_copy.default
2025-03-21T20:32:00.7882624Z [INFO 2025-03-21 20:32:00,738 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_30, aten.squeeze_copy.dims
2025-03-21T20:32:00.7884114Z [INFO 2025-03-21 20:32:00,739 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_31, aten.squeeze_copy.dims
2025-03-21T20:32:00.7885370Z [INFO 2025-03-21 20:32:00,739 qnn_preprocess.py:69] Visiting: aten_sigmoid_default_2, aten.sigmoid.default
2025-03-21T20:32:00.7886723Z [INFO 2025-03-21 20:32:00,740 qnn_preprocess.py:69] Visiting: aten_mul_tensor_43, aten.mul.Tensor
2025-03-21T20:32:00.7888147Z [INFO 2025-03-21 20:32:00,740 qnn_preprocess.py:69] Visiting: aten_mul_tensor_44, aten.mul.Tensor
2025-03-21T20:32:00.7889764Z [INFO 2025-03-21 20:32:00,741 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_32, aten.unsqueeze_copy.default
2025-03-21T20:32:00.7891378Z [INFO 2025-03-21 20:32:00,741 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_704, aten.permute_copy.default
2025-03-21T20:32:00.7892802Z [INFO 2025-03-21 20:32:00,742 qnn_preprocess.py:69] Visiting: aten_convolution_default_20, aten.convolution.default
2025-03-21T20:32:00.7894270Z [INFO 2025-03-21 20:32:00,748 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_705, aten.permute_copy.default
2025-03-21T20:32:00.7895785Z [INFO 2025-03-21 20:32:00,749 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_32, aten.squeeze_copy.dims
2025-03-21T20:32:00.7897188Z [INFO 2025-03-21 20:32:00,749 qnn_preprocess.py:69] Visiting: aten_add_tensor_14, aten.add.Tensor
2025-03-21T20:32:00.7898538Z [INFO 2025-03-21 20:32:00,750 qnn_preprocess.py:69] Visiting: aten_rms_norm_default_6, aten.rms_norm.default
2025-03-21T20:32:00.7900052Z [INFO 2025-03-21 20:32:00,751 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_33, aten.unsqueeze_copy.default
2025-03-21T20:32:00.7901492Z [INFO 2025-03-21 20:32:00,752 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_706, aten.permute_copy.default
2025-03-21T20:32:00.7903094Z [INFO 2025-03-21 20:32:00,752 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_34, aten.unsqueeze_copy.default
2025-03-21T20:32:00.7904684Z [INFO 2025-03-21 20:32:00,753 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_707, aten.permute_copy.default
2025-03-21T20:32:00.7906220Z [INFO 2025-03-21 20:32:00,754 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_35, aten.unsqueeze_copy.default
2025-03-21T20:32:00.7907848Z [INFO 2025-03-21 20:32:00,754 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_708, aten.permute_copy.default
2025-03-21T20:32:00.7909420Z [INFO 2025-03-21 20:32:00,755 qnn_preprocess.py:69] Visiting: aten_convolution_default_21, aten.convolution.default
2025-03-21T20:32:00.7910878Z [INFO 2025-03-21 20:32:00,758 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_709, aten.permute_copy.default
2025-03-21T20:32:00.7912634Z [INFO 2025-03-21 20:32:00,759 qnn_preprocess.py:69] Visiting: aten_convolution_default_22, aten.convolution.default
2025-03-21T20:32:00.7914183Z [INFO 2025-03-21 20:32:00,761 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_710, aten.permute_copy.default
2025-03-21T20:32:00.7915693Z [INFO 2025-03-21 20:32:00,762 qnn_preprocess.py:69] Visiting: aten_convolution_default_23, aten.convolution.default
2025-03-21T20:32:00.7917283Z [INFO 2025-03-21 20:32:00,765 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_711, aten.permute_copy.default
2025-03-21T20:32:00.7918824Z [INFO 2025-03-21 20:32:00,766 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_33, aten.squeeze_copy.dims
2025-03-21T20:32:00.7920172Z [INFO 2025-03-21 20:32:00,766 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_34, aten.squeeze_copy.dims
2025-03-21T20:32:00.7921668Z [INFO 2025-03-21 20:32:00,767 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_35, aten.squeeze_copy.dims
2025-03-21T20:32:00.7923139Z [INFO 2025-03-21 20:32:00,767 qnn_preprocess.py:69] Visiting: aten_view_copy_default_54, aten.view_copy.default
2025-03-21T20:32:00.7924667Z [INFO 2025-03-21 20:32:00,768 qnn_preprocess.py:69] Visiting: aten_view_copy_default_55, aten.view_copy.default
2025-03-21T20:32:00.7926138Z [INFO 2025-03-21 20:32:00,768 qnn_preprocess.py:69] Visiting: aten_view_copy_default_56, aten.view_copy.default
2025-03-21T20:32:00.7927607Z [INFO 2025-03-21 20:32:00,768 qnn_preprocess.py:69] Visiting: aten_view_copy_default_57, aten.view_copy.default
2025-03-21T20:32:00.7929056Z [INFO 2025-03-21 20:32:00,769 qnn_preprocess.py:69] Visiting: aten_view_copy_default_58, aten.view_copy.default
2025-03-21T20:32:00.7930541Z [INFO 2025-03-21 20:32:00,769 qnn_preprocess.py:69] Visiting: aten_index_put_default_7, aten.index_put.default
2025-03-21T20:32:00.7932076Z [INFO 2025-03-21 20:32:00,770 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_12, aten.slice_copy.Tensor
2025-03-21T20:32:00.7933809Z [INFO 2025-03-21 20:32:00,771 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_13, aten.slice_copy.Tensor
2025-03-21T20:32:00.7935191Z [INFO 2025-03-21 20:32:00,771 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_14, aten.slice_copy.Tensor
2025-03-21T20:32:00.7936686Z [INFO 2025-03-21 20:32:00,772 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_15, aten.slice_copy.Tensor
2025-03-21T20:32:00.7938235Z [INFO 2025-03-21 20:32:00,772 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_142, aten.permute_copy.default
2025-03-21T20:32:00.7939678Z [INFO 2025-03-21 20:32:00,773 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_143, aten.permute_copy.default
2025-03-21T20:32:00.7941271Z [INFO 2025-03-21 20:32:00,773 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_144, aten.permute_copy.default
2025-03-21T20:32:00.7942834Z [INFO 2025-03-21 20:32:00,774 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_145, aten.permute_copy.default
2025-03-21T20:32:00.7944336Z [INFO 2025-03-21 20:32:00,775 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_146, aten.permute_copy.default
2025-03-21T20:32:00.7945935Z [INFO 2025-03-21 20:32:00,776 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_147, aten.permute_copy.default
2025-03-21T20:32:00.7947520Z [INFO 2025-03-21 20:32:00,777 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_148, aten.permute_copy.default
2025-03-21T20:32:00.7948997Z [INFO 2025-03-21 20:32:00,777 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_149, aten.permute_copy.default
2025-03-21T20:32:00.7950597Z [INFO 2025-03-21 20:32:00,778 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_150, aten.permute_copy.default
2025-03-21T20:32:00.7952159Z [INFO 2025-03-21 20:32:00,779 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_151, aten.permute_copy.default
2025-03-21T20:32:00.7953682Z [INFO 2025-03-21 20:32:00,780 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_152, aten.permute_copy.default
2025-03-21T20:32:00.7955511Z [INFO 2025-03-21 20:32:00,780 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_153, aten.permute_copy.default
2025-03-21T20:32:00.7957057Z [INFO 2025-03-21 20:32:00,781 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_36, aten.squeeze_copy.dims
2025-03-21T20:32:00.7958383Z [INFO 2025-03-21 20:32:00,781 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_37, aten.squeeze_copy.dims
2025-03-21T20:32:00.7959867Z [INFO 2025-03-21 20:32:00,782 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_38, aten.squeeze_copy.dims
2025-03-21T20:32:00.7961314Z [INFO 2025-03-21 20:32:00,782 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_39, aten.squeeze_copy.dims
2025-03-21T20:32:00.7962739Z [INFO 2025-03-21 20:32:00,783 qnn_preprocess.py:69] Visiting: aten_select_copy_int_168, aten.select_copy.int
2025-03-21T20:32:00.7964143Z [INFO 2025-03-21 20:32:00,783 qnn_preprocess.py:69] Visiting: aten_select_copy_int_170, aten.select_copy.int
2025-03-21T20:32:00.7965577Z [INFO 2025-03-21 20:32:00,784 qnn_preprocess.py:69] Visiting: aten_select_copy_int_172, aten.select_copy.int
2025-03-21T20:32:00.7966999Z [INFO 2025-03-21 20:32:00,784 qnn_preprocess.py:69] Visiting: aten_select_copy_int_174, aten.select_copy.int
2025-03-21T20:32:00.7968452Z [INFO 2025-03-21 20:32:00,784 qnn_preprocess.py:69] Visiting: aten_select_copy_int_176, aten.select_copy.int
2025-03-21T20:32:00.7969953Z [INFO 2025-03-21 20:32:00,785 qnn_preprocess.py:69] Visiting: aten_select_copy_int_178, aten.select_copy.int
2025-03-21T20:32:00.7971397Z [INFO 2025-03-21 20:32:00,785 qnn_preprocess.py:69] Visiting: aten_select_copy_int_180, aten.select_copy.int
2025-03-21T20:32:00.8293605Z [INFO 2025-03-21 20:32:00,786 qnn_preprocess.py:69] Visiting: aten_select_copy_int_182, aten.select_copy.int
2025-03-21T20:32:00.8295005Z [INFO 2025-03-21 20:32:00,786 qnn_preprocess.py:69] Visiting: aten_select_copy_int_184, aten.select_copy.int
2025-03-21T20:32:00.8296544Z [INFO 2025-03-21 20:32:00,787 qnn_preprocess.py:69] Visiting: aten_select_copy_int_186, aten.select_copy.int
2025-03-21T20:32:00.8297707Z [INFO 2025-03-21 20:32:00,788 qnn_preprocess.py:69] Visiting: aten_select_copy_int_188, aten.select_copy.int
2025-03-21T20:32:00.8298986Z [INFO 2025-03-21 20:32:00,789 qnn_preprocess.py:69] Visiting: aten_select_copy_int_190, aten.select_copy.int
2025-03-21T20:32:00.8300260Z [INFO 2025-03-21 20:32:00,790 qnn_preprocess.py:69] Visiting: aten_mul_tensor_47, aten.mul.Tensor
2025-03-21T20:32:00.8301516Z [INFO 2025-03-21 20:32:00,791 qnn_preprocess.py:69] Visiting: aten_mul_tensor_49, aten.mul.Tensor
2025-03-21T20:32:00.8302737Z [INFO 2025-03-21 20:32:00,791 qnn_preprocess.py:69] Visiting: aten_mul_tensor_48, aten.mul.Tensor
2025-03-21T20:32:00.8303994Z [INFO 2025-03-21 20:32:00,792 qnn_preprocess.py:69] Visiting: aten_mul_tensor_50, aten.mul.Tensor
2025-03-21T20:32:00.8305099Z [INFO 2025-03-21 20:32:00,793 qnn_preprocess.py:69] Visiting: aten_mul_tensor_51, aten.mul.Tensor
2025-03-21T20:32:00.8306228Z [INFO 2025-03-21 20:32:00,794 qnn_preprocess.py:69] Visiting: aten_mul_tensor_53, aten.mul.Tensor
2025-03-21T20:32:00.8307461Z [INFO 2025-03-21 20:32:00,795 qnn_preprocess.py:69] Visiting: aten_mul_tensor_52, aten.mul.Tensor
2025-03-21T20:32:00.8308694Z [INFO 2025-03-21 20:32:00,796 qnn_preprocess.py:69] Visiting: aten_mul_tensor_54, aten.mul.Tensor
2025-03-21T20:32:00.8309985Z [INFO 2025-03-21 20:32:00,797 qnn_preprocess.py:69] Visiting: aten_select_copy_int_169, aten.select_copy.int
2025-03-21T20:32:00.8311375Z [INFO 2025-03-21 20:32:00,797 qnn_preprocess.py:69] Visiting: aten_select_copy_int_171, aten.select_copy.int
2025-03-21T20:32:00.8312659Z [INFO 2025-03-21 20:32:00,798 qnn_preprocess.py:69] Visiting: aten_select_copy_int_173, aten.select_copy.int
2025-03-21T20:32:00.8313888Z [INFO 2025-03-21 20:32:00,798 qnn_preprocess.py:69] Visiting: aten_select_copy_int_175, aten.select_copy.int
2025-03-21T20:32:00.8315256Z [INFO 2025-03-21 20:32:00,799 qnn_preprocess.py:69] Visiting: aten_select_copy_int_177, aten.select_copy.int
2025-03-21T20:32:00.8316749Z [INFO 2025-03-21 20:32:00,799 qnn_preprocess.py:69] Visiting: aten_select_copy_int_179, aten.select_copy.int
2025-03-21T20:32:00.8318133Z [INFO 2025-03-21 20:32:00,800 qnn_preprocess.py:69] Visiting: aten_select_copy_int_181, aten.select_copy.int
2025-03-21T20:32:00.8319538Z [INFO 2025-03-21 20:32:00,800 qnn_preprocess.py:69] Visiting: aten_select_copy_int_183, aten.select_copy.int
2025-03-21T20:32:00.8320694Z [INFO 2025-03-21 20:32:00,801 qnn_preprocess.py:69] Visiting: aten_select_copy_int_185, aten.select_copy.int
2025-03-21T20:32:00.8321946Z [INFO 2025-03-21 20:32:00,801 qnn_preprocess.py:69] Visiting: aten_select_copy_int_187, aten.select_copy.int
2025-03-21T20:32:00.8323288Z [INFO 2025-03-21 20:32:00,801 qnn_preprocess.py:69] Visiting: aten_select_copy_int_189, aten.select_copy.int
2025-03-21T20:32:00.8324676Z [INFO 2025-03-21 20:32:00,802 qnn_preprocess.py:69] Visiting: aten_select_copy_int_191, aten.select_copy.int
2025-03-21T20:32:00.8325965Z [INFO 2025-03-21 20:32:00,802 qnn_preprocess.py:69] Visiting: aten_sub_tensor_6, aten.sub.Tensor
2025-03-21T20:32:00.8327210Z [INFO 2025-03-21 20:32:00,803 qnn_preprocess.py:69] Visiting: aten_add_tensor_15, aten.add.Tensor
2025-03-21T20:32:00.8328563Z [INFO 2025-03-21 20:32:00,803 qnn_preprocess.py:69] Visiting: aten_sub_tensor_7, aten.sub.Tensor
2025-03-21T20:32:00.8329889Z [INFO 2025-03-21 20:32:00,804 qnn_preprocess.py:69] Visiting: aten_add_tensor_16, aten.add.Tensor
2025-03-21T20:32:00.8331158Z [INFO 2025-03-21 20:32:00,804 qnn_preprocess.py:69] Visiting: aten_cat_default_15, aten.cat.default
2025-03-21T20:32:00.8332770Z [INFO 2025-03-21 20:32:00,806 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_36, aten.unsqueeze_copy.default
2025-03-21T20:32:00.8334337Z [INFO 2025-03-21 20:32:00,806 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_37, aten.unsqueeze_copy.default
2025-03-21T20:32:00.8336008Z [INFO 2025-03-21 20:32:00,807 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_38, aten.unsqueeze_copy.default
2025-03-21T20:32:00.8337581Z [INFO 2025-03-21 20:32:00,807 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_39, aten.unsqueeze_copy.default
2025-03-21T20:32:00.8339089Z [INFO 2025-03-21 20:32:00,807 qnn_preprocess.py:69] Visiting: aten_view_copy_default_64, aten.view_copy.default
2025-03-21T20:32:00.8340483Z [INFO 2025-03-21 20:32:00,808 qnn_preprocess.py:69] Visiting: aten__to_copy_default_8, aten._to_copy.default
2025-03-21T20:32:00.8341806Z [INFO 2025-03-21 20:32:00,809 qnn_preprocess.py:69] Visiting: aten_cat_default_12, aten.cat.default
2025-03-21T20:32:00.8343080Z [INFO 2025-03-21 20:32:00,809 qnn_preprocess.py:69] Visiting: aten_cat_default_13, aten.cat.default
2025-03-21T20:32:00.8344410Z [INFO 2025-03-21 20:32:00,810 qnn_preprocess.py:69] Visiting: aten_view_copy_default_61, aten.view_copy.default
2025-03-21T20:32:00.8345811Z [INFO 2025-03-21 20:32:00,810 qnn_preprocess.py:69] Visiting: aten_view_copy_default_62, aten.view_copy.default
2025-03-21T20:32:00.8347294Z [INFO 2025-03-21 20:32:00,810 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_129, aten.permute_copy.default
2025-03-21T20:32:00.8348716Z [INFO 2025-03-21 20:32:00,811 qnn_preprocess.py:69] Visiting: aten_index_put_default_6, aten.index_put.default
2025-03-21T20:32:00.8350083Z [INFO 2025-03-21 20:32:00,812 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_130, aten.permute_copy.default
2025-03-21T20:32:00.8351393Z [INFO 2025-03-21 20:32:00,813 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_131, aten.permute_copy.default
2025-03-21T20:32:00.8352889Z [INFO 2025-03-21 20:32:00,814 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_132, aten.permute_copy.default
2025-03-21T20:32:00.8354367Z [INFO 2025-03-21 20:32:00,814 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_133, aten.permute_copy.default
2025-03-21T20:32:00.8355809Z [INFO 2025-03-21 20:32:00,815 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_134, aten.permute_copy.default
2025-03-21T20:32:00.8357339Z [INFO 2025-03-21 20:32:00,815 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_135, aten.permute_copy.default
2025-03-21T20:32:00.8358844Z [INFO 2025-03-21 20:32:00,816 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_136, aten.permute_copy.default
2025-03-21T20:32:00.8360119Z [INFO 2025-03-21 20:32:00,817 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_137, aten.permute_copy.default
2025-03-21T20:32:00.8361464Z [INFO 2025-03-21 20:32:00,817 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_138, aten.permute_copy.default
2025-03-21T20:32:00.8362749Z [INFO 2025-03-21 20:32:00,818 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_139, aten.permute_copy.default
2025-03-21T20:32:00.8364161Z [INFO 2025-03-21 20:32:00,819 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_140, aten.permute_copy.default
2025-03-21T20:32:00.8365577Z [INFO 2025-03-21 20:32:00,819 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_141, aten.permute_copy.default
2025-03-21T20:32:00.8366803Z [INFO 2025-03-21 20:32:00,820 qnn_preprocess.py:69] Visiting: aten_select_copy_int_144, aten.select_copy.int
2025-03-21T20:32:00.8368170Z [INFO 2025-03-21 20:32:00,820 qnn_preprocess.py:69] Visiting: aten_select_copy_int_146, aten.select_copy.int
2025-03-21T20:32:00.8369748Z [INFO 2025-03-21 20:32:00,821 qnn_preprocess.py:69] Visiting: aten_select_copy_int_148, aten.select_copy.int
2025-03-21T20:32:00.8371102Z [INFO 2025-03-21 20:32:00,821 qnn_preprocess.py:69] Visiting: aten_select_copy_int_150, aten.select_copy.int
2025-03-21T20:32:00.8372485Z [INFO 2025-03-21 20:32:00,822 qnn_preprocess.py:69] Visiting: aten_select_copy_int_152, aten.select_copy.int
2025-03-21T20:32:00.8373737Z [INFO 2025-03-21 20:32:00,822 qnn_preprocess.py:69] Visiting: aten_select_copy_int_154, aten.select_copy.int
2025-03-21T20:32:00.8375101Z [INFO 2025-03-21 20:32:00,823 qnn_preprocess.py:69] Visiting: aten_select_copy_int_156, aten.select_copy.int
2025-03-21T20:32:00.8376518Z [INFO 2025-03-21 20:32:00,823 qnn_preprocess.py:69] Visiting: aten_select_copy_int_158, aten.select_copy.int
2025-03-21T20:32:00.8377905Z [INFO 2025-03-21 20:32:00,823 qnn_preprocess.py:69] Visiting: aten_select_copy_int_160, aten.select_copy.int
2025-03-21T20:32:00.8379090Z [INFO 2025-03-21 20:32:00,824 qnn_preprocess.py:69] Visiting: aten_select_copy_int_162, aten.select_copy.int
2025-03-21T20:32:00.8380406Z [INFO 2025-03-21 20:32:00,824 qnn_preprocess.py:69] Visiting: aten_select_copy_int_164, aten.select_copy.int
2025-03-21T20:32:00.8381750Z [INFO 2025-03-21 20:32:00,825 qnn_preprocess.py:69] Visiting: aten_select_copy_int_166, aten.select_copy.int
2025-03-21T20:32:00.8383132Z [INFO 2025-03-21 20:32:00,825 qnn_preprocess.py:69] Visiting: aten_select_copy_int_145, aten.select_copy.int
2025-03-21T20:32:00.8384490Z [INFO 2025-03-21 20:32:00,826 qnn_preprocess.py:69] Visiting: aten_select_copy_int_147, aten.select_copy.int
2025-03-21T20:32:00.8385828Z [INFO 2025-03-21 20:32:00,826 qnn_preprocess.py:69] Visiting: aten_select_copy_int_149, aten.select_copy.int
2025-03-21T20:32:00.8387209Z [INFO 2025-03-21 20:32:00,826 qnn_preprocess.py:69] Visiting: aten_select_copy_int_151, aten.select_copy.int
2025-03-21T20:32:00.8388427Z [INFO 2025-03-21 20:32:00,827 qnn_preprocess.py:69] Visiting: aten_select_copy_int_153, aten.select_copy.int
2025-03-21T20:32:00.8389733Z [INFO 2025-03-21 20:32:00,827 qnn_preprocess.py:69] Visiting: aten_select_copy_int_155, aten.select_copy.int
2025-03-21T20:32:00.8391052Z [INFO 2025-03-21 20:32:00,828 qnn_preprocess.py:69] Visiting: aten_select_copy_int_157, aten.select_copy.int
2025-03-21T20:32:00.8392419Z [INFO 2025-03-21 20:32:00,828 qnn_preprocess.py:69] Visiting: aten_select_copy_int_159, aten.select_copy.int
2025-03-21T20:32:00.9042827Z [INFO 2025-03-21 20:32:00,829 qnn_preprocess.py:69] Visiting: aten_select_copy_int_161, aten.select_copy.int
2025-03-21T20:32:00.9044114Z [INFO 2025-03-21 20:32:00,829 qnn_preprocess.py:69] Visiting: aten_select_copy_int_163, aten.select_copy.int
2025-03-21T20:32:00.9045309Z [INFO 2025-03-21 20:32:00,830 qnn_preprocess.py:69] Visiting: aten_select_copy_int_165, aten.select_copy.int
2025-03-21T20:32:00.9047065Z [INFO 2025-03-21 20:32:00,831 qnn_preprocess.py:69] Visiting: aten_select_copy_int_167, aten.select_copy.int
2025-03-21T20:32:00.9048316Z [INFO 2025-03-21 20:32:00,832 qnn_preprocess.py:69] Visiting: aten_cat_default_14, aten.cat.default
2025-03-21T20:32:00.9049587Z [INFO 2025-03-21 20:32:00,835 qnn_preprocess.py:69] Visiting: aten_view_copy_default_63, aten.view_copy.default
2025-03-21T20:32:00.9051030Z [INFO 2025-03-21 20:32:00,835 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_154, aten.permute_copy.default
2025-03-21T20:32:00.9052254Z [INFO 2025-03-21 20:32:00,836 qnn_preprocess.py:69] Visiting: aten__to_copy_default_9, aten._to_copy.default
2025-03-21T20:32:00.9053432Z [INFO 2025-03-21 20:32:00,837 qnn_preprocess.py:69] Visiting: aten_matmul_default_6, aten.matmul.default
2025-03-21T20:32:00.9054567Z [INFO 2025-03-21 20:32:00,838 qnn_preprocess.py:69] Visiting: aten_mul_tensor_55, aten.mul.Tensor
2025-03-21T20:32:00.9055614Z [INFO 2025-03-21 20:32:00,840 qnn_preprocess.py:69] Visiting: aten_add_tensor_17, aten.add.Tensor
2025-03-21T20:32:00.9056880Z [INFO 2025-03-21 20:32:00,840 qnn_preprocess.py:69] Visiting: aten__softmax_default_3, aten._softmax.default
2025-03-21T20:32:00.9058328Z [INFO 2025-03-21 20:32:00,841 qnn_preprocess.py:69] Visiting: aten_matmul_default_7, aten.matmul.default
2025-03-21T20:32:00.9059553Z [INFO 2025-03-21 20:32:00,841 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_155, aten.permute_copy.default
2025-03-21T20:32:00.9060996Z [INFO 2025-03-21 20:32:00,842 qnn_preprocess.py:69] Visiting: aten_view_copy_default_71, aten.view_copy.default
2025-03-21T20:32:00.9062301Z [INFO 2025-03-21 20:32:00,842 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_40, aten.unsqueeze_copy.default
2025-03-21T20:32:00.9063852Z [INFO 2025-03-21 20:32:00,843 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_712, aten.permute_copy.default
2025-03-21T20:32:00.9065161Z [INFO 2025-03-21 20:32:00,843 qnn_preprocess.py:69] Visiting: aten_convolution_default_24, aten.convolution.default
2025-03-21T20:32:00.9066517Z [INFO 2025-03-21 20:32:00,846 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_713, aten.permute_copy.default
2025-03-21T20:32:00.9067963Z [INFO 2025-03-21 20:32:00,847 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_40, aten.squeeze_copy.dims
2025-03-21T20:32:00.9069088Z [INFO 2025-03-21 20:32:00,847 qnn_preprocess.py:69] Visiting: aten_add_tensor_18, aten.add.Tensor
2025-03-21T20:32:00.9070298Z [INFO 2025-03-21 20:32:00,848 qnn_preprocess.py:69] Visiting: aten_rms_norm_default_7, aten.rms_norm.default
2025-03-21T20:32:00.9071725Z [INFO 2025-03-21 20:32:00,849 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_41, aten.unsqueeze_copy.default
2025-03-21T20:32:00.9073007Z [INFO 2025-03-21 20:32:00,850 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_714, aten.permute_copy.default
2025-03-21T20:32:00.9074574Z [INFO 2025-03-21 20:32:00,850 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_42, aten.unsqueeze_copy.default
2025-03-21T20:32:00.9075889Z [INFO 2025-03-21 20:32:00,851 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_715, aten.permute_copy.default
2025-03-21T20:32:00.9077343Z [INFO 2025-03-21 20:32:00,851 qnn_preprocess.py:69] Visiting: aten_convolution_default_25, aten.convolution.default
2025-03-21T20:32:00.9078711Z [INFO 2025-03-21 20:32:00,857 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_716, aten.permute_copy.default
2025-03-21T20:32:00.9080061Z [INFO 2025-03-21 20:32:00,858 qnn_preprocess.py:69] Visiting: aten_convolution_default_26, aten.convolution.default
2025-03-21T20:32:00.9081550Z [INFO 2025-03-21 20:32:00,866 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_717, aten.permute_copy.default
2025-03-21T20:32:00.9082769Z [INFO 2025-03-21 20:32:00,867 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_41, aten.squeeze_copy.dims
2025-03-21T20:32:00.9084029Z [INFO 2025-03-21 20:32:00,868 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_42, aten.squeeze_copy.dims
2025-03-21T20:32:00.9085465Z [INFO 2025-03-21 20:32:00,868 qnn_preprocess.py:69] Visiting: aten_sigmoid_default_3, aten.sigmoid.default
2025-03-21T20:32:00.9086648Z [INFO 2025-03-21 20:32:00,868 qnn_preprocess.py:69] Visiting: aten_mul_tensor_58, aten.mul.Tensor
2025-03-21T20:32:00.9087869Z [INFO 2025-03-21 20:32:00,869 qnn_preprocess.py:69] Visiting: aten_mul_tensor_59, aten.mul.Tensor
2025-03-21T20:32:00.9089064Z [INFO 2025-03-21 20:32:00,869 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_43, aten.unsqueeze_copy.default
2025-03-21T20:32:00.9090606Z [INFO 2025-03-21 20:32:00,870 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_718, aten.permute_copy.default
2025-03-21T20:32:00.9092040Z [INFO 2025-03-21 20:32:00,870 qnn_preprocess.py:69] Visiting: aten_convolution_default_27, aten.convolution.default
2025-03-21T20:32:00.9093312Z [INFO 2025-03-21 20:32:00,876 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_719, aten.permute_copy.default
2025-03-21T20:32:00.9094630Z [INFO 2025-03-21 20:32:00,877 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_43, aten.squeeze_copy.dims
2025-03-21T20:32:00.9095871Z [INFO 2025-03-21 20:32:00,878 qnn_preprocess.py:69] Visiting: aten_add_tensor_19, aten.add.Tensor
2025-03-21T20:32:00.9097094Z [INFO 2025-03-21 20:32:00,878 qnn_preprocess.py:69] Visiting: aten_rms_norm_default_8, aten.rms_norm.default
2025-03-21T20:32:00.9098513Z [INFO 2025-03-21 20:32:00,880 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_44, aten.unsqueeze_copy.default
2025-03-21T20:32:00.9099778Z [INFO 2025-03-21 20:32:00,880 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_720, aten.permute_copy.default
2025-03-21T20:32:00.9101289Z [INFO 2025-03-21 20:32:00,881 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_45, aten.unsqueeze_copy.default
2025-03-21T20:32:00.9102761Z [INFO 2025-03-21 20:32:00,881 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_721, aten.permute_copy.default
2025-03-21T20:32:00.9104129Z [INFO 2025-03-21 20:32:00,882 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_46, aten.unsqueeze_copy.default
2025-03-21T20:32:00.9105451Z [INFO 2025-03-21 20:32:00,882 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_722, aten.permute_copy.default
2025-03-21T20:32:00.9106780Z [INFO 2025-03-21 20:32:00,883 qnn_preprocess.py:69] Visiting: aten_convolution_default_28, aten.convolution.default
2025-03-21T20:32:00.9108267Z [INFO 2025-03-21 20:32:00,886 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_723, aten.permute_copy.default
2025-03-21T20:32:00.9109526Z [INFO 2025-03-21 20:32:00,887 qnn_preprocess.py:69] Visiting: aten_convolution_default_29, aten.convolution.default
2025-03-21T20:32:00.9110935Z [INFO 2025-03-21 20:32:00,890 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_724, aten.permute_copy.default
2025-03-21T20:32:00.9112420Z [INFO 2025-03-21 20:32:00,891 qnn_preprocess.py:69] Visiting: aten_convolution_default_30, aten.convolution.default
2025-03-21T20:32:00.9113954Z [INFO 2025-03-21 20:32:00,894 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_725, aten.permute_copy.default
2025-03-21T20:32:00.9115381Z [INFO 2025-03-21 20:32:00,894 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_44, aten.squeeze_copy.dims
2025-03-21T20:32:00.9116710Z [INFO 2025-03-21 20:32:00,895 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_45, aten.squeeze_copy.dims
2025-03-21T20:32:00.9118001Z [INFO 2025-03-21 20:32:00,895 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_46, aten.squeeze_copy.dims
2025-03-21T20:32:00.9119397Z [INFO 2025-03-21 20:32:00,896 qnn_preprocess.py:69] Visiting: aten_view_copy_default_72, aten.view_copy.default
2025-03-21T20:32:00.9120790Z [INFO 2025-03-21 20:32:00,896 qnn_preprocess.py:69] Visiting: aten_view_copy_default_73, aten.view_copy.default
2025-03-21T20:32:00.9122183Z [INFO 2025-03-21 20:32:00,896 qnn_preprocess.py:69] Visiting: aten_view_copy_default_74, aten.view_copy.default
2025-03-21T20:32:00.9123718Z [INFO 2025-03-21 20:32:00,897 qnn_preprocess.py:69] Visiting: aten_view_copy_default_75, aten.view_copy.default
2025-03-21T20:32:00.9124997Z [INFO 2025-03-21 20:32:00,897 qnn_preprocess.py:69] Visiting: aten_view_copy_default_76, aten.view_copy.default
2025-03-21T20:32:00.9126397Z [INFO 2025-03-21 20:32:00,897 qnn_preprocess.py:69] Visiting: aten_index_put_default_9, aten.index_put.default
2025-03-21T20:32:00.9127796Z [INFO 2025-03-21 20:32:00,898 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_16, aten.slice_copy.Tensor
2025-03-21T20:32:00.9129168Z [INFO 2025-03-21 20:32:00,899 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_17, aten.slice_copy.Tensor
2025-03-21T20:32:00.9130669Z [INFO 2025-03-21 20:32:00,899 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_18, aten.slice_copy.Tensor
2025-03-21T20:32:00.9131954Z [INFO 2025-03-21 20:32:00,900 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_19, aten.slice_copy.Tensor
2025-03-21T20:32:00.9133565Z [INFO 2025-03-21 20:32:00,900 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_183, aten.permute_copy.default
2025-03-21T20:32:00.9135055Z [INFO 2025-03-21 20:32:00,901 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_184, aten.permute_copy.default
2025-03-21T20:32:00.9136729Z [INFO 2025-03-21 20:32:00,901 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_185, aten.permute_copy.default
2025-03-21T20:32:00.9138258Z [INFO 2025-03-21 20:32:00,902 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_186, aten.permute_copy.default
2025-03-21T20:32:00.9139598Z [INFO 2025-03-21 20:32:00,903 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_187, aten.permute_copy.default
2025-03-21T20:32:00.9475671Z [INFO 2025-03-21 20:32:00,903 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_188, aten.permute_copy.default
2025-03-21T20:32:00.9477256Z [INFO 2025-03-21 20:32:00,904 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_189, aten.permute_copy.default
2025-03-21T20:32:00.9478628Z [INFO 2025-03-21 20:32:00,905 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_190, aten.permute_copy.default
2025-03-21T20:32:00.9479988Z [INFO 2025-03-21 20:32:00,906 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_191, aten.permute_copy.default
2025-03-21T20:32:00.9481340Z [INFO 2025-03-21 20:32:00,907 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_192, aten.permute_copy.default
2025-03-21T20:32:00.9482704Z [INFO 2025-03-21 20:32:00,908 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_193, aten.permute_copy.default
2025-03-21T20:32:00.9484036Z [INFO 2025-03-21 20:32:00,909 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_194, aten.permute_copy.default
2025-03-21T20:32:00.9485357Z [INFO 2025-03-21 20:32:00,910 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_47, aten.squeeze_copy.dims
2025-03-21T20:32:00.9486625Z [INFO 2025-03-21 20:32:00,911 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_48, aten.squeeze_copy.dims
2025-03-21T20:32:00.9487884Z [INFO 2025-03-21 20:32:00,912 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_49, aten.squeeze_copy.dims
2025-03-21T20:32:00.9489147Z [INFO 2025-03-21 20:32:00,913 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_50, aten.squeeze_copy.dims
2025-03-21T20:32:00.9490448Z [INFO 2025-03-21 20:32:00,913 qnn_preprocess.py:69] Visiting: aten_select_copy_int_216, aten.select_copy.int
2025-03-21T20:32:00.9491683Z [INFO 2025-03-21 20:32:00,914 qnn_preprocess.py:69] Visiting: aten_select_copy_int_218, aten.select_copy.int
2025-03-21T20:32:00.9492890Z [INFO 2025-03-21 20:32:00,914 qnn_preprocess.py:69] Visiting: aten_select_copy_int_220, aten.select_copy.int
2025-03-21T20:32:00.9494111Z [INFO 2025-03-21 20:32:00,915 qnn_preprocess.py:69] Visiting: aten_select_copy_int_222, aten.select_copy.int
2025-03-21T20:32:00.9495340Z [INFO 2025-03-21 20:32:00,915 qnn_preprocess.py:69] Visiting: aten_select_copy_int_224, aten.select_copy.int
2025-03-21T20:32:00.9496573Z [INFO 2025-03-21 20:32:00,916 qnn_preprocess.py:69] Visiting: aten_select_copy_int_226, aten.select_copy.int
2025-03-21T20:32:00.9498003Z [INFO 2025-03-21 20:32:00,916 qnn_preprocess.py:69] Visiting: aten_select_copy_int_228, aten.select_copy.int
2025-03-21T20:32:00.9499237Z [INFO 2025-03-21 20:32:00,916 qnn_preprocess.py:69] Visiting: aten_select_copy_int_230, aten.select_copy.int
2025-03-21T20:32:00.9500465Z [INFO 2025-03-21 20:32:00,917 qnn_preprocess.py:69] Visiting: aten_select_copy_int_232, aten.select_copy.int
2025-03-21T20:32:00.9501690Z [INFO 2025-03-21 20:32:00,917 qnn_preprocess.py:69] Visiting: aten_select_copy_int_234, aten.select_copy.int
2025-03-21T20:32:00.9502901Z [INFO 2025-03-21 20:32:00,918 qnn_preprocess.py:69] Visiting: aten_select_copy_int_236, aten.select_copy.int
2025-03-21T20:32:00.9504132Z [INFO 2025-03-21 20:32:00,918 qnn_preprocess.py:69] Visiting: aten_select_copy_int_238, aten.select_copy.int
2025-03-21T20:32:00.9505310Z [INFO 2025-03-21 20:32:00,918 qnn_preprocess.py:69] Visiting: aten_mul_tensor_62, aten.mul.Tensor
2025-03-21T20:32:00.9506433Z [INFO 2025-03-21 20:32:00,919 qnn_preprocess.py:69] Visiting: aten_mul_tensor_64, aten.mul.Tensor
2025-03-21T20:32:00.9507548Z [INFO 2025-03-21 20:32:00,919 qnn_preprocess.py:69] Visiting: aten_mul_tensor_63, aten.mul.Tensor
2025-03-21T20:32:00.9508717Z [INFO 2025-03-21 20:32:00,920 qnn_preprocess.py:69] Visiting: aten_mul_tensor_65, aten.mul.Tensor
2025-03-21T20:32:00.9509828Z [INFO 2025-03-21 20:32:00,921 qnn_preprocess.py:69] Visiting: aten_mul_tensor_66, aten.mul.Tensor
2025-03-21T20:32:00.9510925Z [INFO 2025-03-21 20:32:00,921 qnn_preprocess.py:69] Visiting: aten_mul_tensor_68, aten.mul.Tensor
2025-03-21T20:32:00.9512054Z [INFO 2025-03-21 20:32:00,922 qnn_preprocess.py:69] Visiting: aten_mul_tensor_67, aten.mul.Tensor
2025-03-21T20:32:00.9513163Z [INFO 2025-03-21 20:32:00,922 qnn_preprocess.py:69] Visiting: aten_mul_tensor_69, aten.mul.Tensor
2025-03-21T20:32:00.9514375Z [INFO 2025-03-21 20:32:00,923 qnn_preprocess.py:69] Visiting: aten_select_copy_int_217, aten.select_copy.int
2025-03-21T20:32:00.9515613Z [INFO 2025-03-21 20:32:00,923 qnn_preprocess.py:69] Visiting: aten_select_copy_int_219, aten.select_copy.int
2025-03-21T20:32:00.9516850Z [INFO 2025-03-21 20:32:00,923 qnn_preprocess.py:69] Visiting: aten_select_copy_int_221, aten.select_copy.int
2025-03-21T20:32:00.9518065Z [INFO 2025-03-21 20:32:00,924 qnn_preprocess.py:69] Visiting: aten_select_copy_int_223, aten.select_copy.int
2025-03-21T20:32:00.9519292Z [INFO 2025-03-21 20:32:00,924 qnn_preprocess.py:69] Visiting: aten_select_copy_int_225, aten.select_copy.int
2025-03-21T20:32:00.9520526Z [INFO 2025-03-21 20:32:00,925 qnn_preprocess.py:69] Visiting: aten_select_copy_int_227, aten.select_copy.int
2025-03-21T20:32:00.9521750Z [INFO 2025-03-21 20:32:00,925 qnn_preprocess.py:69] Visiting: aten_select_copy_int_229, aten.select_copy.int
2025-03-21T20:32:00.9522972Z [INFO 2025-03-21 20:32:00,926 qnn_preprocess.py:69] Visiting: aten_select_copy_int_231, aten.select_copy.int
2025-03-21T20:32:00.9524203Z [INFO 2025-03-21 20:32:00,926 qnn_preprocess.py:69] Visiting: aten_select_copy_int_233, aten.select_copy.int
2025-03-21T20:32:00.9525447Z [INFO 2025-03-21 20:32:00,927 qnn_preprocess.py:69] Visiting: aten_select_copy_int_235, aten.select_copy.int
2025-03-21T20:32:00.9526665Z [INFO 2025-03-21 20:32:00,927 qnn_preprocess.py:69] Visiting: aten_select_copy_int_237, aten.select_copy.int
2025-03-21T20:32:00.9527891Z [INFO 2025-03-21 20:32:00,927 qnn_preprocess.py:69] Visiting: aten_select_copy_int_239, aten.select_copy.int
2025-03-21T20:32:00.9529058Z [INFO 2025-03-21 20:32:00,928 qnn_preprocess.py:69] Visiting: aten_sub_tensor_8, aten.sub.Tensor
2025-03-21T20:32:00.9530225Z [INFO 2025-03-21 20:32:00,928 qnn_preprocess.py:69] Visiting: aten_add_tensor_20, aten.add.Tensor
2025-03-21T20:32:00.9531344Z [INFO 2025-03-21 20:32:00,929 qnn_preprocess.py:69] Visiting: aten_sub_tensor_9, aten.sub.Tensor
2025-03-21T20:32:00.9532654Z [INFO 2025-03-21 20:32:00,930 qnn_preprocess.py:69] Visiting: aten_add_tensor_21, aten.add.Tensor
2025-03-21T20:32:00.9533779Z [INFO 2025-03-21 20:32:00,930 qnn_preprocess.py:69] Visiting: aten_cat_default_19, aten.cat.default
2025-03-21T20:32:00.9535184Z [INFO 2025-03-21 20:32:00,932 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_47, aten.unsqueeze_copy.default
2025-03-21T20:32:00.9536609Z [INFO 2025-03-21 20:32:00,932 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_48, aten.unsqueeze_copy.default
2025-03-21T20:32:00.9538021Z [INFO 2025-03-21 20:32:00,932 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_49, aten.unsqueeze_copy.default
2025-03-21T20:32:00.9539427Z [INFO 2025-03-21 20:32:00,933 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_50, aten.unsqueeze_copy.default
2025-03-21T20:32:00.9540763Z [INFO 2025-03-21 20:32:00,933 qnn_preprocess.py:69] Visiting: aten_view_copy_default_82, aten.view_copy.default
2025-03-21T20:32:00.9542013Z [INFO 2025-03-21 20:32:00,934 qnn_preprocess.py:69] Visiting: aten__to_copy_default_10, aten._to_copy.default
2025-03-21T20:32:00.9543188Z [INFO 2025-03-21 20:32:00,934 qnn_preprocess.py:69] Visiting: aten_cat_default_16, aten.cat.default
2025-03-21T20:32:00.9544320Z [INFO 2025-03-21 20:32:00,935 qnn_preprocess.py:69] Visiting: aten_cat_default_17, aten.cat.default
2025-03-21T20:32:00.9545560Z [INFO 2025-03-21 20:32:00,935 qnn_preprocess.py:69] Visiting: aten_view_copy_default_79, aten.view_copy.default
2025-03-21T20:32:00.9546824Z [INFO 2025-03-21 20:32:00,936 qnn_preprocess.py:69] Visiting: aten_view_copy_default_80, aten.view_copy.default
2025-03-21T20:32:00.9548131Z [INFO 2025-03-21 20:32:00,936 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_170, aten.permute_copy.default
2025-03-21T20:32:00.9549436Z [INFO 2025-03-21 20:32:00,937 qnn_preprocess.py:69] Visiting: aten_index_put_default_8, aten.index_put.default
2025-03-21T20:32:00.9550745Z [INFO 2025-03-21 20:32:00,938 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_171, aten.permute_copy.default
2025-03-21T20:32:00.9552136Z [INFO 2025-03-21 20:32:00,938 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_172, aten.permute_copy.default
2025-03-21T20:32:00.9553504Z [INFO 2025-03-21 20:32:00,939 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_173, aten.permute_copy.default
2025-03-21T20:32:00.9554857Z [INFO 2025-03-21 20:32:00,940 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_174, aten.permute_copy.default
2025-03-21T20:32:00.9556215Z [INFO 2025-03-21 20:32:00,940 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_175, aten.permute_copy.default
2025-03-21T20:32:00.9557567Z [INFO 2025-03-21 20:32:00,941 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_176, aten.permute_copy.default
2025-03-21T20:32:00.9558916Z [INFO 2025-03-21 20:32:00,942 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_177, aten.permute_copy.default
2025-03-21T20:32:00.9560270Z [INFO 2025-03-21 20:32:00,942 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_178, aten.permute_copy.default
2025-03-21T20:32:00.9561618Z [INFO 2025-03-21 20:32:00,943 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_179, aten.permute_copy.default
2025-03-21T20:32:00.9562976Z [INFO 2025-03-21 20:32:00,944 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_180, aten.permute_copy.default
2025-03-21T20:32:00.9564331Z [INFO 2025-03-21 20:32:00,945 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_181, aten.permute_copy.default
2025-03-21T20:32:00.9565693Z [INFO 2025-03-21 20:32:00,945 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_182, aten.permute_copy.default
2025-03-21T20:32:00.9566983Z [INFO 2025-03-21 20:32:00,946 qnn_preprocess.py:69] Visiting: aten_select_copy_int_192, aten.select_copy.int
2025-03-21T20:32:00.9568208Z [INFO 2025-03-21 20:32:00,946 qnn_preprocess.py:69] Visiting: aten_select_copy_int_194, aten.select_copy.int
2025-03-21T20:32:01.0160037Z [INFO 2025-03-21 20:32:00,947 qnn_preprocess.py:69] Visiting: aten_select_copy_int_196, aten.select_copy.int
2025-03-21T20:32:01.0161330Z [INFO 2025-03-21 20:32:00,947 qnn_preprocess.py:69] Visiting: aten_select_copy_int_198, aten.select_copy.int
2025-03-21T20:32:01.0162927Z [INFO 2025-03-21 20:32:00,948 qnn_preprocess.py:69] Visiting: aten_select_copy_int_200, aten.select_copy.int
2025-03-21T20:32:01.0164181Z [INFO 2025-03-21 20:32:00,948 qnn_preprocess.py:69] Visiting: aten_select_copy_int_202, aten.select_copy.int
2025-03-21T20:32:01.0165444Z [INFO 2025-03-21 20:32:00,949 qnn_preprocess.py:69] Visiting: aten_select_copy_int_204, aten.select_copy.int
2025-03-21T20:32:01.0166667Z [INFO 2025-03-21 20:32:00,949 qnn_preprocess.py:69] Visiting: aten_select_copy_int_206, aten.select_copy.int
2025-03-21T20:32:01.0167905Z [INFO 2025-03-21 20:32:00,950 qnn_preprocess.py:69] Visiting: aten_select_copy_int_208, aten.select_copy.int
2025-03-21T20:32:01.0169117Z [INFO 2025-03-21 20:32:00,950 qnn_preprocess.py:69] Visiting: aten_select_copy_int_210, aten.select_copy.int
2025-03-21T20:32:01.0170471Z [INFO 2025-03-21 20:32:00,951 qnn_preprocess.py:69] Visiting: aten_select_copy_int_212, aten.select_copy.int
2025-03-21T20:32:01.0171698Z [INFO 2025-03-21 20:32:00,951 qnn_preprocess.py:69] Visiting: aten_select_copy_int_214, aten.select_copy.int
2025-03-21T20:32:01.0172919Z [INFO 2025-03-21 20:32:00,952 qnn_preprocess.py:69] Visiting: aten_select_copy_int_193, aten.select_copy.int
2025-03-21T20:32:01.0174222Z [INFO 2025-03-21 20:32:00,952 qnn_preprocess.py:69] Visiting: aten_select_copy_int_195, aten.select_copy.int
2025-03-21T20:32:01.0175452Z [INFO 2025-03-21 20:32:00,952 qnn_preprocess.py:69] Visiting: aten_select_copy_int_197, aten.select_copy.int
2025-03-21T20:32:01.0176689Z [INFO 2025-03-21 20:32:00,953 qnn_preprocess.py:69] Visiting: aten_select_copy_int_199, aten.select_copy.int
2025-03-21T20:32:01.0177920Z [INFO 2025-03-21 20:32:00,953 qnn_preprocess.py:69] Visiting: aten_select_copy_int_201, aten.select_copy.int
2025-03-21T20:32:01.0179139Z [INFO 2025-03-21 20:32:00,954 qnn_preprocess.py:69] Visiting: aten_select_copy_int_203, aten.select_copy.int
2025-03-21T20:32:01.0180436Z [INFO 2025-03-21 20:32:00,954 qnn_preprocess.py:69] Visiting: aten_select_copy_int_205, aten.select_copy.int
2025-03-21T20:32:01.0181650Z [INFO 2025-03-21 20:32:00,955 qnn_preprocess.py:69] Visiting: aten_select_copy_int_207, aten.select_copy.int
2025-03-21T20:32:01.0182876Z [INFO 2025-03-21 20:32:00,955 qnn_preprocess.py:69] Visiting: aten_select_copy_int_209, aten.select_copy.int
2025-03-21T20:32:01.0184096Z [INFO 2025-03-21 20:32:00,956 qnn_preprocess.py:69] Visiting: aten_select_copy_int_211, aten.select_copy.int
2025-03-21T20:32:01.0185323Z [INFO 2025-03-21 20:32:00,956 qnn_preprocess.py:69] Visiting: aten_select_copy_int_213, aten.select_copy.int
2025-03-21T20:32:01.0186524Z [INFO 2025-03-21 20:32:00,956 qnn_preprocess.py:69] Visiting: aten_select_copy_int_215, aten.select_copy.int
2025-03-21T20:32:01.0187698Z [INFO 2025-03-21 20:32:00,957 qnn_preprocess.py:69] Visiting: aten_cat_default_18, aten.cat.default
2025-03-21T20:32:01.0188890Z [INFO 2025-03-21 20:32:00,958 qnn_preprocess.py:69] Visiting: aten_view_copy_default_81, aten.view_copy.default
2025-03-21T20:32:01.0190214Z [INFO 2025-03-21 20:32:00,959 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_195, aten.permute_copy.default
2025-03-21T20:32:01.0191519Z [INFO 2025-03-21 20:32:00,959 qnn_preprocess.py:69] Visiting: aten__to_copy_default_11, aten._to_copy.default
2025-03-21T20:32:01.0192730Z [INFO 2025-03-21 20:32:00,960 qnn_preprocess.py:69] Visiting: aten_matmul_default_8, aten.matmul.default
2025-03-21T20:32:01.0193878Z [INFO 2025-03-21 20:32:00,961 qnn_preprocess.py:69] Visiting: aten_mul_tensor_70, aten.mul.Tensor
2025-03-21T20:32:01.0194992Z [INFO 2025-03-21 20:32:00,962 qnn_preprocess.py:69] Visiting: aten_add_tensor_22, aten.add.Tensor
2025-03-21T20:32:01.0196167Z [INFO 2025-03-21 20:32:00,962 qnn_preprocess.py:69] Visiting: aten__softmax_default_4, aten._softmax.default
2025-03-21T20:32:01.0197365Z [INFO 2025-03-21 20:32:00,963 qnn_preprocess.py:69] Visiting: aten_matmul_default_9, aten.matmul.default
2025-03-21T20:32:01.0198646Z [INFO 2025-03-21 20:32:00,963 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_196, aten.permute_copy.default
2025-03-21T20:32:01.0200042Z [INFO 2025-03-21 20:32:00,964 qnn_preprocess.py:69] Visiting: aten_view_copy_default_89, aten.view_copy.default
2025-03-21T20:32:01.0201396Z [INFO 2025-03-21 20:32:00,964 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_51, aten.unsqueeze_copy.default
2025-03-21T20:32:01.0202784Z [INFO 2025-03-21 20:32:00,965 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_726, aten.permute_copy.default
2025-03-21T20:32:01.0204120Z [INFO 2025-03-21 20:32:00,965 qnn_preprocess.py:69] Visiting: aten_convolution_default_31, aten.convolution.default
2025-03-21T20:32:01.0205472Z [INFO 2025-03-21 20:32:00,968 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_727, aten.permute_copy.default
2025-03-21T20:32:01.0206776Z [INFO 2025-03-21 20:32:00,969 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_51, aten.squeeze_copy.dims
2025-03-21T20:32:01.0207975Z [INFO 2025-03-21 20:32:00,970 qnn_preprocess.py:69] Visiting: aten_add_tensor_23, aten.add.Tensor
2025-03-21T20:32:01.0209153Z [INFO 2025-03-21 20:32:00,970 qnn_preprocess.py:69] Visiting: aten_rms_norm_default_9, aten.rms_norm.default
2025-03-21T20:32:01.0210602Z [INFO 2025-03-21 20:32:00,971 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_52, aten.unsqueeze_copy.default
2025-03-21T20:32:01.0211986Z [INFO 2025-03-21 20:32:00,972 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_728, aten.permute_copy.default
2025-03-21T20:32:01.0213380Z [INFO 2025-03-21 20:32:00,973 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_53, aten.unsqueeze_copy.default
2025-03-21T20:32:01.0214770Z [INFO 2025-03-21 20:32:00,973 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_729, aten.permute_copy.default
2025-03-21T20:32:01.0216106Z [INFO 2025-03-21 20:32:00,974 qnn_preprocess.py:69] Visiting: aten_convolution_default_32, aten.convolution.default
2025-03-21T20:32:01.0217499Z [INFO 2025-03-21 20:32:00,979 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_730, aten.permute_copy.default
2025-03-21T20:32:01.0218846Z [INFO 2025-03-21 20:32:00,980 qnn_preprocess.py:69] Visiting: aten_convolution_default_33, aten.convolution.default
2025-03-21T20:32:01.0220203Z [INFO 2025-03-21 20:32:00,986 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_731, aten.permute_copy.default
2025-03-21T20:32:01.0221512Z [INFO 2025-03-21 20:32:00,987 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_52, aten.squeeze_copy.dims
2025-03-21T20:32:01.0222774Z [INFO 2025-03-21 20:32:00,988 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_53, aten.squeeze_copy.dims
2025-03-21T20:32:01.0224027Z [INFO 2025-03-21 20:32:00,988 qnn_preprocess.py:69] Visiting: aten_sigmoid_default_4, aten.sigmoid.default
2025-03-21T20:32:01.0225184Z [INFO 2025-03-21 20:32:00,989 qnn_preprocess.py:69] Visiting: aten_mul_tensor_73, aten.mul.Tensor
2025-03-21T20:32:01.0226314Z [INFO 2025-03-21 20:32:00,989 qnn_preprocess.py:69] Visiting: aten_mul_tensor_74, aten.mul.Tensor
2025-03-21T20:32:01.0227588Z [INFO 2025-03-21 20:32:00,990 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_54, aten.unsqueeze_copy.default
2025-03-21T20:32:01.0228967Z [INFO 2025-03-21 20:32:00,990 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_732, aten.permute_copy.default
2025-03-21T20:32:01.0230322Z [INFO 2025-03-21 20:32:00,991 qnn_preprocess.py:69] Visiting: aten_convolution_default_34, aten.convolution.default
2025-03-21T20:32:01.0231677Z [INFO 2025-03-21 20:32:00,997 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_733, aten.permute_copy.default
2025-03-21T20:32:01.0233160Z [INFO 2025-03-21 20:32:00,998 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_54, aten.squeeze_copy.dims
2025-03-21T20:32:01.0234358Z [INFO 2025-03-21 20:32:00,999 qnn_preprocess.py:69] Visiting: aten_add_tensor_24, aten.add.Tensor
2025-03-21T20:32:01.0235545Z [INFO 2025-03-21 20:32:00,999 qnn_preprocess.py:69] Visiting: aten_rms_norm_default_10, aten.rms_norm.default
2025-03-21T20:32:01.0236947Z [INFO 2025-03-21 20:32:01,001 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_55, aten.unsqueeze_copy.default
2025-03-21T20:32:01.0238387Z [INFO 2025-03-21 20:32:01,001 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_734, aten.permute_copy.default
2025-03-21T20:32:01.0239773Z [INFO 2025-03-21 20:32:01,002 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_56, aten.unsqueeze_copy.default
2025-03-21T20:32:01.0241154Z [INFO 2025-03-21 20:32:01,002 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_735, aten.permute_copy.default
2025-03-21T20:32:01.0242533Z [INFO 2025-03-21 20:32:01,003 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_57, aten.unsqueeze_copy.default
2025-03-21T20:32:01.0243901Z [INFO 2025-03-21 20:32:01,003 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_736, aten.permute_copy.default
2025-03-21T20:32:01.0245251Z [INFO 2025-03-21 20:32:01,004 qnn_preprocess.py:69] Visiting: aten_convolution_default_35, aten.convolution.default
2025-03-21T20:32:01.0246597Z [INFO 2025-03-21 20:32:01,007 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_737, aten.permute_copy.default
2025-03-21T20:32:01.0247935Z [INFO 2025-03-21 20:32:01,008 qnn_preprocess.py:69] Visiting: aten_convolution_default_36, aten.convolution.default
2025-03-21T20:32:01.0249380Z [INFO 2025-03-21 20:32:01,011 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_738, aten.permute_copy.default
2025-03-21T20:32:01.0250737Z [INFO 2025-03-21 20:32:01,012 qnn_preprocess.py:69] Visiting: aten_convolution_default_37, aten.convolution.default
2025-03-21T20:32:01.0252081Z [INFO 2025-03-21 20:32:01,014 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_739, aten.permute_copy.default
2025-03-21T20:32:01.0540820Z [INFO 2025-03-21 20:32:01,015 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_55, aten.squeeze_copy.dims
2025-03-21T20:32:01.0542348Z [INFO 2025-03-21 20:32:01,016 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_56, aten.squeeze_copy.dims
2025-03-21T20:32:01.0543665Z [INFO 2025-03-21 20:32:01,016 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_57, aten.squeeze_copy.dims
2025-03-21T20:32:01.0545083Z [INFO 2025-03-21 20:32:01,017 qnn_preprocess.py:69] Visiting: aten_view_copy_default_90, aten.view_copy.default
2025-03-21T20:32:01.0546504Z [INFO 2025-03-21 20:32:01,017 qnn_preprocess.py:69] Visiting: aten_view_copy_default_91, aten.view_copy.default
2025-03-21T20:32:01.0547822Z [INFO 2025-03-21 20:32:01,017 qnn_preprocess.py:69] Visiting: aten_view_copy_default_92, aten.view_copy.default
2025-03-21T20:32:01.0549124Z [INFO 2025-03-21 20:32:01,017 qnn_preprocess.py:69] Visiting: aten_view_copy_default_93, aten.view_copy.default
2025-03-21T20:32:01.0550528Z [INFO 2025-03-21 20:32:01,018 qnn_preprocess.py:69] Visiting: aten_view_copy_default_94, aten.view_copy.default
2025-03-21T20:32:01.0551693Z [INFO 2025-03-21 20:32:01,018 qnn_preprocess.py:69] Visiting: aten_index_put_default_11, aten.index_put.default
2025-03-21T20:32:01.0552938Z [INFO 2025-03-21 20:32:01,019 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_20, aten.slice_copy.Tensor
2025-03-21T20:32:01.0554178Z [INFO 2025-03-21 20:32:01,020 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_21, aten.slice_copy.Tensor
2025-03-21T20:32:01.0555434Z [INFO 2025-03-21 20:32:01,020 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_22, aten.slice_copy.Tensor
2025-03-21T20:32:01.0556817Z [INFO 2025-03-21 20:32:01,021 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_23, aten.slice_copy.Tensor
2025-03-21T20:32:01.0558071Z [INFO 2025-03-21 20:32:01,021 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_224, aten.permute_copy.default
2025-03-21T20:32:01.0559456Z [INFO 2025-03-21 20:32:01,022 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_225, aten.permute_copy.default
2025-03-21T20:32:01.0560936Z [INFO 2025-03-21 20:32:01,023 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_226, aten.permute_copy.default
2025-03-21T20:32:01.0562462Z [INFO 2025-03-21 20:32:01,023 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_227, aten.permute_copy.default
2025-03-21T20:32:01.0564197Z [INFO 2025-03-21 20:32:01,024 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_228, aten.permute_copy.default
2025-03-21T20:32:01.0565610Z [INFO 2025-03-21 20:32:01,025 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_229, aten.permute_copy.default
2025-03-21T20:32:01.0567135Z [INFO 2025-03-21 20:32:01,025 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_230, aten.permute_copy.default
2025-03-21T20:32:01.0568366Z [INFO 2025-03-21 20:32:01,026 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_231, aten.permute_copy.default
2025-03-21T20:32:01.0569790Z [INFO 2025-03-21 20:32:01,027 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_232, aten.permute_copy.default
2025-03-21T20:32:01.0571039Z [INFO 2025-03-21 20:32:01,027 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_233, aten.permute_copy.default
2025-03-21T20:32:01.0572390Z [INFO 2025-03-21 20:32:01,028 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_234, aten.permute_copy.default
2025-03-21T20:32:01.0573724Z [INFO 2025-03-21 20:32:01,029 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_235, aten.permute_copy.default
2025-03-21T20:32:01.0575203Z [INFO 2025-03-21 20:32:01,029 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_58, aten.squeeze_copy.dims
2025-03-21T20:32:01.0576599Z [INFO 2025-03-21 20:32:01,030 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_59, aten.squeeze_copy.dims
2025-03-21T20:32:01.0578031Z [INFO 2025-03-21 20:32:01,030 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_60, aten.squeeze_copy.dims
2025-03-21T20:32:01.0579257Z [INFO 2025-03-21 20:32:01,031 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_61, aten.squeeze_copy.dims
2025-03-21T20:32:01.0580506Z [INFO 2025-03-21 20:32:01,031 qnn_preprocess.py:69] Visiting: aten_select_copy_int_264, aten.select_copy.int
2025-03-21T20:32:01.0581970Z [INFO 2025-03-21 20:32:01,032 qnn_preprocess.py:69] Visiting: aten_select_copy_int_266, aten.select_copy.int
2025-03-21T20:32:01.0583125Z [INFO 2025-03-21 20:32:01,032 qnn_preprocess.py:69] Visiting: aten_select_copy_int_268, aten.select_copy.int
2025-03-21T20:32:01.0584353Z [INFO 2025-03-21 20:32:01,032 qnn_preprocess.py:69] Visiting: aten_select_copy_int_270, aten.select_copy.int
2025-03-21T20:32:01.0585520Z [INFO 2025-03-21 20:32:01,033 qnn_preprocess.py:69] Visiting: aten_select_copy_int_272, aten.select_copy.int
2025-03-21T20:32:01.0586709Z [INFO 2025-03-21 20:32:01,033 qnn_preprocess.py:69] Visiting: aten_select_copy_int_274, aten.select_copy.int
2025-03-21T20:32:01.0588036Z [INFO 2025-03-21 20:32:01,034 qnn_preprocess.py:69] Visiting: aten_select_copy_int_276, aten.select_copy.int
2025-03-21T20:32:01.0589262Z [INFO 2025-03-21 20:32:01,034 qnn_preprocess.py:69] Visiting: aten_select_copy_int_278, aten.select_copy.int
2025-03-21T20:32:01.0590466Z [INFO 2025-03-21 20:32:01,035 qnn_preprocess.py:69] Visiting: aten_select_copy_int_280, aten.select_copy.int
2025-03-21T20:32:01.0591820Z [INFO 2025-03-21 20:32:01,035 qnn_preprocess.py:69] Visiting: aten_select_copy_int_282, aten.select_copy.int
2025-03-21T20:32:01.0593034Z [INFO 2025-03-21 20:32:01,036 qnn_preprocess.py:69] Visiting: aten_select_copy_int_284, aten.select_copy.int
2025-03-21T20:32:01.0594237Z [INFO 2025-03-21 20:32:01,036 qnn_preprocess.py:69] Visiting: aten_select_copy_int_286, aten.select_copy.int
2025-03-21T20:32:01.0595380Z [INFO 2025-03-21 20:32:01,036 qnn_preprocess.py:69] Visiting: aten_mul_tensor_77, aten.mul.Tensor
2025-03-21T20:32:01.0596419Z [INFO 2025-03-21 20:32:01,037 qnn_preprocess.py:69] Visiting: aten_mul_tensor_79, aten.mul.Tensor
2025-03-21T20:32:01.0597599Z [INFO 2025-03-21 20:32:01,037 qnn_preprocess.py:69] Visiting: aten_mul_tensor_78, aten.mul.Tensor
2025-03-21T20:32:01.0598805Z [INFO 2025-03-21 20:32:01,038 qnn_preprocess.py:69] Visiting: aten_mul_tensor_80, aten.mul.Tensor
2025-03-21T20:32:01.0599853Z [INFO 2025-03-21 20:32:01,039 qnn_preprocess.py:69] Visiting: aten_mul_tensor_81, aten.mul.Tensor
2025-03-21T20:32:01.0601122Z [INFO 2025-03-21 20:32:01,039 qnn_preprocess.py:69] Visiting: aten_mul_tensor_83, aten.mul.Tensor
2025-03-21T20:32:01.0602365Z [INFO 2025-03-21 20:32:01,040 qnn_preprocess.py:69] Visiting: aten_mul_tensor_82, aten.mul.Tensor
2025-03-21T20:32:01.0603560Z [INFO 2025-03-21 20:32:01,040 qnn_preprocess.py:69] Visiting: aten_mul_tensor_84, aten.mul.Tensor
2025-03-21T20:32:01.0604753Z [INFO 2025-03-21 20:32:01,041 qnn_preprocess.py:69] Visiting: aten_select_copy_int_265, aten.select_copy.int
2025-03-21T20:32:01.0605905Z [INFO 2025-03-21 20:32:01,041 qnn_preprocess.py:69] Visiting: aten_select_copy_int_267, aten.select_copy.int
2025-03-21T20:32:01.0607120Z [INFO 2025-03-21 20:32:01,041 qnn_preprocess.py:69] Visiting: aten_select_copy_int_269, aten.select_copy.int
2025-03-21T20:32:01.0608464Z [INFO 2025-03-21 20:32:01,042 qnn_preprocess.py:69] Visiting: aten_select_copy_int_271, aten.select_copy.int
2025-03-21T20:32:01.0609741Z [INFO 2025-03-21 20:32:01,042 qnn_preprocess.py:69] Visiting: aten_select_copy_int_273, aten.select_copy.int
2025-03-21T20:32:01.0611000Z [INFO 2025-03-21 20:32:01,043 qnn_preprocess.py:69] Visiting: aten_select_copy_int_275, aten.select_copy.int
2025-03-21T20:32:01.0612463Z [INFO 2025-03-21 20:32:01,043 qnn_preprocess.py:69] Visiting: aten_select_copy_int_277, aten.select_copy.int
2025-03-21T20:32:01.0613575Z [INFO 2025-03-21 20:32:01,044 qnn_preprocess.py:69] Visiting: aten_select_copy_int_279, aten.select_copy.int
2025-03-21T20:32:01.0614809Z [INFO 2025-03-21 20:32:01,044 qnn_preprocess.py:69] Visiting: aten_select_copy_int_281, aten.select_copy.int
2025-03-21T20:32:01.0615987Z [INFO 2025-03-21 20:32:01,045 qnn_preprocess.py:69] Visiting: aten_select_copy_int_283, aten.select_copy.int
2025-03-21T20:32:01.0617187Z [INFO 2025-03-21 20:32:01,045 qnn_preprocess.py:69] Visiting: aten_select_copy_int_285, aten.select_copy.int
2025-03-21T20:32:01.0618672Z [INFO 2025-03-21 20:32:01,045 qnn_preprocess.py:69] Visiting: aten_select_copy_int_287, aten.select_copy.int
2025-03-21T20:32:01.0619795Z [INFO 2025-03-21 20:32:01,046 qnn_preprocess.py:69] Visiting: aten_sub_tensor_10, aten.sub.Tensor
2025-03-21T20:32:01.0620938Z [INFO 2025-03-21 20:32:01,046 qnn_preprocess.py:69] Visiting: aten_add_tensor_25, aten.add.Tensor
2025-03-21T20:32:01.0622155Z [INFO 2025-03-21 20:32:01,047 qnn_preprocess.py:69] Visiting: aten_sub_tensor_11, aten.sub.Tensor
2025-03-21T20:32:01.0623238Z [INFO 2025-03-21 20:32:01,047 qnn_preprocess.py:69] Visiting: aten_add_tensor_26, aten.add.Tensor
2025-03-21T20:32:01.0624304Z [INFO 2025-03-21 20:32:01,048 qnn_preprocess.py:69] Visiting: aten_cat_default_23, aten.cat.default
2025-03-21T20:32:01.0625572Z [INFO 2025-03-21 20:32:01,049 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_58, aten.unsqueeze_copy.default
2025-03-21T20:32:01.0626916Z [INFO 2025-03-21 20:32:01,050 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_59, aten.unsqueeze_copy.default
2025-03-21T20:32:01.0628452Z [INFO 2025-03-21 20:32:01,050 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_60, aten.unsqueeze_copy.default
2025-03-21T20:32:01.0629842Z [INFO 2025-03-21 20:32:01,051 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_61, aten.unsqueeze_copy.default
2025-03-21T20:32:01.0631203Z [INFO 2025-03-21 20:32:01,051 qnn_preprocess.py:69] Visiting: aten_view_copy_default_100, aten.view_copy.default
2025-03-21T20:32:01.0632836Z [INFO 2025-03-21 20:32:01,051 qnn_preprocess.py:69] Visiting: aten__to_copy_default_12, aten._to_copy.default
2025-03-21T20:32:01.0633935Z [INFO 2025-03-21 20:32:01,052 qnn_preprocess.py:69] Visiting: aten_cat_default_20, aten.cat.default
2025-03-21T20:32:01.0635077Z [INFO 2025-03-21 20:32:01,053 qnn_preprocess.py:69] Visiting: aten_cat_default_21, aten.cat.default
2025-03-21T20:32:01.1115860Z [INFO 2025-03-21 20:32:01,053 qnn_preprocess.py:69] Visiting: aten_view_copy_default_97, aten.view_copy.default
2025-03-21T20:32:01.1117272Z [INFO 2025-03-21 20:32:01,054 qnn_preprocess.py:69] Visiting: aten_view_copy_default_98, aten.view_copy.default
2025-03-21T20:32:01.1118808Z [INFO 2025-03-21 20:32:01,054 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_211, aten.permute_copy.default
2025-03-21T20:32:01.1120360Z [INFO 2025-03-21 20:32:01,055 qnn_preprocess.py:69] Visiting: aten_index_put_default_10, aten.index_put.default
2025-03-21T20:32:01.1121614Z [INFO 2025-03-21 20:32:01,057 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_212, aten.permute_copy.default
2025-03-21T20:32:01.1122971Z [INFO 2025-03-21 20:32:01,058 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_213, aten.permute_copy.default
2025-03-21T20:32:01.1124487Z [INFO 2025-03-21 20:32:01,059 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_214, aten.permute_copy.default
2025-03-21T20:32:01.1126008Z [INFO 2025-03-21 20:32:01,060 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_215, aten.permute_copy.default
2025-03-21T20:32:01.1127484Z [INFO 2025-03-21 20:32:01,061 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_216, aten.permute_copy.default
2025-03-21T20:32:01.1129016Z [INFO 2025-03-21 20:32:01,062 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_217, aten.permute_copy.default
2025-03-21T20:32:01.1130538Z [INFO 2025-03-21 20:32:01,063 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_218, aten.permute_copy.default
2025-03-21T20:32:01.1131901Z [INFO 2025-03-21 20:32:01,064 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_219, aten.permute_copy.default
2025-03-21T20:32:01.1133398Z [INFO 2025-03-21 20:32:01,065 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_220, aten.permute_copy.default
2025-03-21T20:32:01.1134804Z [INFO 2025-03-21 20:32:01,065 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_221, aten.permute_copy.default
2025-03-21T20:32:01.1136312Z [INFO 2025-03-21 20:32:01,066 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_222, aten.permute_copy.default
2025-03-21T20:32:01.1138036Z [INFO 2025-03-21 20:32:01,067 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_223, aten.permute_copy.default
2025-03-21T20:32:01.1139370Z [INFO 2025-03-21 20:32:01,067 qnn_preprocess.py:69] Visiting: aten_select_copy_int_240, aten.select_copy.int
2025-03-21T20:32:01.1140909Z [INFO 2025-03-21 20:32:01,068 qnn_preprocess.py:69] Visiting: aten_select_copy_int_242, aten.select_copy.int
2025-03-21T20:32:01.1142427Z [INFO 2025-03-21 20:32:01,068 qnn_preprocess.py:69] Visiting: aten_select_copy_int_244, aten.select_copy.int
2025-03-21T20:32:01.1143925Z [INFO 2025-03-21 20:32:01,069 qnn_preprocess.py:69] Visiting: aten_select_copy_int_246, aten.select_copy.int
2025-03-21T20:32:01.1145455Z [INFO 2025-03-21 20:32:01,069 qnn_preprocess.py:69] Visiting: aten_select_copy_int_248, aten.select_copy.int
2025-03-21T20:32:01.1147028Z [INFO 2025-03-21 20:32:01,069 qnn_preprocess.py:69] Visiting: aten_select_copy_int_250, aten.select_copy.int
2025-03-21T20:32:01.1148581Z [INFO 2025-03-21 20:32:01,070 qnn_preprocess.py:69] Visiting: aten_select_copy_int_252, aten.select_copy.int
2025-03-21T20:32:01.1150133Z [INFO 2025-03-21 20:32:01,070 qnn_preprocess.py:69] Visiting: aten_select_copy_int_254, aten.select_copy.int
2025-03-21T20:32:01.1151710Z [INFO 2025-03-21 20:32:01,071 qnn_preprocess.py:69] Visiting: aten_select_copy_int_256, aten.select_copy.int
2025-03-21T20:32:01.1153256Z [INFO 2025-03-21 20:32:01,071 qnn_preprocess.py:69] Visiting: aten_select_copy_int_258, aten.select_copy.int
2025-03-21T20:32:01.1154792Z [INFO 2025-03-21 20:32:01,072 qnn_preprocess.py:69] Visiting: aten_select_copy_int_260, aten.select_copy.int
2025-03-21T20:32:01.1156032Z [INFO 2025-03-21 20:32:01,072 qnn_preprocess.py:69] Visiting: aten_select_copy_int_262, aten.select_copy.int
2025-03-21T20:32:01.1157320Z [INFO 2025-03-21 20:32:01,072 qnn_preprocess.py:69] Visiting: aten_select_copy_int_241, aten.select_copy.int
2025-03-21T20:32:01.1158699Z [INFO 2025-03-21 20:32:01,073 qnn_preprocess.py:69] Visiting: aten_select_copy_int_243, aten.select_copy.int
2025-03-21T20:32:01.1160077Z [INFO 2025-03-21 20:32:01,073 qnn_preprocess.py:69] Visiting: aten_select_copy_int_245, aten.select_copy.int
2025-03-21T20:32:01.1161517Z [INFO 2025-03-21 20:32:01,074 qnn_preprocess.py:69] Visiting: aten_select_copy_int_247, aten.select_copy.int
2025-03-21T20:32:01.1162789Z [INFO 2025-03-21 20:32:01,074 qnn_preprocess.py:69] Visiting: aten_select_copy_int_249, aten.select_copy.int
2025-03-21T20:32:01.1163873Z [INFO 2025-03-21 20:32:01,075 qnn_preprocess.py:69] Visiting: aten_select_copy_int_251, aten.select_copy.int
2025-03-21T20:32:01.1165330Z [INFO 2025-03-21 20:32:01,075 qnn_preprocess.py:69] Visiting: aten_select_copy_int_253, aten.select_copy.int
2025-03-21T20:32:01.1166742Z [INFO 2025-03-21 20:32:01,075 qnn_preprocess.py:69] Visiting: aten_select_copy_int_255, aten.select_copy.int
2025-03-21T20:32:01.1168175Z [INFO 2025-03-21 20:32:01,076 qnn_preprocess.py:69] Visiting: aten_select_copy_int_257, aten.select_copy.int
2025-03-21T20:32:01.1169713Z [INFO 2025-03-21 20:32:01,076 qnn_preprocess.py:69] Visiting: aten_select_copy_int_259, aten.select_copy.int
2025-03-21T20:32:01.1171151Z [INFO 2025-03-21 20:32:01,077 qnn_preprocess.py:69] Visiting: aten_select_copy_int_261, aten.select_copy.int
2025-03-21T20:32:01.1172538Z [INFO 2025-03-21 20:32:01,077 qnn_preprocess.py:69] Visiting: aten_select_copy_int_263, aten.select_copy.int
2025-03-21T20:32:01.1174100Z [INFO 2025-03-21 20:32:01,077 qnn_preprocess.py:69] Visiting: aten_cat_default_22, aten.cat.default
2025-03-21T20:32:01.1175531Z [INFO 2025-03-21 20:32:01,079 qnn_preprocess.py:69] Visiting: aten_view_copy_default_99, aten.view_copy.default
2025-03-21T20:32:01.1176904Z [INFO 2025-03-21 20:32:01,079 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_236, aten.permute_copy.default
2025-03-21T20:32:01.1178336Z [INFO 2025-03-21 20:32:01,080 qnn_preprocess.py:69] Visiting: aten__to_copy_default_13, aten._to_copy.default
2025-03-21T20:32:01.1180068Z [INFO 2025-03-21 20:32:01,080 qnn_preprocess.py:69] Visiting: aten_matmul_default_10, aten.matmul.default
2025-03-21T20:32:01.1181563Z [INFO 2025-03-21 20:32:01,081 qnn_preprocess.py:69] Visiting: aten_mul_tensor_85, aten.mul.Tensor
2025-03-21T20:32:01.1182706Z [INFO 2025-03-21 20:32:01,082 qnn_preprocess.py:69] Visiting: aten_add_tensor_27, aten.add.Tensor
2025-03-21T20:32:01.1184018Z [INFO 2025-03-21 20:32:01,082 qnn_preprocess.py:69] Visiting: aten__softmax_default_5, aten._softmax.default
2025-03-21T20:32:01.1185339Z [INFO 2025-03-21 20:32:01,083 qnn_preprocess.py:69] Visiting: aten_matmul_default_11, aten.matmul.default
2025-03-21T20:32:01.1186872Z [INFO 2025-03-21 20:32:01,083 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_237, aten.permute_copy.default
2025-03-21T20:32:01.1188628Z [INFO 2025-03-21 20:32:01,084 qnn_preprocess.py:69] Visiting: aten_view_copy_default_107, aten.view_copy.default
2025-03-21T20:32:01.1190122Z [INFO 2025-03-21 20:32:01,084 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_62, aten.unsqueeze_copy.default
2025-03-21T20:32:01.1191778Z [INFO 2025-03-21 20:32:01,085 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_740, aten.permute_copy.default
2025-03-21T20:32:01.1193090Z [INFO 2025-03-21 20:32:01,085 qnn_preprocess.py:69] Visiting: aten_convolution_default_38, aten.convolution.default
2025-03-21T20:32:01.1194539Z [INFO 2025-03-21 20:32:01,088 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_741, aten.permute_copy.default
2025-03-21T20:32:01.1195933Z [INFO 2025-03-21 20:32:01,089 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_62, aten.squeeze_copy.dims
2025-03-21T20:32:01.1197154Z [INFO 2025-03-21 20:32:01,089 qnn_preprocess.py:69] Visiting: aten_add_tensor_28, aten.add.Tensor
2025-03-21T20:32:01.1198501Z [INFO 2025-03-21 20:32:01,090 qnn_preprocess.py:69] Visiting: aten_rms_norm_default_11, aten.rms_norm.default
2025-03-21T20:32:01.1199929Z [INFO 2025-03-21 20:32:01,091 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_63, aten.unsqueeze_copy.default
2025-03-21T20:32:01.1201169Z [INFO 2025-03-21 20:32:01,092 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_742, aten.permute_copy.default
2025-03-21T20:32:01.1202449Z [INFO 2025-03-21 20:32:01,092 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_64, aten.unsqueeze_copy.default
2025-03-21T20:32:01.1203863Z [INFO 2025-03-21 20:32:01,093 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_743, aten.permute_copy.default
2025-03-21T20:32:01.1205273Z [INFO 2025-03-21 20:32:01,093 qnn_preprocess.py:69] Visiting: aten_convolution_default_39, aten.convolution.default
2025-03-21T20:32:01.1206478Z [INFO 2025-03-21 20:32:01,100 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_744, aten.permute_copy.default
2025-03-21T20:32:01.1207807Z [INFO 2025-03-21 20:32:01,101 qnn_preprocess.py:69] Visiting: aten_convolution_default_40, aten.convolution.default
2025-03-21T20:32:01.1209059Z [INFO 2025-03-21 20:32:01,107 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_745, aten.permute_copy.default
2025-03-21T20:32:01.1210390Z [INFO 2025-03-21 20:32:01,108 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_63, aten.squeeze_copy.dims
2025-03-21T20:32:01.1211660Z [INFO 2025-03-21 20:32:01,108 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_64, aten.squeeze_copy.dims
2025-03-21T20:32:01.1212858Z [INFO 2025-03-21 20:32:01,109 qnn_preprocess.py:69] Visiting: aten_sigmoid_default_5, aten.sigmoid.default
2025-03-21T20:32:01.1214113Z [INFO 2025-03-21 20:32:01,109 qnn_preprocess.py:69] Visiting: aten_mul_tensor_88, aten.mul.Tensor
2025-03-21T20:32:01.1215331Z [INFO 2025-03-21 20:32:01,110 qnn_preprocess.py:69] Visiting: aten_mul_tensor_89, aten.mul.Tensor
2025-03-21T20:32:01.1216531Z [INFO 2025-03-21 20:32:01,110 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_65, aten.unsqueeze_copy.default
2025-03-21T20:32:01.1663024Z [INFO 2025-03-21 20:32:01,111 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_746, aten.permute_copy.default
2025-03-21T20:32:01.1664828Z [INFO 2025-03-21 20:32:01,112 qnn_preprocess.py:69] Visiting: aten_convolution_default_41, aten.convolution.default
2025-03-21T20:32:01.1666217Z [INFO 2025-03-21 20:32:01,120 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_747, aten.permute_copy.default
2025-03-21T20:32:01.1667513Z [INFO 2025-03-21 20:32:01,121 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_65, aten.squeeze_copy.dims
2025-03-21T20:32:01.1668863Z [INFO 2025-03-21 20:32:01,122 qnn_preprocess.py:69] Visiting: aten_add_tensor_29, aten.add.Tensor
2025-03-21T20:32:01.1670226Z [INFO 2025-03-21 20:32:01,122 qnn_preprocess.py:69] Visiting: aten_rms_norm_default_12, aten.rms_norm.default
2025-03-21T20:32:01.1671686Z [INFO 2025-03-21 20:32:01,123 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_66, aten.unsqueeze_copy.default
2025-03-21T20:32:01.1673245Z [INFO 2025-03-21 20:32:01,124 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_748, aten.permute_copy.default
2025-03-21T20:32:01.1674576Z [INFO 2025-03-21 20:32:01,125 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_67, aten.unsqueeze_copy.default
2025-03-21T20:32:01.1676071Z [INFO 2025-03-21 20:32:01,125 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_749, aten.permute_copy.default
2025-03-21T20:32:01.1677613Z [INFO 2025-03-21 20:32:01,126 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_68, aten.unsqueeze_copy.default
2025-03-21T20:32:01.1679135Z [INFO 2025-03-21 20:32:01,126 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_750, aten.permute_copy.default
2025-03-21T20:32:01.1680666Z [INFO 2025-03-21 20:32:01,127 qnn_preprocess.py:69] Visiting: aten_convolution_default_42, aten.convolution.default
2025-03-21T20:32:01.1681996Z [INFO 2025-03-21 20:32:01,130 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_751, aten.permute_copy.default
2025-03-21T20:32:01.1683410Z [INFO 2025-03-21 20:32:01,131 qnn_preprocess.py:69] Visiting: aten_convolution_default_43, aten.convolution.default
2025-03-21T20:32:01.1684901Z [INFO 2025-03-21 20:32:01,134 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_752, aten.permute_copy.default
2025-03-21T20:32:01.1686419Z [INFO 2025-03-21 20:32:01,135 qnn_preprocess.py:69] Visiting: aten_convolution_default_44, aten.convolution.default
2025-03-21T20:32:01.1688225Z [INFO 2025-03-21 20:32:01,137 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_753, aten.permute_copy.default
2025-03-21T20:32:01.1689621Z [INFO 2025-03-21 20:32:01,138 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_66, aten.squeeze_copy.dims
2025-03-21T20:32:01.1690924Z [INFO 2025-03-21 20:32:01,139 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_67, aten.squeeze_copy.dims
2025-03-21T20:32:01.1692320Z [INFO 2025-03-21 20:32:01,139 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_68, aten.squeeze_copy.dims
2025-03-21T20:32:01.1693748Z [INFO 2025-03-21 20:32:01,139 qnn_preprocess.py:69] Visiting: aten_view_copy_default_108, aten.view_copy.default
2025-03-21T20:32:01.1695151Z [INFO 2025-03-21 20:32:01,140 qnn_preprocess.py:69] Visiting: aten_view_copy_default_109, aten.view_copy.default
2025-03-21T20:32:01.1696580Z [INFO 2025-03-21 20:32:01,140 qnn_preprocess.py:69] Visiting: aten_view_copy_default_110, aten.view_copy.default
2025-03-21T20:32:01.1697783Z [INFO 2025-03-21 20:32:01,140 qnn_preprocess.py:69] Visiting: aten_view_copy_default_111, aten.view_copy.default
2025-03-21T20:32:01.1699299Z [INFO 2025-03-21 20:32:01,141 qnn_preprocess.py:69] Visiting: aten_view_copy_default_112, aten.view_copy.default
2025-03-21T20:32:01.1700697Z [INFO 2025-03-21 20:32:01,141 qnn_preprocess.py:69] Visiting: aten_index_put_default_13, aten.index_put.default
2025-03-21T20:32:01.1702098Z [INFO 2025-03-21 20:32:01,142 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_24, aten.slice_copy.Tensor
2025-03-21T20:32:01.1703516Z [INFO 2025-03-21 20:32:01,143 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_25, aten.slice_copy.Tensor
2025-03-21T20:32:01.1704790Z [INFO 2025-03-21 20:32:01,143 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_26, aten.slice_copy.Tensor
2025-03-21T20:32:01.1706158Z [INFO 2025-03-21 20:32:01,143 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_27, aten.slice_copy.Tensor
2025-03-21T20:32:01.1707630Z [INFO 2025-03-21 20:32:01,144 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_265, aten.permute_copy.default
2025-03-21T20:32:01.1709095Z [INFO 2025-03-21 20:32:01,145 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_266, aten.permute_copy.default
2025-03-21T20:32:01.1710522Z [INFO 2025-03-21 20:32:01,145 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_267, aten.permute_copy.default
2025-03-21T20:32:01.1712046Z [INFO 2025-03-21 20:32:01,146 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_268, aten.permute_copy.default
2025-03-21T20:32:01.1713552Z [INFO 2025-03-21 20:32:01,146 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_269, aten.permute_copy.default
2025-03-21T20:32:01.1714959Z [INFO 2025-03-21 20:32:01,147 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_270, aten.permute_copy.default
2025-03-21T20:32:01.1716440Z [INFO 2025-03-21 20:32:01,148 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_271, aten.permute_copy.default
2025-03-21T20:32:01.1717925Z [INFO 2025-03-21 20:32:01,148 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_272, aten.permute_copy.default
2025-03-21T20:32:01.1719429Z [INFO 2025-03-21 20:32:01,149 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_273, aten.permute_copy.default
2025-03-21T20:32:01.1720882Z [INFO 2025-03-21 20:32:01,150 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_274, aten.permute_copy.default
2025-03-21T20:32:01.1722394Z [INFO 2025-03-21 20:32:01,150 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_275, aten.permute_copy.default
2025-03-21T20:32:01.1723911Z [INFO 2025-03-21 20:32:01,151 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_276, aten.permute_copy.default
2025-03-21T20:32:01.1725243Z [INFO 2025-03-21 20:32:01,152 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_69, aten.squeeze_copy.dims
2025-03-21T20:32:01.1726673Z [INFO 2025-03-21 20:32:01,152 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_70, aten.squeeze_copy.dims
2025-03-21T20:32:01.1728289Z [INFO 2025-03-21 20:32:01,153 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_71, aten.squeeze_copy.dims
2025-03-21T20:32:01.1729682Z [INFO 2025-03-21 20:32:01,153 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_72, aten.squeeze_copy.dims
2025-03-21T20:32:01.1731094Z [INFO 2025-03-21 20:32:01,154 qnn_preprocess.py:69] Visiting: aten_select_copy_int_312, aten.select_copy.int
2025-03-21T20:32:01.1732688Z [INFO 2025-03-21 20:32:01,154 qnn_preprocess.py:69] Visiting: aten_select_copy_int_314, aten.select_copy.int
2025-03-21T20:32:01.1733981Z [INFO 2025-03-21 20:32:01,154 qnn_preprocess.py:69] Visiting: aten_select_copy_int_316, aten.select_copy.int
2025-03-21T20:32:01.1735251Z [INFO 2025-03-21 20:32:01,155 qnn_preprocess.py:69] Visiting: aten_select_copy_int_318, aten.select_copy.int
2025-03-21T20:32:01.1736610Z [INFO 2025-03-21 20:32:01,155 qnn_preprocess.py:69] Visiting: aten_select_copy_int_320, aten.select_copy.int
2025-03-21T20:32:01.1737998Z [INFO 2025-03-21 20:32:01,156 qnn_preprocess.py:69] Visiting: aten_select_copy_int_322, aten.select_copy.int
2025-03-21T20:32:01.1739260Z [INFO 2025-03-21 20:32:01,156 qnn_preprocess.py:69] Visiting: aten_select_copy_int_324, aten.select_copy.int
2025-03-21T20:32:01.1740801Z [INFO 2025-03-21 20:32:01,157 qnn_preprocess.py:69] Visiting: aten_select_copy_int_326, aten.select_copy.int
2025-03-21T20:32:01.1742173Z [INFO 2025-03-21 20:32:01,157 qnn_preprocess.py:69] Visiting: aten_select_copy_int_328, aten.select_copy.int
2025-03-21T20:32:01.1743483Z [INFO 2025-03-21 20:32:01,157 qnn_preprocess.py:69] Visiting: aten_select_copy_int_330, aten.select_copy.int
2025-03-21T20:32:01.1744714Z [INFO 2025-03-21 20:32:01,158 qnn_preprocess.py:69] Visiting: aten_select_copy_int_332, aten.select_copy.int
2025-03-21T20:32:01.1746091Z [INFO 2025-03-21 20:32:01,158 qnn_preprocess.py:69] Visiting: aten_select_copy_int_334, aten.select_copy.int
2025-03-21T20:32:01.1747539Z [INFO 2025-03-21 20:32:01,159 qnn_preprocess.py:69] Visiting: aten_mul_tensor_92, aten.mul.Tensor
2025-03-21T20:32:01.1748794Z [INFO 2025-03-21 20:32:01,159 qnn_preprocess.py:69] Visiting: aten_mul_tensor_94, aten.mul.Tensor
2025-03-21T20:32:01.1750049Z [INFO 2025-03-21 20:32:01,160 qnn_preprocess.py:69] Visiting: aten_mul_tensor_93, aten.mul.Tensor
2025-03-21T20:32:01.1751290Z [INFO 2025-03-21 20:32:01,160 qnn_preprocess.py:69] Visiting: aten_mul_tensor_95, aten.mul.Tensor
2025-03-21T20:32:01.1752525Z [INFO 2025-03-21 20:32:01,161 qnn_preprocess.py:69] Visiting: aten_mul_tensor_96, aten.mul.Tensor
2025-03-21T20:32:01.1753776Z [INFO 2025-03-21 20:32:01,161 qnn_preprocess.py:69] Visiting: aten_mul_tensor_98, aten.mul.Tensor
2025-03-21T20:32:01.1755012Z [INFO 2025-03-21 20:32:01,162 qnn_preprocess.py:69] Visiting: aten_mul_tensor_97, aten.mul.Tensor
2025-03-21T20:32:01.1756247Z [INFO 2025-03-21 20:32:01,162 qnn_preprocess.py:69] Visiting: aten_mul_tensor_99, aten.mul.Tensor
2025-03-21T20:32:01.1757573Z [INFO 2025-03-21 20:32:01,163 qnn_preprocess.py:69] Visiting: aten_select_copy_int_313, aten.select_copy.int
2025-03-21T20:32:01.1758952Z [INFO 2025-03-21 20:32:01,163 qnn_preprocess.py:69] Visiting: aten_select_copy_int_315, aten.select_copy.int
2025-03-21T20:32:01.1760329Z [INFO 2025-03-21 20:32:01,164 qnn_preprocess.py:69] Visiting: aten_select_copy_int_317, aten.select_copy.int
2025-03-21T20:32:01.1761702Z [INFO 2025-03-21 20:32:01,164 qnn_preprocess.py:69] Visiting: aten_select_copy_int_319, aten.select_copy.int
2025-03-21T20:32:01.1763062Z [INFO 2025-03-21 20:32:01,165 qnn_preprocess.py:69] Visiting: aten_select_copy_int_321, aten.select_copy.int
2025-03-21T20:32:01.1764422Z [INFO 2025-03-21 20:32:01,165 qnn_preprocess.py:69] Visiting: aten_select_copy_int_323, aten.select_copy.int
2025-03-21T20:32:01.2133776Z [INFO 2025-03-21 20:32:01,166 qnn_preprocess.py:69] Visiting: aten_select_copy_int_325, aten.select_copy.int
2025-03-21T20:32:01.2135046Z [INFO 2025-03-21 20:32:01,166 qnn_preprocess.py:69] Visiting: aten_select_copy_int_327, aten.select_copy.int
2025-03-21T20:32:01.2136526Z [INFO 2025-03-21 20:32:01,167 qnn_preprocess.py:69] Visiting: aten_select_copy_int_329, aten.select_copy.int
2025-03-21T20:32:01.2137868Z [INFO 2025-03-21 20:32:01,168 qnn_preprocess.py:69] Visiting: aten_select_copy_int_331, aten.select_copy.int
2025-03-21T20:32:01.2139055Z [INFO 2025-03-21 20:32:01,168 qnn_preprocess.py:69] Visiting: aten_select_copy_int_333, aten.select_copy.int
2025-03-21T20:32:01.2140318Z [INFO 2025-03-21 20:32:01,169 qnn_preprocess.py:69] Visiting: aten_select_copy_int_335, aten.select_copy.int
2025-03-21T20:32:01.2141592Z [INFO 2025-03-21 20:32:01,170 qnn_preprocess.py:69] Visiting: aten_sub_tensor_12, aten.sub.Tensor
2025-03-21T20:32:01.2142639Z [INFO 2025-03-21 20:32:01,171 qnn_preprocess.py:69] Visiting: aten_add_tensor_30, aten.add.Tensor
2025-03-21T20:32:01.2143752Z [INFO 2025-03-21 20:32:01,172 qnn_preprocess.py:69] Visiting: aten_sub_tensor_13, aten.sub.Tensor
2025-03-21T20:32:01.2145006Z [INFO 2025-03-21 20:32:01,173 qnn_preprocess.py:69] Visiting: aten_add_tensor_31, aten.add.Tensor
2025-03-21T20:32:01.2146233Z [INFO 2025-03-21 20:32:01,174 qnn_preprocess.py:69] Visiting: aten_cat_default_27, aten.cat.default
2025-03-21T20:32:01.2147783Z [INFO 2025-03-21 20:32:01,177 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_69, aten.unsqueeze_copy.default
2025-03-21T20:32:01.2149366Z [INFO 2025-03-21 20:32:01,177 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_70, aten.unsqueeze_copy.default
2025-03-21T20:32:01.2150704Z [INFO 2025-03-21 20:32:01,177 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_71, aten.unsqueeze_copy.default
2025-03-21T20:32:01.2152277Z [INFO 2025-03-21 20:32:01,178 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_72, aten.unsqueeze_copy.default
2025-03-21T20:32:01.2153716Z [INFO 2025-03-21 20:32:01,178 qnn_preprocess.py:69] Visiting: aten_view_copy_default_118, aten.view_copy.default
2025-03-21T20:32:01.2155227Z [INFO 2025-03-21 20:32:01,178 qnn_preprocess.py:69] Visiting: aten__to_copy_default_14, aten._to_copy.default
2025-03-21T20:32:01.2156573Z [INFO 2025-03-21 20:32:01,179 qnn_preprocess.py:69] Visiting: aten_cat_default_24, aten.cat.default
2025-03-21T20:32:01.2157839Z [INFO 2025-03-21 20:32:01,180 qnn_preprocess.py:69] Visiting: aten_cat_default_25, aten.cat.default
2025-03-21T20:32:01.2159206Z [INFO 2025-03-21 20:32:01,180 qnn_preprocess.py:69] Visiting: aten_view_copy_default_115, aten.view_copy.default
2025-03-21T20:32:01.2160458Z [INFO 2025-03-21 20:32:01,180 qnn_preprocess.py:69] Visiting: aten_view_copy_default_116, aten.view_copy.default
2025-03-21T20:32:01.2161937Z [INFO 2025-03-21 20:32:01,181 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_252, aten.permute_copy.default
2025-03-21T20:32:01.2163368Z [INFO 2025-03-21 20:32:01,182 qnn_preprocess.py:69] Visiting: aten_index_put_default_12, aten.index_put.default
2025-03-21T20:32:01.2164855Z [INFO 2025-03-21 20:32:01,183 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_253, aten.permute_copy.default
2025-03-21T20:32:01.2166386Z [INFO 2025-03-21 20:32:01,184 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_254, aten.permute_copy.default
2025-03-21T20:32:01.2167872Z [INFO 2025-03-21 20:32:01,184 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_255, aten.permute_copy.default
2025-03-21T20:32:01.2169470Z [INFO 2025-03-21 20:32:01,185 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_256, aten.permute_copy.default
2025-03-21T20:32:01.2170998Z [INFO 2025-03-21 20:32:01,186 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_257, aten.permute_copy.default
2025-03-21T20:32:01.2172339Z [INFO 2025-03-21 20:32:01,186 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_258, aten.permute_copy.default
2025-03-21T20:32:01.2173734Z [INFO 2025-03-21 20:32:01,187 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_259, aten.permute_copy.default
2025-03-21T20:32:01.2175473Z [INFO 2025-03-21 20:32:01,188 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_260, aten.permute_copy.default
2025-03-21T20:32:01.2177134Z [INFO 2025-03-21 20:32:01,188 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_261, aten.permute_copy.default
2025-03-21T20:32:01.2178920Z [INFO 2025-03-21 20:32:01,189 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_262, aten.permute_copy.default
2025-03-21T20:32:01.2180641Z [INFO 2025-03-21 20:32:01,190 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_263, aten.permute_copy.default
2025-03-21T20:32:01.2182380Z [INFO 2025-03-21 20:32:01,190 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_264, aten.permute_copy.default
2025-03-21T20:32:01.2183842Z [INFO 2025-03-21 20:32:01,191 qnn_preprocess.py:69] Visiting: aten_select_copy_int_288, aten.select_copy.int
2025-03-21T20:32:01.2185152Z [INFO 2025-03-21 20:32:01,191 qnn_preprocess.py:69] Visiting: aten_select_copy_int_290, aten.select_copy.int
2025-03-21T20:32:01.2186506Z [INFO 2025-03-21 20:32:01,192 qnn_preprocess.py:69] Visiting: aten_select_copy_int_292, aten.select_copy.int
2025-03-21T20:32:01.2187906Z [INFO 2025-03-21 20:32:01,192 qnn_preprocess.py:69] Visiting: aten_select_copy_int_294, aten.select_copy.int
2025-03-21T20:32:01.2189247Z [INFO 2025-03-21 20:32:01,193 qnn_preprocess.py:69] Visiting: aten_select_copy_int_296, aten.select_copy.int
2025-03-21T20:32:01.2190661Z [INFO 2025-03-21 20:32:01,193 qnn_preprocess.py:69] Visiting: aten_select_copy_int_298, aten.select_copy.int
2025-03-21T20:32:01.2191886Z [INFO 2025-03-21 20:32:01,194 qnn_preprocess.py:69] Visiting: aten_select_copy_int_300, aten.select_copy.int
2025-03-21T20:32:01.2193246Z [INFO 2025-03-21 20:32:01,194 qnn_preprocess.py:69] Visiting: aten_select_copy_int_302, aten.select_copy.int
2025-03-21T20:32:01.2194391Z [INFO 2025-03-21 20:32:01,194 qnn_preprocess.py:69] Visiting: aten_select_copy_int_304, aten.select_copy.int
2025-03-21T20:32:01.2195572Z [INFO 2025-03-21 20:32:01,195 qnn_preprocess.py:69] Visiting: aten_select_copy_int_306, aten.select_copy.int
2025-03-21T20:32:01.2196855Z [INFO 2025-03-21 20:32:01,195 qnn_preprocess.py:69] Visiting: aten_select_copy_int_308, aten.select_copy.int
2025-03-21T20:32:01.2198033Z [INFO 2025-03-21 20:32:01,196 qnn_preprocess.py:69] Visiting: aten_select_copy_int_310, aten.select_copy.int
2025-03-21T20:32:01.2199350Z [INFO 2025-03-21 20:32:01,196 qnn_preprocess.py:69] Visiting: aten_select_copy_int_289, aten.select_copy.int
2025-03-21T20:32:01.2200612Z [INFO 2025-03-21 20:32:01,197 qnn_preprocess.py:69] Visiting: aten_select_copy_int_291, aten.select_copy.int
2025-03-21T20:32:01.2201752Z [INFO 2025-03-21 20:32:01,197 qnn_preprocess.py:69] Visiting: aten_select_copy_int_293, aten.select_copy.int
2025-03-21T20:32:01.2203105Z [INFO 2025-03-21 20:32:01,197 qnn_preprocess.py:69] Visiting: aten_select_copy_int_295, aten.select_copy.int
2025-03-21T20:32:01.2204457Z [INFO 2025-03-21 20:32:01,198 qnn_preprocess.py:69] Visiting: aten_select_copy_int_297, aten.select_copy.int
2025-03-21T20:32:01.2205830Z [INFO 2025-03-21 20:32:01,198 qnn_preprocess.py:69] Visiting: aten_select_copy_int_299, aten.select_copy.int
2025-03-21T20:32:01.2207195Z [INFO 2025-03-21 20:32:01,199 qnn_preprocess.py:69] Visiting: aten_select_copy_int_301, aten.select_copy.int
2025-03-21T20:32:01.2208477Z [INFO 2025-03-21 20:32:01,199 qnn_preprocess.py:69] Visiting: aten_select_copy_int_303, aten.select_copy.int
2025-03-21T20:32:01.2209815Z [INFO 2025-03-21 20:32:01,199 qnn_preprocess.py:69] Visiting: aten_select_copy_int_305, aten.select_copy.int
2025-03-21T20:32:01.2211172Z [INFO 2025-03-21 20:32:01,200 qnn_preprocess.py:69] Visiting: aten_select_copy_int_307, aten.select_copy.int
2025-03-21T20:32:01.2212284Z [INFO 2025-03-21 20:32:01,200 qnn_preprocess.py:69] Visiting: aten_select_copy_int_309, aten.select_copy.int
2025-03-21T20:32:01.2213502Z [INFO 2025-03-21 20:32:01,201 qnn_preprocess.py:69] Visiting: aten_select_copy_int_311, aten.select_copy.int
2025-03-21T20:32:01.2214645Z [INFO 2025-03-21 20:32:01,201 qnn_preprocess.py:69] Visiting: aten_cat_default_26, aten.cat.default
2025-03-21T20:32:01.2215811Z [INFO 2025-03-21 20:32:01,203 qnn_preprocess.py:69] Visiting: aten_view_copy_default_117, aten.view_copy.default
2025-03-21T20:32:01.2217419Z [INFO 2025-03-21 20:32:01,203 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_277, aten.permute_copy.default
2025-03-21T20:32:01.2218688Z [INFO 2025-03-21 20:32:01,204 qnn_preprocess.py:69] Visiting: aten__to_copy_default_15, aten._to_copy.default
2025-03-21T20:32:01.2219904Z [INFO 2025-03-21 20:32:01,204 qnn_preprocess.py:69] Visiting: aten_matmul_default_12, aten.matmul.default
2025-03-21T20:32:01.2221204Z [INFO 2025-03-21 20:32:01,205 qnn_preprocess.py:69] Visiting: aten_mul_tensor_100, aten.mul.Tensor
2025-03-21T20:32:01.2222473Z [INFO 2025-03-21 20:32:01,206 qnn_preprocess.py:69] Visiting: aten_add_tensor_32, aten.add.Tensor
2025-03-21T20:32:01.2223779Z [INFO 2025-03-21 20:32:01,207 qnn_preprocess.py:69] Visiting: aten__softmax_default_6, aten._softmax.default
2025-03-21T20:32:01.2225109Z [INFO 2025-03-21 20:32:01,207 qnn_preprocess.py:69] Visiting: aten_matmul_default_13, aten.matmul.default
2025-03-21T20:32:01.2226456Z [INFO 2025-03-21 20:32:01,207 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_278, aten.permute_copy.default
2025-03-21T20:32:01.2227698Z [INFO 2025-03-21 20:32:01,208 qnn_preprocess.py:69] Visiting: aten_view_copy_default_125, aten.view_copy.default
2025-03-21T20:32:01.2229117Z [INFO 2025-03-21 20:32:01,208 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_73, aten.unsqueeze_copy.default
2025-03-21T20:32:01.2230423Z [INFO 2025-03-21 20:32:01,209 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_754, aten.permute_copy.default
2025-03-21T20:32:01.2231875Z [INFO 2025-03-21 20:32:01,210 qnn_preprocess.py:69] Visiting: aten_convolution_default_45, aten.convolution.default
2025-03-21T20:32:01.2840435Z [INFO 2025-03-21 20:32:01,212 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_755, aten.permute_copy.default
2025-03-21T20:32:01.2842455Z [INFO 2025-03-21 20:32:01,214 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_73, aten.squeeze_copy.dims
2025-03-21T20:32:01.2843606Z [INFO 2025-03-21 20:32:01,215 qnn_preprocess.py:69] Visiting: aten_add_tensor_33, aten.add.Tensor
2025-03-21T20:32:01.2844829Z [INFO 2025-03-21 20:32:01,215 qnn_preprocess.py:69] Visiting: aten_rms_norm_default_13, aten.rms_norm.default
2025-03-21T20:32:01.2846312Z [INFO 2025-03-21 20:32:01,218 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_74, aten.unsqueeze_copy.default
2025-03-21T20:32:01.2847914Z [INFO 2025-03-21 20:32:01,219 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_756, aten.permute_copy.default
2025-03-21T20:32:01.2849427Z [INFO 2025-03-21 20:32:01,220 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_75, aten.unsqueeze_copy.default
2025-03-21T20:32:01.2851025Z [INFO 2025-03-21 20:32:01,220 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_757, aten.permute_copy.default
2025-03-21T20:32:01.2852446Z [INFO 2025-03-21 20:32:01,221 qnn_preprocess.py:69] Visiting: aten_convolution_default_46, aten.convolution.default
2025-03-21T20:32:01.2853767Z [INFO 2025-03-21 20:32:01,228 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_758, aten.permute_copy.default
2025-03-21T20:32:01.2855266Z [INFO 2025-03-21 20:32:01,229 qnn_preprocess.py:69] Visiting: aten_convolution_default_47, aten.convolution.default
2025-03-21T20:32:01.2856771Z [INFO 2025-03-21 20:32:01,236 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_759, aten.permute_copy.default
2025-03-21T20:32:01.2858207Z [INFO 2025-03-21 20:32:01,237 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_74, aten.squeeze_copy.dims
2025-03-21T20:32:01.2859553Z [INFO 2025-03-21 20:32:01,237 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_75, aten.squeeze_copy.dims
2025-03-21T20:32:01.2860881Z [INFO 2025-03-21 20:32:01,238 qnn_preprocess.py:69] Visiting: aten_sigmoid_default_6, aten.sigmoid.default
2025-03-21T20:32:01.2862000Z [INFO 2025-03-21 20:32:01,238 qnn_preprocess.py:69] Visiting: aten_mul_tensor_103, aten.mul.Tensor
2025-03-21T20:32:01.2863222Z [INFO 2025-03-21 20:32:01,239 qnn_preprocess.py:69] Visiting: aten_mul_tensor_104, aten.mul.Tensor
2025-03-21T20:32:01.2864956Z [INFO 2025-03-21 20:32:01,239 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_76, aten.unsqueeze_copy.default
2025-03-21T20:32:01.2866487Z [INFO 2025-03-21 20:32:01,240 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_760, aten.permute_copy.default
2025-03-21T20:32:01.2880159Z [INFO 2025-03-21 20:32:01,240 qnn_preprocess.py:69] Visiting: aten_convolution_default_48, aten.convolution.default
2025-03-21T20:32:01.2881673Z [INFO 2025-03-21 20:32:01,247 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_761, aten.permute_copy.default
2025-03-21T20:32:01.2883149Z [INFO 2025-03-21 20:32:01,248 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_76, aten.squeeze_copy.dims
2025-03-21T20:32:01.2884355Z [INFO 2025-03-21 20:32:01,248 qnn_preprocess.py:69] Visiting: aten_add_tensor_34, aten.add.Tensor
2025-03-21T20:32:01.2885453Z [INFO 2025-03-21 20:32:01,249 qnn_preprocess.py:69] Visiting: aten_rms_norm_default_14, aten.rms_norm.default
2025-03-21T20:32:01.2886934Z [INFO 2025-03-21 20:32:01,250 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_77, aten.unsqueeze_copy.default
2025-03-21T20:32:01.2888591Z [INFO 2025-03-21 20:32:01,251 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_762, aten.permute_copy.default
2025-03-21T20:32:01.2890152Z [INFO 2025-03-21 20:32:01,251 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_78, aten.unsqueeze_copy.default
2025-03-21T20:32:01.2891682Z [INFO 2025-03-21 20:32:01,252 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_763, aten.permute_copy.default
2025-03-21T20:32:01.2893212Z [INFO 2025-03-21 20:32:01,252 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_79, aten.unsqueeze_copy.default
2025-03-21T20:32:01.2894695Z [INFO 2025-03-21 20:32:01,253 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_764, aten.permute_copy.default
2025-03-21T20:32:01.2896226Z [INFO 2025-03-21 20:32:01,254 qnn_preprocess.py:69] Visiting: aten_convolution_default_49, aten.convolution.default
2025-03-21T20:32:01.2897673Z [INFO 2025-03-21 20:32:01,256 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_765, aten.permute_copy.default
2025-03-21T20:32:01.2899192Z [INFO 2025-03-21 20:32:01,257 qnn_preprocess.py:69] Visiting: aten_convolution_default_50, aten.convolution.default
2025-03-21T20:32:01.2900614Z [INFO 2025-03-21 20:32:01,260 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_766, aten.permute_copy.default
2025-03-21T20:32:01.2902127Z [INFO 2025-03-21 20:32:01,261 qnn_preprocess.py:69] Visiting: aten_convolution_default_51, aten.convolution.default
2025-03-21T20:32:01.2903639Z [INFO 2025-03-21 20:32:01,264 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_767, aten.permute_copy.default
2025-03-21T20:32:01.2904969Z [INFO 2025-03-21 20:32:01,265 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_77, aten.squeeze_copy.dims
2025-03-21T20:32:01.2906376Z [INFO 2025-03-21 20:32:01,265 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_78, aten.squeeze_copy.dims
2025-03-21T20:32:01.2907770Z [INFO 2025-03-21 20:32:01,266 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_79, aten.squeeze_copy.dims
2025-03-21T20:32:01.2909210Z [INFO 2025-03-21 20:32:01,266 qnn_preprocess.py:69] Visiting: aten_view_copy_default_126, aten.view_copy.default
2025-03-21T20:32:01.2910538Z [INFO 2025-03-21 20:32:01,266 qnn_preprocess.py:69] Visiting: aten_view_copy_default_127, aten.view_copy.default
2025-03-21T20:32:01.2911953Z [INFO 2025-03-21 20:32:01,267 qnn_preprocess.py:69] Visiting: aten_view_copy_default_128, aten.view_copy.default
2025-03-21T20:32:01.2913387Z [INFO 2025-03-21 20:32:01,267 qnn_preprocess.py:69] Visiting: aten_view_copy_default_129, aten.view_copy.default
2025-03-21T20:32:01.2914652Z [INFO 2025-03-21 20:32:01,267 qnn_preprocess.py:69] Visiting: aten_view_copy_default_130, aten.view_copy.default
2025-03-21T20:32:01.2916082Z [INFO 2025-03-21 20:32:01,268 qnn_preprocess.py:69] Visiting: aten_index_put_default_15, aten.index_put.default
2025-03-21T20:32:01.2917618Z [INFO 2025-03-21 20:32:01,269 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_28, aten.slice_copy.Tensor
2025-03-21T20:32:01.2918983Z [INFO 2025-03-21 20:32:01,269 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_29, aten.slice_copy.Tensor
2025-03-21T20:32:01.2920377Z [INFO 2025-03-21 20:32:01,270 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_30, aten.slice_copy.Tensor
2025-03-21T20:32:01.2921776Z [INFO 2025-03-21 20:32:01,270 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_31, aten.slice_copy.Tensor
2025-03-21T20:32:01.2923241Z [INFO 2025-03-21 20:32:01,271 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_306, aten.permute_copy.default
2025-03-21T20:32:01.2924611Z [INFO 2025-03-21 20:32:01,271 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_307, aten.permute_copy.default
2025-03-21T20:32:01.2926114Z [INFO 2025-03-21 20:32:01,272 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_308, aten.permute_copy.default
2025-03-21T20:32:01.2927639Z [INFO 2025-03-21 20:32:01,273 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_309, aten.permute_copy.default
2025-03-21T20:32:01.2929161Z [INFO 2025-03-21 20:32:01,273 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_310, aten.permute_copy.default
2025-03-21T20:32:01.2930761Z [INFO 2025-03-21 20:32:01,274 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_311, aten.permute_copy.default
2025-03-21T20:32:01.2932500Z [INFO 2025-03-21 20:32:01,275 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_312, aten.permute_copy.default
2025-03-21T20:32:01.2933862Z [INFO 2025-03-21 20:32:01,275 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_313, aten.permute_copy.default
2025-03-21T20:32:01.2935361Z [INFO 2025-03-21 20:32:01,276 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_314, aten.permute_copy.default
2025-03-21T20:32:01.2936987Z [INFO 2025-03-21 20:32:01,277 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_315, aten.permute_copy.default
2025-03-21T20:32:01.2938424Z [INFO 2025-03-21 20:32:01,277 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_316, aten.permute_copy.default
2025-03-21T20:32:01.2939960Z [INFO 2025-03-21 20:32:01,278 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_317, aten.permute_copy.default
2025-03-21T20:32:01.2941415Z [INFO 2025-03-21 20:32:01,279 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_80, aten.squeeze_copy.dims
2025-03-21T20:32:01.2942770Z [INFO 2025-03-21 20:32:01,279 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_81, aten.squeeze_copy.dims
2025-03-21T20:32:01.2944104Z [INFO 2025-03-21 20:32:01,280 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_82, aten.squeeze_copy.dims
2025-03-21T20:32:01.2945468Z [INFO 2025-03-21 20:32:01,280 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_83, aten.squeeze_copy.dims
2025-03-21T20:32:01.2946877Z [INFO 2025-03-21 20:32:01,280 qnn_preprocess.py:69] Visiting: aten_select_copy_int_360, aten.select_copy.int
2025-03-21T20:32:01.2948175Z [INFO 2025-03-21 20:32:01,281 qnn_preprocess.py:69] Visiting: aten_select_copy_int_362, aten.select_copy.int
2025-03-21T20:32:01.2949558Z [INFO 2025-03-21 20:32:01,281 qnn_preprocess.py:69] Visiting: aten_select_copy_int_364, aten.select_copy.int
2025-03-21T20:32:01.2950924Z [INFO 2025-03-21 20:32:01,282 qnn_preprocess.py:69] Visiting: aten_select_copy_int_366, aten.select_copy.int
2025-03-21T20:32:01.2952229Z [INFO 2025-03-21 20:32:01,282 qnn_preprocess.py:69] Visiting: aten_select_copy_int_368, aten.select_copy.int
2025-03-21T20:32:01.2953520Z [INFO 2025-03-21 20:32:01,283 qnn_preprocess.py:69] Visiting: aten_select_copy_int_370, aten.select_copy.int
2025-03-21T20:32:01.3281179Z [INFO 2025-03-21 20:32:01,283 qnn_preprocess.py:69] Visiting: aten_select_copy_int_372, aten.select_copy.int
2025-03-21T20:32:01.3282571Z [INFO 2025-03-21 20:32:01,284 qnn_preprocess.py:69] Visiting: aten_select_copy_int_374, aten.select_copy.int
2025-03-21T20:32:01.3283926Z [INFO 2025-03-21 20:32:01,285 qnn_preprocess.py:69] Visiting: aten_select_copy_int_376, aten.select_copy.int
2025-03-21T20:32:01.3285463Z [INFO 2025-03-21 20:32:01,286 qnn_preprocess.py:69] Visiting: aten_select_copy_int_378, aten.select_copy.int
2025-03-21T20:32:01.3286822Z [INFO 2025-03-21 20:32:01,286 qnn_preprocess.py:69] Visiting: aten_select_copy_int_380, aten.select_copy.int
2025-03-21T20:32:01.3288174Z [INFO 2025-03-21 20:32:01,287 qnn_preprocess.py:69] Visiting: aten_select_copy_int_382, aten.select_copy.int
2025-03-21T20:32:01.3289599Z [INFO 2025-03-21 20:32:01,288 qnn_preprocess.py:69] Visiting: aten_mul_tensor_107, aten.mul.Tensor
2025-03-21T20:32:01.3290905Z [INFO 2025-03-21 20:32:01,289 qnn_preprocess.py:69] Visiting: aten_mul_tensor_109, aten.mul.Tensor
2025-03-21T20:32:01.3292116Z [INFO 2025-03-21 20:32:01,290 qnn_preprocess.py:69] Visiting: aten_mul_tensor_108, aten.mul.Tensor
2025-03-21T20:32:01.3293155Z [INFO 2025-03-21 20:32:01,291 qnn_preprocess.py:69] Visiting: aten_mul_tensor_110, aten.mul.Tensor
2025-03-21T20:32:01.3294387Z [INFO 2025-03-21 20:32:01,292 qnn_preprocess.py:69] Visiting: aten_mul_tensor_111, aten.mul.Tensor
2025-03-21T20:32:01.3295625Z [INFO 2025-03-21 20:32:01,293 qnn_preprocess.py:69] Visiting: aten_mul_tensor_113, aten.mul.Tensor
2025-03-21T20:32:01.3297032Z [INFO 2025-03-21 20:32:01,294 qnn_preprocess.py:69] Visiting: aten_mul_tensor_112, aten.mul.Tensor
2025-03-21T20:32:01.3298260Z [INFO 2025-03-21 20:32:01,295 qnn_preprocess.py:69] Visiting: aten_mul_tensor_114, aten.mul.Tensor
2025-03-21T20:32:01.3299559Z [INFO 2025-03-21 20:32:01,296 qnn_preprocess.py:69] Visiting: aten_select_copy_int_361, aten.select_copy.int
2025-03-21T20:32:01.3300719Z [INFO 2025-03-21 20:32:01,296 qnn_preprocess.py:69] Visiting: aten_select_copy_int_363, aten.select_copy.int
2025-03-21T20:32:01.3302056Z [INFO 2025-03-21 20:32:01,296 qnn_preprocess.py:69] Visiting: aten_select_copy_int_365, aten.select_copy.int
2025-03-21T20:32:01.3303404Z [INFO 2025-03-21 20:32:01,297 qnn_preprocess.py:69] Visiting: aten_select_copy_int_367, aten.select_copy.int
2025-03-21T20:32:01.3304802Z [INFO 2025-03-21 20:32:01,297 qnn_preprocess.py:69] Visiting: aten_select_copy_int_369, aten.select_copy.int
2025-03-21T20:32:01.3306148Z [INFO 2025-03-21 20:32:01,298 qnn_preprocess.py:69] Visiting: aten_select_copy_int_371, aten.select_copy.int
2025-03-21T20:32:01.3307460Z [INFO 2025-03-21 20:32:01,298 qnn_preprocess.py:69] Visiting: aten_select_copy_int_373, aten.select_copy.int
2025-03-21T20:32:01.3308627Z [INFO 2025-03-21 20:32:01,298 qnn_preprocess.py:69] Visiting: aten_select_copy_int_375, aten.select_copy.int
2025-03-21T20:32:01.3309992Z [INFO 2025-03-21 20:32:01,299 qnn_preprocess.py:69] Visiting: aten_select_copy_int_377, aten.select_copy.int
2025-03-21T20:32:01.3311363Z [INFO 2025-03-21 20:32:01,299 qnn_preprocess.py:69] Visiting: aten_select_copy_int_379, aten.select_copy.int
2025-03-21T20:32:01.3312726Z [INFO 2025-03-21 20:32:01,300 qnn_preprocess.py:69] Visiting: aten_select_copy_int_381, aten.select_copy.int
2025-03-21T20:32:01.3314116Z [INFO 2025-03-21 20:32:01,300 qnn_preprocess.py:69] Visiting: aten_select_copy_int_383, aten.select_copy.int
2025-03-21T20:32:01.3315321Z [INFO 2025-03-21 20:32:01,300 qnn_preprocess.py:69] Visiting: aten_sub_tensor_14, aten.sub.Tensor
2025-03-21T20:32:01.3316383Z [INFO 2025-03-21 20:32:01,301 qnn_preprocess.py:69] Visiting: aten_add_tensor_35, aten.add.Tensor
2025-03-21T20:32:01.3317615Z [INFO 2025-03-21 20:32:01,302 qnn_preprocess.py:69] Visiting: aten_sub_tensor_15, aten.sub.Tensor
2025-03-21T20:32:01.3318840Z [INFO 2025-03-21 20:32:01,302 qnn_preprocess.py:69] Visiting: aten_add_tensor_36, aten.add.Tensor
2025-03-21T20:32:01.3320108Z [INFO 2025-03-21 20:32:01,303 qnn_preprocess.py:69] Visiting: aten_cat_default_31, aten.cat.default
2025-03-21T20:32:01.3321782Z [INFO 2025-03-21 20:32:01,304 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_80, aten.unsqueeze_copy.default
2025-03-21T20:32:01.3323361Z [INFO 2025-03-21 20:32:01,305 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_81, aten.unsqueeze_copy.default
2025-03-21T20:32:01.3324989Z [INFO 2025-03-21 20:32:01,305 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_82, aten.unsqueeze_copy.default
2025-03-21T20:32:01.3326596Z [INFO 2025-03-21 20:32:01,305 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_83, aten.unsqueeze_copy.default
2025-03-21T20:32:01.3328108Z [INFO 2025-03-21 20:32:01,306 qnn_preprocess.py:69] Visiting: aten_view_copy_default_136, aten.view_copy.default
2025-03-21T20:32:01.3329598Z [INFO 2025-03-21 20:32:01,306 qnn_preprocess.py:69] Visiting: aten__to_copy_default_16, aten._to_copy.default
2025-03-21T20:32:01.3330925Z [INFO 2025-03-21 20:32:01,307 qnn_preprocess.py:69] Visiting: aten_cat_default_28, aten.cat.default
2025-03-21T20:32:01.3332396Z [INFO 2025-03-21 20:32:01,307 qnn_preprocess.py:69] Visiting: aten_cat_default_29, aten.cat.default
2025-03-21T20:32:01.3333741Z [INFO 2025-03-21 20:32:01,308 qnn_preprocess.py:69] Visiting: aten_view_copy_default_133, aten.view_copy.default
2025-03-21T20:32:01.3335171Z [INFO 2025-03-21 20:32:01,308 qnn_preprocess.py:69] Visiting: aten_view_copy_default_134, aten.view_copy.default
2025-03-21T20:32:01.3336637Z [INFO 2025-03-21 20:32:01,308 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_293, aten.permute_copy.default
2025-03-21T20:32:01.3338244Z [INFO 2025-03-21 20:32:01,309 qnn_preprocess.py:69] Visiting: aten_index_put_default_14, aten.index_put.default
2025-03-21T20:32:01.3339713Z [INFO 2025-03-21 20:32:01,310 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_294, aten.permute_copy.default
2025-03-21T20:32:01.3341223Z [INFO 2025-03-21 20:32:01,311 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_295, aten.permute_copy.default
2025-03-21T20:32:01.3342722Z [INFO 2025-03-21 20:32:01,312 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_296, aten.permute_copy.default
2025-03-21T20:32:01.3344242Z [INFO 2025-03-21 20:32:01,313 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_297, aten.permute_copy.default
2025-03-21T20:32:01.3345578Z [INFO 2025-03-21 20:32:01,313 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_298, aten.permute_copy.default
2025-03-21T20:32:01.3346926Z [INFO 2025-03-21 20:32:01,314 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_299, aten.permute_copy.default
2025-03-21T20:32:01.3348421Z [INFO 2025-03-21 20:32:01,315 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_300, aten.permute_copy.default
2025-03-21T20:32:01.3349918Z [INFO 2025-03-21 20:32:01,315 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_301, aten.permute_copy.default
2025-03-21T20:32:01.3351305Z [INFO 2025-03-21 20:32:01,316 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_302, aten.permute_copy.default
2025-03-21T20:32:01.3352726Z [INFO 2025-03-21 20:32:01,317 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_303, aten.permute_copy.default
2025-03-21T20:32:01.3354117Z [INFO 2025-03-21 20:32:01,317 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_304, aten.permute_copy.default
2025-03-21T20:32:01.3355279Z [INFO 2025-03-21 20:32:01,318 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_305, aten.permute_copy.default
2025-03-21T20:32:01.3356426Z [INFO 2025-03-21 20:32:01,319 qnn_preprocess.py:69] Visiting: aten_select_copy_int_336, aten.select_copy.int
2025-03-21T20:32:01.3357551Z [INFO 2025-03-21 20:32:01,319 qnn_preprocess.py:69] Visiting: aten_select_copy_int_338, aten.select_copy.int
2025-03-21T20:32:01.3358670Z [INFO 2025-03-21 20:32:01,320 qnn_preprocess.py:69] Visiting: aten_select_copy_int_340, aten.select_copy.int
2025-03-21T20:32:01.3359810Z [INFO 2025-03-21 20:32:01,320 qnn_preprocess.py:69] Visiting: aten_select_copy_int_342, aten.select_copy.int
2025-03-21T20:32:01.3361136Z [INFO 2025-03-21 20:32:01,320 qnn_preprocess.py:69] Visiting: aten_select_copy_int_344, aten.select_copy.int
2025-03-21T20:32:01.3362505Z [INFO 2025-03-21 20:32:01,321 qnn_preprocess.py:69] Visiting: aten_select_copy_int_346, aten.select_copy.int
2025-03-21T20:32:01.3363710Z [INFO 2025-03-21 20:32:01,321 qnn_preprocess.py:69] Visiting: aten_select_copy_int_348, aten.select_copy.int
2025-03-21T20:32:01.3365276Z [INFO 2025-03-21 20:32:01,322 qnn_preprocess.py:69] Visiting: aten_select_copy_int_350, aten.select_copy.int
2025-03-21T20:32:01.3366637Z [INFO 2025-03-21 20:32:01,322 qnn_preprocess.py:69] Visiting: aten_select_copy_int_352, aten.select_copy.int
2025-03-21T20:32:01.3367985Z [INFO 2025-03-21 20:32:01,323 qnn_preprocess.py:69] Visiting: aten_select_copy_int_354, aten.select_copy.int
2025-03-21T20:32:01.3369455Z [INFO 2025-03-21 20:32:01,323 qnn_preprocess.py:69] Visiting: aten_select_copy_int_356, aten.select_copy.int
2025-03-21T20:32:01.3370723Z [INFO 2025-03-21 20:32:01,324 qnn_preprocess.py:69] Visiting: aten_select_copy_int_358, aten.select_copy.int
2025-03-21T20:32:01.3372114Z [INFO 2025-03-21 20:32:01,324 qnn_preprocess.py:69] Visiting: aten_select_copy_int_337, aten.select_copy.int
2025-03-21T20:32:01.3373450Z [INFO 2025-03-21 20:32:01,325 qnn_preprocess.py:69] Visiting: aten_select_copy_int_339, aten.select_copy.int
2025-03-21T20:32:01.3374786Z [INFO 2025-03-21 20:32:01,325 qnn_preprocess.py:69] Visiting: aten_select_copy_int_341, aten.select_copy.int
2025-03-21T20:32:01.3375977Z [INFO 2025-03-21 20:32:01,325 qnn_preprocess.py:69] Visiting: aten_select_copy_int_343, aten.select_copy.int
2025-03-21T20:32:01.3377431Z [INFO 2025-03-21 20:32:01,326 qnn_preprocess.py:69] Visiting: aten_select_copy_int_345, aten.select_copy.int
2025-03-21T20:32:01.3378788Z [INFO 2025-03-21 20:32:01,326 qnn_preprocess.py:69] Visiting: aten_select_copy_int_347, aten.select_copy.int
2025-03-21T20:32:01.3380161Z [INFO 2025-03-21 20:32:01,327 qnn_preprocess.py:69] Visiting: aten_select_copy_int_349, aten.select_copy.int
2025-03-21T20:32:01.4042245Z [INFO 2025-03-21 20:32:01,327 qnn_preprocess.py:69] Visiting: aten_select_copy_int_351, aten.select_copy.int
2025-03-21T20:32:01.4043593Z [INFO 2025-03-21 20:32:01,328 qnn_preprocess.py:69] Visiting: aten_select_copy_int_353, aten.select_copy.int
2025-03-21T20:32:01.4044791Z [INFO 2025-03-21 20:32:01,329 qnn_preprocess.py:69] Visiting: aten_select_copy_int_355, aten.select_copy.int
2025-03-21T20:32:01.4046096Z [INFO 2025-03-21 20:32:01,330 qnn_preprocess.py:69] Visiting: aten_select_copy_int_357, aten.select_copy.int
2025-03-21T20:32:01.4047414Z [INFO 2025-03-21 20:32:01,330 qnn_preprocess.py:69] Visiting: aten_select_copy_int_359, aten.select_copy.int
2025-03-21T20:32:01.4048526Z [INFO 2025-03-21 20:32:01,331 qnn_preprocess.py:69] Visiting: aten_cat_default_30, aten.cat.default
2025-03-21T20:32:01.4049899Z [INFO 2025-03-21 20:32:01,334 qnn_preprocess.py:69] Visiting: aten_view_copy_default_135, aten.view_copy.default
2025-03-21T20:32:01.4051248Z [INFO 2025-03-21 20:32:01,335 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_318, aten.permute_copy.default
2025-03-21T20:32:01.4052493Z [INFO 2025-03-21 20:32:01,336 qnn_preprocess.py:69] Visiting: aten__to_copy_default_17, aten._to_copy.default
2025-03-21T20:32:01.4053711Z [INFO 2025-03-21 20:32:01,337 qnn_preprocess.py:69] Visiting: aten_matmul_default_14, aten.matmul.default
2025-03-21T20:32:01.4054816Z [INFO 2025-03-21 20:32:01,338 qnn_preprocess.py:69] Visiting: aten_mul_tensor_115, aten.mul.Tensor
2025-03-21T20:32:01.4055989Z [INFO 2025-03-21 20:32:01,339 qnn_preprocess.py:69] Visiting: aten_add_tensor_37, aten.add.Tensor
2025-03-21T20:32:01.4057278Z [INFO 2025-03-21 20:32:01,339 qnn_preprocess.py:69] Visiting: aten__softmax_default_7, aten._softmax.default
2025-03-21T20:32:01.4058411Z [INFO 2025-03-21 20:32:01,340 qnn_preprocess.py:69] Visiting: aten_matmul_default_15, aten.matmul.default
2025-03-21T20:32:01.4059753Z [INFO 2025-03-21 20:32:01,340 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_319, aten.permute_copy.default
2025-03-21T20:32:01.4061398Z [INFO 2025-03-21 20:32:01,341 qnn_preprocess.py:69] Visiting: aten_view_copy_default_143, aten.view_copy.default
2025-03-21T20:32:01.4062691Z [INFO 2025-03-21 20:32:01,341 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_84, aten.unsqueeze_copy.default
2025-03-21T20:32:01.4064197Z [INFO 2025-03-21 20:32:01,342 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_768, aten.permute_copy.default
2025-03-21T20:32:01.4065625Z [INFO 2025-03-21 20:32:01,342 qnn_preprocess.py:69] Visiting: aten_convolution_default_52, aten.convolution.default
2025-03-21T20:32:01.4067121Z [INFO 2025-03-21 20:32:01,345 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_769, aten.permute_copy.default
2025-03-21T20:32:01.4068351Z [INFO 2025-03-21 20:32:01,346 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_84, aten.squeeze_copy.dims
2025-03-21T20:32:01.4069585Z [INFO 2025-03-21 20:32:01,347 qnn_preprocess.py:69] Visiting: aten_add_tensor_38, aten.add.Tensor
2025-03-21T20:32:01.4070890Z [INFO 2025-03-21 20:32:01,347 qnn_preprocess.py:69] Visiting: aten_rms_norm_default_15, aten.rms_norm.default
2025-03-21T20:32:01.4072084Z [INFO 2025-03-21 20:32:01,349 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_85, aten.unsqueeze_copy.default
2025-03-21T20:32:01.4073484Z [INFO 2025-03-21 20:32:01,349 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_770, aten.permute_copy.default
2025-03-21T20:32:01.4074800Z [INFO 2025-03-21 20:32:01,350 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_86, aten.unsqueeze_copy.default
2025-03-21T20:32:01.4076426Z [INFO 2025-03-21 20:32:01,350 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_771, aten.permute_copy.default
2025-03-21T20:32:01.4077796Z [INFO 2025-03-21 20:32:01,351 qnn_preprocess.py:69] Visiting: aten_convolution_default_53, aten.convolution.default
2025-03-21T20:32:01.4079131Z [INFO 2025-03-21 20:32:01,356 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_772, aten.permute_copy.default
2025-03-21T20:32:01.4080640Z [INFO 2025-03-21 20:32:01,357 qnn_preprocess.py:69] Visiting: aten_convolution_default_54, aten.convolution.default
2025-03-21T20:32:01.4081889Z [INFO 2025-03-21 20:32:01,365 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_773, aten.permute_copy.default
2025-03-21T20:32:01.4083196Z [INFO 2025-03-21 20:32:01,366 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_85, aten.squeeze_copy.dims
2025-03-21T20:32:01.4084415Z [INFO 2025-03-21 20:32:01,367 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_86, aten.squeeze_copy.dims
2025-03-21T20:32:01.4085667Z [INFO 2025-03-21 20:32:01,367 qnn_preprocess.py:69] Visiting: aten_sigmoid_default_7, aten.sigmoid.default
2025-03-21T20:32:01.4086957Z [INFO 2025-03-21 20:32:01,368 qnn_preprocess.py:69] Visiting: aten_mul_tensor_118, aten.mul.Tensor
2025-03-21T20:32:01.4088033Z [INFO 2025-03-21 20:32:01,368 qnn_preprocess.py:69] Visiting: aten_mul_tensor_119, aten.mul.Tensor
2025-03-21T20:32:01.4089391Z [INFO 2025-03-21 20:32:01,369 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_87, aten.unsqueeze_copy.default
2025-03-21T20:32:01.4090920Z [INFO 2025-03-21 20:32:01,369 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_774, aten.permute_copy.default
2025-03-21T20:32:01.4092157Z [INFO 2025-03-21 20:32:01,370 qnn_preprocess.py:69] Visiting: aten_convolution_default_55, aten.convolution.default
2025-03-21T20:32:01.4093520Z [INFO 2025-03-21 20:32:01,376 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_775, aten.permute_copy.default
2025-03-21T20:32:01.4094789Z [INFO 2025-03-21 20:32:01,377 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_87, aten.squeeze_copy.dims
2025-03-21T20:32:01.4096011Z [INFO 2025-03-21 20:32:01,378 qnn_preprocess.py:69] Visiting: aten_add_tensor_39, aten.add.Tensor
2025-03-21T20:32:01.4097309Z [INFO 2025-03-21 20:32:01,378 qnn_preprocess.py:69] Visiting: aten_rms_norm_default_16, aten.rms_norm.default
2025-03-21T20:32:01.4098549Z [INFO 2025-03-21 20:32:01,379 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_88, aten.unsqueeze_copy.default
2025-03-21T20:32:01.4100172Z [INFO 2025-03-21 20:32:01,380 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_776, aten.permute_copy.default
2025-03-21T20:32:01.4101558Z [INFO 2025-03-21 20:32:01,381 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_89, aten.unsqueeze_copy.default
2025-03-21T20:32:01.4103069Z [INFO 2025-03-21 20:32:01,381 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_777, aten.permute_copy.default
2025-03-21T20:32:01.4104405Z [INFO 2025-03-21 20:32:01,382 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_90, aten.unsqueeze_copy.default
2025-03-21T20:32:01.4105757Z [INFO 2025-03-21 20:32:01,382 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_778, aten.permute_copy.default
2025-03-21T20:32:01.4107237Z [INFO 2025-03-21 20:32:01,383 qnn_preprocess.py:69] Visiting: aten_convolution_default_56, aten.convolution.default
2025-03-21T20:32:01.4108521Z [INFO 2025-03-21 20:32:01,386 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_779, aten.permute_copy.default
2025-03-21T20:32:01.4109932Z [INFO 2025-03-21 20:32:01,387 qnn_preprocess.py:69] Visiting: aten_convolution_default_57, aten.convolution.default
2025-03-21T20:32:01.4111336Z [INFO 2025-03-21 20:32:01,390 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_780, aten.permute_copy.default
2025-03-21T20:32:01.4112629Z [INFO 2025-03-21 20:32:01,391 qnn_preprocess.py:69] Visiting: aten_convolution_default_58, aten.convolution.default
2025-03-21T20:32:01.4114084Z [INFO 2025-03-21 20:32:01,394 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_781, aten.permute_copy.default
2025-03-21T20:32:01.4115332Z [INFO 2025-03-21 20:32:01,394 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_88, aten.squeeze_copy.dims
2025-03-21T20:32:01.4116685Z [INFO 2025-03-21 20:32:01,395 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_89, aten.squeeze_copy.dims
2025-03-21T20:32:01.4117985Z [INFO 2025-03-21 20:32:01,395 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_90, aten.squeeze_copy.dims
2025-03-21T20:32:01.4119181Z [INFO 2025-03-21 20:32:01,396 qnn_preprocess.py:69] Visiting: aten_view_copy_default_144, aten.view_copy.default
2025-03-21T20:32:01.4120579Z [INFO 2025-03-21 20:32:01,396 qnn_preprocess.py:69] Visiting: aten_view_copy_default_145, aten.view_copy.default
2025-03-21T20:32:01.4121987Z [INFO 2025-03-21 20:32:01,396 qnn_preprocess.py:69] Visiting: aten_view_copy_default_146, aten.view_copy.default
2025-03-21T20:32:01.4123385Z [INFO 2025-03-21 20:32:01,397 qnn_preprocess.py:69] Visiting: aten_view_copy_default_147, aten.view_copy.default
2025-03-21T20:32:01.4124802Z [INFO 2025-03-21 20:32:01,397 qnn_preprocess.py:69] Visiting: aten_view_copy_default_148, aten.view_copy.default
2025-03-21T20:32:01.4126090Z [INFO 2025-03-21 20:32:01,397 qnn_preprocess.py:69] Visiting: aten_index_put_default_17, aten.index_put.default
2025-03-21T20:32:01.4127417Z [INFO 2025-03-21 20:32:01,399 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_32, aten.slice_copy.Tensor
2025-03-21T20:32:01.4128814Z [INFO 2025-03-21 20:32:01,399 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_33, aten.slice_copy.Tensor
2025-03-21T20:32:01.4130318Z [INFO 2025-03-21 20:32:01,400 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_34, aten.slice_copy.Tensor
2025-03-21T20:32:01.4131703Z [INFO 2025-03-21 20:32:01,400 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_35, aten.slice_copy.Tensor
2025-03-21T20:32:01.4133348Z [INFO 2025-03-21 20:32:01,401 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_347, aten.permute_copy.default
2025-03-21T20:32:01.4134722Z [INFO 2025-03-21 20:32:01,401 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_348, aten.permute_copy.default
2025-03-21T20:32:01.4136234Z [INFO 2025-03-21 20:32:01,402 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_349, aten.permute_copy.default
2025-03-21T20:32:01.4137739Z [INFO 2025-03-21 20:32:01,403 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_350, aten.permute_copy.default
2025-03-21T20:32:01.4476103Z [INFO 2025-03-21 20:32:01,403 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_351, aten.permute_copy.default
2025-03-21T20:32:01.4477637Z [INFO 2025-03-21 20:32:01,404 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_352, aten.permute_copy.default
2025-03-21T20:32:01.4479355Z [INFO 2025-03-21 20:32:01,405 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_353, aten.permute_copy.default
2025-03-21T20:32:01.4480757Z [INFO 2025-03-21 20:32:01,406 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_354, aten.permute_copy.default
2025-03-21T20:32:01.4482247Z [INFO 2025-03-21 20:32:01,407 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_355, aten.permute_copy.default
2025-03-21T20:32:01.4483794Z [INFO 2025-03-21 20:32:01,408 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_356, aten.permute_copy.default
2025-03-21T20:32:01.4485275Z [INFO 2025-03-21 20:32:01,409 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_357, aten.permute_copy.default
2025-03-21T20:32:01.4486810Z [INFO 2025-03-21 20:32:01,410 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_358, aten.permute_copy.default
2025-03-21T20:32:01.4488071Z [INFO 2025-03-21 20:32:01,411 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_91, aten.squeeze_copy.dims
2025-03-21T20:32:01.4489537Z [INFO 2025-03-21 20:32:01,412 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_92, aten.squeeze_copy.dims
2025-03-21T20:32:01.4490919Z [INFO 2025-03-21 20:32:01,413 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_93, aten.squeeze_copy.dims
2025-03-21T20:32:01.4492494Z [INFO 2025-03-21 20:32:01,414 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_94, aten.squeeze_copy.dims
2025-03-21T20:32:01.4493869Z [INFO 2025-03-21 20:32:01,414 qnn_preprocess.py:69] Visiting: aten_select_copy_int_408, aten.select_copy.int
2025-03-21T20:32:01.4495168Z [INFO 2025-03-21 20:32:01,414 qnn_preprocess.py:69] Visiting: aten_select_copy_int_410, aten.select_copy.int
2025-03-21T20:32:01.4496340Z [INFO 2025-03-21 20:32:01,415 qnn_preprocess.py:69] Visiting: aten_select_copy_int_412, aten.select_copy.int
2025-03-21T20:32:01.4497694Z [INFO 2025-03-21 20:32:01,415 qnn_preprocess.py:69] Visiting: aten_select_copy_int_414, aten.select_copy.int
2025-03-21T20:32:01.4499027Z [INFO 2025-03-21 20:32:01,416 qnn_preprocess.py:69] Visiting: aten_select_copy_int_416, aten.select_copy.int
2025-03-21T20:32:01.4500410Z [INFO 2025-03-21 20:32:01,416 qnn_preprocess.py:69] Visiting: aten_select_copy_int_418, aten.select_copy.int
2025-03-21T20:32:01.4501792Z [INFO 2025-03-21 20:32:01,417 qnn_preprocess.py:69] Visiting: aten_select_copy_int_420, aten.select_copy.int
2025-03-21T20:32:01.4503067Z [INFO 2025-03-21 20:32:01,417 qnn_preprocess.py:69] Visiting: aten_select_copy_int_422, aten.select_copy.int
2025-03-21T20:32:01.4504286Z [INFO 2025-03-21 20:32:01,417 qnn_preprocess.py:69] Visiting: aten_select_copy_int_424, aten.select_copy.int
2025-03-21T20:32:01.4505650Z [INFO 2025-03-21 20:32:01,418 qnn_preprocess.py:69] Visiting: aten_select_copy_int_426, aten.select_copy.int
2025-03-21T20:32:01.4507015Z [INFO 2025-03-21 20:32:01,418 qnn_preprocess.py:69] Visiting: aten_select_copy_int_428, aten.select_copy.int
2025-03-21T20:32:01.4508343Z [INFO 2025-03-21 20:32:01,419 qnn_preprocess.py:69] Visiting: aten_select_copy_int_430, aten.select_copy.int
2025-03-21T20:32:01.4509678Z [INFO 2025-03-21 20:32:01,419 qnn_preprocess.py:69] Visiting: aten_mul_tensor_122, aten.mul.Tensor
2025-03-21T20:32:01.4510807Z [INFO 2025-03-21 20:32:01,420 qnn_preprocess.py:69] Visiting: aten_mul_tensor_124, aten.mul.Tensor
2025-03-21T20:32:01.4511947Z [INFO 2025-03-21 20:32:01,420 qnn_preprocess.py:69] Visiting: aten_mul_tensor_123, aten.mul.Tensor
2025-03-21T20:32:01.4513181Z [INFO 2025-03-21 20:32:01,421 qnn_preprocess.py:69] Visiting: aten_mul_tensor_125, aten.mul.Tensor
2025-03-21T20:32:01.4514414Z [INFO 2025-03-21 20:32:01,421 qnn_preprocess.py:69] Visiting: aten_mul_tensor_126, aten.mul.Tensor
2025-03-21T20:32:01.4515661Z [INFO 2025-03-21 20:32:01,422 qnn_preprocess.py:69] Visiting: aten_mul_tensor_128, aten.mul.Tensor
2025-03-21T20:32:01.4517066Z [INFO 2025-03-21 20:32:01,422 qnn_preprocess.py:69] Visiting: aten_mul_tensor_127, aten.mul.Tensor
2025-03-21T20:32:01.4518208Z [INFO 2025-03-21 20:32:01,423 qnn_preprocess.py:69] Visiting: aten_mul_tensor_129, aten.mul.Tensor
2025-03-21T20:32:01.4519496Z [INFO 2025-03-21 20:32:01,423 qnn_preprocess.py:69] Visiting: aten_select_copy_int_409, aten.select_copy.int
2025-03-21T20:32:01.4520870Z [INFO 2025-03-21 20:32:01,424 qnn_preprocess.py:69] Visiting: aten_select_copy_int_411, aten.select_copy.int
2025-03-21T20:32:01.4522219Z [INFO 2025-03-21 20:32:01,424 qnn_preprocess.py:69] Visiting: aten_select_copy_int_413, aten.select_copy.int
2025-03-21T20:32:01.4523559Z [INFO 2025-03-21 20:32:01,424 qnn_preprocess.py:69] Visiting: aten_select_copy_int_415, aten.select_copy.int
2025-03-21T20:32:01.4524922Z [INFO 2025-03-21 20:32:01,425 qnn_preprocess.py:69] Visiting: aten_select_copy_int_417, aten.select_copy.int
2025-03-21T20:32:01.4526151Z [INFO 2025-03-21 20:32:01,425 qnn_preprocess.py:69] Visiting: aten_select_copy_int_419, aten.select_copy.int
2025-03-21T20:32:01.4527401Z [INFO 2025-03-21 20:32:01,426 qnn_preprocess.py:69] Visiting: aten_select_copy_int_421, aten.select_copy.int
2025-03-21T20:32:01.4528767Z [INFO 2025-03-21 20:32:01,426 qnn_preprocess.py:69] Visiting: aten_select_copy_int_423, aten.select_copy.int
2025-03-21T20:32:01.4530204Z [INFO 2025-03-21 20:32:01,426 qnn_preprocess.py:69] Visiting: aten_select_copy_int_425, aten.select_copy.int
2025-03-21T20:32:01.4531639Z [INFO 2025-03-21 20:32:01,427 qnn_preprocess.py:69] Visiting: aten_select_copy_int_427, aten.select_copy.int
2025-03-21T20:32:01.4533210Z [INFO 2025-03-21 20:32:01,427 qnn_preprocess.py:69] Visiting: aten_select_copy_int_429, aten.select_copy.int
2025-03-21T20:32:01.4534354Z [INFO 2025-03-21 20:32:01,428 qnn_preprocess.py:69] Visiting: aten_select_copy_int_431, aten.select_copy.int
2025-03-21T20:32:01.4535563Z [INFO 2025-03-21 20:32:01,428 qnn_preprocess.py:69] Visiting: aten_sub_tensor_16, aten.sub.Tensor
2025-03-21T20:32:01.4536820Z [INFO 2025-03-21 20:32:01,429 qnn_preprocess.py:69] Visiting: aten_add_tensor_40, aten.add.Tensor
2025-03-21T20:32:01.4538059Z [INFO 2025-03-21 20:32:01,429 qnn_preprocess.py:69] Visiting: aten_sub_tensor_17, aten.sub.Tensor
2025-03-21T20:32:01.4539286Z [INFO 2025-03-21 20:32:01,430 qnn_preprocess.py:69] Visiting: aten_add_tensor_41, aten.add.Tensor
2025-03-21T20:32:01.4540556Z [INFO 2025-03-21 20:32:01,430 qnn_preprocess.py:69] Visiting: aten_cat_default_35, aten.cat.default
2025-03-21T20:32:01.4541814Z [INFO 2025-03-21 20:32:01,432 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_91, aten.unsqueeze_copy.default
2025-03-21T20:32:01.4543281Z [INFO 2025-03-21 20:32:01,432 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_92, aten.unsqueeze_copy.default
2025-03-21T20:32:01.4544838Z [INFO 2025-03-21 20:32:01,433 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_93, aten.unsqueeze_copy.default
2025-03-21T20:32:01.4546425Z [INFO 2025-03-21 20:32:01,433 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_94, aten.unsqueeze_copy.default
2025-03-21T20:32:01.4547887Z [INFO 2025-03-21 20:32:01,434 qnn_preprocess.py:69] Visiting: aten_view_copy_default_154, aten.view_copy.default
2025-03-21T20:32:01.4549192Z [INFO 2025-03-21 20:32:01,434 qnn_preprocess.py:69] Visiting: aten__to_copy_default_18, aten._to_copy.default
2025-03-21T20:32:01.4550377Z [INFO 2025-03-21 20:32:01,435 qnn_preprocess.py:69] Visiting: aten_cat_default_32, aten.cat.default
2025-03-21T20:32:01.4551632Z [INFO 2025-03-21 20:32:01,435 qnn_preprocess.py:69] Visiting: aten_cat_default_33, aten.cat.default
2025-03-21T20:32:01.4552969Z [INFO 2025-03-21 20:32:01,436 qnn_preprocess.py:69] Visiting: aten_view_copy_default_151, aten.view_copy.default
2025-03-21T20:32:01.4554378Z [INFO 2025-03-21 20:32:01,436 qnn_preprocess.py:69] Visiting: aten_view_copy_default_152, aten.view_copy.default
2025-03-21T20:32:01.4555867Z [INFO 2025-03-21 20:32:01,437 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_334, aten.permute_copy.default
2025-03-21T20:32:01.4557263Z [INFO 2025-03-21 20:32:01,437 qnn_preprocess.py:69] Visiting: aten_index_put_default_16, aten.index_put.default
2025-03-21T20:32:01.4558767Z [INFO 2025-03-21 20:32:01,439 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_335, aten.permute_copy.default
2025-03-21T20:32:01.4560332Z [INFO 2025-03-21 20:32:01,439 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_336, aten.permute_copy.default
2025-03-21T20:32:01.4561826Z [INFO 2025-03-21 20:32:01,440 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_337, aten.permute_copy.default
2025-03-21T20:32:01.4563360Z [INFO 2025-03-21 20:32:01,441 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_338, aten.permute_copy.default
2025-03-21T20:32:01.4564701Z [INFO 2025-03-21 20:32:01,441 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_339, aten.permute_copy.default
2025-03-21T20:32:01.4566113Z [INFO 2025-03-21 20:32:01,442 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_340, aten.permute_copy.default
2025-03-21T20:32:01.4567595Z [INFO 2025-03-21 20:32:01,443 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_341, aten.permute_copy.default
2025-03-21T20:32:01.4569131Z [INFO 2025-03-21 20:32:01,443 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_342, aten.permute_copy.default
2025-03-21T20:32:01.4570692Z [INFO 2025-03-21 20:32:01,444 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_343, aten.permute_copy.default
2025-03-21T20:32:01.4572221Z [INFO 2025-03-21 20:32:01,445 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_344, aten.permute_copy.default
2025-03-21T20:32:01.4573580Z [INFO 2025-03-21 20:32:01,445 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_345, aten.permute_copy.default
2025-03-21T20:32:01.4575080Z [INFO 2025-03-21 20:32:01,446 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_346, aten.permute_copy.default
2025-03-21T20:32:01.5175575Z [INFO 2025-03-21 20:32:01,447 qnn_preprocess.py:69] Visiting: aten_select_copy_int_384, aten.select_copy.int
2025-03-21T20:32:01.5176970Z [INFO 2025-03-21 20:32:01,447 qnn_preprocess.py:69] Visiting: aten_select_copy_int_386, aten.select_copy.int
2025-03-21T20:32:01.5178338Z [INFO 2025-03-21 20:32:01,448 qnn_preprocess.py:69] Visiting: aten_select_copy_int_388, aten.select_copy.int
2025-03-21T20:32:01.5179511Z [INFO 2025-03-21 20:32:01,449 qnn_preprocess.py:69] Visiting: aten_select_copy_int_390, aten.select_copy.int
2025-03-21T20:32:01.5180764Z [INFO 2025-03-21 20:32:01,450 qnn_preprocess.py:69] Visiting: aten_select_copy_int_392, aten.select_copy.int
2025-03-21T20:32:01.5181916Z [INFO 2025-03-21 20:32:01,451 qnn_preprocess.py:69] Visiting: aten_select_copy_int_394, aten.select_copy.int
2025-03-21T20:32:01.5183127Z [INFO 2025-03-21 20:32:01,451 qnn_preprocess.py:69] Visiting: aten_select_copy_int_396, aten.select_copy.int
2025-03-21T20:32:01.5184478Z [INFO 2025-03-21 20:32:01,452 qnn_preprocess.py:69] Visiting: aten_select_copy_int_398, aten.select_copy.int
2025-03-21T20:32:01.5185883Z [INFO 2025-03-21 20:32:01,453 qnn_preprocess.py:69] Visiting: aten_select_copy_int_400, aten.select_copy.int
2025-03-21T20:32:01.5187245Z [INFO 2025-03-21 20:32:01,454 qnn_preprocess.py:69] Visiting: aten_select_copy_int_402, aten.select_copy.int
2025-03-21T20:32:01.5188515Z [INFO 2025-03-21 20:32:01,454 qnn_preprocess.py:69] Visiting: aten_select_copy_int_404, aten.select_copy.int
2025-03-21T20:32:01.5189824Z [INFO 2025-03-21 20:32:01,455 qnn_preprocess.py:69] Visiting: aten_select_copy_int_406, aten.select_copy.int
2025-03-21T20:32:01.5191033Z [INFO 2025-03-21 20:32:01,456 qnn_preprocess.py:69] Visiting: aten_select_copy_int_385, aten.select_copy.int
2025-03-21T20:32:01.5192354Z [INFO 2025-03-21 20:32:01,457 qnn_preprocess.py:69] Visiting: aten_select_copy_int_387, aten.select_copy.int
2025-03-21T20:32:01.5193737Z [INFO 2025-03-21 20:32:01,457 qnn_preprocess.py:69] Visiting: aten_select_copy_int_389, aten.select_copy.int
2025-03-21T20:32:01.5195338Z [INFO 2025-03-21 20:32:01,458 qnn_preprocess.py:69] Visiting: aten_select_copy_int_391, aten.select_copy.int
2025-03-21T20:32:01.5196449Z [INFO 2025-03-21 20:32:01,458 qnn_preprocess.py:69] Visiting: aten_select_copy_int_393, aten.select_copy.int
2025-03-21T20:32:01.5198173Z [INFO 2025-03-21 20:32:01,459 qnn_preprocess.py:69] Visiting: aten_select_copy_int_395, aten.select_copy.int
2025-03-21T20:32:01.5199792Z [INFO 2025-03-21 20:32:01,459 qnn_preprocess.py:69] Visiting: aten_select_copy_int_397, aten.select_copy.int
2025-03-21T20:32:01.5201116Z [INFO 2025-03-21 20:32:01,459 qnn_preprocess.py:69] Visiting: aten_select_copy_int_399, aten.select_copy.int
2025-03-21T20:32:01.5202621Z [INFO 2025-03-21 20:32:01,460 qnn_preprocess.py:69] Visiting: aten_select_copy_int_401, aten.select_copy.int
2025-03-21T20:32:01.5204142Z [INFO 2025-03-21 20:32:01,460 qnn_preprocess.py:69] Visiting: aten_select_copy_int_403, aten.select_copy.int
2025-03-21T20:32:01.5205601Z [INFO 2025-03-21 20:32:01,461 qnn_preprocess.py:69] Visiting: aten_select_copy_int_405, aten.select_copy.int
2025-03-21T20:32:01.5206778Z [INFO 2025-03-21 20:32:01,461 qnn_preprocess.py:69] Visiting: aten_select_copy_int_407, aten.select_copy.int
2025-03-21T20:32:01.5207961Z [INFO 2025-03-21 20:32:01,462 qnn_preprocess.py:69] Visiting: aten_cat_default_34, aten.cat.default
2025-03-21T20:32:01.5209086Z [INFO 2025-03-21 20:32:01,463 qnn_preprocess.py:69] Visiting: aten_view_copy_default_153, aten.view_copy.default
2025-03-21T20:32:01.5210771Z [INFO 2025-03-21 20:32:01,464 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_359, aten.permute_copy.default
2025-03-21T20:32:01.5212104Z [INFO 2025-03-21 20:32:01,464 qnn_preprocess.py:69] Visiting: aten__to_copy_default_19, aten._to_copy.default
2025-03-21T20:32:01.5213228Z [INFO 2025-03-21 20:32:01,465 qnn_preprocess.py:69] Visiting: aten_matmul_default_16, aten.matmul.default
2025-03-21T20:32:01.5214419Z [INFO 2025-03-21 20:32:01,465 qnn_preprocess.py:69] Visiting: aten_mul_tensor_130, aten.mul.Tensor
2025-03-21T20:32:01.5215676Z [INFO 2025-03-21 20:32:01,467 qnn_preprocess.py:69] Visiting: aten_add_tensor_42, aten.add.Tensor
2025-03-21T20:32:01.5216739Z [INFO 2025-03-21 20:32:01,467 qnn_preprocess.py:69] Visiting: aten__softmax_default_8, aten._softmax.default
2025-03-21T20:32:01.5217963Z [INFO 2025-03-21 20:32:01,468 qnn_preprocess.py:69] Visiting: aten_matmul_default_17, aten.matmul.default
2025-03-21T20:32:01.5219180Z [INFO 2025-03-21 20:32:01,468 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_360, aten.permute_copy.default
2025-03-21T20:32:01.5220423Z [INFO 2025-03-21 20:32:01,469 qnn_preprocess.py:69] Visiting: aten_view_copy_default_161, aten.view_copy.default
2025-03-21T20:32:01.5221794Z [INFO 2025-03-21 20:32:01,469 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_95, aten.unsqueeze_copy.default
2025-03-21T20:32:01.5223123Z [INFO 2025-03-21 20:32:01,470 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_782, aten.permute_copy.default
2025-03-21T20:32:01.5224558Z [INFO 2025-03-21 20:32:01,470 qnn_preprocess.py:69] Visiting: aten_convolution_default_59, aten.convolution.default
2025-03-21T20:32:01.5225991Z [INFO 2025-03-21 20:32:01,473 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_783, aten.permute_copy.default
2025-03-21T20:32:01.5227227Z [INFO 2025-03-21 20:32:01,474 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_95, aten.squeeze_copy.dims
2025-03-21T20:32:01.5228533Z [INFO 2025-03-21 20:32:01,475 qnn_preprocess.py:69] Visiting: aten_add_tensor_43, aten.add.Tensor
2025-03-21T20:32:01.5229821Z [INFO 2025-03-21 20:32:01,475 qnn_preprocess.py:69] Visiting: aten_rms_norm_default_17, aten.rms_norm.default
2025-03-21T20:32:01.5231305Z [INFO 2025-03-21 20:32:01,476 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_96, aten.unsqueeze_copy.default
2025-03-21T20:32:01.5233048Z [INFO 2025-03-21 20:32:01,477 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_784, aten.permute_copy.default
2025-03-21T20:32:01.5234459Z [INFO 2025-03-21 20:32:01,478 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_97, aten.unsqueeze_copy.default
2025-03-21T20:32:01.5236060Z [INFO 2025-03-21 20:32:01,478 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_785, aten.permute_copy.default
2025-03-21T20:32:01.5237638Z [INFO 2025-03-21 20:32:01,479 qnn_preprocess.py:69] Visiting: aten_convolution_default_60, aten.convolution.default
2025-03-21T20:32:01.5239204Z [INFO 2025-03-21 20:32:01,485 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_786, aten.permute_copy.default
2025-03-21T20:32:01.5240717Z [INFO 2025-03-21 20:32:01,486 qnn_preprocess.py:69] Visiting: aten_convolution_default_61, aten.convolution.default
2025-03-21T20:32:01.5242075Z [INFO 2025-03-21 20:32:01,492 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_787, aten.permute_copy.default
2025-03-21T20:32:01.5243434Z [INFO 2025-03-21 20:32:01,493 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_96, aten.squeeze_copy.dims
2025-03-21T20:32:01.5244827Z [INFO 2025-03-21 20:32:01,494 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_97, aten.squeeze_copy.dims
2025-03-21T20:32:01.5246238Z [INFO 2025-03-21 20:32:01,494 qnn_preprocess.py:69] Visiting: aten_sigmoid_default_8, aten.sigmoid.default
2025-03-21T20:32:01.5247524Z [INFO 2025-03-21 20:32:01,495 qnn_preprocess.py:69] Visiting: aten_mul_tensor_133, aten.mul.Tensor
2025-03-21T20:32:01.5248776Z [INFO 2025-03-21 20:32:01,495 qnn_preprocess.py:69] Visiting: aten_mul_tensor_134, aten.mul.Tensor
2025-03-21T20:32:01.5250205Z [INFO 2025-03-21 20:32:01,496 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_98, aten.unsqueeze_copy.default
2025-03-21T20:32:01.5251740Z [INFO 2025-03-21 20:32:01,496 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_788, aten.permute_copy.default
2025-03-21T20:32:01.5253197Z [INFO 2025-03-21 20:32:01,497 qnn_preprocess.py:69] Visiting: aten_convolution_default_62, aten.convolution.default
2025-03-21T20:32:01.5254633Z [INFO 2025-03-21 20:32:01,502 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_789, aten.permute_copy.default
2025-03-21T20:32:01.5255971Z [INFO 2025-03-21 20:32:01,503 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_98, aten.squeeze_copy.dims
2025-03-21T20:32:01.5257311Z [INFO 2025-03-21 20:32:01,504 qnn_preprocess.py:69] Visiting: aten_add_tensor_44, aten.add.Tensor
2025-03-21T20:32:01.5258594Z [INFO 2025-03-21 20:32:01,504 qnn_preprocess.py:69] Visiting: aten_rms_norm_default_18, aten.rms_norm.default
2025-03-21T20:32:01.5260135Z [INFO 2025-03-21 20:32:01,506 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_99, aten.unsqueeze_copy.default
2025-03-21T20:32:01.5261587Z [INFO 2025-03-21 20:32:01,506 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_790, aten.permute_copy.default
2025-03-21T20:32:01.5263126Z [INFO 2025-03-21 20:32:01,507 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_100, aten.unsqueeze_copy.default
2025-03-21T20:32:01.5264689Z [INFO 2025-03-21 20:32:01,507 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_791, aten.permute_copy.default
2025-03-21T20:32:01.5266068Z [INFO 2025-03-21 20:32:01,508 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_101, aten.unsqueeze_copy.default
2025-03-21T20:32:01.5267623Z [INFO 2025-03-21 20:32:01,508 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_792, aten.permute_copy.default
2025-03-21T20:32:01.5269091Z [INFO 2025-03-21 20:32:01,509 qnn_preprocess.py:69] Visiting: aten_convolution_default_63, aten.convolution.default
2025-03-21T20:32:01.5270560Z [INFO 2025-03-21 20:32:01,512 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_793, aten.permute_copy.default
2025-03-21T20:32:01.5271953Z [INFO 2025-03-21 20:32:01,513 qnn_preprocess.py:69] Visiting: aten_convolution_default_64, aten.convolution.default
2025-03-21T20:32:01.5273437Z [INFO 2025-03-21 20:32:01,516 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_794, aten.permute_copy.default
2025-03-21T20:32:01.5274944Z [INFO 2025-03-21 20:32:01,517 qnn_preprocess.py:69] Visiting: aten_convolution_default_65, aten.convolution.default
2025-03-21T20:32:01.5634801Z [INFO 2025-03-21 20:32:01,521 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_795, aten.permute_copy.default
2025-03-21T20:32:01.5636321Z [INFO 2025-03-21 20:32:01,522 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_99, aten.squeeze_copy.dims
2025-03-21T20:32:01.5638035Z [INFO 2025-03-21 20:32:01,523 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_100, aten.squeeze_copy.dims
2025-03-21T20:32:01.5639428Z [INFO 2025-03-21 20:32:01,524 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_101, aten.squeeze_copy.dims
2025-03-21T20:32:01.5640776Z [INFO 2025-03-21 20:32:01,524 qnn_preprocess.py:69] Visiting: aten_view_copy_default_162, aten.view_copy.default
2025-03-21T20:32:01.5641956Z [INFO 2025-03-21 20:32:01,525 qnn_preprocess.py:69] Visiting: aten_view_copy_default_163, aten.view_copy.default
2025-03-21T20:32:01.5643352Z [INFO 2025-03-21 20:32:01,526 qnn_preprocess.py:69] Visiting: aten_view_copy_default_164, aten.view_copy.default
2025-03-21T20:32:01.5644735Z [INFO 2025-03-21 20:32:01,526 qnn_preprocess.py:69] Visiting: aten_view_copy_default_165, aten.view_copy.default
2025-03-21T20:32:01.5646175Z [INFO 2025-03-21 20:32:01,527 qnn_preprocess.py:69] Visiting: aten_view_copy_default_166, aten.view_copy.default
2025-03-21T20:32:01.5647396Z [INFO 2025-03-21 20:32:01,527 qnn_preprocess.py:69] Visiting: aten_index_put_default_19, aten.index_put.default
2025-03-21T20:32:01.5648792Z [INFO 2025-03-21 20:32:01,528 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_36, aten.slice_copy.Tensor
2025-03-21T20:32:01.5650373Z [INFO 2025-03-21 20:32:01,529 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_37, aten.slice_copy.Tensor
2025-03-21T20:32:01.5651784Z [INFO 2025-03-21 20:32:01,529 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_38, aten.slice_copy.Tensor
2025-03-21T20:32:01.5652988Z [INFO 2025-03-21 20:32:01,530 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_39, aten.slice_copy.Tensor
2025-03-21T20:32:01.5654457Z [INFO 2025-03-21 20:32:01,530 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_388, aten.permute_copy.default
2025-03-21T20:32:01.5655758Z [INFO 2025-03-21 20:32:01,531 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_389, aten.permute_copy.default
2025-03-21T20:32:01.5657038Z [INFO 2025-03-21 20:32:01,532 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_390, aten.permute_copy.default
2025-03-21T20:32:01.5658348Z [INFO 2025-03-21 20:32:01,532 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_391, aten.permute_copy.default
2025-03-21T20:32:01.5659606Z [INFO 2025-03-21 20:32:01,533 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_392, aten.permute_copy.default
2025-03-21T20:32:01.5661058Z [INFO 2025-03-21 20:32:01,534 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_393, aten.permute_copy.default
2025-03-21T20:32:01.5662404Z [INFO 2025-03-21 20:32:01,534 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_394, aten.permute_copy.default
2025-03-21T20:32:01.5663747Z [INFO 2025-03-21 20:32:01,535 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_395, aten.permute_copy.default
2025-03-21T20:32:01.5665251Z [INFO 2025-03-21 20:32:01,536 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_396, aten.permute_copy.default
2025-03-21T20:32:01.5666741Z [INFO 2025-03-21 20:32:01,536 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_397, aten.permute_copy.default
2025-03-21T20:32:01.5668223Z [INFO 2025-03-21 20:32:01,537 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_398, aten.permute_copy.default
2025-03-21T20:32:01.5669732Z [INFO 2025-03-21 20:32:01,538 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_399, aten.permute_copy.default
2025-03-21T20:32:01.5671175Z [INFO 2025-03-21 20:32:01,538 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_102, aten.squeeze_copy.dims
2025-03-21T20:32:01.5672453Z [INFO 2025-03-21 20:32:01,539 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_103, aten.squeeze_copy.dims
2025-03-21T20:32:01.5673808Z [INFO 2025-03-21 20:32:01,539 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_104, aten.squeeze_copy.dims
2025-03-21T20:32:01.5675026Z [INFO 2025-03-21 20:32:01,540 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_105, aten.squeeze_copy.dims
2025-03-21T20:32:01.5676297Z [INFO 2025-03-21 20:32:01,540 qnn_preprocess.py:69] Visiting: aten_select_copy_int_456, aten.select_copy.int
2025-03-21T20:32:01.5677578Z [INFO 2025-03-21 20:32:01,541 qnn_preprocess.py:69] Visiting: aten_select_copy_int_458, aten.select_copy.int
2025-03-21T20:32:01.5678741Z [INFO 2025-03-21 20:32:01,541 qnn_preprocess.py:69] Visiting: aten_select_copy_int_460, aten.select_copy.int
2025-03-21T20:32:01.5680022Z [INFO 2025-03-21 20:32:01,542 qnn_preprocess.py:69] Visiting: aten_select_copy_int_462, aten.select_copy.int
2025-03-21T20:32:01.5681364Z [INFO 2025-03-21 20:32:01,542 qnn_preprocess.py:69] Visiting: aten_select_copy_int_464, aten.select_copy.int
2025-03-21T20:32:01.5682750Z [INFO 2025-03-21 20:32:01,542 qnn_preprocess.py:69] Visiting: aten_select_copy_int_466, aten.select_copy.int
2025-03-21T20:32:01.5683969Z [INFO 2025-03-21 20:32:01,543 qnn_preprocess.py:69] Visiting: aten_select_copy_int_468, aten.select_copy.int
2025-03-21T20:32:01.5685150Z [INFO 2025-03-21 20:32:01,543 qnn_preprocess.py:69] Visiting: aten_select_copy_int_470, aten.select_copy.int
2025-03-21T20:32:01.5686500Z [INFO 2025-03-21 20:32:01,544 qnn_preprocess.py:69] Visiting: aten_select_copy_int_472, aten.select_copy.int
2025-03-21T20:32:01.5687835Z [INFO 2025-03-21 20:32:01,544 qnn_preprocess.py:69] Visiting: aten_select_copy_int_474, aten.select_copy.int
2025-03-21T20:32:01.5689044Z [INFO 2025-03-21 20:32:01,545 qnn_preprocess.py:69] Visiting: aten_select_copy_int_476, aten.select_copy.int
2025-03-21T20:32:01.5690339Z [INFO 2025-03-21 20:32:01,545 qnn_preprocess.py:69] Visiting: aten_select_copy_int_478, aten.select_copy.int
2025-03-21T20:32:01.5691435Z [INFO 2025-03-21 20:32:01,546 qnn_preprocess.py:69] Visiting: aten_mul_tensor_137, aten.mul.Tensor
2025-03-21T20:32:01.5692635Z [INFO 2025-03-21 20:32:01,546 qnn_preprocess.py:69] Visiting: aten_mul_tensor_139, aten.mul.Tensor
2025-03-21T20:32:01.5693834Z [INFO 2025-03-21 20:32:01,547 qnn_preprocess.py:69] Visiting: aten_mul_tensor_138, aten.mul.Tensor
2025-03-21T20:32:01.5694860Z [INFO 2025-03-21 20:32:01,547 qnn_preprocess.py:69] Visiting: aten_mul_tensor_140, aten.mul.Tensor
2025-03-21T20:32:01.5696025Z [INFO 2025-03-21 20:32:01,548 qnn_preprocess.py:69] Visiting: aten_mul_tensor_141, aten.mul.Tensor
2025-03-21T20:32:01.5697269Z [INFO 2025-03-21 20:32:01,548 qnn_preprocess.py:69] Visiting: aten_mul_tensor_143, aten.mul.Tensor
2025-03-21T20:32:01.5698278Z [INFO 2025-03-21 20:32:01,549 qnn_preprocess.py:69] Visiting: aten_mul_tensor_142, aten.mul.Tensor
2025-03-21T20:32:01.5699389Z [INFO 2025-03-21 20:32:01,549 qnn_preprocess.py:69] Visiting: aten_mul_tensor_144, aten.mul.Tensor
2025-03-21T20:32:01.5700527Z [INFO 2025-03-21 20:32:01,550 qnn_preprocess.py:69] Visiting: aten_select_copy_int_457, aten.select_copy.int
2025-03-21T20:32:01.5701689Z [INFO 2025-03-21 20:32:01,550 qnn_preprocess.py:69] Visiting: aten_select_copy_int_459, aten.select_copy.int
2025-03-21T20:32:01.5703003Z [INFO 2025-03-21 20:32:01,551 qnn_preprocess.py:69] Visiting: aten_select_copy_int_461, aten.select_copy.int
2025-03-21T20:32:01.5704244Z [INFO 2025-03-21 20:32:01,551 qnn_preprocess.py:69] Visiting: aten_select_copy_int_463, aten.select_copy.int
2025-03-21T20:32:01.5705410Z [INFO 2025-03-21 20:32:01,552 qnn_preprocess.py:69] Visiting: aten_select_copy_int_465, aten.select_copy.int
2025-03-21T20:32:01.5706765Z [INFO 2025-03-21 20:32:01,552 qnn_preprocess.py:69] Visiting: aten_select_copy_int_467, aten.select_copy.int
2025-03-21T20:32:01.5707974Z [INFO 2025-03-21 20:32:01,553 qnn_preprocess.py:69] Visiting: aten_select_copy_int_469, aten.select_copy.int
2025-03-21T20:32:01.5709139Z [INFO 2025-03-21 20:32:01,553 qnn_preprocess.py:69] Visiting: aten_select_copy_int_471, aten.select_copy.int
2025-03-21T20:32:01.5710438Z [INFO 2025-03-21 20:32:01,554 qnn_preprocess.py:69] Visiting: aten_select_copy_int_473, aten.select_copy.int
2025-03-21T20:32:01.5711585Z [INFO 2025-03-21 20:32:01,554 qnn_preprocess.py:69] Visiting: aten_select_copy_int_475, aten.select_copy.int
2025-03-21T20:32:01.5712903Z [INFO 2025-03-21 20:32:01,555 qnn_preprocess.py:69] Visiting: aten_select_copy_int_477, aten.select_copy.int
2025-03-21T20:32:01.5714313Z [INFO 2025-03-21 20:32:01,555 qnn_preprocess.py:69] Visiting: aten_select_copy_int_479, aten.select_copy.int
2025-03-21T20:32:01.5715451Z [INFO 2025-03-21 20:32:01,556 qnn_preprocess.py:69] Visiting: aten_sub_tensor_18, aten.sub.Tensor
2025-03-21T20:32:01.5716676Z [INFO 2025-03-21 20:32:01,556 qnn_preprocess.py:69] Visiting: aten_add_tensor_45, aten.add.Tensor
2025-03-21T20:32:01.5717796Z [INFO 2025-03-21 20:32:01,557 qnn_preprocess.py:69] Visiting: aten_sub_tensor_19, aten.sub.Tensor
2025-03-21T20:32:01.5718820Z [INFO 2025-03-21 20:32:01,557 qnn_preprocess.py:69] Visiting: aten_add_tensor_46, aten.add.Tensor
2025-03-21T20:32:01.5719966Z [INFO 2025-03-21 20:32:01,558 qnn_preprocess.py:69] Visiting: aten_cat_default_39, aten.cat.default
2025-03-21T20:32:01.5721180Z [INFO 2025-03-21 20:32:01,559 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_102, aten.unsqueeze_copy.default
2025-03-21T20:32:01.5722639Z [INFO 2025-03-21 20:32:01,560 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_103, aten.unsqueeze_copy.default
2025-03-21T20:32:01.5724147Z [INFO 2025-03-21 20:32:01,560 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_104, aten.unsqueeze_copy.default
2025-03-21T20:32:01.5725642Z [INFO 2025-03-21 20:32:01,561 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_105, aten.unsqueeze_copy.default
2025-03-21T20:32:01.5727142Z [INFO 2025-03-21 20:32:01,561 qnn_preprocess.py:69] Visiting: aten_view_copy_default_172, aten.view_copy.default
2025-03-21T20:32:01.5728306Z [INFO 2025-03-21 20:32:01,561 qnn_preprocess.py:69] Visiting: aten__to_copy_default_20, aten._to_copy.default
2025-03-21T20:32:01.5729595Z [INFO 2025-03-21 20:32:01,562 qnn_preprocess.py:69] Visiting: aten_cat_default_36, aten.cat.default
2025-03-21T20:32:01.6237172Z [INFO 2025-03-21 20:32:01,563 qnn_preprocess.py:69] Visiting: aten_cat_default_37, aten.cat.default
2025-03-21T20:32:01.6238461Z [INFO 2025-03-21 20:32:01,564 qnn_preprocess.py:69] Visiting: aten_view_copy_default_169, aten.view_copy.default
2025-03-21T20:32:01.6239922Z [INFO 2025-03-21 20:32:01,564 qnn_preprocess.py:69] Visiting: aten_view_copy_default_170, aten.view_copy.default
2025-03-21T20:32:01.6241251Z [INFO 2025-03-21 20:32:01,565 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_375, aten.permute_copy.default
2025-03-21T20:32:01.6242566Z [INFO 2025-03-21 20:32:01,566 qnn_preprocess.py:69] Visiting: aten_index_put_default_18, aten.index_put.default
2025-03-21T20:32:01.6243869Z [INFO 2025-03-21 20:32:01,568 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_376, aten.permute_copy.default
2025-03-21T20:32:01.6245232Z [INFO 2025-03-21 20:32:01,569 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_377, aten.permute_copy.default
2025-03-21T20:32:01.6246732Z [INFO 2025-03-21 20:32:01,570 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_378, aten.permute_copy.default
2025-03-21T20:32:01.6248098Z [INFO 2025-03-21 20:32:01,571 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_379, aten.permute_copy.default
2025-03-21T20:32:01.6249519Z [INFO 2025-03-21 20:32:01,572 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_380, aten.permute_copy.default
2025-03-21T20:32:01.6250880Z [INFO 2025-03-21 20:32:01,573 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_381, aten.permute_copy.default
2025-03-21T20:32:01.6252238Z [INFO 2025-03-21 20:32:01,573 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_382, aten.permute_copy.default
2025-03-21T20:32:01.6253575Z [INFO 2025-03-21 20:32:01,574 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_383, aten.permute_copy.default
2025-03-21T20:32:01.6255226Z [INFO 2025-03-21 20:32:01,575 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_384, aten.permute_copy.default
2025-03-21T20:32:01.6256760Z [INFO 2025-03-21 20:32:01,575 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_385, aten.permute_copy.default
2025-03-21T20:32:01.6258861Z [INFO 2025-03-21 20:32:01,576 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_386, aten.permute_copy.default
2025-03-21T20:32:01.6260589Z [INFO 2025-03-21 20:32:01,577 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_387, aten.permute_copy.default
2025-03-21T20:32:01.6261955Z [INFO 2025-03-21 20:32:01,577 qnn_preprocess.py:69] Visiting: aten_select_copy_int_432, aten.select_copy.int
2025-03-21T20:32:01.6263235Z [INFO 2025-03-21 20:32:01,578 qnn_preprocess.py:69] Visiting: aten_select_copy_int_434, aten.select_copy.int
2025-03-21T20:32:01.6264546Z [INFO 2025-03-21 20:32:01,578 qnn_preprocess.py:69] Visiting: aten_select_copy_int_436, aten.select_copy.int
2025-03-21T20:32:01.6265799Z [INFO 2025-03-21 20:32:01,579 qnn_preprocess.py:69] Visiting: aten_select_copy_int_438, aten.select_copy.int
2025-03-21T20:32:01.6267114Z [INFO 2025-03-21 20:32:01,579 qnn_preprocess.py:69] Visiting: aten_select_copy_int_440, aten.select_copy.int
2025-03-21T20:32:01.6268452Z [INFO 2025-03-21 20:32:01,580 qnn_preprocess.py:69] Visiting: aten_select_copy_int_442, aten.select_copy.int
2025-03-21T20:32:01.6270083Z [INFO 2025-03-21 20:32:01,580 qnn_preprocess.py:69] Visiting: aten_select_copy_int_444, aten.select_copy.int
2025-03-21T20:32:01.6271810Z [INFO 2025-03-21 20:32:01,581 qnn_preprocess.py:69] Visiting: aten_select_copy_int_446, aten.select_copy.int
2025-03-21T20:32:01.6273337Z [INFO 2025-03-21 20:32:01,581 qnn_preprocess.py:69] Visiting: aten_select_copy_int_448, aten.select_copy.int
2025-03-21T20:32:01.6274872Z [INFO 2025-03-21 20:32:01,582 qnn_preprocess.py:69] Visiting: aten_select_copy_int_450, aten.select_copy.int
2025-03-21T20:32:01.6276301Z [INFO 2025-03-21 20:32:01,582 qnn_preprocess.py:69] Visiting: aten_select_copy_int_452, aten.select_copy.int
2025-03-21T20:32:01.6277544Z [INFO 2025-03-21 20:32:01,583 qnn_preprocess.py:69] Visiting: aten_select_copy_int_454, aten.select_copy.int
2025-03-21T20:32:01.6278751Z [INFO 2025-03-21 20:32:01,583 qnn_preprocess.py:69] Visiting: aten_select_copy_int_433, aten.select_copy.int
2025-03-21T20:32:01.6279984Z [INFO 2025-03-21 20:32:01,584 qnn_preprocess.py:69] Visiting: aten_select_copy_int_435, aten.select_copy.int
2025-03-21T20:32:01.6281218Z [INFO 2025-03-21 20:32:01,584 qnn_preprocess.py:69] Visiting: aten_select_copy_int_437, aten.select_copy.int
2025-03-21T20:32:01.6282445Z [INFO 2025-03-21 20:32:01,584 qnn_preprocess.py:69] Visiting: aten_select_copy_int_439, aten.select_copy.int
2025-03-21T20:32:01.6283678Z [INFO 2025-03-21 20:32:01,585 qnn_preprocess.py:69] Visiting: aten_select_copy_int_441, aten.select_copy.int
2025-03-21T20:32:01.6284895Z [INFO 2025-03-21 20:32:01,585 qnn_preprocess.py:69] Visiting: aten_select_copy_int_443, aten.select_copy.int
2025-03-21T20:32:01.6286058Z [INFO 2025-03-21 20:32:01,586 qnn_preprocess.py:69] Visiting: aten_select_copy_int_445, aten.select_copy.int
2025-03-21T20:32:01.6287339Z [INFO 2025-03-21 20:32:01,586 qnn_preprocess.py:69] Visiting: aten_select_copy_int_447, aten.select_copy.int
2025-03-21T20:32:01.6288763Z [INFO 2025-03-21 20:32:01,587 qnn_preprocess.py:69] Visiting: aten_select_copy_int_449, aten.select_copy.int
2025-03-21T20:32:01.6290398Z [INFO 2025-03-21 20:32:01,587 qnn_preprocess.py:69] Visiting: aten_select_copy_int_451, aten.select_copy.int
2025-03-21T20:32:01.6291812Z [INFO 2025-03-21 20:32:01,588 qnn_preprocess.py:69] Visiting: aten_select_copy_int_453, aten.select_copy.int
2025-03-21T20:32:01.6293252Z [INFO 2025-03-21 20:32:01,588 qnn_preprocess.py:69] Visiting: aten_select_copy_int_455, aten.select_copy.int
2025-03-21T20:32:01.6294758Z [INFO 2025-03-21 20:32:01,589 qnn_preprocess.py:69] Visiting: aten_cat_default_38, aten.cat.default
2025-03-21T20:32:01.6296247Z [INFO 2025-03-21 20:32:01,590 qnn_preprocess.py:69] Visiting: aten_view_copy_default_171, aten.view_copy.default
2025-03-21T20:32:01.6297995Z [INFO 2025-03-21 20:32:01,590 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_400, aten.permute_copy.default
2025-03-21T20:32:01.6299576Z [INFO 2025-03-21 20:32:01,591 qnn_preprocess.py:69] Visiting: aten__to_copy_default_21, aten._to_copy.default
2025-03-21T20:32:01.6300909Z [INFO 2025-03-21 20:32:01,592 qnn_preprocess.py:69] Visiting: aten_matmul_default_18, aten.matmul.default
2025-03-21T20:32:01.6302075Z [INFO 2025-03-21 20:32:01,592 qnn_preprocess.py:69] Visiting: aten_mul_tensor_145, aten.mul.Tensor
2025-03-21T20:32:01.6303185Z [INFO 2025-03-21 20:32:01,594 qnn_preprocess.py:69] Visiting: aten_add_tensor_47, aten.add.Tensor
2025-03-21T20:32:01.6304371Z [INFO 2025-03-21 20:32:01,594 qnn_preprocess.py:69] Visiting: aten__softmax_default_9, aten._softmax.default
2025-03-21T20:32:01.6305593Z [INFO 2025-03-21 20:32:01,595 qnn_preprocess.py:69] Visiting: aten_matmul_default_19, aten.matmul.default
2025-03-21T20:32:01.6306881Z [INFO 2025-03-21 20:32:01,595 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_401, aten.permute_copy.default
2025-03-21T20:32:01.6308193Z [INFO 2025-03-21 20:32:01,596 qnn_preprocess.py:69] Visiting: aten_view_copy_default_179, aten.view_copy.default
2025-03-21T20:32:01.6309547Z [INFO 2025-03-21 20:32:01,596 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_106, aten.unsqueeze_copy.default
2025-03-21T20:32:01.6310943Z [INFO 2025-03-21 20:32:01,597 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_796, aten.permute_copy.default
2025-03-21T20:32:01.6312321Z [INFO 2025-03-21 20:32:01,597 qnn_preprocess.py:69] Visiting: aten_convolution_default_66, aten.convolution.default
2025-03-21T20:32:01.6313689Z [INFO 2025-03-21 20:32:01,600 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_797, aten.permute_copy.default
2025-03-21T20:32:01.6315005Z [INFO 2025-03-21 20:32:01,601 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_106, aten.squeeze_copy.dims
2025-03-21T20:32:01.6316192Z [INFO 2025-03-21 20:32:01,601 qnn_preprocess.py:69] Visiting: aten_add_tensor_48, aten.add.Tensor
2025-03-21T20:32:01.6317382Z [INFO 2025-03-21 20:32:01,602 qnn_preprocess.py:69] Visiting: aten_rms_norm_default_19, aten.rms_norm.default
2025-03-21T20:32:01.6318713Z [INFO 2025-03-21 20:32:01,603 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_107, aten.unsqueeze_copy.default
2025-03-21T20:32:01.6320110Z [INFO 2025-03-21 20:32:01,604 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_798, aten.permute_copy.default
2025-03-21T20:32:01.6321494Z [INFO 2025-03-21 20:32:01,605 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_108, aten.unsqueeze_copy.default
2025-03-21T20:32:01.6322877Z [INFO 2025-03-21 20:32:01,605 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_799, aten.permute_copy.default
2025-03-21T20:32:01.6324227Z [INFO 2025-03-21 20:32:01,606 qnn_preprocess.py:69] Visiting: aten_convolution_default_67, aten.convolution.default
2025-03-21T20:32:01.6325587Z [INFO 2025-03-21 20:32:01,612 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_800, aten.permute_copy.default
2025-03-21T20:32:01.6326942Z [INFO 2025-03-21 20:32:01,613 qnn_preprocess.py:69] Visiting: aten_convolution_default_68, aten.convolution.default
2025-03-21T20:32:01.6328295Z [INFO 2025-03-21 20:32:01,619 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_801, aten.permute_copy.default
2025-03-21T20:32:01.6329713Z [INFO 2025-03-21 20:32:01,620 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_107, aten.squeeze_copy.dims
2025-03-21T20:32:01.6330973Z [INFO 2025-03-21 20:32:01,621 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_108, aten.squeeze_copy.dims
2025-03-21T20:32:01.6332446Z [INFO 2025-03-21 20:32:01,621 qnn_preprocess.py:69] Visiting: aten_sigmoid_default_9, aten.sigmoid.default
2025-03-21T20:32:01.6333623Z [INFO 2025-03-21 20:32:01,622 qnn_preprocess.py:69] Visiting: aten_mul_tensor_148, aten.mul.Tensor
2025-03-21T20:32:01.6334724Z [INFO 2025-03-21 20:32:01,622 qnn_preprocess.py:69] Visiting: aten_mul_tensor_149, aten.mul.Tensor
2025-03-21T20:32:01.6772900Z [INFO 2025-03-21 20:32:01,623 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_109, aten.unsqueeze_copy.default
2025-03-21T20:32:01.6774345Z [INFO 2025-03-21 20:32:01,623 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_802, aten.permute_copy.default
2025-03-21T20:32:01.6776059Z [INFO 2025-03-21 20:32:01,624 qnn_preprocess.py:69] Visiting: aten_convolution_default_69, aten.convolution.default
2025-03-21T20:32:01.6777407Z [INFO 2025-03-21 20:32:01,631 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_803, aten.permute_copy.default
2025-03-21T20:32:01.6778770Z [INFO 2025-03-21 20:32:01,632 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_109, aten.squeeze_copy.dims
2025-03-21T20:32:01.6779961Z [INFO 2025-03-21 20:32:01,632 qnn_preprocess.py:69] Visiting: aten_add_tensor_49, aten.add.Tensor
2025-03-21T20:32:01.6781137Z [INFO 2025-03-21 20:32:01,633 qnn_preprocess.py:69] Visiting: aten_rms_norm_default_20, aten.rms_norm.default
2025-03-21T20:32:01.6782477Z [INFO 2025-03-21 20:32:01,634 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_110, aten.unsqueeze_copy.default
2025-03-21T20:32:01.6783858Z [INFO 2025-03-21 20:32:01,635 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_804, aten.permute_copy.default
2025-03-21T20:32:01.6785253Z [INFO 2025-03-21 20:32:01,635 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_111, aten.unsqueeze_copy.default
2025-03-21T20:32:01.6786708Z [INFO 2025-03-21 20:32:01,636 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_805, aten.permute_copy.default
2025-03-21T20:32:01.6788098Z [INFO 2025-03-21 20:32:01,637 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_112, aten.unsqueeze_copy.default
2025-03-21T20:32:01.6789476Z [INFO 2025-03-21 20:32:01,637 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_806, aten.permute_copy.default
2025-03-21T20:32:01.6790834Z [INFO 2025-03-21 20:32:01,638 qnn_preprocess.py:69] Visiting: aten_convolution_default_70, aten.convolution.default
2025-03-21T20:32:01.6792194Z [INFO 2025-03-21 20:32:01,641 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_807, aten.permute_copy.default
2025-03-21T20:32:01.6793543Z [INFO 2025-03-21 20:32:01,641 qnn_preprocess.py:69] Visiting: aten_convolution_default_71, aten.convolution.default
2025-03-21T20:32:01.6794901Z [INFO 2025-03-21 20:32:01,644 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_808, aten.permute_copy.default
2025-03-21T20:32:01.6796257Z [INFO 2025-03-21 20:32:01,645 qnn_preprocess.py:69] Visiting: aten_convolution_default_72, aten.convolution.default
2025-03-21T20:32:01.6797613Z [INFO 2025-03-21 20:32:01,648 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_809, aten.permute_copy.default
2025-03-21T20:32:01.6798921Z [INFO 2025-03-21 20:32:01,649 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_110, aten.squeeze_copy.dims
2025-03-21T20:32:01.6800209Z [INFO 2025-03-21 20:32:01,649 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_111, aten.squeeze_copy.dims
2025-03-21T20:32:01.6801489Z [INFO 2025-03-21 20:32:01,650 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_112, aten.squeeze_copy.dims
2025-03-21T20:32:01.6802759Z [INFO 2025-03-21 20:32:01,650 qnn_preprocess.py:69] Visiting: aten_view_copy_default_180, aten.view_copy.default
2025-03-21T20:32:01.6804035Z [INFO 2025-03-21 20:32:01,650 qnn_preprocess.py:69] Visiting: aten_view_copy_default_181, aten.view_copy.default
2025-03-21T20:32:01.6805309Z [INFO 2025-03-21 20:32:01,651 qnn_preprocess.py:69] Visiting: aten_view_copy_default_182, aten.view_copy.default
2025-03-21T20:32:01.6806579Z [INFO 2025-03-21 20:32:01,651 qnn_preprocess.py:69] Visiting: aten_view_copy_default_183, aten.view_copy.default
2025-03-21T20:32:01.6807842Z [INFO 2025-03-21 20:32:01,651 qnn_preprocess.py:69] Visiting: aten_view_copy_default_184, aten.view_copy.default
2025-03-21T20:32:01.6809118Z [INFO 2025-03-21 20:32:01,652 qnn_preprocess.py:69] Visiting: aten_index_put_default_21, aten.index_put.default
2025-03-21T20:32:01.6810538Z [INFO 2025-03-21 20:32:01,653 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_40, aten.slice_copy.Tensor
2025-03-21T20:32:01.6811811Z [INFO 2025-03-21 20:32:01,654 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_41, aten.slice_copy.Tensor
2025-03-21T20:32:01.6813120Z [INFO 2025-03-21 20:32:01,654 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_42, aten.slice_copy.Tensor
2025-03-21T20:32:01.6814427Z [INFO 2025-03-21 20:32:01,654 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_43, aten.slice_copy.Tensor
2025-03-21T20:32:01.6815753Z [INFO 2025-03-21 20:32:01,655 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_429, aten.permute_copy.default
2025-03-21T20:32:01.6817098Z [INFO 2025-03-21 20:32:01,656 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_430, aten.permute_copy.default
2025-03-21T20:32:01.6818458Z [INFO 2025-03-21 20:32:01,656 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_431, aten.permute_copy.default
2025-03-21T20:32:01.6819824Z [INFO 2025-03-21 20:32:01,657 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_432, aten.permute_copy.default
2025-03-21T20:32:01.6821189Z [INFO 2025-03-21 20:32:01,658 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_433, aten.permute_copy.default
2025-03-21T20:32:01.6822543Z [INFO 2025-03-21 20:32:01,658 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_434, aten.permute_copy.default
2025-03-21T20:32:01.6823900Z [INFO 2025-03-21 20:32:01,659 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_435, aten.permute_copy.default
2025-03-21T20:32:01.6825299Z [INFO 2025-03-21 20:32:01,660 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_436, aten.permute_copy.default
2025-03-21T20:32:01.6826645Z [INFO 2025-03-21 20:32:01,660 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_437, aten.permute_copy.default
2025-03-21T20:32:01.6828003Z [INFO 2025-03-21 20:32:01,661 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_438, aten.permute_copy.default
2025-03-21T20:32:01.6829363Z [INFO 2025-03-21 20:32:01,662 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_439, aten.permute_copy.default
2025-03-21T20:32:01.6830708Z [INFO 2025-03-21 20:32:01,662 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_440, aten.permute_copy.default
2025-03-21T20:32:01.6832024Z [INFO 2025-03-21 20:32:01,663 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_113, aten.squeeze_copy.dims
2025-03-21T20:32:01.6833468Z [INFO 2025-03-21 20:32:01,663 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_114, aten.squeeze_copy.dims
2025-03-21T20:32:01.6834741Z [INFO 2025-03-21 20:32:01,664 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_115, aten.squeeze_copy.dims
2025-03-21T20:32:01.6835995Z [INFO 2025-03-21 20:32:01,664 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_116, aten.squeeze_copy.dims
2025-03-21T20:32:01.6837240Z [INFO 2025-03-21 20:32:01,665 qnn_preprocess.py:69] Visiting: aten_select_copy_int_504, aten.select_copy.int
2025-03-21T20:32:01.6838472Z [INFO 2025-03-21 20:32:01,665 qnn_preprocess.py:69] Visiting: aten_select_copy_int_506, aten.select_copy.int
2025-03-21T20:32:01.6839703Z [INFO 2025-03-21 20:32:01,666 qnn_preprocess.py:69] Visiting: aten_select_copy_int_508, aten.select_copy.int
2025-03-21T20:32:01.6840931Z [INFO 2025-03-21 20:32:01,666 qnn_preprocess.py:69] Visiting: aten_select_copy_int_510, aten.select_copy.int
2025-03-21T20:32:01.6842162Z [INFO 2025-03-21 20:32:01,667 qnn_preprocess.py:69] Visiting: aten_select_copy_int_512, aten.select_copy.int
2025-03-21T20:32:01.6843389Z [INFO 2025-03-21 20:32:01,667 qnn_preprocess.py:69] Visiting: aten_select_copy_int_514, aten.select_copy.int
2025-03-21T20:32:01.6844604Z [INFO 2025-03-21 20:32:01,668 qnn_preprocess.py:69] Visiting: aten_select_copy_int_516, aten.select_copy.int
2025-03-21T20:32:01.6845831Z [INFO 2025-03-21 20:32:01,668 qnn_preprocess.py:69] Visiting: aten_select_copy_int_518, aten.select_copy.int
2025-03-21T20:32:01.6847053Z [INFO 2025-03-21 20:32:01,669 qnn_preprocess.py:69] Visiting: aten_select_copy_int_520, aten.select_copy.int
2025-03-21T20:32:01.6848400Z [INFO 2025-03-21 20:32:01,669 qnn_preprocess.py:69] Visiting: aten_select_copy_int_522, aten.select_copy.int
2025-03-21T20:32:01.6849689Z [INFO 2025-03-21 20:32:01,669 qnn_preprocess.py:69] Visiting: aten_select_copy_int_524, aten.select_copy.int
2025-03-21T20:32:01.6851046Z [INFO 2025-03-21 20:32:01,670 qnn_preprocess.py:69] Visiting: aten_select_copy_int_526, aten.select_copy.int
2025-03-21T20:32:01.6852218Z [INFO 2025-03-21 20:32:01,670 qnn_preprocess.py:69] Visiting: aten_mul_tensor_152, aten.mul.Tensor
2025-03-21T20:32:01.6853348Z [INFO 2025-03-21 20:32:01,671 qnn_preprocess.py:69] Visiting: aten_mul_tensor_154, aten.mul.Tensor
2025-03-21T20:32:01.6854473Z [INFO 2025-03-21 20:32:01,671 qnn_preprocess.py:69] Visiting: aten_mul_tensor_153, aten.mul.Tensor
2025-03-21T20:32:01.6855606Z [INFO 2025-03-21 20:32:01,672 qnn_preprocess.py:69] Visiting: aten_mul_tensor_155, aten.mul.Tensor
2025-03-21T20:32:01.6856729Z [INFO 2025-03-21 20:32:01,672 qnn_preprocess.py:69] Visiting: aten_mul_tensor_156, aten.mul.Tensor
2025-03-21T20:32:01.6857851Z [INFO 2025-03-21 20:32:01,673 qnn_preprocess.py:69] Visiting: aten_mul_tensor_158, aten.mul.Tensor
2025-03-21T20:32:01.6858979Z [INFO 2025-03-21 20:32:01,674 qnn_preprocess.py:69] Visiting: aten_mul_tensor_157, aten.mul.Tensor
2025-03-21T20:32:01.6860094Z [INFO 2025-03-21 20:32:01,674 qnn_preprocess.py:69] Visiting: aten_mul_tensor_159, aten.mul.Tensor
2025-03-21T20:32:01.6861338Z [INFO 2025-03-21 20:32:01,675 qnn_preprocess.py:69] Visiting: aten_select_copy_int_505, aten.select_copy.int
2025-03-21T20:32:01.6862573Z [INFO 2025-03-21 20:32:01,675 qnn_preprocess.py:69] Visiting: aten_select_copy_int_507, aten.select_copy.int
2025-03-21T20:32:01.6863800Z [INFO 2025-03-21 20:32:01,676 qnn_preprocess.py:69] Visiting: aten_select_copy_int_509, aten.select_copy.int
2025-03-21T20:32:01.6865040Z [INFO 2025-03-21 20:32:01,676 qnn_preprocess.py:69] Visiting: aten_select_copy_int_511, aten.select_copy.int
2025-03-21T20:32:01.7185144Z [INFO 2025-03-21 20:32:01,676 qnn_preprocess.py:69] Visiting: aten_select_copy_int_513, aten.select_copy.int
2025-03-21T20:32:01.7186485Z [INFO 2025-03-21 20:32:01,677 qnn_preprocess.py:69] Visiting: aten_select_copy_int_515, aten.select_copy.int
2025-03-21T20:32:01.7187811Z [INFO 2025-03-21 20:32:01,677 qnn_preprocess.py:69] Visiting: aten_select_copy_int_517, aten.select_copy.int
2025-03-21T20:32:01.7189136Z [INFO 2025-03-21 20:32:01,678 qnn_preprocess.py:69] Visiting: aten_select_copy_int_519, aten.select_copy.int
2025-03-21T20:32:01.7190467Z [INFO 2025-03-21 20:32:01,678 qnn_preprocess.py:69] Visiting: aten_select_copy_int_521, aten.select_copy.int
2025-03-21T20:32:01.7191781Z [INFO 2025-03-21 20:32:01,679 qnn_preprocess.py:69] Visiting: aten_select_copy_int_523, aten.select_copy.int
2025-03-21T20:32:01.7193076Z [INFO 2025-03-21 20:32:01,679 qnn_preprocess.py:69] Visiting: aten_select_copy_int_525, aten.select_copy.int
2025-03-21T20:32:01.7194386Z [INFO 2025-03-21 20:32:01,680 qnn_preprocess.py:69] Visiting: aten_select_copy_int_527, aten.select_copy.int
2025-03-21T20:32:01.7195639Z [INFO 2025-03-21 20:32:01,680 qnn_preprocess.py:69] Visiting: aten_sub_tensor_20, aten.sub.Tensor
2025-03-21T20:32:01.7196812Z [INFO 2025-03-21 20:32:01,681 qnn_preprocess.py:69] Visiting: aten_add_tensor_50, aten.add.Tensor
2025-03-21T20:32:01.7197999Z [INFO 2025-03-21 20:32:01,681 qnn_preprocess.py:69] Visiting: aten_sub_tensor_21, aten.sub.Tensor
2025-03-21T20:32:01.7199179Z [INFO 2025-03-21 20:32:01,682 qnn_preprocess.py:69] Visiting: aten_add_tensor_51, aten.add.Tensor
2025-03-21T20:32:01.7200472Z [INFO 2025-03-21 20:32:01,682 qnn_preprocess.py:69] Visiting: aten_cat_default_43, aten.cat.default
2025-03-21T20:32:01.7201940Z [INFO 2025-03-21 20:32:01,684 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_113, aten.unsqueeze_copy.default
2025-03-21T20:32:01.7203451Z [INFO 2025-03-21 20:32:01,684 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_114, aten.unsqueeze_copy.default
2025-03-21T20:32:01.7205124Z [INFO 2025-03-21 20:32:01,685 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_115, aten.unsqueeze_copy.default
2025-03-21T20:32:01.7206525Z [INFO 2025-03-21 20:32:01,685 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_116, aten.unsqueeze_copy.default
2025-03-21T20:32:01.7208423Z [INFO 2025-03-21 20:32:01,686 qnn_preprocess.py:69] Visiting: aten_view_copy_default_190, aten.view_copy.default
2025-03-21T20:32:01.7210184Z [INFO 2025-03-21 20:32:01,686 qnn_preprocess.py:69] Visiting: aten__to_copy_default_22, aten._to_copy.default
2025-03-21T20:32:01.7211602Z [INFO 2025-03-21 20:32:01,687 qnn_preprocess.py:69] Visiting: aten_cat_default_40, aten.cat.default
2025-03-21T20:32:01.7212901Z [INFO 2025-03-21 20:32:01,687 qnn_preprocess.py:69] Visiting: aten_cat_default_41, aten.cat.default
2025-03-21T20:32:01.7214305Z [INFO 2025-03-21 20:32:01,688 qnn_preprocess.py:69] Visiting: aten_view_copy_default_187, aten.view_copy.default
2025-03-21T20:32:01.7215802Z [INFO 2025-03-21 20:32:01,688 qnn_preprocess.py:69] Visiting: aten_view_copy_default_188, aten.view_copy.default
2025-03-21T20:32:01.7217108Z [INFO 2025-03-21 20:32:01,688 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_416, aten.permute_copy.default
2025-03-21T20:32:01.7218429Z [INFO 2025-03-21 20:32:01,689 qnn_preprocess.py:69] Visiting: aten_index_put_default_20, aten.index_put.default
2025-03-21T20:32:01.7219741Z [INFO 2025-03-21 20:32:01,691 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_417, aten.permute_copy.default
2025-03-21T20:32:01.7221200Z [INFO 2025-03-21 20:32:01,691 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_418, aten.permute_copy.default
2025-03-21T20:32:01.7222558Z [INFO 2025-03-21 20:32:01,692 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_419, aten.permute_copy.default
2025-03-21T20:32:01.7223916Z [INFO 2025-03-21 20:32:01,693 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_420, aten.permute_copy.default
2025-03-21T20:32:01.7225277Z [INFO 2025-03-21 20:32:01,693 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_421, aten.permute_copy.default
2025-03-21T20:32:01.7226635Z [INFO 2025-03-21 20:32:01,694 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_422, aten.permute_copy.default
2025-03-21T20:32:01.7227961Z [INFO 2025-03-21 20:32:01,695 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_423, aten.permute_copy.default
2025-03-21T20:32:01.7229319Z [INFO 2025-03-21 20:32:01,695 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_424, aten.permute_copy.default
2025-03-21T20:32:01.7230678Z [INFO 2025-03-21 20:32:01,696 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_425, aten.permute_copy.default
2025-03-21T20:32:01.7232038Z [INFO 2025-03-21 20:32:01,697 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_426, aten.permute_copy.default
2025-03-21T20:32:01.7233659Z [INFO 2025-03-21 20:32:01,697 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_427, aten.permute_copy.default
2025-03-21T20:32:01.7235026Z [INFO 2025-03-21 20:32:01,698 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_428, aten.permute_copy.default
2025-03-21T20:32:01.7236319Z [INFO 2025-03-21 20:32:01,699 qnn_preprocess.py:69] Visiting: aten_select_copy_int_480, aten.select_copy.int
2025-03-21T20:32:01.7237553Z [INFO 2025-03-21 20:32:01,699 qnn_preprocess.py:69] Visiting: aten_select_copy_int_482, aten.select_copy.int
2025-03-21T20:32:01.7238788Z [INFO 2025-03-21 20:32:01,700 qnn_preprocess.py:69] Visiting: aten_select_copy_int_484, aten.select_copy.int
2025-03-21T20:32:01.7240021Z [INFO 2025-03-21 20:32:01,700 qnn_preprocess.py:69] Visiting: aten_select_copy_int_486, aten.select_copy.int
2025-03-21T20:32:01.7241247Z [INFO 2025-03-21 20:32:01,701 qnn_preprocess.py:69] Visiting: aten_select_copy_int_488, aten.select_copy.int
2025-03-21T20:32:01.7242472Z [INFO 2025-03-21 20:32:01,701 qnn_preprocess.py:69] Visiting: aten_select_copy_int_490, aten.select_copy.int
2025-03-21T20:32:01.7243702Z [INFO 2025-03-21 20:32:01,702 qnn_preprocess.py:69] Visiting: aten_select_copy_int_492, aten.select_copy.int
2025-03-21T20:32:01.7245011Z [INFO 2025-03-21 20:32:01,702 qnn_preprocess.py:69] Visiting: aten_select_copy_int_494, aten.select_copy.int
2025-03-21T20:32:01.7246226Z [INFO 2025-03-21 20:32:01,702 qnn_preprocess.py:69] Visiting: aten_select_copy_int_496, aten.select_copy.int
2025-03-21T20:32:01.7247559Z [INFO 2025-03-21 20:32:01,703 qnn_preprocess.py:69] Visiting: aten_select_copy_int_498, aten.select_copy.int
2025-03-21T20:32:01.7248794Z [INFO 2025-03-21 20:32:01,703 qnn_preprocess.py:69] Visiting: aten_select_copy_int_500, aten.select_copy.int
2025-03-21T20:32:01.7250066Z [INFO 2025-03-21 20:32:01,704 qnn_preprocess.py:69] Visiting: aten_select_copy_int_502, aten.select_copy.int
2025-03-21T20:32:01.7251294Z [INFO 2025-03-21 20:32:01,704 qnn_preprocess.py:69] Visiting: aten_select_copy_int_481, aten.select_copy.int
2025-03-21T20:32:01.7252524Z [INFO 2025-03-21 20:32:01,705 qnn_preprocess.py:69] Visiting: aten_select_copy_int_483, aten.select_copy.int
2025-03-21T20:32:01.7253738Z [INFO 2025-03-21 20:32:01,705 qnn_preprocess.py:69] Visiting: aten_select_copy_int_485, aten.select_copy.int
2025-03-21T20:32:01.7254966Z [INFO 2025-03-21 20:32:01,706 qnn_preprocess.py:69] Visiting: aten_select_copy_int_487, aten.select_copy.int
2025-03-21T20:32:01.7256196Z [INFO 2025-03-21 20:32:01,706 qnn_preprocess.py:69] Visiting: aten_select_copy_int_489, aten.select_copy.int
2025-03-21T20:32:01.7257431Z [INFO 2025-03-21 20:32:01,707 qnn_preprocess.py:69] Visiting: aten_select_copy_int_491, aten.select_copy.int
2025-03-21T20:32:01.7258717Z [INFO 2025-03-21 20:32:01,707 qnn_preprocess.py:69] Visiting: aten_select_copy_int_493, aten.select_copy.int
2025-03-21T20:32:01.7259949Z [INFO 2025-03-21 20:32:01,707 qnn_preprocess.py:69] Visiting: aten_select_copy_int_495, aten.select_copy.int
2025-03-21T20:32:01.7261174Z [INFO 2025-03-21 20:32:01,708 qnn_preprocess.py:69] Visiting: aten_select_copy_int_497, aten.select_copy.int
2025-03-21T20:32:01.7262391Z [INFO 2025-03-21 20:32:01,708 qnn_preprocess.py:69] Visiting: aten_select_copy_int_499, aten.select_copy.int
2025-03-21T20:32:01.7263596Z [INFO 2025-03-21 20:32:01,709 qnn_preprocess.py:69] Visiting: aten_select_copy_int_501, aten.select_copy.int
2025-03-21T20:32:01.7264810Z [INFO 2025-03-21 20:32:01,709 qnn_preprocess.py:69] Visiting: aten_select_copy_int_503, aten.select_copy.int
2025-03-21T20:32:01.7265983Z [INFO 2025-03-21 20:32:01,710 qnn_preprocess.py:69] Visiting: aten_cat_default_42, aten.cat.default
2025-03-21T20:32:01.7267183Z [INFO 2025-03-21 20:32:01,711 qnn_preprocess.py:69] Visiting: aten_view_copy_default_189, aten.view_copy.default
2025-03-21T20:32:01.7268479Z [INFO 2025-03-21 20:32:01,712 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_441, aten.permute_copy.default
2025-03-21T20:32:01.7269749Z [INFO 2025-03-21 20:32:01,712 qnn_preprocess.py:69] Visiting: aten__to_copy_default_23, aten._to_copy.default
2025-03-21T20:32:01.7270949Z [INFO 2025-03-21 20:32:01,713 qnn_preprocess.py:69] Visiting: aten_matmul_default_20, aten.matmul.default
2025-03-21T20:32:01.7272105Z [INFO 2025-03-21 20:32:01,714 qnn_preprocess.py:69] Visiting: aten_mul_tensor_160, aten.mul.Tensor
2025-03-21T20:32:01.7273212Z [INFO 2025-03-21 20:32:01,715 qnn_preprocess.py:69] Visiting: aten_add_tensor_52, aten.add.Tensor
2025-03-21T20:32:01.7274379Z [INFO 2025-03-21 20:32:01,715 qnn_preprocess.py:69] Visiting: aten__softmax_default_10, aten._softmax.default
2025-03-21T20:32:01.7275590Z [INFO 2025-03-21 20:32:01,716 qnn_preprocess.py:69] Visiting: aten_matmul_default_21, aten.matmul.default
2025-03-21T20:32:01.7276850Z [INFO 2025-03-21 20:32:01,716 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_442, aten.permute_copy.default
2025-03-21T20:32:01.7278141Z [INFO 2025-03-21 20:32:01,717 qnn_preprocess.py:69] Visiting: aten_view_copy_default_197, aten.view_copy.default
2025-03-21T20:32:01.7279474Z [INFO 2025-03-21 20:32:01,717 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_117, aten.unsqueeze_copy.default
2025-03-21T20:32:01.7902458Z [INFO 2025-03-21 20:32:01,718 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_810, aten.permute_copy.default
2025-03-21T20:32:01.7903854Z [INFO 2025-03-21 20:32:01,718 qnn_preprocess.py:69] Visiting: aten_convolution_default_73, aten.convolution.default
2025-03-21T20:32:01.7905401Z [INFO 2025-03-21 20:32:01,721 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_811, aten.permute_copy.default
2025-03-21T20:32:01.7906787Z [INFO 2025-03-21 20:32:01,722 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_117, aten.squeeze_copy.dims
2025-03-21T20:32:01.7908004Z [INFO 2025-03-21 20:32:01,723 qnn_preprocess.py:69] Visiting: aten_add_tensor_53, aten.add.Tensor
2025-03-21T20:32:01.7909196Z [INFO 2025-03-21 20:32:01,723 qnn_preprocess.py:69] Visiting: aten_rms_norm_default_21, aten.rms_norm.default
2025-03-21T20:32:01.7910535Z [INFO 2025-03-21 20:32:01,725 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_118, aten.unsqueeze_copy.default
2025-03-21T20:32:01.7911923Z [INFO 2025-03-21 20:32:01,725 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_812, aten.permute_copy.default
2025-03-21T20:32:01.7913325Z [INFO 2025-03-21 20:32:01,726 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_119, aten.unsqueeze_copy.default
2025-03-21T20:32:01.7914695Z [INFO 2025-03-21 20:32:01,726 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_813, aten.permute_copy.default
2025-03-21T20:32:01.7916031Z [INFO 2025-03-21 20:32:01,727 qnn_preprocess.py:69] Visiting: aten_convolution_default_74, aten.convolution.default
2025-03-21T20:32:01.7917447Z [INFO 2025-03-21 20:32:01,733 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_814, aten.permute_copy.default
2025-03-21T20:32:01.7918799Z [INFO 2025-03-21 20:32:01,734 qnn_preprocess.py:69] Visiting: aten_convolution_default_75, aten.convolution.default
2025-03-21T20:32:01.7920152Z [INFO 2025-03-21 20:32:01,741 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_815, aten.permute_copy.default
2025-03-21T20:32:01.7921471Z [INFO 2025-03-21 20:32:01,742 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_118, aten.squeeze_copy.dims
2025-03-21T20:32:01.7922757Z [INFO 2025-03-21 20:32:01,743 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_119, aten.squeeze_copy.dims
2025-03-21T20:32:01.7924014Z [INFO 2025-03-21 20:32:01,743 qnn_preprocess.py:69] Visiting: aten_sigmoid_default_10, aten.sigmoid.default
2025-03-21T20:32:01.7925192Z [INFO 2025-03-21 20:32:01,744 qnn_preprocess.py:69] Visiting: aten_mul_tensor_163, aten.mul.Tensor
2025-03-21T20:32:01.7926322Z [INFO 2025-03-21 20:32:01,744 qnn_preprocess.py:69] Visiting: aten_mul_tensor_164, aten.mul.Tensor
2025-03-21T20:32:01.7927598Z [INFO 2025-03-21 20:32:01,745 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_120, aten.unsqueeze_copy.default
2025-03-21T20:32:01.7928984Z [INFO 2025-03-21 20:32:01,745 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_816, aten.permute_copy.default
2025-03-21T20:32:01.7930410Z [INFO 2025-03-21 20:32:01,746 qnn_preprocess.py:69] Visiting: aten_convolution_default_76, aten.convolution.default
2025-03-21T20:32:01.7931759Z [INFO 2025-03-21 20:32:01,753 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_817, aten.permute_copy.default
2025-03-21T20:32:01.7933224Z [INFO 2025-03-21 20:32:01,754 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_120, aten.squeeze_copy.dims
2025-03-21T20:32:01.7934415Z [INFO 2025-03-21 20:32:01,754 qnn_preprocess.py:69] Visiting: aten_add_tensor_54, aten.add.Tensor
2025-03-21T20:32:01.7935604Z [INFO 2025-03-21 20:32:01,755 qnn_preprocess.py:69] Visiting: aten_rms_norm_default_22, aten.rms_norm.default
2025-03-21T20:32:01.7936971Z [INFO 2025-03-21 20:32:01,756 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_121, aten.unsqueeze_copy.default
2025-03-21T20:32:01.7938363Z [INFO 2025-03-21 20:32:01,757 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_818, aten.permute_copy.default
2025-03-21T20:32:01.7939738Z [INFO 2025-03-21 20:32:01,757 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_122, aten.unsqueeze_copy.default
2025-03-21T20:32:01.7941239Z [INFO 2025-03-21 20:32:01,758 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_819, aten.permute_copy.default
2025-03-21T20:32:01.7942635Z [INFO 2025-03-21 20:32:01,758 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_123, aten.unsqueeze_copy.default
2025-03-21T20:32:01.7944123Z [INFO 2025-03-21 20:32:01,759 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_820, aten.permute_copy.default
2025-03-21T20:32:01.7945460Z [INFO 2025-03-21 20:32:01,760 qnn_preprocess.py:69] Visiting: aten_convolution_default_77, aten.convolution.default
2025-03-21T20:32:01.7946805Z [INFO 2025-03-21 20:32:01,762 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_821, aten.permute_copy.default
2025-03-21T20:32:01.7948141Z [INFO 2025-03-21 20:32:01,763 qnn_preprocess.py:69] Visiting: aten_convolution_default_78, aten.convolution.default
2025-03-21T20:32:01.7949494Z [INFO 2025-03-21 20:32:01,766 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_822, aten.permute_copy.default
2025-03-21T20:32:01.7950848Z [INFO 2025-03-21 20:32:01,767 qnn_preprocess.py:69] Visiting: aten_convolution_default_79, aten.convolution.default
2025-03-21T20:32:01.7952204Z [INFO 2025-03-21 20:32:01,770 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_823, aten.permute_copy.default
2025-03-21T20:32:01.7953525Z [INFO 2025-03-21 20:32:01,771 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_121, aten.squeeze_copy.dims
2025-03-21T20:32:01.7954858Z [INFO 2025-03-21 20:32:01,772 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_122, aten.squeeze_copy.dims
2025-03-21T20:32:01.7956143Z [INFO 2025-03-21 20:32:01,772 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_123, aten.squeeze_copy.dims
2025-03-21T20:32:01.7957407Z [INFO 2025-03-21 20:32:01,773 qnn_preprocess.py:69] Visiting: aten_view_copy_default_198, aten.view_copy.default
2025-03-21T20:32:01.7958675Z [INFO 2025-03-21 20:32:01,773 qnn_preprocess.py:69] Visiting: aten_view_copy_default_199, aten.view_copy.default
2025-03-21T20:32:01.7959955Z [INFO 2025-03-21 20:32:01,773 qnn_preprocess.py:69] Visiting: aten_view_copy_default_200, aten.view_copy.default
2025-03-21T20:32:01.7961233Z [INFO 2025-03-21 20:32:01,774 qnn_preprocess.py:69] Visiting: aten_view_copy_default_201, aten.view_copy.default
2025-03-21T20:32:01.7962504Z [INFO 2025-03-21 20:32:01,774 qnn_preprocess.py:69] Visiting: aten_view_copy_default_202, aten.view_copy.default
2025-03-21T20:32:01.7963780Z [INFO 2025-03-21 20:32:01,774 qnn_preprocess.py:69] Visiting: aten_index_put_default_23, aten.index_put.default
2025-03-21T20:32:01.7965048Z [INFO 2025-03-21 20:32:01,776 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_44, aten.slice_copy.Tensor
2025-03-21T20:32:01.7966283Z [INFO 2025-03-21 20:32:01,776 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_45, aten.slice_copy.Tensor
2025-03-21T20:32:01.7967549Z [INFO 2025-03-21 20:32:01,776 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_46, aten.slice_copy.Tensor
2025-03-21T20:32:01.7968819Z [INFO 2025-03-21 20:32:01,777 qnn_preprocess.py:69] Visiting: aten_slice_copy_tensor_47, aten.slice_copy.Tensor
2025-03-21T20:32:01.7970227Z [INFO 2025-03-21 20:32:01,777 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_470, aten.permute_copy.default
2025-03-21T20:32:01.7971590Z [INFO 2025-03-21 20:32:01,778 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_471, aten.permute_copy.default
2025-03-21T20:32:01.7972943Z [INFO 2025-03-21 20:32:01,779 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_472, aten.permute_copy.default
2025-03-21T20:32:01.7974303Z [INFO 2025-03-21 20:32:01,779 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_473, aten.permute_copy.default
2025-03-21T20:32:01.7975634Z [INFO 2025-03-21 20:32:01,780 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_474, aten.permute_copy.default
2025-03-21T20:32:01.7976978Z [INFO 2025-03-21 20:32:01,781 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_475, aten.permute_copy.default
2025-03-21T20:32:01.7978355Z [INFO 2025-03-21 20:32:01,781 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_476, aten.permute_copy.default
2025-03-21T20:32:01.7979687Z [INFO 2025-03-21 20:32:01,782 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_477, aten.permute_copy.default
2025-03-21T20:32:01.7981085Z [INFO 2025-03-21 20:32:01,783 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_478, aten.permute_copy.default
2025-03-21T20:32:01.7982457Z [INFO 2025-03-21 20:32:01,783 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_479, aten.permute_copy.default
2025-03-21T20:32:01.7983798Z [INFO 2025-03-21 20:32:01,784 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_480, aten.permute_copy.default
2025-03-21T20:32:01.7985101Z [INFO 2025-03-21 20:32:01,785 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_481, aten.permute_copy.default
2025-03-21T20:32:01.7986401Z [INFO 2025-03-21 20:32:01,785 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_124, aten.squeeze_copy.dims
2025-03-21T20:32:01.7987669Z [INFO 2025-03-21 20:32:01,786 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_125, aten.squeeze_copy.dims
2025-03-21T20:32:01.7988932Z [INFO 2025-03-21 20:32:01,786 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_126, aten.squeeze_copy.dims
2025-03-21T20:32:01.7990185Z [INFO 2025-03-21 20:32:01,787 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_127, aten.squeeze_copy.dims
2025-03-21T20:32:01.7991438Z [INFO 2025-03-21 20:32:01,787 qnn_preprocess.py:69] Visiting: aten_select_copy_int_552, aten.select_copy.int
2025-03-21T20:32:01.7992696Z [INFO 2025-03-21 20:32:01,788 qnn_preprocess.py:69] Visiting: aten_select_copy_int_554, aten.select_copy.int
2025-03-21T20:32:01.7993907Z [INFO 2025-03-21 20:32:01,789 qnn_preprocess.py:69] Visiting: aten_select_copy_int_556, aten.select_copy.int
2025-03-21T20:32:01.7995130Z [INFO 2025-03-21 20:32:01,789 qnn_preprocess.py:69] Visiting: aten_select_copy_int_558, aten.select_copy.int
2025-03-21T20:32:01.8296251Z [INFO 2025-03-21 20:32:01,789 qnn_preprocess.py:69] Visiting: aten_select_copy_int_560, aten.select_copy.int
2025-03-21T20:32:01.8297515Z [INFO 2025-03-21 20:32:01,790 qnn_preprocess.py:69] Visiting: aten_select_copy_int_562, aten.select_copy.int
2025-03-21T20:32:01.8298747Z [INFO 2025-03-21 20:32:01,791 qnn_preprocess.py:69] Visiting: aten_select_copy_int_564, aten.select_copy.int
2025-03-21T20:32:01.8299999Z [INFO 2025-03-21 20:32:01,791 qnn_preprocess.py:69] Visiting: aten_select_copy_int_566, aten.select_copy.int
2025-03-21T20:32:01.8301232Z [INFO 2025-03-21 20:32:01,791 qnn_preprocess.py:69] Visiting: aten_select_copy_int_568, aten.select_copy.int
2025-03-21T20:32:01.8302469Z [INFO 2025-03-21 20:32:01,792 qnn_preprocess.py:69] Visiting: aten_select_copy_int_570, aten.select_copy.int
2025-03-21T20:32:01.8303682Z [INFO 2025-03-21 20:32:01,792 qnn_preprocess.py:69] Visiting: aten_select_copy_int_572, aten.select_copy.int
2025-03-21T20:32:01.8304910Z [INFO 2025-03-21 20:32:01,793 qnn_preprocess.py:69] Visiting: aten_select_copy_int_574, aten.select_copy.int
2025-03-21T20:32:01.8306095Z [INFO 2025-03-21 20:32:01,793 qnn_preprocess.py:69] Visiting: aten_mul_tensor_167, aten.mul.Tensor
2025-03-21T20:32:01.8307217Z [INFO 2025-03-21 20:32:01,794 qnn_preprocess.py:69] Visiting: aten_mul_tensor_169, aten.mul.Tensor
2025-03-21T20:32:01.8308342Z [INFO 2025-03-21 20:32:01,795 qnn_preprocess.py:69] Visiting: aten_mul_tensor_168, aten.mul.Tensor
2025-03-21T20:32:01.8309460Z [INFO 2025-03-21 20:32:01,795 qnn_preprocess.py:69] Visiting: aten_mul_tensor_170, aten.mul.Tensor
2025-03-21T20:32:01.8310569Z [INFO 2025-03-21 20:32:01,796 qnn_preprocess.py:69] Visiting: aten_mul_tensor_171, aten.mul.Tensor
2025-03-21T20:32:01.8311694Z [INFO 2025-03-21 20:32:01,796 qnn_preprocess.py:69] Visiting: aten_mul_tensor_173, aten.mul.Tensor
2025-03-21T20:32:01.8312808Z [INFO 2025-03-21 20:32:01,797 qnn_preprocess.py:69] Visiting: aten_mul_tensor_172, aten.mul.Tensor
2025-03-21T20:32:01.8313912Z [INFO 2025-03-21 20:32:01,797 qnn_preprocess.py:69] Visiting: aten_mul_tensor_174, aten.mul.Tensor
2025-03-21T20:32:01.8315292Z [INFO 2025-03-21 20:32:01,798 qnn_preprocess.py:69] Visiting: aten_select_copy_int_553, aten.select_copy.int
2025-03-21T20:32:01.8316523Z [INFO 2025-03-21 20:32:01,798 qnn_preprocess.py:69] Visiting: aten_select_copy_int_555, aten.select_copy.int
2025-03-21T20:32:01.8317878Z [INFO 2025-03-21 20:32:01,799 qnn_preprocess.py:69] Visiting: aten_select_copy_int_557, aten.select_copy.int
2025-03-21T20:32:01.8319100Z [INFO 2025-03-21 20:32:01,799 qnn_preprocess.py:69] Visiting: aten_select_copy_int_559, aten.select_copy.int
2025-03-21T20:32:01.8320326Z [INFO 2025-03-21 20:32:01,800 qnn_preprocess.py:69] Visiting: aten_select_copy_int_561, aten.select_copy.int
2025-03-21T20:32:01.8321555Z [INFO 2025-03-21 20:32:01,800 qnn_preprocess.py:69] Visiting: aten_select_copy_int_563, aten.select_copy.int
2025-03-21T20:32:01.8322781Z [INFO 2025-03-21 20:32:01,800 qnn_preprocess.py:69] Visiting: aten_select_copy_int_565, aten.select_copy.int
2025-03-21T20:32:01.8324002Z [INFO 2025-03-21 20:32:01,801 qnn_preprocess.py:69] Visiting: aten_select_copy_int_567, aten.select_copy.int
2025-03-21T20:32:01.8325227Z [INFO 2025-03-21 20:32:01,801 qnn_preprocess.py:69] Visiting: aten_select_copy_int_569, aten.select_copy.int
2025-03-21T20:32:01.8326458Z [INFO 2025-03-21 20:32:01,802 qnn_preprocess.py:69] Visiting: aten_select_copy_int_571, aten.select_copy.int
2025-03-21T20:32:01.8327666Z [INFO 2025-03-21 20:32:01,802 qnn_preprocess.py:69] Visiting: aten_select_copy_int_573, aten.select_copy.int
2025-03-21T20:32:01.8328935Z [INFO 2025-03-21 20:32:01,803 qnn_preprocess.py:69] Visiting: aten_select_copy_int_575, aten.select_copy.int
2025-03-21T20:32:01.8330183Z [INFO 2025-03-21 20:32:01,803 qnn_preprocess.py:69] Visiting: aten_sub_tensor_22, aten.sub.Tensor
2025-03-21T20:32:01.8331280Z [INFO 2025-03-21 20:32:01,804 qnn_preprocess.py:69] Visiting: aten_add_tensor_55, aten.add.Tensor
2025-03-21T20:32:01.8332585Z [INFO 2025-03-21 20:32:01,804 qnn_preprocess.py:69] Visiting: aten_sub_tensor_23, aten.sub.Tensor
2025-03-21T20:32:01.8333694Z [INFO 2025-03-21 20:32:01,805 qnn_preprocess.py:69] Visiting: aten_add_tensor_56, aten.add.Tensor
2025-03-21T20:32:01.8334801Z [INFO 2025-03-21 20:32:01,805 qnn_preprocess.py:69] Visiting: aten_cat_default_47, aten.cat.default
2025-03-21T20:32:01.8336118Z [INFO 2025-03-21 20:32:01,807 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_124, aten.unsqueeze_copy.default
2025-03-21T20:32:01.8337547Z [INFO 2025-03-21 20:32:01,807 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_125, aten.unsqueeze_copy.default
2025-03-21T20:32:01.8338973Z [INFO 2025-03-21 20:32:01,808 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_126, aten.unsqueeze_copy.default
2025-03-21T20:32:01.8340393Z [INFO 2025-03-21 20:32:01,808 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_127, aten.unsqueeze_copy.default
2025-03-21T20:32:01.8341731Z [INFO 2025-03-21 20:32:01,808 qnn_preprocess.py:69] Visiting: aten_view_copy_default_208, aten.view_copy.default
2025-03-21T20:32:01.8342992Z [INFO 2025-03-21 20:32:01,809 qnn_preprocess.py:69] Visiting: aten__to_copy_default_24, aten._to_copy.default
2025-03-21T20:32:01.8344179Z [INFO 2025-03-21 20:32:01,809 qnn_preprocess.py:69] Visiting: aten_cat_default_44, aten.cat.default
2025-03-21T20:32:01.8345284Z [INFO 2025-03-21 20:32:01,810 qnn_preprocess.py:69] Visiting: aten_cat_default_45, aten.cat.default
2025-03-21T20:32:01.8346498Z [INFO 2025-03-21 20:32:01,810 qnn_preprocess.py:69] Visiting: aten_view_copy_default_205, aten.view_copy.default
2025-03-21T20:32:01.8347767Z [INFO 2025-03-21 20:32:01,811 qnn_preprocess.py:69] Visiting: aten_view_copy_default_206, aten.view_copy.default
2025-03-21T20:32:01.8349083Z [INFO 2025-03-21 20:32:01,811 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_457, aten.permute_copy.default
2025-03-21T20:32:01.8350393Z [INFO 2025-03-21 20:32:01,812 qnn_preprocess.py:69] Visiting: aten_index_put_default_22, aten.index_put.default
2025-03-21T20:32:01.8351780Z [INFO 2025-03-21 20:32:01,813 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_458, aten.permute_copy.default
2025-03-21T20:32:01.8353135Z [INFO 2025-03-21 20:32:01,814 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_459, aten.permute_copy.default
2025-03-21T20:32:01.8354525Z [INFO 2025-03-21 20:32:01,815 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_460, aten.permute_copy.default
2025-03-21T20:32:01.8355935Z [INFO 2025-03-21 20:32:01,815 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_461, aten.permute_copy.default
2025-03-21T20:32:01.8357296Z [INFO 2025-03-21 20:32:01,816 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_462, aten.permute_copy.default
2025-03-21T20:32:01.8358662Z [INFO 2025-03-21 20:32:01,817 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_463, aten.permute_copy.default
2025-03-21T20:32:01.8360017Z [INFO 2025-03-21 20:32:01,817 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_464, aten.permute_copy.default
2025-03-21T20:32:01.8361386Z [INFO 2025-03-21 20:32:01,818 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_465, aten.permute_copy.default
2025-03-21T20:32:01.8362740Z [INFO 2025-03-21 20:32:01,819 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_466, aten.permute_copy.default
2025-03-21T20:32:01.8364066Z [INFO 2025-03-21 20:32:01,819 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_467, aten.permute_copy.default
2025-03-21T20:32:01.8365426Z [INFO 2025-03-21 20:32:01,820 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_468, aten.permute_copy.default
2025-03-21T20:32:01.8366843Z [INFO 2025-03-21 20:32:01,821 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_469, aten.permute_copy.default
2025-03-21T20:32:01.8368138Z [INFO 2025-03-21 20:32:01,821 qnn_preprocess.py:69] Visiting: aten_select_copy_int_528, aten.select_copy.int
2025-03-21T20:32:01.8369428Z [INFO 2025-03-21 20:32:01,822 qnn_preprocess.py:69] Visiting: aten_select_copy_int_530, aten.select_copy.int
2025-03-21T20:32:01.8370665Z [INFO 2025-03-21 20:32:01,822 qnn_preprocess.py:69] Visiting: aten_select_copy_int_532, aten.select_copy.int
2025-03-21T20:32:01.8372079Z [INFO 2025-03-21 20:32:01,823 qnn_preprocess.py:69] Visiting: aten_select_copy_int_534, aten.select_copy.int
2025-03-21T20:32:01.8373371Z [INFO 2025-03-21 20:32:01,823 qnn_preprocess.py:69] Visiting: aten_select_copy_int_536, aten.select_copy.int
2025-03-21T20:32:01.8374947Z [INFO 2025-03-21 20:32:01,824 qnn_preprocess.py:69] Visiting: aten_select_copy_int_538, aten.select_copy.int
2025-03-21T20:32:01.8388440Z [INFO 2025-03-21 20:32:01,824 qnn_preprocess.py:69] Visiting: aten_select_copy_int_540, aten.select_copy.int
2025-03-21T20:32:01.8389691Z [INFO 2025-03-21 20:32:01,825 qnn_preprocess.py:69] Visiting: aten_select_copy_int_542, aten.select_copy.int
2025-03-21T20:32:01.8390921Z [INFO 2025-03-21 20:32:01,825 qnn_preprocess.py:69] Visiting: aten_select_copy_int_544, aten.select_copy.int
2025-03-21T20:32:01.8392143Z [INFO 2025-03-21 20:32:01,825 qnn_preprocess.py:69] Visiting: aten_select_copy_int_546, aten.select_copy.int
2025-03-21T20:32:01.8393353Z [INFO 2025-03-21 20:32:01,826 qnn_preprocess.py:69] Visiting: aten_select_copy_int_548, aten.select_copy.int
2025-03-21T20:32:01.8394578Z [INFO 2025-03-21 20:32:01,826 qnn_preprocess.py:69] Visiting: aten_select_copy_int_550, aten.select_copy.int
2025-03-21T20:32:01.8395812Z [INFO 2025-03-21 20:32:01,827 qnn_preprocess.py:69] Visiting: aten_select_copy_int_529, aten.select_copy.int
2025-03-21T20:32:01.8397023Z [INFO 2025-03-21 20:32:01,827 qnn_preprocess.py:69] Visiting: aten_select_copy_int_531, aten.select_copy.int
2025-03-21T20:32:01.8398246Z [INFO 2025-03-21 20:32:01,828 qnn_preprocess.py:69] Visiting: aten_select_copy_int_533, aten.select_copy.int
2025-03-21T20:32:01.8399466Z [INFO 2025-03-21 20:32:01,828 qnn_preprocess.py:69] Visiting: aten_select_copy_int_535, aten.select_copy.int
2025-03-21T20:32:01.8400690Z [INFO 2025-03-21 20:32:01,828 qnn_preprocess.py:69] Visiting: aten_select_copy_int_537, aten.select_copy.int
2025-03-21T20:32:06.9957258Z [INFO 2025-03-21 20:32:01,829 qnn_preprocess.py:69] Visiting: aten_select_copy_int_539, aten.select_copy.int
2025-03-21T20:32:06.9958511Z [INFO 2025-03-21 20:32:01,829 qnn_preprocess.py:69] Visiting: aten_select_copy_int_541, aten.select_copy.int
2025-03-21T20:32:06.9959896Z [INFO 2025-03-21 20:32:01,830 qnn_preprocess.py:69] Visiting: aten_select_copy_int_543, aten.select_copy.int
2025-03-21T20:32:06.9961152Z [INFO 2025-03-21 20:32:01,830 qnn_preprocess.py:69] Visiting: aten_select_copy_int_545, aten.select_copy.int
2025-03-21T20:32:06.9962336Z [INFO 2025-03-21 20:32:01,831 qnn_preprocess.py:69] Visiting: aten_select_copy_int_547, aten.select_copy.int
2025-03-21T20:32:06.9963556Z [INFO 2025-03-21 20:32:01,831 qnn_preprocess.py:69] Visiting: aten_select_copy_int_549, aten.select_copy.int
2025-03-21T20:32:06.9964843Z [INFO 2025-03-21 20:32:01,832 qnn_preprocess.py:69] Visiting: aten_select_copy_int_551, aten.select_copy.int
2025-03-21T20:32:06.9965940Z [INFO 2025-03-21 20:32:01,832 qnn_preprocess.py:69] Visiting: aten_cat_default_46, aten.cat.default
2025-03-21T20:32:06.9967183Z [INFO 2025-03-21 20:32:01,833 qnn_preprocess.py:69] Visiting: aten_view_copy_default_207, aten.view_copy.default
2025-03-21T20:32:06.9968493Z [INFO 2025-03-21 20:32:01,834 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_482, aten.permute_copy.default
2025-03-21T20:32:06.9969843Z [INFO 2025-03-21 20:32:01,834 qnn_preprocess.py:69] Visiting: aten__to_copy_default_25, aten._to_copy.default
2025-03-21T20:32:06.9971105Z [INFO 2025-03-21 20:32:01,835 qnn_preprocess.py:69] Visiting: aten_matmul_default_22, aten.matmul.default
2025-03-21T20:32:06.9972289Z [INFO 2025-03-21 20:32:01,836 qnn_preprocess.py:69] Visiting: aten_mul_tensor_175, aten.mul.Tensor
2025-03-21T20:32:06.9973376Z [INFO 2025-03-21 20:32:01,837 qnn_preprocess.py:69] Visiting: aten_add_tensor_57, aten.add.Tensor
2025-03-21T20:32:06.9974565Z [INFO 2025-03-21 20:32:01,837 qnn_preprocess.py:69] Visiting: aten__softmax_default_11, aten._softmax.default
2025-03-21T20:32:06.9975730Z [INFO 2025-03-21 20:32:01,838 qnn_preprocess.py:69] Visiting: aten_matmul_default_23, aten.matmul.default
2025-03-21T20:32:06.9976981Z [INFO 2025-03-21 20:32:01,838 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_483, aten.permute_copy.default
2025-03-21T20:32:06.9978270Z [INFO 2025-03-21 20:32:01,839 qnn_preprocess.py:69] Visiting: aten_view_copy_default_215, aten.view_copy.default
2025-03-21T20:32:06.9979650Z [INFO 2025-03-21 20:32:01,839 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_128, aten.unsqueeze_copy.default
2025-03-21T20:32:06.9981101Z [INFO 2025-03-21 20:32:01,840 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_824, aten.permute_copy.default
2025-03-21T20:32:06.9982491Z [INFO 2025-03-21 20:32:01,840 qnn_preprocess.py:69] Visiting: aten_convolution_default_80, aten.convolution.default
2025-03-21T20:32:06.9983756Z [INFO 2025-03-21 20:32:01,843 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_825, aten.permute_copy.default
2025-03-21T20:32:06.9985070Z [INFO 2025-03-21 20:32:01,844 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_128, aten.squeeze_copy.dims
2025-03-21T20:32:06.9986307Z [INFO 2025-03-21 20:32:01,845 qnn_preprocess.py:69] Visiting: aten_add_tensor_58, aten.add.Tensor
2025-03-21T20:32:06.9987499Z [INFO 2025-03-21 20:32:01,845 qnn_preprocess.py:69] Visiting: aten_rms_norm_default_23, aten.rms_norm.default
2025-03-21T20:32:06.9988856Z [INFO 2025-03-21 20:32:01,847 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_129, aten.unsqueeze_copy.default
2025-03-21T20:32:06.9990133Z [INFO 2025-03-21 20:32:01,847 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_826, aten.permute_copy.default
2025-03-21T20:32:06.9991502Z [INFO 2025-03-21 20:32:01,848 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_130, aten.unsqueeze_copy.default
2025-03-21T20:32:06.9992912Z [INFO 2025-03-21 20:32:01,848 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_827, aten.permute_copy.default
2025-03-21T20:32:06.9994419Z [INFO 2025-03-21 20:32:01,849 qnn_preprocess.py:69] Visiting: aten_convolution_default_81, aten.convolution.default
2025-03-21T20:32:06.9995772Z [INFO 2025-03-21 20:32:01,855 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_828, aten.permute_copy.default
2025-03-21T20:32:06.9997203Z [INFO 2025-03-21 20:32:01,856 qnn_preprocess.py:69] Visiting: aten_convolution_default_82, aten.convolution.default
2025-03-21T20:32:06.9998556Z [INFO 2025-03-21 20:32:01,862 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_829, aten.permute_copy.default
2025-03-21T20:32:06.9999558Z [INFO 2025-03-21 20:32:01,863 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_129, aten.squeeze_copy.dims
2025-03-21T20:32:07.0000549Z [INFO 2025-03-21 20:32:01,864 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_130, aten.squeeze_copy.dims
2025-03-21T20:32:07.0001375Z [INFO 2025-03-21 20:32:01,864 qnn_preprocess.py:69] Visiting: aten_sigmoid_default_11, aten.sigmoid.default
2025-03-21T20:32:07.0002078Z [INFO 2025-03-21 20:32:01,864 qnn_preprocess.py:69] Visiting: aten_mul_tensor_178, aten.mul.Tensor
2025-03-21T20:32:07.0002744Z [INFO 2025-03-21 20:32:01,865 qnn_preprocess.py:69] Visiting: aten_mul_tensor_179, aten.mul.Tensor
2025-03-21T20:32:07.0003559Z [INFO 2025-03-21 20:32:01,866 qnn_preprocess.py:69] Visiting: aten_unsqueeze_copy_default_131, aten.unsqueeze_copy.default
2025-03-21T20:32:07.0004376Z [INFO 2025-03-21 20:32:01,866 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_830, aten.permute_copy.default
2025-03-21T20:32:07.0005217Z [INFO 2025-03-21 20:32:01,867 qnn_preprocess.py:69] Visiting: aten_convolution_default_83, aten.convolution.default
2025-03-21T20:32:07.0006000Z [INFO 2025-03-21 20:32:01,873 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_831, aten.permute_copy.default
2025-03-21T20:32:07.0006837Z [INFO 2025-03-21 20:32:01,874 qnn_preprocess.py:69] Visiting: aten_squeeze_copy_dims_131, aten.squeeze_copy.dims
2025-03-21T20:32:07.0007553Z [INFO 2025-03-21 20:32:01,875 qnn_preprocess.py:69] Visiting: aten_add_tensor_59, aten.add.Tensor
2025-03-21T20:32:07.0008246Z [INFO 2025-03-21 20:32:01,875 qnn_preprocess.py:69] Visiting: aten_select_copy_int_576, aten.select_copy.int
2025-03-21T20:32:07.0008976Z [INFO 2025-03-21 20:32:01,876 qnn_preprocess.py:69] Visiting: aten_rms_norm_default_24, aten.rms_norm.default
2025-03-21T20:32:07.0009805Z [INFO 2025-03-21 20:32:01,877 qnn_preprocess.py:69] Visiting: aten_view_copy_default_216, aten.view_copy.default
2025-03-21T20:32:07.0010583Z [INFO 2025-03-21 20:32:01,877 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_832, aten.permute_copy.default
2025-03-21T20:32:07.0011432Z [INFO 2025-03-21 20:32:01,878 qnn_preprocess.py:69] Visiting: aten_convolution_default_84, aten.convolution.default
2025-03-21T20:32:07.0012217Z [INFO 2025-03-21 20:32:02,049 qnn_preprocess.py:69] Visiting: aten_permute_copy_default_833, aten.permute_copy.default
2025-03-21T20:32:07.0012989Z [INFO 2025-03-21 20:32:02,051 qnn_preprocess.py:69] Visiting: aten_view_copy_default_217, aten.view_copy.default
2025-03-21T20:32:07.0014027Z [INFO 2025-03-21 20:32:02,052 qnn_preprocess.py:69] Visiting: quantized_decomposed_dequantize_per_tensor_tensor, quantized_decomposed.dequantize_per_tensor.tensor
2025-03-21T20:32:07.0014832Z [INFO] [Qnn ExecuTorch]: Destroy Qnn backend parameters
2025-03-21T20:32:07.0015231Z [INFO] [Qnn ExecuTorch]: Destroy Qnn context
2025-03-21T20:32:07.0015586Z [INFO] [Qnn ExecuTorch]: Destroy Qnn device
2025-03-21T20:32:07.0015947Z [INFO] [Qnn ExecuTorch]: Destroy Qnn backend
2025-03-21T20:32:07.0016326Z [INFO 2025-03-21 20:32:06,994 builder.py:443] graph():
2025-03-21T20:32:07.0016987Z   %b_layers_0_attention_kv_cache_past_k_caches : [num_users=2] = placeholder[target=b_layers_0_attention_kv_cache_past_k_caches]
2025-03-21T20:32:07.0017891Z   %b_layers_0_attention_kv_cache_past_v_caches : [num_users=2] = placeholder[target=b_layers_0_attention_kv_cache_past_v_caches]
2025-03-21T20:32:07.0018776Z   %b_layers_1_attention_kv_cache_past_k_caches : [num_users=2] = placeholder[target=b_layers_1_attention_kv_cache_past_k_caches]
2025-03-21T20:32:07.0019716Z   %b_layers_1_attention_kv_cache_past_v_caches : [num_users=2] = placeholder[target=b_layers_1_attention_kv_cache_past_v_caches]
2025-03-21T20:32:07.0020592Z   %b_layers_2_attention_kv_cache_past_k_caches : [num_users=2] = placeholder[target=b_layers_2_attention_kv_cache_past_k_caches]
2025-03-21T20:32:07.0021619Z   %b_layers_2_attention_kv_cache_past_v_caches : [num_users=2] = placeholder[target=b_layers_2_attention_kv_cache_past_v_caches]
2025-03-21T20:32:07.0022546Z   %b_layers_3_attention_kv_cache_past_k_caches : [num_users=2] = placeholder[target=b_layers_3_attention_kv_cache_past_k_caches]
2025-03-21T20:32:07.0023517Z   %b_layers_3_attention_kv_cache_past_v_caches : [num_users=2] = placeholder[target=b_layers_3_attention_kv_cache_past_v_caches]
2025-03-21T20:32:07.0024405Z   %b_layers_4_attention_kv_cache_past_k_caches : [num_users=2] = placeholder[target=b_layers_4_attention_kv_cache_past_k_caches]
2025-03-21T20:32:07.0025295Z   %b_layers_4_attention_kv_cache_past_v_caches : [num_users=2] = placeholder[target=b_layers_4_attention_kv_cache_past_v_caches]
2025-03-21T20:32:07.0026182Z   %b_layers_5_attention_kv_cache_past_k_caches : [num_users=2] = placeholder[target=b_layers_5_attention_kv_cache_past_k_caches]
2025-03-21T20:32:07.0027082Z   %b_layers_5_attention_kv_cache_past_v_caches : [num_users=2] = placeholder[target=b_layers_5_attention_kv_cache_past_v_caches]
2025-03-21T20:32:07.0028081Z   %b_layers_6_attention_kv_cache_past_k_caches : [num_users=2] = placeholder[target=b_layers_6_attention_kv_cache_past_k_caches]
2025-03-21T20:32:07.0028977Z   %b_layers_6_attention_kv_cache_past_v_caches : [num_users=2] = placeholder[target=b_layers_6_attention_kv_cache_past_v_caches]
2025-03-21T20:32:07.0029865Z   %b_layers_7_attention_kv_cache_past_k_caches : [num_users=2] = placeholder[target=b_layers_7_attention_kv_cache_past_k_caches]
2025-03-21T20:32:07.0031215Z   %b_layers_7_attention_kv_cache_past_v_caches : [num_users=2] = placeholder[target=b_layers_7_attention_kv_cache_past_v_caches]
2025-03-21T20:32:07.0032469Z   %b_layers_8_attention_kv_cache_past_k_caches : [num_users=2] = placeholder[target=b_layers_8_attention_kv_cache_past_k_caches]
2025-03-21T20:32:07.0033376Z   %b_layers_8_attention_kv_cache_past_v_caches : [num_users=2] = placeholder[target=b_layers_8_attention_kv_cache_past_v_caches]
2025-03-21T20:32:07.0034361Z   %b_layers_9_attention_kv_cache_past_k_caches : [num_users=2] = placeholder[target=b_layers_9_attention_kv_cache_past_k_caches]
2025-03-21T20:32:07.0035329Z   %b_layers_9_attention_kv_cache_past_v_caches : [num_users=2] = placeholder[target=b_layers_9_attention_kv_cache_past_v_caches]
2025-03-21T20:32:07.0036247Z   %b_layers_10_attention_kv_cache_past_k_caches : [num_users=2] = placeholder[target=b_layers_10_attention_kv_cache_past_k_caches]
2025-03-21T20:32:07.0037149Z   %b_layers_10_attention_kv_cache_past_v_caches : [num_users=2] = placeholder[target=b_layers_10_attention_kv_cache_past_v_caches]
2025-03-21T20:32:07.0038061Z   %b_layers_11_attention_kv_cache_past_k_caches : [num_users=2] = placeholder[target=b_layers_11_attention_kv_cache_past_k_caches]
2025-03-21T20:32:07.0038961Z   %b_layers_11_attention_kv_cache_past_v_caches : [num_users=2] = placeholder[target=b_layers_11_attention_kv_cache_past_v_caches]
2025-03-21T20:32:07.0039626Z   %tokens : [num_users=1] = placeholder[target=tokens]
2025-03-21T20:32:07.0040144Z   %attn_options_input_pos : [num_users=1] = placeholder[target=attn_options_input_pos]
2025-03-21T20:32:07.0040722Z   %lowered_module_0 : [num_users=1] = get_attr[target=lowered_module_0]
2025-03-21T20:32:07.0041135Z     backend_id: QnnBackend
2025-03-21T20:32:07.0041415Z     lowered graph():
2025-03-21T20:32:07.0041793Z       %b__frozen_param0 : [num_users=1] = placeholder[target=b__frozen_param0]
2025-03-21T20:32:07.0042329Z       %b__frozen_param1 : [num_users=1] = placeholder[target=b__frozen_param1]
2025-03-21T20:32:07.0042854Z       %b__frozen_param2 : [num_users=1] = placeholder[target=b__frozen_param2]
2025-03-21T20:32:07.0043472Z       %b__frozen_param3 : [num_users=1] = placeholder[target=b__frozen_param3]
2025-03-21T20:32:07.0044001Z       %b__frozen_param4 : [num_users=1] = placeholder[target=b__frozen_param4]
2025-03-21T20:32:07.0044594Z       %b__frozen_param5 : [num_users=1] = placeholder[target=b__frozen_param5]
2025-03-21T20:32:07.0045232Z       %b__frozen_param6 : [num_users=1] = placeholder[target=b__frozen_param6]
2025-03-21T20:32:07.0045759Z       %b__frozen_param7 : [num_users=1] = placeholder[target=b__frozen_param7]
2025-03-21T20:32:07.0046287Z       %b__frozen_param8 : [num_users=1] = placeholder[target=b__frozen_param8]
2025-03-21T20:32:07.0046801Z       %b__frozen_param9 : [num_users=1] = placeholder[target=b__frozen_param9]
2025-03-21T20:32:07.0047334Z       %b__frozen_param10 : [num_users=1] = placeholder[target=b__frozen_param10]
2025-03-21T20:32:07.0047873Z       %b__frozen_param11 : [num_users=1] = placeholder[target=b__frozen_param11]
2025-03-21T20:32:07.0048552Z       %b__frozen_param12 : [num_users=1] = placeholder[target=b__frozen_param12]
2025-03-21T20:32:07.0049106Z       %b__frozen_param13 : [num_users=1] = placeholder[target=b__frozen_param13]
2025-03-21T20:32:07.0049729Z       %b__frozen_param14 : [num_users=1] = placeholder[target=b__frozen_param14]
2025-03-21T20:32:07.0050290Z       %b__frozen_param15 : [num_users=1] = placeholder[target=b__frozen_param15]
2025-03-21T20:32:07.0050829Z       %b__frozen_param16 : [num_users=1] = placeholder[target=b__frozen_param16]
2025-03-21T20:32:07.0051418Z       %b__frozen_param17 : [num_users=1] = placeholder[target=b__frozen_param17]
2025-03-21T20:32:07.0051956Z       %b__frozen_param18 : [num_users=1] = placeholder[target=b__frozen_param18]
2025-03-21T20:32:07.0052491Z       %b__frozen_param19 : [num_users=1] = placeholder[target=b__frozen_param19]
2025-03-21T20:32:07.0053026Z       %b__frozen_param20 : [num_users=1] = placeholder[target=b__frozen_param20]
2025-03-21T20:32:07.0053623Z       %b__frozen_param21 : [num_users=1] = placeholder[target=b__frozen_param21]
2025-03-21T20:32:07.0054162Z       %b__frozen_param22 : [num_users=1] = placeholder[target=b__frozen_param22]
2025-03-21T20:32:07.0054697Z       %b__frozen_param23 : [num_users=1] = placeholder[target=b__frozen_param23]
2025-03-21T20:32:07.0055231Z       %b__frozen_param24 : [num_users=1] = placeholder[target=b__frozen_param24]
2025-03-21T20:32:07.0055771Z       %b__frozen_param25 : [num_users=1] = placeholder[target=b__frozen_param25]
2025-03-21T20:32:07.0056315Z       %b__frozen_param26 : [num_users=1] = placeholder[target=b__frozen_param26]
2025-03-21T20:32:07.0056839Z       %b__frozen_param27 : [num_users=1] = placeholder[target=b__frozen_param27]
2025-03-21T20:32:07.0057374Z       %b__frozen_param28 : [num_users=1] = placeholder[target=b__frozen_param28]
2025-03-21T20:32:07.0057909Z       %b__frozen_param29 : [num_users=1] = placeholder[target=b__frozen_param29]
2025-03-21T20:32:07.0058447Z       %b__frozen_param30 : [num_users=1] = placeholder[target=b__frozen_param30]
2025-03-21T20:32:07.0058986Z       %b__frozen_param31 : [num_users=1] = placeholder[target=b__frozen_param31]
2025-03-21T20:32:07.0059523Z       %b__frozen_param32 : [num_users=1] = placeholder[target=b__frozen_param32]
2025-03-21T20:32:07.0060044Z       %b__frozen_param33 : [num_users=1] = placeholder[target=b__frozen_param33]
2025-03-21T20:32:07.0060668Z       %b__frozen_param34 : [num_users=1] = placeholder[target=b__frozen_param34]
2025-03-21T20:32:07.0061202Z       %b__frozen_param35 : [num_users=1] = placeholder[target=b__frozen_param35]
2025-03-21T20:32:07.0061740Z       %b__frozen_param36 : [num_users=1] = placeholder[target=b__frozen_param36]
2025-03-21T20:32:07.0064746Z       %b__frozen_param37 : [num_users=1] = placeholder[target=b__frozen_param37]
2025-03-21T20:32:07.0065330Z       %b__frozen_param38 : [num_users=1] = placeholder[target=b__frozen_param38]
2025-03-21T20:32:07.0065876Z       %b__frozen_param39 : [num_users=1] = placeholder[target=b__frozen_param39]
2025-03-21T20:32:07.0066461Z       %b__frozen_param40 : [num_users=1] = placeholder[target=b__frozen_param40]
2025-03-21T20:32:07.0066996Z       %b__frozen_param41 : [num_users=1] = placeholder[target=b__frozen_param41]
2025-03-21T20:32:07.0067533Z       %b__frozen_param42 : [num_users=1] = placeholder[target=b__frozen_param42]
2025-03-21T20:32:07.0068119Z       %b__frozen_param43 : [num_users=1] = placeholder[target=b__frozen_param43]
2025-03-21T20:32:07.0068659Z       %b__frozen_param44 : [num_users=1] = placeholder[target=b__frozen_param44]
2025-03-21T20:32:07.0069213Z       %b__frozen_param45 : [num_users=1] = placeholder[target=b__frozen_param45]
2025-03-21T20:32:07.0069802Z       %b__frozen_param46 : [num_users=1] = placeholder[target=b__frozen_param46]
2025-03-21T20:32:07.0070373Z       %b__frozen_param47 : [num_users=1] = placeholder[target=b__frozen_param47]
2025-03-21T20:32:07.0070896Z       %b__frozen_param48 : [num_users=1] = placeholder[target=b__frozen_param48]
2025-03-21T20:32:07.0071430Z       %b__frozen_param49 : [num_users=1] = placeholder[target=b__frozen_param49]
2025-03-21T20:32:07.0071967Z       %b__frozen_param50 : [num_users=1] = placeholder[target=b__frozen_param50]
2025-03-21T20:32:07.0072499Z       %b__frozen_param51 : [num_users=1] = placeholder[target=b__frozen_param51]
2025-03-21T20:32:07.0073032Z       %b__frozen_param52 : [num_users=1] = placeholder[target=b__frozen_param52]
2025-03-21T20:32:07.0073574Z       %b__frozen_param53 : [num_users=1] = placeholder[target=b__frozen_param53]
2025-03-21T20:32:07.0074095Z       %b__frozen_param54 : [num_users=1] = placeholder[target=b__frozen_param54]
2025-03-21T20:32:07.0074630Z       %b__frozen_param55 : [num_users=1] = placeholder[target=b__frozen_param55]
2025-03-21T20:32:07.0075169Z       %b__frozen_param56 : [num_users=1] = placeholder[target=b__frozen_param56]
2025-03-21T20:32:07.0075707Z       %b__frozen_param57 : [num_users=1] = placeholder[target=b__frozen_param57]
2025-03-21T20:32:07.0076249Z       %b__frozen_param58 : [num_users=1] = placeholder[target=b__frozen_param58]
2025-03-21T20:32:07.0076789Z       %b__frozen_param59 : [num_users=1] = placeholder[target=b__frozen_param59]
2025-03-21T20:32:07.0077312Z       %b__frozen_param60 : [num_users=1] = placeholder[target=b__frozen_param60]
2025-03-21T20:32:07.0077846Z       %b__frozen_param61 : [num_users=1] = placeholder[target=b__frozen_param61]
2025-03-21T20:32:07.0078385Z       %b__frozen_param62 : [num_users=1] = placeholder[target=b__frozen_param62]
2025-03-21T20:32:07.0078920Z       %b__frozen_param63 : [num_users=1] = placeholder[target=b__frozen_param63]
2025-03-21T20:32:07.0079459Z       %b__frozen_param64 : [num_users=1] = placeholder[target=b__frozen_param64]
2025-03-21T20:32:07.0079995Z       %b__frozen_param65 : [num_users=1] = placeholder[target=b__frozen_param65]
2025-03-21T20:32:07.0080517Z       %b__frozen_param66 : [num_users=1] = placeholder[target=b__frozen_param66]
2025-03-21T20:32:07.0081052Z       %b__frozen_param67 : [num_users=1] = placeholder[target=b__frozen_param67]
2025-03-21T20:32:07.0081588Z       %b__frozen_param68 : [num_users=1] = placeholder[target=b__frozen_param68]
2025-03-21T20:32:07.0082123Z       %b__frozen_param69 : [num_users=1] = placeholder[target=b__frozen_param69]
2025-03-21T20:32:07.0082664Z       %b__frozen_param70 : [num_users=1] = placeholder[target=b__frozen_param70]
2025-03-21T20:32:07.0083205Z       %b__frozen_param71 : [num_users=1] = placeholder[target=b__frozen_param71]
2025-03-21T20:32:07.0083729Z       %b__frozen_param72 : [num_users=1] = placeholder[target=b__frozen_param72]
2025-03-21T20:32:07.0084272Z       %b__frozen_param73 : [num_users=1] = placeholder[target=b__frozen_param73]
2025-03-21T20:32:07.0084809Z       %b__frozen_param74 : [num_users=1] = placeholder[target=b__frozen_param74]
2025-03-21T20:32:07.0085438Z       %b__frozen_param75 : [num_users=1] = placeholder[target=b__frozen_param75]
2025-03-21T20:32:07.0086035Z       %b__frozen_param76 : [num_users=1] = placeholder[target=b__frozen_param76]
2025-03-21T20:32:07.0086575Z       %b__frozen_param77 : [num_users=1] = placeholder[target=b__frozen_param77]
2025-03-21T20:32:07.0087135Z       %b__frozen_param78 : [num_users=1] = placeholder[target=b__frozen_param78]
2025-03-21T20:32:07.0087678Z       %b__frozen_param79 : [num_users=1] = placeholder[target=b__frozen_param79]
2025-03-21T20:32:07.0088249Z       %b__frozen_param80 : [num_users=1] = placeholder[target=b__frozen_param80]
2025-03-21T20:32:07.0088824Z       %b__frozen_param81 : [num_users=1] = placeholder[target=b__frozen_param81]
2025-03-21T20:32:07.0089449Z       %b__frozen_param82 : [num_users=1] = placeholder[target=b__frozen_param82]
2025-03-21T20:32:07.0089989Z       %b__frozen_param83 : [num_users=1] = placeholder[target=b__frozen_param83]
2025-03-21T20:32:07.0090523Z       %b__frozen_param84 : [num_users=1] = placeholder[target=b__frozen_param84]
2025-03-21T20:32:07.0091066Z       %b__frozen_param85 : [num_users=1] = placeholder[target=b__frozen_param85]
2025-03-21T20:32:07.0091610Z       %b__frozen_param86 : [num_users=1] = placeholder[target=b__frozen_param86]
2025-03-21T20:32:07.0092159Z       %b__frozen_param87 : [num_users=1] = placeholder[target=b__frozen_param87]
2025-03-21T20:32:07.0092697Z       %b__frozen_param88 : [num_users=1] = placeholder[target=b__frozen_param88]
2025-03-21T20:32:07.0093236Z       %b__frozen_param89 : [num_users=1] = placeholder[target=b__frozen_param89]
2025-03-21T20:32:07.0093762Z       %b__frozen_param90 : [num_users=1] = placeholder[target=b__frozen_param90]
2025-03-21T20:32:07.0094298Z       %b__frozen_param91 : [num_users=1] = placeholder[target=b__frozen_param91]
2025-03-21T20:32:07.0094832Z       %b__frozen_param92 : [num_users=1] = placeholder[target=b__frozen_param92]
2025-03-21T20:32:07.0095413Z       %b__frozen_param93 : [num_users=1] = placeholder[target=b__frozen_param93]
2025-03-21T20:32:07.0095951Z       %b__frozen_param94 : [num_users=1] = placeholder[target=b__frozen_param94]
2025-03-21T20:32:07.0096487Z       %b__frozen_param95 : [num_users=1] = placeholder[target=b__frozen_param95]
2025-03-21T20:32:07.0097010Z       %b__frozen_param96 : [num_users=1] = placeholder[target=b__frozen_param96]
2025-03-21T20:32:07.0097546Z       %b__frozen_param97 : [num_users=1] = placeholder[target=b__frozen_param97]
2025-03-21T20:32:07.0098082Z       %b__frozen_param98 : [num_users=1] = placeholder[target=b__frozen_param98]
2025-03-21T20:32:07.0098655Z       %b__frozen_param99 : [num_users=1] = placeholder[target=b__frozen_param99]
2025-03-21T20:32:07.0099201Z       %b__frozen_param100 : [num_users=1] = placeholder[target=b__frozen_param100]
2025-03-21T20:32:07.0099754Z       %b__frozen_param101 : [num_users=1] = placeholder[target=b__frozen_param101]
2025-03-21T20:32:07.0100304Z       %b__frozen_param102 : [num_users=1] = placeholder[target=b__frozen_param102]
2025-03-21T20:32:07.0100858Z       %b__frozen_param103 : [num_users=1] = placeholder[target=b__frozen_param103]
2025-03-21T20:32:07.0101410Z       %b__frozen_param104 : [num_users=1] = placeholder[target=b__frozen_param104]
2025-03-21T20:32:07.0101962Z       %b__frozen_param105 : [num_users=1] = placeholder[target=b__frozen_param105]
2025-03-21T20:32:07.0102513Z       %b__frozen_param106 : [num_users=1] = placeholder[target=b__frozen_param106]
2025-03-21T20:32:07.0103050Z       %b__frozen_param107 : [num_users=1] = placeholder[target=b__frozen_param107]
2025-03-21T20:32:07.0103600Z       %b__frozen_param108 : [num_users=1] = placeholder[target=b__frozen_param108]
2025-03-21T20:32:07.0104157Z       %b__frozen_param109 : [num_users=1] = placeholder[target=b__frozen_param109]
2025-03-21T20:32:07.0104749Z       %b__frozen_param110 : [num_users=1] = placeholder[target=b__frozen_param110]
2025-03-21T20:32:07.0105372Z       %b__frozen_param111 : [num_users=1] = placeholder[target=b__frozen_param111]
2025-03-21T20:32:07.0105994Z       %b__frozen_param112 : [num_users=1] = placeholder[target=b__frozen_param112]
2025-03-21T20:32:07.0106538Z       %b__frozen_param113 : [num_users=0] = placeholder[target=b__frozen_param113]
2025-03-21T20:32:07.0107096Z       %b__frozen_param114 : [num_users=0] = placeholder[target=b__frozen_param114]
2025-03-21T20:32:07.0107686Z       %b__frozen_param115 : [num_users=1] = placeholder[target=b__frozen_param115]
2025-03-21T20:32:07.0108239Z       %b__frozen_param116 : [num_users=0] = placeholder[target=b__frozen_param116]
2025-03-21T20:32:07.0108814Z       %b__frozen_param117 : [num_users=0] = placeholder[target=b__frozen_param117]
2025-03-21T20:32:07.0109396Z       %b__frozen_param118 : [num_users=1] = placeholder[target=b__frozen_param118]
2025-03-21T20:32:07.0109932Z       %b__frozen_param119 : [num_users=0] = placeholder[target=b__frozen_param119]
2025-03-21T20:32:07.0110480Z       %b__frozen_param120 : [num_users=0] = placeholder[target=b__frozen_param120]
2025-03-21T20:32:07.0111034Z       %b__frozen_param121 : [num_users=1] = placeholder[target=b__frozen_param121]
2025-03-21T20:32:07.0111589Z       %b__frozen_param122 : [num_users=0] = placeholder[target=b__frozen_param122]
2025-03-21T20:32:07.0112142Z       %b__frozen_param123 : [num_users=0] = placeholder[target=b__frozen_param123]
2025-03-21T20:32:07.0112692Z       %b__frozen_param124 : [num_users=1] = placeholder[target=b__frozen_param124]
2025-03-21T20:32:07.0113231Z       %b__frozen_param125 : [num_users=0] = placeholder[target=b__frozen_param125]
2025-03-21T20:32:07.0113783Z       %b__frozen_param126 : [num_users=0] = placeholder[target=b__frozen_param126]
2025-03-21T20:32:07.0114384Z       %b__frozen_param127 : [num_users=1] = placeholder[target=b__frozen_param127]
2025-03-21T20:32:07.0114935Z       %b__frozen_param128 : [num_users=0] = placeholder[target=b__frozen_param128]
2025-03-21T20:32:07.0115484Z       %b__frozen_param129 : [num_users=0] = placeholder[target=b__frozen_param129]
2025-03-21T20:32:07.0116037Z       %b__frozen_param130 : [num_users=1] = placeholder[target=b__frozen_param130]
2025-03-21T20:32:07.0116576Z       %b__frozen_param131 : [num_users=0] = placeholder[target=b__frozen_param131]
2025-03-21T20:32:07.0117130Z       %b__frozen_param132 : [num_users=0] = placeholder[target=b__frozen_param132]
2025-03-21T20:32:07.0117681Z       %b__frozen_param133 : [num_users=1] = placeholder[target=b__frozen_param133]
2025-03-21T20:32:07.0118229Z       %b__frozen_param134 : [num_users=0] = placeholder[target=b__frozen_param134]
2025-03-21T20:32:07.0118777Z       %b__frozen_param135 : [num_users=0] = placeholder[target=b__frozen_param135]
2025-03-21T20:32:07.0119329Z       %b__frozen_param136 : [num_users=1] = placeholder[target=b__frozen_param136]
2025-03-21T20:32:07.0119869Z       %b__frozen_param137 : [num_users=0] = placeholder[target=b__frozen_param137]
2025-03-21T20:32:07.0120415Z       %b__frozen_param138 : [num_users=0] = placeholder[target=b__frozen_param138]
2025-03-21T20:32:07.0120964Z       %b__frozen_param139 : [num_users=1] = placeholder[target=b__frozen_param139]
2025-03-21T20:32:07.0121515Z       %b__frozen_param140 : [num_users=0] = placeholder[target=b__frozen_param140]
2025-03-21T20:32:07.0122066Z       %b__frozen_param141 : [num_users=0] = placeholder[target=b__frozen_param141]
2025-03-21T20:32:07.0122618Z       %b__frozen_param142 : [num_users=1] = placeholder[target=b__frozen_param142]
2025-03-21T20:32:07.0123156Z       %b__frozen_param143 : [num_users=0] = placeholder[target=b__frozen_param143]
2025-03-21T20:32:07.0123706Z       %b__frozen_param144 : [num_users=0] = placeholder[target=b__frozen_param144]
2025-03-21T20:32:07.0124259Z       %b__frozen_param145 : [num_users=1] = placeholder[target=b__frozen_param145]
2025-03-21T20:32:07.0124815Z       %b__frozen_param146 : [num_users=0] = placeholder[target=b__frozen_param146]
2025-03-21T20:32:07.0125367Z       %b__frozen_param147 : [num_users=0] = placeholder[target=b__frozen_param147]
2025-03-21T20:32:07.0125961Z       %b__frozen_param148 : [num_users=1] = placeholder[target=b__frozen_param148]
2025-03-21T20:32:07.0126500Z       %b__frozen_param149 : [num_users=1] = placeholder[target=b__frozen_param149]
2025-03-21T20:32:07.0127050Z       %b__frozen_param150 : [num_users=1] = placeholder[target=b__frozen_param150]
2025-03-21T20:32:07.0127696Z       %b__frozen_param151 : [num_users=1] = placeholder[target=b__frozen_param151]
2025-03-21T20:32:07.0128244Z       %b__frozen_param152 : [num_users=1] = placeholder[target=b__frozen_param152]
2025-03-21T20:32:07.0128792Z       %b__frozen_param153 : [num_users=1] = placeholder[target=b__frozen_param153]
2025-03-21T20:32:07.0129471Z       %b__frozen_param154 : [num_users=1] = placeholder[target=b__frozen_param154]
2025-03-21T20:32:07.0130009Z       %b__frozen_param155 : [num_users=1] = placeholder[target=b__frozen_param155]
2025-03-21T20:32:07.0130563Z       %b__frozen_param156 : [num_users=1] = placeholder[target=b__frozen_param156]
2025-03-21T20:32:07.0131115Z       %b__frozen_param157 : [num_users=1] = placeholder[target=b__frozen_param157]
2025-03-21T20:32:07.0131678Z       %b__frozen_param158 : [num_users=1] = placeholder[target=b__frozen_param158]
2025-03-21T20:32:07.0132386Z       %b__frozen_param159 : [num_users=1] = placeholder[target=b__frozen_param159]
2025-03-21T20:32:07.0132969Z       %b__frozen_param160 : [num_users=1] = placeholder[target=b__frozen_param160]
2025-03-21T20:32:07.0133692Z       %b_layers_0_attention_kv_cache_past_v_caches : [num_users=1] = placeholder[target=b_layers_0_attention_kv_cache_past_v_caches]
2025-03-21T20:32:07.0134598Z       %b_layers_0_attention_kv_cache_past_k_caches : [num_users=1] = placeholder[target=b_layers_0_attention_kv_cache_past_k_caches]
2025-03-21T20:32:07.0135501Z       %b_layers_1_attention_kv_cache_past_v_caches : [num_users=1] = placeholder[target=b_layers_1_attention_kv_cache_past_v_caches]
2025-03-21T20:32:07.0136399Z       %b_layers_1_attention_kv_cache_past_k_caches : [num_users=1] = placeholder[target=b_layers_1_attention_kv_cache_past_k_caches]
2025-03-21T20:32:07.0137299Z       %b_layers_2_attention_kv_cache_past_v_caches : [num_users=1] = placeholder[target=b_layers_2_attention_kv_cache_past_v_caches]
2025-03-21T20:32:07.0138192Z       %b_layers_2_attention_kv_cache_past_k_caches : [num_users=1] = placeholder[target=b_layers_2_attention_kv_cache_past_k_caches]
2025-03-21T20:32:07.0139134Z       %b_layers_3_attention_kv_cache_past_v_caches : [num_users=1] = placeholder[target=b_layers_3_attention_kv_cache_past_v_caches]
2025-03-21T20:32:07.0140035Z       %b_layers_3_attention_kv_cache_past_k_caches : [num_users=1] = placeholder[target=b_layers_3_attention_kv_cache_past_k_caches]
2025-03-21T20:32:07.0140918Z       %b_layers_4_attention_kv_cache_past_v_caches : [num_users=1] = placeholder[target=b_layers_4_attention_kv_cache_past_v_caches]
2025-03-21T20:32:07.0141814Z       %b_layers_4_attention_kv_cache_past_k_caches : [num_users=1] = placeholder[target=b_layers_4_attention_kv_cache_past_k_caches]
2025-03-21T20:32:07.0142716Z       %b_layers_5_attention_kv_cache_past_v_caches : [num_users=1] = placeholder[target=b_layers_5_attention_kv_cache_past_v_caches]
2025-03-21T20:32:07.0143612Z       %b_layers_5_attention_kv_cache_past_k_caches : [num_users=1] = placeholder[target=b_layers_5_attention_kv_cache_past_k_caches]
2025-03-21T20:32:07.0144504Z       %b_layers_6_attention_kv_cache_past_v_caches : [num_users=1] = placeholder[target=b_layers_6_attention_kv_cache_past_v_caches]
2025-03-21T20:32:07.0145399Z       %b_layers_6_attention_kv_cache_past_k_caches : [num_users=1] = placeholder[target=b_layers_6_attention_kv_cache_past_k_caches]
2025-03-21T20:32:07.0146297Z       %b_layers_7_attention_kv_cache_past_v_caches : [num_users=1] = placeholder[target=b_layers_7_attention_kv_cache_past_v_caches]
2025-03-21T20:32:07.0147223Z       %b_layers_7_attention_kv_cache_past_k_caches : [num_users=1] = placeholder[target=b_layers_7_attention_kv_cache_past_k_caches]
2025-03-21T20:32:07.0148178Z       %b_layers_8_attention_kv_cache_past_v_caches : [num_users=1] = placeholder[target=b_layers_8_attention_kv_cache_past_v_caches]
2025-03-21T20:32:07.0149074Z       %b_layers_8_attention_kv_cache_past_k_caches : [num_users=1] = placeholder[target=b_layers_8_attention_kv_cache_past_k_caches]
2025-03-21T20:32:07.0149965Z       %b_layers_9_attention_kv_cache_past_v_caches : [num_users=1] = placeholder[target=b_layers_9_attention_kv_cache_past_v_caches]
2025-03-21T20:32:07.0150895Z       %b_layers_9_attention_kv_cache_past_k_caches : [num_users=1] = placeholder[target=b_layers_9_attention_kv_cache_past_k_caches]
2025-03-21T20:32:07.0151836Z       %b_layers_10_attention_kv_cache_past_v_caches : [num_users=1] = placeholder[target=b_layers_10_attention_kv_cache_past_v_caches]
2025-03-21T20:32:07.0152778Z       %b_layers_10_attention_kv_cache_past_k_caches : [num_users=1] = placeholder[target=b_layers_10_attention_kv_cache_past_k_caches]
2025-03-21T20:32:07.0153674Z       %b_layers_11_attention_kv_cache_past_v_caches : [num_users=1] = placeholder[target=b_layers_11_attention_kv_cache_past_v_caches]
2025-03-21T20:32:07.0154560Z       %b_layers_11_attention_kv_cache_past_k_caches : [num_users=1] = placeholder[target=b_layers_11_attention_kv_cache_past_k_caches]
2025-03-21T20:32:07.0155224Z       %tokens : [num_users=1] = placeholder[target=tokens]
2025-03-21T20:32:07.0155739Z       %attn_options_input_pos : [num_users=1] = placeholder[target=attn_options_input_pos]
2025-03-21T20:32:07.0156668Z       %aten__to_copy_default : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten._to_copy.default](args = (%tokens,), kwargs = {dtype: torch.int32})
2025-03-21T20:32:07.0157959Z       %aten__to_copy_default_1 : [num_users=38] = call_function[target=executorch.exir.dialects.edge._ops.aten._to_copy.default](args = (%attn_options_input_pos,), kwargs = {dtype: torch.int32})
2025-03-21T20:32:07.0159320Z       %aten_embedding_default : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.embedding.default](args = (%b__frozen_param0, %aten__to_copy_default), kwargs = {})
2025-03-21T20:32:07.0160673Z       %aten_index_tensor : [num_users=12] = call_function[target=executorch.exir.dialects.edge._ops.aten.index.Tensor](args = (%b__frozen_param111, [%aten__to_copy_default_1]), kwargs = {})
2025-03-21T20:32:07.0161994Z       %aten_index_tensor_1 : [num_users=12] = call_function[target=executorch.exir.dialects.edge._ops.aten.index.Tensor](args = (%b__frozen_param112, [%aten__to_copy_default_1]), kwargs = {})
2025-03-21T20:32:07.0163319Z       %aten_index_tensor_2 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.index.Tensor](args = (%b__frozen_param115, [%aten__to_copy_default_1]), kwargs = {})
2025-03-21T20:32:07.0165032Z       %aten_index_tensor_3 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.index.Tensor](args = (%b__frozen_param118, [%aten__to_copy_default_1]), kwargs = {})
2025-03-21T20:32:07.0166410Z       %aten_index_tensor_4 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.index.Tensor](args = (%b__frozen_param121, [%aten__to_copy_default_1]), kwargs = {})
2025-03-21T20:32:07.0167728Z       %aten_index_tensor_5 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.index.Tensor](args = (%b__frozen_param124, [%aten__to_copy_default_1]), kwargs = {})
2025-03-21T20:32:07.0169104Z       %aten_index_tensor_6 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.index.Tensor](args = (%b__frozen_param127, [%aten__to_copy_default_1]), kwargs = {})
2025-03-21T20:32:07.0170510Z       %aten_index_tensor_7 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.index.Tensor](args = (%b__frozen_param130, [%aten__to_copy_default_1]), kwargs = {})
2025-03-21T20:32:07.0171828Z       %aten_index_tensor_8 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.index.Tensor](args = (%b__frozen_param133, [%aten__to_copy_default_1]), kwargs = {})
2025-03-21T20:32:07.0173197Z       %aten_index_tensor_9 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.index.Tensor](args = (%b__frozen_param136, [%aten__to_copy_default_1]), kwargs = {})
2025-03-21T20:32:07.0174523Z       %aten_index_tensor_10 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.index.Tensor](args = (%b__frozen_param139, [%aten__to_copy_default_1]), kwargs = {})
2025-03-21T20:32:07.0175877Z       %aten_index_tensor_11 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.index.Tensor](args = (%b__frozen_param142, [%aten__to_copy_default_1]), kwargs = {})
2025-03-21T20:32:07.0177254Z       %aten_index_tensor_12 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.index.Tensor](args = (%b__frozen_param145, [%aten__to_copy_default_1]), kwargs = {})
2025-03-21T20:32:07.0178576Z       %aten_index_tensor_13 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.index.Tensor](args = (%b__frozen_param148, [%aten__to_copy_default_1]), kwargs = {})
2025-03-21T20:32:07.0179992Z       %aten_rms_norm_default : [num_users=3] = call_function[target=executorch.exir.dialects.edge._ops.aten.rms_norm.default](args = (%aten_embedding_default, [768], %b__frozen_param1, 9.999999747378752e-06), kwargs = {})
2025-03-21T20:32:07.0181379Z       %aten_view_copy_default_5 : [num_users=4] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_index_tensor, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:32:07.0182677Z       %aten_view_copy_default_23 : [num_users=4] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_index_tensor, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:32:07.0183971Z       %aten_view_copy_default_41 : [num_users=4] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_index_tensor, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:32:07.0185261Z       %aten_view_copy_default_59 : [num_users=4] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_index_tensor, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:32:07.0186551Z       %aten_view_copy_default_77 : [num_users=4] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_index_tensor, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:32:07.0187844Z       %aten_view_copy_default_95 : [num_users=4] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_index_tensor, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:32:07.0189146Z       %aten_view_copy_default_113 : [num_users=4] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_index_tensor, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:32:07.0190446Z       %aten_view_copy_default_131 : [num_users=4] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_index_tensor, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:32:07.0191750Z       %aten_view_copy_default_149 : [num_users=4] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_index_tensor, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:32:07.0193045Z       %aten_view_copy_default_167 : [num_users=4] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_index_tensor, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:32:07.0194344Z       %aten_view_copy_default_185 : [num_users=4] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_index_tensor, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:32:07.0195633Z       %aten_view_copy_default_203 : [num_users=4] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_index_tensor, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:32:07.0196934Z       %aten_view_copy_default_6 : [num_users=4] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_index_tensor_1, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:32:07.0198263Z       %aten_view_copy_default_24 : [num_users=4] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_index_tensor_1, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:32:07.0199589Z       %aten_view_copy_default_42 : [num_users=4] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_index_tensor_1, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:32:07.0200909Z       %aten_view_copy_default_60 : [num_users=4] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_index_tensor_1, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:32:07.0202230Z       %aten_view_copy_default_78 : [num_users=4] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_index_tensor_1, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:32:07.0203531Z       %aten_view_copy_default_96 : [num_users=4] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_index_tensor_1, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:32:07.0204837Z       %aten_view_copy_default_114 : [num_users=4] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_index_tensor_1, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:32:07.0206223Z       %aten_view_copy_default_132 : [num_users=4] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_index_tensor_1, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:32:07.0207532Z       %aten_view_copy_default_150 : [num_users=4] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_index_tensor_1, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:32:07.0208843Z       %aten_view_copy_default_168 : [num_users=4] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_index_tensor_1, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:32:07.0210200Z       %aten_view_copy_default_186 : [num_users=4] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_index_tensor_1, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:32:07.0211516Z       %aten_view_copy_default_204 : [num_users=4] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_index_tensor_1, [1, 1, 1, 32]), kwargs = {})
2025-03-21T20:32:07.0212859Z       %aten_unsqueeze_copy_default : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default, -1), kwargs = {})
2025-03-21T20:32:07.0214218Z       %aten_unsqueeze_copy_default_1 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default, -1), kwargs = {})
2025-03-21T20:32:07.0215575Z       %aten_unsqueeze_copy_default_2 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default, -1), kwargs = {})
2025-03-21T20:32:07.0216965Z       %aten_permute_copy_default : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0218394Z       %aten_permute_copy_default_2 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_1, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0219828Z       %aten_permute_copy_default_4 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_2, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0221405Z       %aten_convolution_default : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default, %b__frozen_param2, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.0223199Z       %aten_convolution_default_1 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_2, %b__frozen_param3, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.0224948Z       %aten_convolution_default_2 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_4, %b__frozen_param4, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.0226533Z       %aten_permute_copy_default_1 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0227964Z       %aten_permute_copy_default_3 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_1, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0229357Z       %aten_permute_copy_default_5 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_2, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0230716Z       %aten_squeeze_copy_dims : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_1, [-1]), kwargs = {})
2025-03-21T20:32:07.0232022Z       %aten_squeeze_copy_dims_1 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_3, [-1]), kwargs = {})
2025-03-21T20:32:07.0233508Z       %aten_squeeze_copy_dims_2 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_5, [-1]), kwargs = {})
2025-03-21T20:32:07.0234829Z       %aten_view_copy_default : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_squeeze_copy_dims, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.0236159Z       %aten_view_copy_default_1 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_squeeze_copy_dims_1, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.0237500Z       %aten_view_copy_default_2 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_squeeze_copy_dims_2, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.0238857Z       %aten_view_copy_default_3 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_view_copy_default, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:32:07.0240211Z       %aten_view_copy_default_4 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_view_copy_default_1, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:32:07.0241786Z       %aten_index_put_default_1 : [num_users=13] = call_function[target=executorch.exir.dialects.edge._ops.aten.index_put.default](args = (%b_layers_0_attention_kv_cache_past_v_caches, [None, %aten__to_copy_default_1], %aten_view_copy_default_2), kwargs = {})
2025-03-21T20:32:07.0243333Z       %aten_slice_copy_tensor : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_3, 4, 0, 1), kwargs = {})
2025-03-21T20:32:07.0244643Z       %aten_slice_copy_tensor_1 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_3, 4, 1, 2), kwargs = {})
2025-03-21T20:32:07.0245938Z       %aten_slice_copy_tensor_2 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_4, 4, 0, 1), kwargs = {})
2025-03-21T20:32:07.0247310Z       %aten_slice_copy_tensor_3 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_4, 4, 1, 2), kwargs = {})
2025-03-21T20:32:07.0248662Z       %aten_permute_copy_default_19 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_1, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0250174Z       %aten_permute_copy_default_20 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_1, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0251615Z       %aten_permute_copy_default_21 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_1, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0253045Z       %aten_permute_copy_default_22 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_1, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0254444Z       %aten_permute_copy_default_23 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_1, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0255834Z       %aten_permute_copy_default_24 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_1, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0257226Z       %aten_permute_copy_default_25 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_1, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0258620Z       %aten_permute_copy_default_26 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_1, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0260011Z       %aten_permute_copy_default_27 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_1, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0261404Z       %aten_permute_copy_default_28 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_1, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0262782Z       %aten_permute_copy_default_29 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_1, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0264174Z       %aten_permute_copy_default_30 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_1, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0265509Z       %aten_squeeze_copy_dims_3 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor, [4]), kwargs = {})
2025-03-21T20:32:07.0266787Z       %aten_squeeze_copy_dims_4 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_1, [4]), kwargs = {})
2025-03-21T20:32:07.0268068Z       %aten_squeeze_copy_dims_5 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_2, [4]), kwargs = {})
2025-03-21T20:32:07.0269350Z       %aten_squeeze_copy_dims_6 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_3, [4]), kwargs = {})
2025-03-21T20:32:07.0270627Z       %aten_select_copy_int_24 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_19, 0, 0), kwargs = {})
2025-03-21T20:32:07.0271903Z       %aten_select_copy_int_26 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_20, 0, 0), kwargs = {})
2025-03-21T20:32:07.0273203Z       %aten_select_copy_int_28 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_21, 0, 0), kwargs = {})
2025-03-21T20:32:07.0274469Z       %aten_select_copy_int_30 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_22, 0, 0), kwargs = {})
2025-03-21T20:32:07.0275767Z       %aten_select_copy_int_32 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_23, 0, 0), kwargs = {})
2025-03-21T20:32:07.0277074Z       %aten_select_copy_int_34 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_24, 0, 0), kwargs = {})
2025-03-21T20:32:07.0278347Z       %aten_select_copy_int_36 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_25, 0, 0), kwargs = {})
2025-03-21T20:32:07.0279620Z       %aten_select_copy_int_38 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_26, 0, 0), kwargs = {})
2025-03-21T20:32:07.0280894Z       %aten_select_copy_int_40 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_27, 0, 0), kwargs = {})
2025-03-21T20:32:07.0282170Z       %aten_select_copy_int_42 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_28, 0, 0), kwargs = {})
2025-03-21T20:32:07.0283439Z       %aten_select_copy_int_44 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_29, 0, 0), kwargs = {})
2025-03-21T20:32:07.0284709Z       %aten_select_copy_int_46 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_30, 0, 0), kwargs = {})
2025-03-21T20:32:07.0286006Z       %aten_mul_tensor_2 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_3, %aten_view_copy_default_5), kwargs = {})
2025-03-21T20:32:07.0287324Z       %aten_mul_tensor_4 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_3, %aten_view_copy_default_6), kwargs = {})
2025-03-21T20:32:07.0288640Z       %aten_mul_tensor_3 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_4, %aten_view_copy_default_6), kwargs = {})
2025-03-21T20:32:07.0290028Z       %aten_mul_tensor_5 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_4, %aten_view_copy_default_5), kwargs = {})
2025-03-21T20:32:07.0291348Z       %aten_mul_tensor_6 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_5, %aten_view_copy_default_5), kwargs = {})
2025-03-21T20:32:07.0292649Z       %aten_mul_tensor_8 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_5, %aten_view_copy_default_6), kwargs = {})
2025-03-21T20:32:07.0293976Z       %aten_mul_tensor_7 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_6, %aten_view_copy_default_6), kwargs = {})
2025-03-21T20:32:07.0295303Z       %aten_mul_tensor_9 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_6, %aten_view_copy_default_5), kwargs = {})
2025-03-21T20:32:07.0296585Z       %aten_select_copy_int_25 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_24, 0, 0), kwargs = {})
2025-03-21T20:32:07.0297861Z       %aten_select_copy_int_27 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_26, 0, 1), kwargs = {})
2025-03-21T20:32:07.0299105Z       %aten_select_copy_int_29 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_28, 0, 2), kwargs = {})
2025-03-21T20:32:07.0300372Z       %aten_select_copy_int_31 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_30, 0, 3), kwargs = {})
2025-03-21T20:32:07.0301676Z       %aten_select_copy_int_33 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_32, 0, 4), kwargs = {})
2025-03-21T20:32:07.0302917Z       %aten_select_copy_int_35 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_34, 0, 5), kwargs = {})
2025-03-21T20:32:07.0304157Z       %aten_select_copy_int_37 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_36, 0, 6), kwargs = {})
2025-03-21T20:32:07.0305384Z       %aten_select_copy_int_39 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_38, 0, 7), kwargs = {})
2025-03-21T20:32:07.0306712Z       %aten_select_copy_int_41 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_40, 0, 8), kwargs = {})
2025-03-21T20:32:07.0308013Z       %aten_select_copy_int_43 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_42, 0, 9), kwargs = {})
2025-03-21T20:32:07.0309257Z       %aten_select_copy_int_45 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_44, 0, 10), kwargs = {})
2025-03-21T20:32:07.0310501Z       %aten_select_copy_int_47 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_46, 0, 11), kwargs = {})
2025-03-21T20:32:07.0311736Z       %aten_sub_tensor : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.sub.Tensor](args = (%aten_mul_tensor_2, %aten_mul_tensor_3), kwargs = {})
2025-03-21T20:32:07.0312954Z       %aten_add_tensor : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_mul_tensor_4, %aten_mul_tensor_5), kwargs = {})
2025-03-21T20:32:07.0314172Z       %aten_sub_tensor_1 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.sub.Tensor](args = (%aten_mul_tensor_6, %aten_mul_tensor_7), kwargs = {})
2025-03-21T20:32:07.0315397Z       %aten_add_tensor_1 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_mul_tensor_8, %aten_mul_tensor_9), kwargs = {})
2025-03-21T20:32:07.0317455Z       %aten_cat_default_3 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_select_copy_int_25, %aten_select_copy_int_27, %aten_select_copy_int_29, %aten_select_copy_int_31, %aten_select_copy_int_33, %aten_select_copy_int_35, %aten_select_copy_int_37, %aten_select_copy_int_39, %aten_select_copy_int_41, %aten_select_copy_int_43, %aten_select_copy_int_45, %aten_select_copy_int_47],), kwargs = {})
2025-03-21T20:32:07.0319567Z       %aten_unsqueeze_copy_default_3 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_sub_tensor, 4), kwargs = {})
2025-03-21T20:32:07.0320887Z       %aten_unsqueeze_copy_default_4 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_add_tensor, 4), kwargs = {})
2025-03-21T20:32:07.0322239Z       %aten_unsqueeze_copy_default_5 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_sub_tensor_1, 4), kwargs = {})
2025-03-21T20:32:07.0323554Z       %aten_unsqueeze_copy_default_6 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_add_tensor_1, 4), kwargs = {})
2025-03-21T20:32:07.0324902Z       %aten_view_copy_default_10 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_3, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:32:07.0326339Z       %aten_cat_default : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_unsqueeze_copy_default_3, %aten_unsqueeze_copy_default_4], -1), kwargs = {})
2025-03-21T20:32:07.0327785Z       %aten_cat_default_1 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_unsqueeze_copy_default_5, %aten_unsqueeze_copy_default_6], -1), kwargs = {})
2025-03-21T20:32:07.0329158Z       %aten_view_copy_default_7 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.0330521Z       %aten_view_copy_default_8 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_1, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.0331872Z       %aten_permute_copy_default_6 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_view_copy_default_7, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0333644Z       %aten_index_put_default : [num_users=13] = call_function[target=executorch.exir.dialects.edge._ops.aten.index_put.default](args = (%b_layers_0_attention_kv_cache_past_k_caches, [None, %aten__to_copy_default_1], %aten_view_copy_default_8), kwargs = {})
2025-03-21T20:32:07.0335223Z       %aten_permute_copy_default_7 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0336602Z       %aten_permute_copy_default_8 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0337985Z       %aten_permute_copy_default_9 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0339361Z       %aten_permute_copy_default_10 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0340727Z       %aten_permute_copy_default_11 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0342102Z       %aten_permute_copy_default_12 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0343479Z       %aten_permute_copy_default_13 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0344857Z       %aten_permute_copy_default_14 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0346232Z       %aten_permute_copy_default_15 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0347675Z       %aten_permute_copy_default_16 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0349048Z       %aten_permute_copy_default_17 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0350509Z       %aten_permute_copy_default_18 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0351863Z       %aten_select_copy_int : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_7, 0, 0), kwargs = {})
2025-03-21T20:32:07.0353128Z       %aten_select_copy_int_2 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_8, 0, 0), kwargs = {})
2025-03-21T20:32:07.0354388Z       %aten_select_copy_int_4 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_9, 0, 0), kwargs = {})
2025-03-21T20:32:07.0355666Z       %aten_select_copy_int_6 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_10, 0, 0), kwargs = {})
2025-03-21T20:32:07.0356991Z       %aten_select_copy_int_8 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_11, 0, 0), kwargs = {})
2025-03-21T20:32:07.0358264Z       %aten_select_copy_int_10 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_12, 0, 0), kwargs = {})
2025-03-21T20:32:07.0359542Z       %aten_select_copy_int_12 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_13, 0, 0), kwargs = {})
2025-03-21T20:32:07.0360815Z       %aten_select_copy_int_14 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_14, 0, 0), kwargs = {})
2025-03-21T20:32:07.0362095Z       %aten_select_copy_int_16 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_15, 0, 0), kwargs = {})
2025-03-21T20:32:07.0363375Z       %aten_select_copy_int_18 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_16, 0, 0), kwargs = {})
2025-03-21T20:32:07.0364661Z       %aten_select_copy_int_20 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_17, 0, 0), kwargs = {})
2025-03-21T20:32:07.0365943Z       %aten_select_copy_int_22 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_18, 0, 0), kwargs = {})
2025-03-21T20:32:07.0367196Z       %aten_select_copy_int_1 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int, 0, 0), kwargs = {})
2025-03-21T20:32:07.0368439Z       %aten_select_copy_int_3 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_2, 0, 1), kwargs = {})
2025-03-21T20:32:07.0369725Z       %aten_select_copy_int_5 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_4, 0, 2), kwargs = {})
2025-03-21T20:32:07.0370965Z       %aten_select_copy_int_7 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_6, 0, 3), kwargs = {})
2025-03-21T20:32:07.0372234Z       %aten_select_copy_int_9 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_8, 0, 4), kwargs = {})
2025-03-21T20:32:07.0373471Z       %aten_select_copy_int_11 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_10, 0, 5), kwargs = {})
2025-03-21T20:32:07.0374742Z       %aten_select_copy_int_13 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_12, 0, 6), kwargs = {})
2025-03-21T20:32:07.0376026Z       %aten_select_copy_int_15 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_14, 0, 7), kwargs = {})
2025-03-21T20:32:07.0377262Z       %aten_select_copy_int_17 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_16, 0, 8), kwargs = {})
2025-03-21T20:32:07.0378507Z       %aten_select_copy_int_19 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_18, 0, 9), kwargs = {})
2025-03-21T20:32:07.0379747Z       %aten_select_copy_int_21 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_20, 0, 10), kwargs = {})
2025-03-21T20:32:07.0380997Z       %aten_select_copy_int_23 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_22, 0, 11), kwargs = {})
2025-03-21T20:32:07.0383061Z       %aten_cat_default_2 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_select_copy_int_1, %aten_select_copy_int_3, %aten_select_copy_int_5, %aten_select_copy_int_7, %aten_select_copy_int_9, %aten_select_copy_int_11, %aten_select_copy_int_13, %aten_select_copy_int_15, %aten_select_copy_int_17, %aten_select_copy_int_19, %aten_select_copy_int_21, %aten_select_copy_int_23],), kwargs = {})
2025-03-21T20:32:07.0385153Z       %aten_view_copy_default_9 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_2, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:32:07.0386507Z       %aten_permute_copy_default_31 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_view_copy_default_9, [0, 1, 3, 2]), kwargs = {})
2025-03-21T20:32:07.0387921Z       %aten_matmul_default : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.matmul.default](args = (%aten_permute_copy_default_6, %aten_permute_copy_default_31), kwargs = {})
2025-03-21T20:32:07.0389274Z       %aten_mul_tensor_10 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_matmul_default, %b__frozen_param149), kwargs = {})
2025-03-21T20:32:07.0390517Z       %aten_add_tensor_2 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_mul_tensor_10, %aten_index_tensor_2), kwargs = {})
2025-03-21T20:32:07.0391770Z       %aten__softmax_default : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten._softmax.default](args = (%aten_add_tensor_2, -1, False), kwargs = {})
2025-03-21T20:32:07.0393097Z       %aten_matmul_default_1 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.matmul.default](args = (%aten__softmax_default, %aten_view_copy_default_10), kwargs = {})
2025-03-21T20:32:07.0394484Z       %aten_permute_copy_default_32 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_matmul_default_1, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0395846Z       %aten_view_copy_default_17 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_permute_copy_default_32, [1, 1, 768]), kwargs = {})
2025-03-21T20:32:07.0397240Z       %aten_unsqueeze_copy_default_7 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_view_copy_default_17, -1), kwargs = {})
2025-03-21T20:32:07.0398671Z       %aten_permute_copy_default_33 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_7, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0400295Z       %aten_convolution_default_3 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_33, %b__frozen_param5, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.0401893Z       %aten_permute_copy_default_34 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_3, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0403258Z       %aten_squeeze_copy_dims_7 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_34, [-1]), kwargs = {})
2025-03-21T20:32:07.0404564Z       %aten_add_tensor_3 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_embedding_default, %aten_squeeze_copy_dims_7), kwargs = {})
2025-03-21T20:32:07.0405949Z       %aten_rms_norm_default_1 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.rms_norm.default](args = (%aten_add_tensor_3, [768], %b__frozen_param6, 9.999999747378752e-06), kwargs = {})
2025-03-21T20:32:07.0407363Z       %aten_unsqueeze_copy_default_8 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_1, -1), kwargs = {})
2025-03-21T20:32:07.0408732Z       %aten_unsqueeze_copy_default_9 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_1, -1), kwargs = {})
2025-03-21T20:32:07.0410188Z       %aten_permute_copy_default_35 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_8, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0411619Z       %aten_permute_copy_default_37 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_9, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0413200Z       %aten_convolution_default_4 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_35, %b__frozen_param7, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.0414937Z       %aten_convolution_default_5 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_37, %b__frozen_param8, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.0416511Z       %aten_permute_copy_default_36 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_4, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0417920Z       %aten_permute_copy_default_38 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_5, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0419282Z       %aten_squeeze_copy_dims_8 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_36, [-1]), kwargs = {})
2025-03-21T20:32:07.0420596Z       %aten_squeeze_copy_dims_9 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_38, [-1]), kwargs = {})
2025-03-21T20:32:07.0421917Z       %aten_sigmoid_default : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.sigmoid.default](args = (%aten_squeeze_copy_dims_8,), kwargs = {})
2025-03-21T20:32:07.0423180Z       %aten_mul_tensor_13 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_8, %aten_sigmoid_default), kwargs = {})
2025-03-21T20:32:07.0424491Z       %aten_mul_tensor_14 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_mul_tensor_13, %aten_squeeze_copy_dims_9), kwargs = {})
2025-03-21T20:32:07.0425846Z       %aten_unsqueeze_copy_default_10 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_mul_tensor_14, -1), kwargs = {})
2025-03-21T20:32:07.0427240Z       %aten_permute_copy_default_39 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_10, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0428829Z       %aten_convolution_default_6 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_39, %b__frozen_param9, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.0430400Z       %aten_permute_copy_default_40 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_6, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0431760Z       %aten_squeeze_copy_dims_10 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_40, [-1]), kwargs = {})
2025-03-21T20:32:07.0433221Z       %aten_add_tensor_4 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_add_tensor_3, %aten_squeeze_copy_dims_10), kwargs = {})
2025-03-21T20:32:07.0434587Z       %aten_rms_norm_default_2 : [num_users=3] = call_function[target=executorch.exir.dialects.edge._ops.aten.rms_norm.default](args = (%aten_add_tensor_4, [768], %b__frozen_param10, 9.999999747378752e-06), kwargs = {})
2025-03-21T20:32:07.0436004Z       %aten_unsqueeze_copy_default_11 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_2, -1), kwargs = {})
2025-03-21T20:32:07.0437380Z       %aten_unsqueeze_copy_default_12 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_2, -1), kwargs = {})
2025-03-21T20:32:07.0438750Z       %aten_unsqueeze_copy_default_13 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_2, -1), kwargs = {})
2025-03-21T20:32:07.0440145Z       %aten_permute_copy_default_41 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_11, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0441586Z       %aten_permute_copy_default_43 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_12, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0443022Z       %aten_permute_copy_default_45 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_13, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0444608Z       %aten_convolution_default_7 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_41, %b__frozen_param11, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.0446402Z       %aten_convolution_default_8 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_43, %b__frozen_param12, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.0448132Z       %aten_convolution_default_9 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_45, %b__frozen_param13, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.0449794Z       %aten_permute_copy_default_42 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_7, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0451291Z       %aten_permute_copy_default_44 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_8, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0452704Z       %aten_permute_copy_default_46 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_9, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0454064Z       %aten_squeeze_copy_dims_11 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_42, [-1]), kwargs = {})
2025-03-21T20:32:07.0455377Z       %aten_squeeze_copy_dims_12 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_44, [-1]), kwargs = {})
2025-03-21T20:32:07.0456693Z       %aten_squeeze_copy_dims_13 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_46, [-1]), kwargs = {})
2025-03-21T20:32:07.0458019Z       %aten_view_copy_default_18 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_squeeze_copy_dims_11, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.0459366Z       %aten_view_copy_default_19 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_squeeze_copy_dims_12, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.0460695Z       %aten_view_copy_default_20 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_squeeze_copy_dims_13, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.0462056Z       %aten_view_copy_default_21 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_view_copy_default_18, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:32:07.0463422Z       %aten_view_copy_default_22 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_view_copy_default_19, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:32:07.0465007Z       %aten_index_put_default_3 : [num_users=13] = call_function[target=executorch.exir.dialects.edge._ops.aten.index_put.default](args = (%b_layers_1_attention_kv_cache_past_v_caches, [None, %aten__to_copy_default_1], %aten_view_copy_default_20), kwargs = {})
2025-03-21T20:32:07.0466553Z       %aten_slice_copy_tensor_4 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_21, 4, 0, 1), kwargs = {})
2025-03-21T20:32:07.0467856Z       %aten_slice_copy_tensor_5 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_21, 4, 1, 2), kwargs = {})
2025-03-21T20:32:07.0469153Z       %aten_slice_copy_tensor_6 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_22, 4, 0, 1), kwargs = {})
2025-03-21T20:32:07.0470458Z       %aten_slice_copy_tensor_7 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_22, 4, 1, 2), kwargs = {})
2025-03-21T20:32:07.0471857Z       %aten_permute_copy_default_60 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_3, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0473251Z       %aten_permute_copy_default_61 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_3, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0474669Z       %aten_permute_copy_default_62 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_3, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0476109Z       %aten_permute_copy_default_63 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_3, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0477493Z       %aten_permute_copy_default_64 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_3, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0478887Z       %aten_permute_copy_default_65 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_3, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0480288Z       %aten_permute_copy_default_66 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_3, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0481681Z       %aten_permute_copy_default_67 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_3, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0483076Z       %aten_permute_copy_default_68 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_3, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0484469Z       %aten_permute_copy_default_69 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_3, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0485862Z       %aten_permute_copy_default_70 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_3, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0487263Z       %aten_permute_copy_default_71 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_3, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0488611Z       %aten_squeeze_copy_dims_14 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_4, [4]), kwargs = {})
2025-03-21T20:32:07.0489959Z       %aten_squeeze_copy_dims_15 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_5, [4]), kwargs = {})
2025-03-21T20:32:07.0491248Z       %aten_squeeze_copy_dims_16 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_6, [4]), kwargs = {})
2025-03-21T20:32:07.0492536Z       %aten_squeeze_copy_dims_17 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_7, [4]), kwargs = {})
2025-03-21T20:32:07.0493807Z       %aten_select_copy_int_72 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_60, 0, 0), kwargs = {})
2025-03-21T20:32:07.0495082Z       %aten_select_copy_int_74 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_61, 0, 0), kwargs = {})
2025-03-21T20:32:07.0496382Z       %aten_select_copy_int_76 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_62, 0, 0), kwargs = {})
2025-03-21T20:32:07.0497659Z       %aten_select_copy_int_78 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_63, 0, 0), kwargs = {})
2025-03-21T20:32:07.0498974Z       %aten_select_copy_int_80 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_64, 0, 0), kwargs = {})
2025-03-21T20:32:07.0500269Z       %aten_select_copy_int_82 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_65, 0, 0), kwargs = {})
2025-03-21T20:32:07.0501563Z       %aten_select_copy_int_84 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_66, 0, 0), kwargs = {})
2025-03-21T20:32:07.0502831Z       %aten_select_copy_int_86 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_67, 0, 0), kwargs = {})
2025-03-21T20:32:07.0504102Z       %aten_select_copy_int_88 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_68, 0, 0), kwargs = {})
2025-03-21T20:32:07.0505375Z       %aten_select_copy_int_90 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_69, 0, 0), kwargs = {})
2025-03-21T20:32:07.0506648Z       %aten_select_copy_int_92 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_70, 0, 0), kwargs = {})
2025-03-21T20:32:07.0507906Z       %aten_select_copy_int_94 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_71, 0, 0), kwargs = {})
2025-03-21T20:32:07.0509210Z       %aten_mul_tensor_17 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_14, %aten_view_copy_default_23), kwargs = {})
2025-03-21T20:32:07.0510539Z       %aten_mul_tensor_19 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_14, %aten_view_copy_default_24), kwargs = {})
2025-03-21T20:32:07.0511872Z       %aten_mul_tensor_18 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_15, %aten_view_copy_default_24), kwargs = {})
2025-03-21T20:32:07.0513203Z       %aten_mul_tensor_20 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_15, %aten_view_copy_default_23), kwargs = {})
2025-03-21T20:32:07.0514526Z       %aten_mul_tensor_21 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_16, %aten_view_copy_default_23), kwargs = {})
2025-03-21T20:32:07.0515850Z       %aten_mul_tensor_23 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_16, %aten_view_copy_default_24), kwargs = {})
2025-03-21T20:32:07.0517177Z       %aten_mul_tensor_22 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_17, %aten_view_copy_default_24), kwargs = {})
2025-03-21T20:32:07.0518509Z       %aten_mul_tensor_24 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_17, %aten_view_copy_default_23), kwargs = {})
2025-03-21T20:32:07.0519802Z       %aten_select_copy_int_73 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_72, 0, 0), kwargs = {})
2025-03-21T20:32:07.0521074Z       %aten_select_copy_int_75 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_74, 0, 1), kwargs = {})
2025-03-21T20:32:07.0522303Z       %aten_select_copy_int_77 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_76, 0, 2), kwargs = {})
2025-03-21T20:32:07.0523565Z       %aten_select_copy_int_79 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_78, 0, 3), kwargs = {})
2025-03-21T20:32:07.0524826Z       %aten_select_copy_int_81 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_80, 0, 4), kwargs = {})
2025-03-21T20:32:07.0526088Z       %aten_select_copy_int_83 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_82, 0, 5), kwargs = {})
2025-03-21T20:32:07.0527330Z       %aten_select_copy_int_85 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_84, 0, 6), kwargs = {})
2025-03-21T20:32:07.0528567Z       %aten_select_copy_int_87 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_86, 0, 7), kwargs = {})
2025-03-21T20:32:07.0529869Z       %aten_select_copy_int_89 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_88, 0, 8), kwargs = {})
2025-03-21T20:32:07.0531114Z       %aten_select_copy_int_91 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_90, 0, 9), kwargs = {})
2025-03-21T20:32:07.0532521Z       %aten_select_copy_int_93 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_92, 0, 10), kwargs = {})
2025-03-21T20:32:07.0533781Z       %aten_select_copy_int_95 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_94, 0, 11), kwargs = {})
2025-03-21T20:32:07.0535013Z       %aten_sub_tensor_2 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.sub.Tensor](args = (%aten_mul_tensor_17, %aten_mul_tensor_18), kwargs = {})
2025-03-21T20:32:07.0536253Z       %aten_add_tensor_5 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_mul_tensor_19, %aten_mul_tensor_20), kwargs = {})
2025-03-21T20:32:07.0537487Z       %aten_sub_tensor_3 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.sub.Tensor](args = (%aten_mul_tensor_21, %aten_mul_tensor_22), kwargs = {})
2025-03-21T20:32:07.0538723Z       %aten_add_tensor_6 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_mul_tensor_23, %aten_mul_tensor_24), kwargs = {})
2025-03-21T20:32:07.0540785Z       %aten_cat_default_7 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_select_copy_int_73, %aten_select_copy_int_75, %aten_select_copy_int_77, %aten_select_copy_int_79, %aten_select_copy_int_81, %aten_select_copy_int_83, %aten_select_copy_int_85, %aten_select_copy_int_87, %aten_select_copy_int_89, %aten_select_copy_int_91, %aten_select_copy_int_93, %aten_select_copy_int_95],), kwargs = {})
2025-03-21T20:32:07.0542903Z       %aten_unsqueeze_copy_default_14 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_sub_tensor_2, 4), kwargs = {})
2025-03-21T20:32:07.0544236Z       %aten_unsqueeze_copy_default_15 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_add_tensor_5, 4), kwargs = {})
2025-03-21T20:32:07.0545622Z       %aten_unsqueeze_copy_default_16 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_sub_tensor_3, 4), kwargs = {})
2025-03-21T20:32:07.0546949Z       %aten_unsqueeze_copy_default_17 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_add_tensor_6, 4), kwargs = {})
2025-03-21T20:32:07.0548309Z       %aten_view_copy_default_28 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_7, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:32:07.0549739Z       %aten_cat_default_4 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_unsqueeze_copy_default_14, %aten_unsqueeze_copy_default_15], -1), kwargs = {})
2025-03-21T20:32:07.0551227Z       %aten_cat_default_5 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_unsqueeze_copy_default_16, %aten_unsqueeze_copy_default_17], -1), kwargs = {})
2025-03-21T20:32:07.0552615Z       %aten_view_copy_default_25 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_4, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.0553916Z       %aten_view_copy_default_26 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_5, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.0555254Z       %aten_permute_copy_default_47 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_view_copy_default_25, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0556857Z       %aten_index_put_default_2 : [num_users=13] = call_function[target=executorch.exir.dialects.edge._ops.aten.index_put.default](args = (%b_layers_1_attention_kv_cache_past_k_caches, [None, %aten__to_copy_default_1], %aten_view_copy_default_26), kwargs = {})
2025-03-21T20:32:07.0558449Z       %aten_permute_copy_default_48 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_2, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0559842Z       %aten_permute_copy_default_49 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_2, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0561240Z       %aten_permute_copy_default_50 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_2, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0562632Z       %aten_permute_copy_default_51 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_2, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0564024Z       %aten_permute_copy_default_52 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_2, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0565408Z       %aten_permute_copy_default_53 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_2, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0566793Z       %aten_permute_copy_default_54 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_2, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0568182Z       %aten_permute_copy_default_55 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_2, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0569627Z       %aten_permute_copy_default_56 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_2, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0571052Z       %aten_permute_copy_default_57 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_2, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0572430Z       %aten_permute_copy_default_58 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_2, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0573848Z       %aten_permute_copy_default_59 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_2, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0575234Z       %aten_select_copy_int_48 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_48, 0, 0), kwargs = {})
2025-03-21T20:32:07.0576509Z       %aten_select_copy_int_50 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_49, 0, 0), kwargs = {})
2025-03-21T20:32:07.0577781Z       %aten_select_copy_int_52 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_50, 0, 0), kwargs = {})
2025-03-21T20:32:07.0579054Z       %aten_select_copy_int_54 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_51, 0, 0), kwargs = {})
2025-03-21T20:32:07.0580329Z       %aten_select_copy_int_56 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_52, 0, 0), kwargs = {})
2025-03-21T20:32:07.0581601Z       %aten_select_copy_int_58 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_53, 0, 0), kwargs = {})
2025-03-21T20:32:07.0582875Z       %aten_select_copy_int_60 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_54, 0, 0), kwargs = {})
2025-03-21T20:32:07.0584145Z       %aten_select_copy_int_62 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_55, 0, 0), kwargs = {})
2025-03-21T20:32:07.0585415Z       %aten_select_copy_int_64 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_56, 0, 0), kwargs = {})
2025-03-21T20:32:07.0586689Z       %aten_select_copy_int_66 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_57, 0, 0), kwargs = {})
2025-03-21T20:32:07.0587944Z       %aten_select_copy_int_68 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_58, 0, 0), kwargs = {})
2025-03-21T20:32:07.0589216Z       %aten_select_copy_int_70 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_59, 0, 0), kwargs = {})
2025-03-21T20:32:07.0590474Z       %aten_select_copy_int_49 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_48, 0, 0), kwargs = {})
2025-03-21T20:32:07.0591718Z       %aten_select_copy_int_51 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_50, 0, 1), kwargs = {})
2025-03-21T20:32:07.0592957Z       %aten_select_copy_int_53 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_52, 0, 2), kwargs = {})
2025-03-21T20:32:07.0594195Z       %aten_select_copy_int_55 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_54, 0, 3), kwargs = {})
2025-03-21T20:32:07.0595479Z       %aten_select_copy_int_57 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_56, 0, 4), kwargs = {})
2025-03-21T20:32:07.0596723Z       %aten_select_copy_int_59 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_58, 0, 5), kwargs = {})
2025-03-21T20:32:07.0597988Z       %aten_select_copy_int_61 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_60, 0, 6), kwargs = {})
2025-03-21T20:32:07.0599258Z       %aten_select_copy_int_63 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_62, 0, 7), kwargs = {})
2025-03-21T20:32:07.0600510Z       %aten_select_copy_int_65 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_64, 0, 8), kwargs = {})
2025-03-21T20:32:07.0601756Z       %aten_select_copy_int_67 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_66, 0, 9), kwargs = {})
2025-03-21T20:32:07.0603001Z       %aten_select_copy_int_69 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_68, 0, 10), kwargs = {})
2025-03-21T20:32:07.0604258Z       %aten_select_copy_int_71 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_70, 0, 11), kwargs = {})
2025-03-21T20:32:07.0606337Z       %aten_cat_default_6 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_select_copy_int_49, %aten_select_copy_int_51, %aten_select_copy_int_53, %aten_select_copy_int_55, %aten_select_copy_int_57, %aten_select_copy_int_59, %aten_select_copy_int_61, %aten_select_copy_int_63, %aten_select_copy_int_65, %aten_select_copy_int_67, %aten_select_copy_int_69, %aten_select_copy_int_71],), kwargs = {})
2025-03-21T20:32:07.0608440Z       %aten_view_copy_default_27 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_6, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:32:07.0609867Z       %aten_permute_copy_default_72 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_view_copy_default_27, [0, 1, 3, 2]), kwargs = {})
2025-03-21T20:32:07.0611305Z       %aten_matmul_default_2 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.matmul.default](args = (%aten_permute_copy_default_47, %aten_permute_copy_default_72), kwargs = {})
2025-03-21T20:32:07.0612676Z       %aten_mul_tensor_25 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_matmul_default_2, %b__frozen_param150), kwargs = {})
2025-03-21T20:32:07.0613928Z       %aten_add_tensor_7 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_mul_tensor_25, %aten_index_tensor_3), kwargs = {})
2025-03-21T20:32:07.0615190Z       %aten__softmax_default_1 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten._softmax.default](args = (%aten_add_tensor_7, -1, False), kwargs = {})
2025-03-21T20:32:07.0616533Z       %aten_matmul_default_3 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.matmul.default](args = (%aten__softmax_default_1, %aten_view_copy_default_28), kwargs = {})
2025-03-21T20:32:07.0617919Z       %aten_permute_copy_default_73 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_matmul_default_3, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0619267Z       %aten_view_copy_default_35 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_permute_copy_default_73, [1, 1, 768]), kwargs = {})
2025-03-21T20:32:07.0620662Z       %aten_unsqueeze_copy_default_18 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_view_copy_default_35, -1), kwargs = {})
2025-03-21T20:32:07.0622095Z       %aten_permute_copy_default_74 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_18, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0623711Z       %aten_convolution_default_10 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_74, %b__frozen_param14, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.0625313Z       %aten_permute_copy_default_75 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_10, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0626681Z       %aten_squeeze_copy_dims_18 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_75, [-1]), kwargs = {})
2025-03-21T20:32:07.0627972Z       %aten_add_tensor_8 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_add_tensor_4, %aten_squeeze_copy_dims_18), kwargs = {})
2025-03-21T20:32:07.0629330Z       %aten_rms_norm_default_3 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.rms_norm.default](args = (%aten_add_tensor_8, [768], %b__frozen_param15, 9.999999747378752e-06), kwargs = {})
2025-03-21T20:32:07.0630741Z       %aten_unsqueeze_copy_default_19 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_3, -1), kwargs = {})
2025-03-21T20:32:07.0632113Z       %aten_unsqueeze_copy_default_20 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_3, -1), kwargs = {})
2025-03-21T20:32:07.0633674Z       %aten_permute_copy_default_76 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_19, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0635115Z       %aten_permute_copy_default_78 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_20, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0636708Z       %aten_convolution_default_11 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_76, %b__frozen_param16, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.0638448Z       %aten_convolution_default_12 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_78, %b__frozen_param17, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.0640019Z       %aten_permute_copy_default_77 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_11, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0641438Z       %aten_permute_copy_default_79 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_12, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0642803Z       %aten_squeeze_copy_dims_19 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_77, [-1]), kwargs = {})
2025-03-21T20:32:07.0644118Z       %aten_squeeze_copy_dims_20 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_79, [-1]), kwargs = {})
2025-03-21T20:32:07.0645459Z       %aten_sigmoid_default_1 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.sigmoid.default](args = (%aten_squeeze_copy_dims_19,), kwargs = {})
2025-03-21T20:32:07.0646748Z       %aten_mul_tensor_28 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_19, %aten_sigmoid_default_1), kwargs = {})
2025-03-21T20:32:07.0648077Z       %aten_mul_tensor_29 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_mul_tensor_28, %aten_squeeze_copy_dims_20), kwargs = {})
2025-03-21T20:32:07.0649532Z       %aten_unsqueeze_copy_default_21 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_mul_tensor_29, -1), kwargs = {})
2025-03-21T20:32:07.0650928Z       %aten_permute_copy_default_80 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_21, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0652519Z       %aten_convolution_default_13 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_80, %b__frozen_param18, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.0654099Z       %aten_permute_copy_default_81 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_13, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0655468Z       %aten_squeeze_copy_dims_21 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_81, [-1]), kwargs = {})
2025-03-21T20:32:07.0656750Z       %aten_add_tensor_9 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_add_tensor_8, %aten_squeeze_copy_dims_21), kwargs = {})
2025-03-21T20:32:07.0658114Z       %aten_rms_norm_default_4 : [num_users=3] = call_function[target=executorch.exir.dialects.edge._ops.aten.rms_norm.default](args = (%aten_add_tensor_9, [768], %b__frozen_param19, 9.999999747378752e-06), kwargs = {})
2025-03-21T20:32:07.0659529Z       %aten_unsqueeze_copy_default_22 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_4, -1), kwargs = {})
2025-03-21T20:32:07.0660898Z       %aten_unsqueeze_copy_default_23 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_4, -1), kwargs = {})
2025-03-21T20:32:07.0662264Z       %aten_unsqueeze_copy_default_24 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_4, -1), kwargs = {})
2025-03-21T20:32:07.0663664Z       %aten_permute_copy_default_82 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_22, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0665099Z       %aten_permute_copy_default_84 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_23, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0666539Z       %aten_permute_copy_default_86 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_24, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0668132Z       %aten_convolution_default_14 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_82, %b__frozen_param20, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.0669899Z       %aten_convolution_default_15 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_84, %b__frozen_param21, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.0671636Z       %aten_convolution_default_16 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_86, %b__frozen_param22, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.0673235Z       %aten_permute_copy_default_83 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_14, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0674708Z       %aten_permute_copy_default_85 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_15, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0676129Z       %aten_permute_copy_default_87 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_16, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0677480Z       %aten_squeeze_copy_dims_22 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_83, [-1]), kwargs = {})
2025-03-21T20:32:07.0678795Z       %aten_squeeze_copy_dims_23 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_85, [-1]), kwargs = {})
2025-03-21T20:32:07.0680104Z       %aten_squeeze_copy_dims_24 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_87, [-1]), kwargs = {})
2025-03-21T20:32:07.0681437Z       %aten_view_copy_default_36 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_squeeze_copy_dims_22, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.0682789Z       %aten_view_copy_default_37 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_squeeze_copy_dims_23, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.0684131Z       %aten_view_copy_default_38 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_squeeze_copy_dims_24, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.0685488Z       %aten_view_copy_default_39 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_view_copy_default_36, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:32:07.0686859Z       %aten_view_copy_default_40 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_view_copy_default_37, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:32:07.0688434Z       %aten_index_put_default_5 : [num_users=13] = call_function[target=executorch.exir.dialects.edge._ops.aten.index_put.default](args = (%b_layers_2_attention_kv_cache_past_v_caches, [None, %aten__to_copy_default_1], %aten_view_copy_default_38), kwargs = {})
2025-03-21T20:32:07.0690042Z       %aten_slice_copy_tensor_8 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_39, 4, 0, 1), kwargs = {})
2025-03-21T20:32:07.0691351Z       %aten_slice_copy_tensor_9 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_39, 4, 1, 2), kwargs = {})
2025-03-21T20:32:07.0692658Z       %aten_slice_copy_tensor_10 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_40, 4, 0, 1), kwargs = {})
2025-03-21T20:32:07.0693951Z       %aten_slice_copy_tensor_11 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_40, 4, 1, 2), kwargs = {})
2025-03-21T20:32:07.0695334Z       %aten_permute_copy_default_101 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_5, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0696738Z       %aten_permute_copy_default_102 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_5, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0698159Z       %aten_permute_copy_default_103 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_5, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0699606Z       %aten_permute_copy_default_104 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_5, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0701004Z       %aten_permute_copy_default_105 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_5, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0702404Z       %aten_permute_copy_default_106 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_5, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0703801Z       %aten_permute_copy_default_107 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_5, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0705202Z       %aten_permute_copy_default_108 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_5, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0706598Z       %aten_permute_copy_default_109 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_5, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0707996Z       %aten_permute_copy_default_110 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_5, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0709394Z       %aten_permute_copy_default_111 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_5, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0710780Z       %aten_permute_copy_default_112 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_5, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0712126Z       %aten_squeeze_copy_dims_25 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_8, [4]), kwargs = {})
2025-03-21T20:32:07.0713411Z       %aten_squeeze_copy_dims_26 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_9, [4]), kwargs = {})
2025-03-21T20:32:07.0714698Z       %aten_squeeze_copy_dims_27 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_10, [4]), kwargs = {})
2025-03-21T20:32:07.0715986Z       %aten_squeeze_copy_dims_28 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_11, [4]), kwargs = {})
2025-03-21T20:32:07.0717279Z       %aten_select_copy_int_120 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_101, 0, 0), kwargs = {})
2025-03-21T20:32:07.0718563Z       %aten_select_copy_int_122 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_102, 0, 0), kwargs = {})
2025-03-21T20:32:07.0719879Z       %aten_select_copy_int_124 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_103, 0, 0), kwargs = {})
2025-03-21T20:32:07.0721167Z       %aten_select_copy_int_126 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_104, 0, 0), kwargs = {})
2025-03-21T20:32:07.0722479Z       %aten_select_copy_int_128 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_105, 0, 0), kwargs = {})
2025-03-21T20:32:07.0723792Z       %aten_select_copy_int_130 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_106, 0, 0), kwargs = {})
2025-03-21T20:32:07.0725086Z       %aten_select_copy_int_132 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_107, 0, 0), kwargs = {})
2025-03-21T20:32:07.0726375Z       %aten_select_copy_int_134 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_108, 0, 0), kwargs = {})
2025-03-21T20:32:07.0727663Z       %aten_select_copy_int_136 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_109, 0, 0), kwargs = {})
2025-03-21T20:32:07.0728955Z       %aten_select_copy_int_138 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_110, 0, 0), kwargs = {})
2025-03-21T20:32:07.0730311Z       %aten_select_copy_int_140 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_111, 0, 0), kwargs = {})
2025-03-21T20:32:07.0731605Z       %aten_select_copy_int_142 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_112, 0, 0), kwargs = {})
2025-03-21T20:32:07.0733456Z       %aten_mul_tensor_32 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_25, %aten_view_copy_default_41), kwargs = {})
2025-03-21T20:32:07.0734915Z       %aten_mul_tensor_34 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_25, %aten_view_copy_default_42), kwargs = {})
2025-03-21T20:32:07.0736345Z       %aten_mul_tensor_33 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_26, %aten_view_copy_default_42), kwargs = {})
2025-03-21T20:32:07.0737903Z       %aten_mul_tensor_35 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_26, %aten_view_copy_default_41), kwargs = {})
2025-03-21T20:32:07.0754628Z       %aten_mul_tensor_36 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_27, %aten_view_copy_default_41), kwargs = {})
2025-03-21T20:32:07.0755983Z       %aten_mul_tensor_38 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_27, %aten_view_copy_default_42), kwargs = {})
2025-03-21T20:32:07.0757312Z       %aten_mul_tensor_37 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_28, %aten_view_copy_default_42), kwargs = {})
2025-03-21T20:32:07.0758633Z       %aten_mul_tensor_39 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_28, %aten_view_copy_default_41), kwargs = {})
2025-03-21T20:32:07.0759928Z       %aten_select_copy_int_121 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_120, 0, 0), kwargs = {})
2025-03-21T20:32:07.0761299Z       %aten_select_copy_int_123 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_122, 0, 1), kwargs = {})
2025-03-21T20:32:07.0762547Z       %aten_select_copy_int_125 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_124, 0, 2), kwargs = {})
2025-03-21T20:32:07.0763851Z       %aten_select_copy_int_127 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_126, 0, 3), kwargs = {})
2025-03-21T20:32:07.0765271Z       %aten_select_copy_int_129 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_128, 0, 4), kwargs = {})
2025-03-21T20:32:07.0766523Z       %aten_select_copy_int_131 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_130, 0, 5), kwargs = {})
2025-03-21T20:32:07.0767769Z       %aten_select_copy_int_133 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_132, 0, 6), kwargs = {})
2025-03-21T20:32:07.0769013Z       %aten_select_copy_int_135 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_134, 0, 7), kwargs = {})
2025-03-21T20:32:07.0770355Z       %aten_select_copy_int_137 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_136, 0, 8), kwargs = {})
2025-03-21T20:32:07.0771601Z       %aten_select_copy_int_139 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_138, 0, 9), kwargs = {})
2025-03-21T20:32:07.0772857Z       %aten_select_copy_int_141 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_140, 0, 10), kwargs = {})
2025-03-21T20:32:07.0774110Z       %aten_select_copy_int_143 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_142, 0, 11), kwargs = {})
2025-03-21T20:32:07.0775352Z       %aten_sub_tensor_4 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.sub.Tensor](args = (%aten_mul_tensor_32, %aten_mul_tensor_33), kwargs = {})
2025-03-21T20:32:07.0776576Z       %aten_add_tensor_10 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_mul_tensor_34, %aten_mul_tensor_35), kwargs = {})
2025-03-21T20:32:07.0777803Z       %aten_sub_tensor_5 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.sub.Tensor](args = (%aten_mul_tensor_36, %aten_mul_tensor_37), kwargs = {})
2025-03-21T20:32:07.0779026Z       %aten_add_tensor_11 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_mul_tensor_38, %aten_mul_tensor_39), kwargs = {})
2025-03-21T20:32:07.0781139Z       %aten_cat_default_11 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_select_copy_int_121, %aten_select_copy_int_123, %aten_select_copy_int_125, %aten_select_copy_int_127, %aten_select_copy_int_129, %aten_select_copy_int_131, %aten_select_copy_int_133, %aten_select_copy_int_135, %aten_select_copy_int_137, %aten_select_copy_int_139, %aten_select_copy_int_141, %aten_select_copy_int_143],), kwargs = {})
2025-03-21T20:32:07.0783314Z       %aten_unsqueeze_copy_default_25 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_sub_tensor_4, 4), kwargs = {})
2025-03-21T20:32:07.0784631Z       %aten_unsqueeze_copy_default_26 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_add_tensor_10, 4), kwargs = {})
2025-03-21T20:32:07.0785982Z       %aten_unsqueeze_copy_default_27 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_sub_tensor_5, 4), kwargs = {})
2025-03-21T20:32:07.0787290Z       %aten_unsqueeze_copy_default_28 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_add_tensor_11, 4), kwargs = {})
2025-03-21T20:32:07.0788625Z       %aten_view_copy_default_46 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_11, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:32:07.0790064Z       %aten_cat_default_8 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_unsqueeze_copy_default_25, %aten_unsqueeze_copy_default_26], -1), kwargs = {})
2025-03-21T20:32:07.0791527Z       %aten_cat_default_9 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_unsqueeze_copy_default_27, %aten_unsqueeze_copy_default_28], -1), kwargs = {})
2025-03-21T20:32:07.0792907Z       %aten_view_copy_default_43 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_8, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.0794215Z       %aten_view_copy_default_44 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_9, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.0795557Z       %aten_permute_copy_default_88 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_view_copy_default_43, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0797144Z       %aten_index_put_default_4 : [num_users=13] = call_function[target=executorch.exir.dialects.edge._ops.aten.index_put.default](args = (%b_layers_2_attention_kv_cache_past_k_caches, [None, %aten__to_copy_default_1], %aten_view_copy_default_44), kwargs = {})
2025-03-21T20:32:07.0798731Z       %aten_permute_copy_default_89 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_4, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0800120Z       %aten_permute_copy_default_90 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_4, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0801509Z       %aten_permute_copy_default_91 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_4, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0802888Z       %aten_permute_copy_default_92 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_4, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0804258Z       %aten_permute_copy_default_93 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_4, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0805639Z       %aten_permute_copy_default_94 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_4, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0807015Z       %aten_permute_copy_default_95 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_4, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0808394Z       %aten_permute_copy_default_96 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_4, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0809858Z       %aten_permute_copy_default_97 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_4, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0811236Z       %aten_permute_copy_default_98 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_4, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0812644Z       %aten_permute_copy_default_99 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_4, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0814051Z       %aten_permute_copy_default_100 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_4, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0815402Z       %aten_select_copy_int_96 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_89, 0, 0), kwargs = {})
2025-03-21T20:32:07.0816671Z       %aten_select_copy_int_98 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_90, 0, 0), kwargs = {})
2025-03-21T20:32:07.0817945Z       %aten_select_copy_int_100 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_91, 0, 0), kwargs = {})
2025-03-21T20:32:07.0819223Z       %aten_select_copy_int_102 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_92, 0, 0), kwargs = {})
2025-03-21T20:32:07.0820488Z       %aten_select_copy_int_104 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_93, 0, 0), kwargs = {})
2025-03-21T20:32:07.0821753Z       %aten_select_copy_int_106 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_94, 0, 0), kwargs = {})
2025-03-21T20:32:07.0823026Z       %aten_select_copy_int_108 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_95, 0, 0), kwargs = {})
2025-03-21T20:32:07.0824291Z       %aten_select_copy_int_110 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_96, 0, 0), kwargs = {})
2025-03-21T20:32:07.0825562Z       %aten_select_copy_int_112 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_97, 0, 0), kwargs = {})
2025-03-21T20:32:07.0826837Z       %aten_select_copy_int_114 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_98, 0, 0), kwargs = {})
2025-03-21T20:32:07.0828109Z       %aten_select_copy_int_116 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_99, 0, 0), kwargs = {})
2025-03-21T20:32:07.0829376Z       %aten_select_copy_int_118 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_100, 0, 0), kwargs = {})
2025-03-21T20:32:07.0830635Z       %aten_select_copy_int_97 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_96, 0, 0), kwargs = {})
2025-03-21T20:32:07.0831869Z       %aten_select_copy_int_99 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_98, 0, 1), kwargs = {})
2025-03-21T20:32:07.0833305Z       %aten_select_copy_int_101 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_100, 0, 2), kwargs = {})
2025-03-21T20:32:07.0834617Z       %aten_select_copy_int_103 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_102, 0, 3), kwargs = {})
2025-03-21T20:32:07.0835863Z       %aten_select_copy_int_105 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_104, 0, 4), kwargs = {})
2025-03-21T20:32:07.0837142Z       %aten_select_copy_int_107 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_106, 0, 5), kwargs = {})
2025-03-21T20:32:07.0838424Z       %aten_select_copy_int_109 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_108, 0, 6), kwargs = {})
2025-03-21T20:32:07.0839699Z       %aten_select_copy_int_111 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_110, 0, 7), kwargs = {})
2025-03-21T20:32:07.0840948Z       %aten_select_copy_int_113 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_112, 0, 8), kwargs = {})
2025-03-21T20:32:07.0842193Z       %aten_select_copy_int_115 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_114, 0, 9), kwargs = {})
2025-03-21T20:32:07.0843446Z       %aten_select_copy_int_117 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_116, 0, 10), kwargs = {})
2025-03-21T20:32:07.0844699Z       %aten_select_copy_int_119 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_118, 0, 11), kwargs = {})
2025-03-21T20:32:07.0846824Z       %aten_cat_default_10 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_select_copy_int_97, %aten_select_copy_int_99, %aten_select_copy_int_101, %aten_select_copy_int_103, %aten_select_copy_int_105, %aten_select_copy_int_107, %aten_select_copy_int_109, %aten_select_copy_int_111, %aten_select_copy_int_113, %aten_select_copy_int_115, %aten_select_copy_int_117, %aten_select_copy_int_119],), kwargs = {})
2025-03-21T20:32:07.0849332Z       %aten_view_copy_default_45 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_10, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:32:07.0850705Z       %aten_permute_copy_default_113 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_view_copy_default_45, [0, 1, 3, 2]), kwargs = {})
2025-03-21T20:32:07.0852141Z       %aten_matmul_default_4 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.matmul.default](args = (%aten_permute_copy_default_88, %aten_permute_copy_default_113), kwargs = {})
2025-03-21T20:32:07.0853491Z       %aten_mul_tensor_40 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_matmul_default_4, %b__frozen_param151), kwargs = {})
2025-03-21T20:32:07.0854739Z       %aten_add_tensor_12 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_mul_tensor_40, %aten_index_tensor_4), kwargs = {})
2025-03-21T20:32:07.0855994Z       %aten__softmax_default_2 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten._softmax.default](args = (%aten_add_tensor_12, -1, False), kwargs = {})
2025-03-21T20:32:07.0857333Z       %aten_matmul_default_5 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.matmul.default](args = (%aten__softmax_default_2, %aten_view_copy_default_46), kwargs = {})
2025-03-21T20:32:07.0858712Z       %aten_permute_copy_default_114 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_matmul_default_5, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0860125Z       %aten_view_copy_default_53 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_permute_copy_default_114, [1, 1, 768]), kwargs = {})
2025-03-21T20:32:07.0861482Z       %aten_unsqueeze_copy_default_29 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_view_copy_default_53, -1), kwargs = {})
2025-03-21T20:32:07.0862914Z       %aten_permute_copy_default_115 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_29, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0864555Z       %aten_convolution_default_17 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_115, %b__frozen_param23, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.0866135Z       %aten_permute_copy_default_116 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_17, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0867502Z       %aten_squeeze_copy_dims_29 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_116, [-1]), kwargs = {})
2025-03-21T20:32:07.0868789Z       %aten_add_tensor_13 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_add_tensor_9, %aten_squeeze_copy_dims_29), kwargs = {})
2025-03-21T20:32:07.0870132Z       %aten_rms_norm_default_5 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.rms_norm.default](args = (%aten_add_tensor_13, [768], %b__frozen_param24, 9.999999747378752e-06), kwargs = {})
2025-03-21T20:32:07.0871536Z       %aten_unsqueeze_copy_default_30 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_5, -1), kwargs = {})
2025-03-21T20:32:07.0872896Z       %aten_unsqueeze_copy_default_31 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_5, -1), kwargs = {})
2025-03-21T20:32:07.0874295Z       %aten_permute_copy_default_117 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_30, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0875726Z       %aten_permute_copy_default_119 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_31, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0877312Z       %aten_convolution_default_18 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_117, %b__frozen_param25, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.0879050Z       %aten_convolution_default_19 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_119, %b__frozen_param26, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.0880629Z       %aten_permute_copy_default_118 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_18, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0882043Z       %aten_permute_copy_default_120 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_19, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0883405Z       %aten_squeeze_copy_dims_30 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_118, [-1]), kwargs = {})
2025-03-21T20:32:07.0884756Z       %aten_squeeze_copy_dims_31 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_120, [-1]), kwargs = {})
2025-03-21T20:32:07.0886033Z       %aten_sigmoid_default_2 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.sigmoid.default](args = (%aten_squeeze_copy_dims_30,), kwargs = {})
2025-03-21T20:32:07.0887335Z       %aten_mul_tensor_43 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_30, %aten_sigmoid_default_2), kwargs = {})
2025-03-21T20:32:07.0888639Z       %aten_mul_tensor_44 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_mul_tensor_43, %aten_squeeze_copy_dims_31), kwargs = {})
2025-03-21T20:32:07.0890022Z       %aten_unsqueeze_copy_default_32 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_mul_tensor_44, -1), kwargs = {})
2025-03-21T20:32:07.0891413Z       %aten_permute_copy_default_121 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_32, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0893007Z       %aten_convolution_default_20 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_121, %b__frozen_param27, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.0894586Z       %aten_permute_copy_default_122 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_20, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0895960Z       %aten_squeeze_copy_dims_32 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_122, [-1]), kwargs = {})
2025-03-21T20:32:07.0897248Z       %aten_add_tensor_14 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_add_tensor_13, %aten_squeeze_copy_dims_32), kwargs = {})
2025-03-21T20:32:07.0898604Z       %aten_rms_norm_default_6 : [num_users=3] = call_function[target=executorch.exir.dialects.edge._ops.aten.rms_norm.default](args = (%aten_add_tensor_14, [768], %b__frozen_param28, 9.999999747378752e-06), kwargs = {})
2025-03-21T20:32:07.0900012Z       %aten_unsqueeze_copy_default_33 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_6, -1), kwargs = {})
2025-03-21T20:32:07.0901370Z       %aten_unsqueeze_copy_default_34 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_6, -1), kwargs = {})
2025-03-21T20:32:07.0902721Z       %aten_unsqueeze_copy_default_35 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_6, -1), kwargs = {})
2025-03-21T20:32:07.0904114Z       %aten_permute_copy_default_123 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_33, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0905545Z       %aten_permute_copy_default_125 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_34, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0906970Z       %aten_permute_copy_default_127 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_35, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0908555Z       %aten_convolution_default_21 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_123, %b__frozen_param29, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.0910316Z       %aten_convolution_default_22 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_125, %b__frozen_param30, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.0912073Z       %aten_convolution_default_23 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_127, %b__frozen_param31, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.0913696Z       %aten_permute_copy_default_124 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_21, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0915109Z       %aten_permute_copy_default_126 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_22, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0916525Z       %aten_permute_copy_default_128 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_23, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0917888Z       %aten_squeeze_copy_dims_33 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_124, [-1]), kwargs = {})
2025-03-21T20:32:07.0919203Z       %aten_squeeze_copy_dims_34 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_126, [-1]), kwargs = {})
2025-03-21T20:32:07.0920510Z       %aten_squeeze_copy_dims_35 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_128, [-1]), kwargs = {})
2025-03-21T20:32:07.0921831Z       %aten_view_copy_default_54 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_squeeze_copy_dims_33, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.0923170Z       %aten_view_copy_default_55 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_squeeze_copy_dims_34, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.0924504Z       %aten_view_copy_default_56 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_squeeze_copy_dims_35, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.0925838Z       %aten_view_copy_default_57 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_view_copy_default_54, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:32:07.0927198Z       %aten_view_copy_default_58 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_view_copy_default_55, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:32:07.0928767Z       %aten_index_put_default_7 : [num_users=13] = call_function[target=executorch.exir.dialects.edge._ops.aten.index_put.default](args = (%b_layers_3_attention_kv_cache_past_v_caches, [None, %aten__to_copy_default_1], %aten_view_copy_default_56), kwargs = {})
2025-03-21T20:32:07.0930358Z       %aten_slice_copy_tensor_12 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_57, 4, 0, 1), kwargs = {})
2025-03-21T20:32:07.0931654Z       %aten_slice_copy_tensor_13 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_57, 4, 1, 2), kwargs = {})
2025-03-21T20:32:07.0933094Z       %aten_slice_copy_tensor_14 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_58, 4, 0, 1), kwargs = {})
2025-03-21T20:32:07.0934449Z       %aten_slice_copy_tensor_15 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_58, 4, 1, 2), kwargs = {})
2025-03-21T20:32:07.0935804Z       %aten_permute_copy_default_142 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_7, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0937240Z       %aten_permute_copy_default_143 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_7, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0938712Z       %aten_permute_copy_default_144 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_7, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0940105Z       %aten_permute_copy_default_145 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_7, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0941497Z       %aten_permute_copy_default_146 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_7, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0942893Z       %aten_permute_copy_default_147 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_7, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0944275Z       %aten_permute_copy_default_148 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_7, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0945671Z       %aten_permute_copy_default_149 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_7, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0947060Z       %aten_permute_copy_default_150 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_7, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0948440Z       %aten_permute_copy_default_151 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_7, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0949830Z       %aten_permute_copy_default_152 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_7, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0951216Z       %aten_permute_copy_default_153 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_7, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.0952556Z       %aten_squeeze_copy_dims_36 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_12, [4]), kwargs = {})
2025-03-21T20:32:07.0953837Z       %aten_squeeze_copy_dims_37 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_13, [4]), kwargs = {})
2025-03-21T20:32:07.0955121Z       %aten_squeeze_copy_dims_38 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_14, [4]), kwargs = {})
2025-03-21T20:32:07.0956405Z       %aten_squeeze_copy_dims_39 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_15, [4]), kwargs = {})
2025-03-21T20:32:07.0957688Z       %aten_select_copy_int_168 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_142, 0, 0), kwargs = {})
2025-03-21T20:32:07.0958988Z       %aten_select_copy_int_170 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_143, 0, 0), kwargs = {})
2025-03-21T20:32:07.0960270Z       %aten_select_copy_int_172 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_144, 0, 0), kwargs = {})
2025-03-21T20:32:07.0961603Z       %aten_select_copy_int_174 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_145, 0, 0), kwargs = {})
2025-03-21T20:32:07.0962902Z       %aten_select_copy_int_176 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_146, 0, 0), kwargs = {})
2025-03-21T20:32:07.0964211Z       %aten_select_copy_int_178 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_147, 0, 0), kwargs = {})
2025-03-21T20:32:07.0965491Z       %aten_select_copy_int_180 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_148, 0, 0), kwargs = {})
2025-03-21T20:32:07.0966767Z       %aten_select_copy_int_182 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_149, 0, 0), kwargs = {})
2025-03-21T20:32:07.0968045Z       %aten_select_copy_int_184 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_150, 0, 0), kwargs = {})
2025-03-21T20:32:07.0969376Z       %aten_select_copy_int_186 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_151, 0, 0), kwargs = {})
2025-03-21T20:32:07.0970649Z       %aten_select_copy_int_188 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_152, 0, 0), kwargs = {})
2025-03-21T20:32:07.0971922Z       %aten_select_copy_int_190 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_153, 0, 0), kwargs = {})
2025-03-21T20:32:07.0973216Z       %aten_mul_tensor_47 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_36, %aten_view_copy_default_59), kwargs = {})
2025-03-21T20:32:07.0974551Z       %aten_mul_tensor_49 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_36, %aten_view_copy_default_60), kwargs = {})
2025-03-21T20:32:07.0975872Z       %aten_mul_tensor_48 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_37, %aten_view_copy_default_60), kwargs = {})
2025-03-21T20:32:07.0977195Z       %aten_mul_tensor_50 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_37, %aten_view_copy_default_59), kwargs = {})
2025-03-21T20:32:07.0978513Z       %aten_mul_tensor_51 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_38, %aten_view_copy_default_59), kwargs = {})
2025-03-21T20:32:07.0979830Z       %aten_mul_tensor_53 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_38, %aten_view_copy_default_60), kwargs = {})
2025-03-21T20:32:07.0981153Z       %aten_mul_tensor_52 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_39, %aten_view_copy_default_60), kwargs = {})
2025-03-21T20:32:07.0982471Z       %aten_mul_tensor_54 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_39, %aten_view_copy_default_59), kwargs = {})
2025-03-21T20:32:07.0983789Z       %aten_select_copy_int_169 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_168, 0, 0), kwargs = {})
2025-03-21T20:32:07.0985041Z       %aten_select_copy_int_171 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_170, 0, 1), kwargs = {})
2025-03-21T20:32:07.0986311Z       %aten_select_copy_int_173 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_172, 0, 2), kwargs = {})
2025-03-21T20:32:07.0987606Z       %aten_select_copy_int_175 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_174, 0, 3), kwargs = {})
2025-03-21T20:32:07.0988839Z       %aten_select_copy_int_177 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_176, 0, 4), kwargs = {})
2025-03-21T20:32:07.0990080Z       %aten_select_copy_int_179 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_178, 0, 5), kwargs = {})
2025-03-21T20:32:07.0991323Z       %aten_select_copy_int_181 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_180, 0, 6), kwargs = {})
2025-03-21T20:32:07.0992568Z       %aten_select_copy_int_183 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_182, 0, 7), kwargs = {})
2025-03-21T20:32:07.0993822Z       %aten_select_copy_int_185 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_184, 0, 8), kwargs = {})
2025-03-21T20:32:07.0995072Z       %aten_select_copy_int_187 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_186, 0, 9), kwargs = {})
2025-03-21T20:32:07.0996335Z       %aten_select_copy_int_189 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_188, 0, 10), kwargs = {})
2025-03-21T20:32:07.0997602Z       %aten_select_copy_int_191 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_190, 0, 11), kwargs = {})
2025-03-21T20:32:07.0998858Z       %aten_sub_tensor_6 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.sub.Tensor](args = (%aten_mul_tensor_47, %aten_mul_tensor_48), kwargs = {})
2025-03-21T20:32:07.1000095Z       %aten_add_tensor_15 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_mul_tensor_49, %aten_mul_tensor_50), kwargs = {})
2025-03-21T20:32:07.1001323Z       %aten_sub_tensor_7 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.sub.Tensor](args = (%aten_mul_tensor_51, %aten_mul_tensor_52), kwargs = {})
2025-03-21T20:32:07.1002554Z       %aten_add_tensor_16 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_mul_tensor_53, %aten_mul_tensor_54), kwargs = {})
2025-03-21T20:32:07.1004691Z       %aten_cat_default_15 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_select_copy_int_169, %aten_select_copy_int_171, %aten_select_copy_int_173, %aten_select_copy_int_175, %aten_select_copy_int_177, %aten_select_copy_int_179, %aten_select_copy_int_181, %aten_select_copy_int_183, %aten_select_copy_int_185, %aten_select_copy_int_187, %aten_select_copy_int_189, %aten_select_copy_int_191],), kwargs = {})
2025-03-21T20:32:07.1006872Z       %aten_unsqueeze_copy_default_36 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_sub_tensor_6, 4), kwargs = {})
2025-03-21T20:32:07.1008233Z       %aten_unsqueeze_copy_default_37 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_add_tensor_15, 4), kwargs = {})
2025-03-21T20:32:07.1009631Z       %aten_unsqueeze_copy_default_38 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_sub_tensor_7, 4), kwargs = {})
2025-03-21T20:32:07.1010992Z       %aten_unsqueeze_copy_default_39 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_add_tensor_16, 4), kwargs = {})
2025-03-21T20:32:07.1012367Z       %aten_view_copy_default_64 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_15, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:32:07.1013761Z       %aten_cat_default_12 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_unsqueeze_copy_default_36, %aten_unsqueeze_copy_default_37], -1), kwargs = {})
2025-03-21T20:32:07.1015224Z       %aten_cat_default_13 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_unsqueeze_copy_default_38, %aten_unsqueeze_copy_default_39], -1), kwargs = {})
2025-03-21T20:32:07.1016605Z       %aten_view_copy_default_61 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_12, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1017901Z       %aten_view_copy_default_62 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_13, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1019266Z       %aten_permute_copy_default_129 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_view_copy_default_61, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1020865Z       %aten_index_put_default_6 : [num_users=13] = call_function[target=executorch.exir.dialects.edge._ops.aten.index_put.default](args = (%b_layers_3_attention_kv_cache_past_k_caches, [None, %aten__to_copy_default_1], %aten_view_copy_default_62), kwargs = {})
2025-03-21T20:32:07.1022459Z       %aten_permute_copy_default_130 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_6, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1023847Z       %aten_permute_copy_default_131 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_6, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1025237Z       %aten_permute_copy_default_132 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_6, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1026630Z       %aten_permute_copy_default_133 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_6, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1028023Z       %aten_permute_copy_default_134 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_6, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1029414Z       %aten_permute_copy_default_135 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_6, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1030806Z       %aten_permute_copy_default_136 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_6, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1032203Z       %aten_permute_copy_default_137 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_6, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1033777Z       %aten_permute_copy_default_138 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_6, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1035203Z       %aten_permute_copy_default_139 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_6, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1036645Z       %aten_permute_copy_default_140 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_6, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1038070Z       %aten_permute_copy_default_141 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_6, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1039417Z       %aten_select_copy_int_144 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_130, 0, 0), kwargs = {})
2025-03-21T20:32:07.1040690Z       %aten_select_copy_int_146 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_131, 0, 0), kwargs = {})
2025-03-21T20:32:07.1041973Z       %aten_select_copy_int_148 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_132, 0, 0), kwargs = {})
2025-03-21T20:32:07.1043250Z       %aten_select_copy_int_150 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_133, 0, 0), kwargs = {})
2025-03-21T20:32:07.1044527Z       %aten_select_copy_int_152 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_134, 0, 0), kwargs = {})
2025-03-21T20:32:07.1045805Z       %aten_select_copy_int_154 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_135, 0, 0), kwargs = {})
2025-03-21T20:32:07.1047078Z       %aten_select_copy_int_156 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_136, 0, 0), kwargs = {})
2025-03-21T20:32:07.1048358Z       %aten_select_copy_int_158 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_137, 0, 0), kwargs = {})
2025-03-21T20:32:07.1049700Z       %aten_select_copy_int_160 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_138, 0, 0), kwargs = {})
2025-03-21T20:32:07.1050983Z       %aten_select_copy_int_162 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_139, 0, 0), kwargs = {})
2025-03-21T20:32:07.1052258Z       %aten_select_copy_int_164 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_140, 0, 0), kwargs = {})
2025-03-21T20:32:07.1053542Z       %aten_select_copy_int_166 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_141, 0, 0), kwargs = {})
2025-03-21T20:32:07.1054799Z       %aten_select_copy_int_145 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_144, 0, 0), kwargs = {})
2025-03-21T20:32:07.1056057Z       %aten_select_copy_int_147 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_146, 0, 1), kwargs = {})
2025-03-21T20:32:07.1057335Z       %aten_select_copy_int_149 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_148, 0, 2), kwargs = {})
2025-03-21T20:32:07.1058582Z       %aten_select_copy_int_151 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_150, 0, 3), kwargs = {})
2025-03-21T20:32:07.1059859Z       %aten_select_copy_int_153 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_152, 0, 4), kwargs = {})
2025-03-21T20:32:07.1061133Z       %aten_select_copy_int_155 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_154, 0, 5), kwargs = {})
2025-03-21T20:32:07.1062407Z       %aten_select_copy_int_157 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_156, 0, 6), kwargs = {})
2025-03-21T20:32:07.1063656Z       %aten_select_copy_int_159 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_158, 0, 7), kwargs = {})
2025-03-21T20:32:07.1064909Z       %aten_select_copy_int_161 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_160, 0, 8), kwargs = {})
2025-03-21T20:32:07.1066162Z       %aten_select_copy_int_163 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_162, 0, 9), kwargs = {})
2025-03-21T20:32:07.1067421Z       %aten_select_copy_int_165 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_164, 0, 10), kwargs = {})
2025-03-21T20:32:07.1068666Z       %aten_select_copy_int_167 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_166, 0, 11), kwargs = {})
2025-03-21T20:32:07.1070807Z       %aten_cat_default_14 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_select_copy_int_145, %aten_select_copy_int_147, %aten_select_copy_int_149, %aten_select_copy_int_151, %aten_select_copy_int_153, %aten_select_copy_int_155, %aten_select_copy_int_157, %aten_select_copy_int_159, %aten_select_copy_int_161, %aten_select_copy_int_163, %aten_select_copy_int_165, %aten_select_copy_int_167],), kwargs = {})
2025-03-21T20:32:07.1072972Z       %aten_view_copy_default_63 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_14, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:32:07.1074327Z       %aten_permute_copy_default_154 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_view_copy_default_63, [0, 1, 3, 2]), kwargs = {})
2025-03-21T20:32:07.1075767Z       %aten_matmul_default_6 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.matmul.default](args = (%aten_permute_copy_default_129, %aten_permute_copy_default_154), kwargs = {})
2025-03-21T20:32:07.1077135Z       %aten_mul_tensor_55 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_matmul_default_6, %b__frozen_param152), kwargs = {})
2025-03-21T20:32:07.1078381Z       %aten_add_tensor_17 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_mul_tensor_55, %aten_index_tensor_5), kwargs = {})
2025-03-21T20:32:07.1079637Z       %aten__softmax_default_3 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten._softmax.default](args = (%aten_add_tensor_17, -1, False), kwargs = {})
2025-03-21T20:32:07.1080978Z       %aten_matmul_default_7 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.matmul.default](args = (%aten__softmax_default_3, %aten_view_copy_default_64), kwargs = {})
2025-03-21T20:32:07.1082392Z       %aten_permute_copy_default_155 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_matmul_default_7, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1083764Z       %aten_view_copy_default_71 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_permute_copy_default_155, [1, 1, 768]), kwargs = {})
2025-03-21T20:32:07.1085155Z       %aten_unsqueeze_copy_default_40 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_view_copy_default_71, -1), kwargs = {})
2025-03-21T20:32:07.1086617Z       %aten_permute_copy_default_156 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_40, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1088213Z       %aten_convolution_default_24 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_156, %b__frozen_param32, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1089841Z       %aten_permute_copy_default_157 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_24, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1091219Z       %aten_squeeze_copy_dims_40 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_157, [-1]), kwargs = {})
2025-03-21T20:32:07.1092524Z       %aten_add_tensor_18 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_add_tensor_14, %aten_squeeze_copy_dims_40), kwargs = {})
2025-03-21T20:32:07.1093886Z       %aten_rms_norm_default_7 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.rms_norm.default](args = (%aten_add_tensor_18, [768], %b__frozen_param33, 9.999999747378752e-06), kwargs = {})
2025-03-21T20:32:07.1095297Z       %aten_unsqueeze_copy_default_41 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_7, -1), kwargs = {})
2025-03-21T20:32:07.1096660Z       %aten_unsqueeze_copy_default_42 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_7, -1), kwargs = {})
2025-03-21T20:32:07.1098065Z       %aten_permute_copy_default_158 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_41, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1099512Z       %aten_permute_copy_default_160 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_42, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1101110Z       %aten_convolution_default_25 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_158, %b__frozen_param34, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1102849Z       %aten_convolution_default_26 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_160, %b__frozen_param35, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1104435Z       %aten_permute_copy_default_159 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_25, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1105864Z       %aten_permute_copy_default_161 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_26, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1107261Z       %aten_squeeze_copy_dims_41 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_159, [-1]), kwargs = {})
2025-03-21T20:32:07.1108572Z       %aten_squeeze_copy_dims_42 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_161, [-1]), kwargs = {})
2025-03-21T20:32:07.1109883Z       %aten_sigmoid_default_3 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.sigmoid.default](args = (%aten_squeeze_copy_dims_41,), kwargs = {})
2025-03-21T20:32:07.1111223Z       %aten_mul_tensor_58 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_41, %aten_sigmoid_default_3), kwargs = {})
2025-03-21T20:32:07.1112519Z       %aten_mul_tensor_59 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_mul_tensor_58, %aten_squeeze_copy_dims_42), kwargs = {})
2025-03-21T20:32:07.1113826Z       %aten_unsqueeze_copy_default_43 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_mul_tensor_59, -1), kwargs = {})
2025-03-21T20:32:07.1115212Z       %aten_permute_copy_default_162 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_43, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1116814Z       %aten_convolution_default_27 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_162, %b__frozen_param36, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1118396Z       %aten_permute_copy_default_163 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_27, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1119773Z       %aten_squeeze_copy_dims_43 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_163, [-1]), kwargs = {})
2025-03-21T20:32:07.1121078Z       %aten_add_tensor_19 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_add_tensor_18, %aten_squeeze_copy_dims_43), kwargs = {})
2025-03-21T20:32:07.1122450Z       %aten_rms_norm_default_8 : [num_users=3] = call_function[target=executorch.exir.dialects.edge._ops.aten.rms_norm.default](args = (%aten_add_tensor_19, [768], %b__frozen_param37, 9.999999747378752e-06), kwargs = {})
2025-03-21T20:32:07.1123869Z       %aten_unsqueeze_copy_default_44 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_8, -1), kwargs = {})
2025-03-21T20:32:07.1125226Z       %aten_unsqueeze_copy_default_45 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_8, -1), kwargs = {})
2025-03-21T20:32:07.1126590Z       %aten_unsqueeze_copy_default_46 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_8, -1), kwargs = {})
2025-03-21T20:32:07.1127999Z       %aten_permute_copy_default_164 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_44, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1129508Z       %aten_permute_copy_default_166 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_45, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1130960Z       %aten_permute_copy_default_168 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_46, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1132742Z       %aten_convolution_default_28 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_164, %b__frozen_param38, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1134526Z       %aten_convolution_default_29 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_166, %b__frozen_param39, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1136301Z       %aten_convolution_default_30 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_168, %b__frozen_param40, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1137991Z       %aten_permute_copy_default_165 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_28, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1139428Z       %aten_permute_copy_default_167 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_29, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1140855Z       %aten_permute_copy_default_169 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_30, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1142231Z       %aten_squeeze_copy_dims_44 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_165, [-1]), kwargs = {})
2025-03-21T20:32:07.1143552Z       %aten_squeeze_copy_dims_45 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_167, [-1]), kwargs = {})
2025-03-21T20:32:07.1144873Z       %aten_squeeze_copy_dims_46 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_169, [-1]), kwargs = {})
2025-03-21T20:32:07.1146191Z       %aten_view_copy_default_72 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_squeeze_copy_dims_44, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1147533Z       %aten_view_copy_default_73 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_squeeze_copy_dims_45, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1148875Z       %aten_view_copy_default_74 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_squeeze_copy_dims_46, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1150227Z       %aten_view_copy_default_75 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_view_copy_default_72, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:32:07.1151584Z       %aten_view_copy_default_76 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_view_copy_default_73, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:32:07.1153158Z       %aten_index_put_default_9 : [num_users=13] = call_function[target=executorch.exir.dialects.edge._ops.aten.index_put.default](args = (%b_layers_4_attention_kv_cache_past_v_caches, [None, %aten__to_copy_default_1], %aten_view_copy_default_74), kwargs = {})
2025-03-21T20:32:07.1154706Z       %aten_slice_copy_tensor_16 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_75, 4, 0, 1), kwargs = {})
2025-03-21T20:32:07.1156016Z       %aten_slice_copy_tensor_17 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_75, 4, 1, 2), kwargs = {})
2025-03-21T20:32:07.1157350Z       %aten_slice_copy_tensor_18 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_76, 4, 0, 1), kwargs = {})
2025-03-21T20:32:07.1158651Z       %aten_slice_copy_tensor_19 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_76, 4, 1, 2), kwargs = {})
2025-03-21T20:32:07.1160031Z       %aten_permute_copy_default_183 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_9, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1161485Z       %aten_permute_copy_default_184 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_9, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1162880Z       %aten_permute_copy_default_185 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_9, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1164278Z       %aten_permute_copy_default_186 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_9, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1165677Z       %aten_permute_copy_default_187 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_9, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1167071Z       %aten_permute_copy_default_188 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_9, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1168464Z       %aten_permute_copy_default_189 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_9, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1169915Z       %aten_permute_copy_default_190 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_9, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1171310Z       %aten_permute_copy_default_191 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_9, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1172707Z       %aten_permute_copy_default_192 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_9, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1174100Z       %aten_permute_copy_default_193 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_9, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1175492Z       %aten_permute_copy_default_194 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_9, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1176839Z       %aten_squeeze_copy_dims_47 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_16, [4]), kwargs = {})
2025-03-21T20:32:07.1178133Z       %aten_squeeze_copy_dims_48 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_17, [4]), kwargs = {})
2025-03-21T20:32:07.1179411Z       %aten_squeeze_copy_dims_49 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_18, [4]), kwargs = {})
2025-03-21T20:32:07.1180708Z       %aten_squeeze_copy_dims_50 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_19, [4]), kwargs = {})
2025-03-21T20:32:07.1182028Z       %aten_select_copy_int_216 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_183, 0, 0), kwargs = {})
2025-03-21T20:32:07.1183318Z       %aten_select_copy_int_218 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_184, 0, 0), kwargs = {})
2025-03-21T20:32:07.1184624Z       %aten_select_copy_int_220 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_185, 0, 0), kwargs = {})
2025-03-21T20:32:07.1185934Z       %aten_select_copy_int_222 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_186, 0, 0), kwargs = {})
2025-03-21T20:32:07.1187249Z       %aten_select_copy_int_224 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_187, 0, 0), kwargs = {})
2025-03-21T20:32:07.1188537Z       %aten_select_copy_int_226 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_188, 0, 0), kwargs = {})
2025-03-21T20:32:07.1189816Z       %aten_select_copy_int_228 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_189, 0, 0), kwargs = {})
2025-03-21T20:32:07.1191103Z       %aten_select_copy_int_230 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_190, 0, 0), kwargs = {})
2025-03-21T20:32:07.1192388Z       %aten_select_copy_int_232 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_191, 0, 0), kwargs = {})
2025-03-21T20:32:07.1193665Z       %aten_select_copy_int_234 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_192, 0, 0), kwargs = {})
2025-03-21T20:32:07.1194956Z       %aten_select_copy_int_236 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_193, 0, 0), kwargs = {})
2025-03-21T20:32:07.1196240Z       %aten_select_copy_int_238 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_194, 0, 0), kwargs = {})
2025-03-21T20:32:07.1197552Z       %aten_mul_tensor_62 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_47, %aten_view_copy_default_77), kwargs = {})
2025-03-21T20:32:07.1198890Z       %aten_mul_tensor_64 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_47, %aten_view_copy_default_78), kwargs = {})
2025-03-21T20:32:07.1200216Z       %aten_mul_tensor_63 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_48, %aten_view_copy_default_78), kwargs = {})
2025-03-21T20:32:07.1201547Z       %aten_mul_tensor_65 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_48, %aten_view_copy_default_77), kwargs = {})
2025-03-21T20:32:07.1202875Z       %aten_mul_tensor_66 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_49, %aten_view_copy_default_77), kwargs = {})
2025-03-21T20:32:07.1204204Z       %aten_mul_tensor_68 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_49, %aten_view_copy_default_78), kwargs = {})
2025-03-21T20:32:07.1205534Z       %aten_mul_tensor_67 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_50, %aten_view_copy_default_78), kwargs = {})
2025-03-21T20:32:07.1206898Z       %aten_mul_tensor_69 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_50, %aten_view_copy_default_77), kwargs = {})
2025-03-21T20:32:07.1208194Z       %aten_select_copy_int_217 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_216, 0, 0), kwargs = {})
2025-03-21T20:32:07.1208798Z       %aten_select_copy_int_219 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_218, 0, 1), kwargs = {})
2025-03-21T20:32:07.1209500Z       %aten_select_copy_int_221 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_220, 0, 2), kwargs = {})
2025-03-21T20:32:07.1210074Z       %aten_select_copy_int_223 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_222, 0, 3), kwargs = {})
2025-03-21T20:32:07.1210645Z       %aten_select_copy_int_225 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_224, 0, 4), kwargs = {})
2025-03-21T20:32:07.1211228Z       %aten_select_copy_int_227 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_226, 0, 5), kwargs = {})
2025-03-21T20:32:07.1211801Z       %aten_select_copy_int_229 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_228, 0, 6), kwargs = {})
2025-03-21T20:32:07.1212385Z       %aten_select_copy_int_231 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_230, 0, 7), kwargs = {})
2025-03-21T20:32:07.1212956Z       %aten_select_copy_int_233 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_232, 0, 8), kwargs = {})
2025-03-21T20:32:07.1213541Z       %aten_select_copy_int_235 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_234, 0, 9), kwargs = {})
2025-03-21T20:32:07.1214114Z       %aten_select_copy_int_237 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_236, 0, 10), kwargs = {})
2025-03-21T20:32:07.1214697Z       %aten_select_copy_int_239 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_238, 0, 11), kwargs = {})
2025-03-21T20:32:07.1215256Z       %aten_sub_tensor_8 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.sub.Tensor](args = (%aten_mul_tensor_62, %aten_mul_tensor_63), kwargs = {})
2025-03-21T20:32:07.1215822Z       %aten_add_tensor_20 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_mul_tensor_64, %aten_mul_tensor_65), kwargs = {})
2025-03-21T20:32:07.1216377Z       %aten_sub_tensor_9 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.sub.Tensor](args = (%aten_mul_tensor_66, %aten_mul_tensor_67), kwargs = {})
2025-03-21T20:32:07.1216945Z       %aten_add_tensor_21 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_mul_tensor_68, %aten_mul_tensor_69), kwargs = {})
2025-03-21T20:32:07.1218404Z       %aten_cat_default_19 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_select_copy_int_217, %aten_select_copy_int_219, %aten_select_copy_int_221, %aten_select_copy_int_223, %aten_select_copy_int_225, %aten_select_copy_int_227, %aten_select_copy_int_229, %aten_select_copy_int_231, %aten_select_copy_int_233, %aten_select_copy_int_235, %aten_select_copy_int_237, %aten_select_copy_int_239],), kwargs = {})
2025-03-21T20:32:07.1219074Z       %aten_unsqueeze_copy_default_47 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_sub_tensor_8, 4), kwargs = {})
2025-03-21T20:32:07.1219687Z       %aten_unsqueeze_copy_default_48 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_add_tensor_20, 4), kwargs = {})
2025-03-21T20:32:07.1220332Z       %aten_unsqueeze_copy_default_49 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_sub_tensor_9, 4), kwargs = {})
2025-03-21T20:32:07.1220995Z       %aten_unsqueeze_copy_default_50 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_add_tensor_21, 4), kwargs = {})
2025-03-21T20:32:07.1221606Z       %aten_view_copy_default_82 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_19, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:32:07.1222285Z       %aten_cat_default_16 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_unsqueeze_copy_default_47, %aten_unsqueeze_copy_default_48], -1), kwargs = {})
2025-03-21T20:32:07.1222972Z       %aten_cat_default_17 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_unsqueeze_copy_default_49, %aten_unsqueeze_copy_default_50], -1), kwargs = {})
2025-03-21T20:32:07.1223571Z       %aten_view_copy_default_79 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_16, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1224172Z       %aten_view_copy_default_80 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_17, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1224823Z       %aten_permute_copy_default_170 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_view_copy_default_79, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1225671Z       %aten_index_put_default_8 : [num_users=13] = call_function[target=executorch.exir.dialects.edge._ops.aten.index_put.default](args = (%b_layers_4_attention_kv_cache_past_k_caches, [None, %aten__to_copy_default_1], %aten_view_copy_default_80), kwargs = {})
2025-03-21T20:32:07.1226323Z       %aten_permute_copy_default_171 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_8, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1226974Z       %aten_permute_copy_default_172 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_8, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1227613Z       %aten_permute_copy_default_173 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_8, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1228264Z       %aten_permute_copy_default_174 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_8, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1228904Z       %aten_permute_copy_default_175 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_8, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1229558Z       %aten_permute_copy_default_176 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_8, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1230223Z       %aten_permute_copy_default_177 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_8, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1230873Z       %aten_permute_copy_default_178 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_8, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1231539Z       %aten_permute_copy_default_179 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_8, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1232214Z       %aten_permute_copy_default_180 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_8, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1233053Z       %aten_permute_copy_default_181 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_8, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1233707Z       %aten_permute_copy_default_182 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_8, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1234296Z       %aten_select_copy_int_192 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_171, 0, 0), kwargs = {})
2025-03-21T20:32:07.1234906Z       %aten_select_copy_int_194 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_172, 0, 0), kwargs = {})
2025-03-21T20:32:07.1235489Z       %aten_select_copy_int_196 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_173, 0, 0), kwargs = {})
2025-03-21T20:32:07.1236083Z       %aten_select_copy_int_198 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_174, 0, 0), kwargs = {})
2025-03-21T20:32:07.1236668Z       %aten_select_copy_int_200 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_175, 0, 0), kwargs = {})
2025-03-21T20:32:07.1237269Z       %aten_select_copy_int_202 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_176, 0, 0), kwargs = {})
2025-03-21T20:32:07.1237855Z       %aten_select_copy_int_204 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_177, 0, 0), kwargs = {})
2025-03-21T20:32:07.1238451Z       %aten_select_copy_int_206 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_178, 0, 0), kwargs = {})
2025-03-21T20:32:07.1239037Z       %aten_select_copy_int_208 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_179, 0, 0), kwargs = {})
2025-03-21T20:32:07.1239639Z       %aten_select_copy_int_210 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_180, 0, 0), kwargs = {})
2025-03-21T20:32:07.1240223Z       %aten_select_copy_int_212 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_181, 0, 0), kwargs = {})
2025-03-21T20:32:07.1240823Z       %aten_select_copy_int_214 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_182, 0, 0), kwargs = {})
2025-03-21T20:32:07.1241391Z       %aten_select_copy_int_193 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_192, 0, 0), kwargs = {})
2025-03-21T20:32:07.1242018Z       %aten_select_copy_int_195 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_194, 0, 1), kwargs = {})
2025-03-21T20:32:07.1242590Z       %aten_select_copy_int_197 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_196, 0, 2), kwargs = {})
2025-03-21T20:32:07.1243203Z       %aten_select_copy_int_199 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_198, 0, 3), kwargs = {})
2025-03-21T20:32:07.1243803Z       %aten_select_copy_int_201 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_200, 0, 4), kwargs = {})
2025-03-21T20:32:07.1244406Z       %aten_select_copy_int_203 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_202, 0, 5), kwargs = {})
2025-03-21T20:32:07.1244975Z       %aten_select_copy_int_205 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_204, 0, 6), kwargs = {})
2025-03-21T20:32:07.1245552Z       %aten_select_copy_int_207 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_206, 0, 7), kwargs = {})
2025-03-21T20:32:07.1246123Z       %aten_select_copy_int_209 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_208, 0, 8), kwargs = {})
2025-03-21T20:32:07.1246707Z       %aten_select_copy_int_211 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_210, 0, 9), kwargs = {})
2025-03-21T20:32:07.1247279Z       %aten_select_copy_int_213 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_212, 0, 10), kwargs = {})
2025-03-21T20:32:07.1247849Z       %aten_select_copy_int_215 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_214, 0, 11), kwargs = {})
2025-03-21T20:32:07.1249381Z       %aten_cat_default_18 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_select_copy_int_193, %aten_select_copy_int_195, %aten_select_copy_int_197, %aten_select_copy_int_199, %aten_select_copy_int_201, %aten_select_copy_int_203, %aten_select_copy_int_205, %aten_select_copy_int_207, %aten_select_copy_int_209, %aten_select_copy_int_211, %aten_select_copy_int_213, %aten_select_copy_int_215],), kwargs = {})
2025-03-21T20:32:07.1250004Z       %aten_view_copy_default_81 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_18, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:32:07.1250651Z       %aten_permute_copy_default_195 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_view_copy_default_81, [0, 1, 3, 2]), kwargs = {})
2025-03-21T20:32:07.1251348Z       %aten_matmul_default_8 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.matmul.default](args = (%aten_permute_copy_default_170, %aten_permute_copy_default_195), kwargs = {})
2025-03-21T20:32:07.1251923Z       %aten_mul_tensor_70 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_matmul_default_8, %b__frozen_param153), kwargs = {})
2025-03-21T20:32:07.1252498Z       %aten_add_tensor_22 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_mul_tensor_70, %aten_index_tensor_6), kwargs = {})
2025-03-21T20:32:07.1253080Z       %aten__softmax_default_4 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten._softmax.default](args = (%aten_add_tensor_22, -1, False), kwargs = {})
2025-03-21T20:32:07.1253769Z       %aten_matmul_default_9 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.matmul.default](args = (%aten__softmax_default_4, %aten_view_copy_default_82), kwargs = {})
2025-03-21T20:32:07.1254401Z       %aten_permute_copy_default_196 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_matmul_default_9, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1255057Z       %aten_view_copy_default_89 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_permute_copy_default_196, [1, 1, 768]), kwargs = {})
2025-03-21T20:32:07.1255762Z       %aten_unsqueeze_copy_default_51 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_view_copy_default_89, -1), kwargs = {})
2025-03-21T20:32:07.1256443Z       %aten_permute_copy_default_197 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_51, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1257262Z       %aten_convolution_default_31 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_197, %b__frozen_param41, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1257928Z       %aten_permute_copy_default_198 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_31, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1258532Z       %aten_squeeze_copy_dims_51 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_198, [-1]), kwargs = {})
2025-03-21T20:32:07.1259121Z       %aten_add_tensor_23 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_add_tensor_19, %aten_squeeze_copy_dims_51), kwargs = {})
2025-03-21T20:32:07.1259791Z       %aten_rms_norm_default_9 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.rms_norm.default](args = (%aten_add_tensor_23, [768], %b__frozen_param42, 9.999999747378752e-06), kwargs = {})
2025-03-21T20:32:07.1260435Z       %aten_unsqueeze_copy_default_52 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_9, -1), kwargs = {})
2025-03-21T20:32:07.1261060Z       %aten_unsqueeze_copy_default_53 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_9, -1), kwargs = {})
2025-03-21T20:32:07.1261728Z       %aten_permute_copy_default_199 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_52, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1262407Z       %aten_permute_copy_default_201 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_53, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1263229Z       %aten_convolution_default_32 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_199, %b__frozen_param43, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1264044Z       %aten_convolution_default_33 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_201, %b__frozen_param44, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1264704Z       %aten_permute_copy_default_200 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_32, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1265380Z       %aten_permute_copy_default_202 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_33, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1265994Z       %aten_squeeze_copy_dims_52 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_200, [-1]), kwargs = {})
2025-03-21T20:32:07.1266618Z       %aten_squeeze_copy_dims_53 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_202, [-1]), kwargs = {})
2025-03-21T20:32:07.1267237Z       %aten_sigmoid_default_4 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.sigmoid.default](args = (%aten_squeeze_copy_dims_52,), kwargs = {})
2025-03-21T20:32:07.1267848Z       %aten_mul_tensor_73 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_52, %aten_sigmoid_default_4), kwargs = {})
2025-03-21T20:32:07.1268429Z       %aten_mul_tensor_74 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_mul_tensor_73, %aten_squeeze_copy_dims_53), kwargs = {})
2025-03-21T20:32:07.1269050Z       %aten_unsqueeze_copy_default_54 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_mul_tensor_74, -1), kwargs = {})
2025-03-21T20:32:07.1269719Z       %aten_permute_copy_default_203 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_54, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1270543Z       %aten_convolution_default_34 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_203, %b__frozen_param45, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1271200Z       %aten_permute_copy_default_204 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_34, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1271810Z       %aten_squeeze_copy_dims_54 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_204, [-1]), kwargs = {})
2025-03-21T20:32:07.1272391Z       %aten_add_tensor_24 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_add_tensor_23, %aten_squeeze_copy_dims_54), kwargs = {})
2025-03-21T20:32:07.1273073Z       %aten_rms_norm_default_10 : [num_users=3] = call_function[target=executorch.exir.dialects.edge._ops.aten.rms_norm.default](args = (%aten_add_tensor_24, [768], %b__frozen_param46, 9.999999747378752e-06), kwargs = {})
2025-03-21T20:32:07.1273706Z       %aten_unsqueeze_copy_default_55 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_10, -1), kwargs = {})
2025-03-21T20:32:07.1274342Z       %aten_unsqueeze_copy_default_56 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_10, -1), kwargs = {})
2025-03-21T20:32:07.1274968Z       %aten_unsqueeze_copy_default_57 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_10, -1), kwargs = {})
2025-03-21T20:32:07.1275649Z       %aten_permute_copy_default_205 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_55, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1276318Z       %aten_permute_copy_default_207 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_56, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1277020Z       %aten_permute_copy_default_209 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_57, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1277839Z       %aten_convolution_default_35 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_205, %b__frozen_param47, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1278720Z       %aten_convolution_default_36 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_207, %b__frozen_param48, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1279557Z       %aten_convolution_default_37 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_209, %b__frozen_param49, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1280228Z       %aten_permute_copy_default_206 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_35, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1280883Z       %aten_permute_copy_default_208 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_36, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1281548Z       %aten_permute_copy_default_210 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_37, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1282151Z       %aten_squeeze_copy_dims_55 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_206, [-1]), kwargs = {})
2025-03-21T20:32:07.1282763Z       %aten_squeeze_copy_dims_56 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_208, [-1]), kwargs = {})
2025-03-21T20:32:07.1283362Z       %aten_squeeze_copy_dims_57 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_210, [-1]), kwargs = {})
2025-03-21T20:32:07.1283989Z       %aten_view_copy_default_90 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_squeeze_copy_dims_55, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1284606Z       %aten_view_copy_default_91 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_squeeze_copy_dims_56, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1285231Z       %aten_view_copy_default_92 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_squeeze_copy_dims_57, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1285853Z       %aten_view_copy_default_93 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_view_copy_default_90, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:32:07.1286488Z       %aten_view_copy_default_94 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_view_copy_default_91, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:32:07.1287325Z       %aten_index_put_default_11 : [num_users=13] = call_function[target=executorch.exir.dialects.edge._ops.aten.index_put.default](args = (%b_layers_5_attention_kv_cache_past_v_caches, [None, %aten__to_copy_default_1], %aten_view_copy_default_92), kwargs = {})
2025-03-21T20:32:07.1287937Z       %aten_slice_copy_tensor_20 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_93, 4, 0, 1), kwargs = {})
2025-03-21T20:32:07.1288560Z       %aten_slice_copy_tensor_21 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_93, 4, 1, 2), kwargs = {})
2025-03-21T20:32:07.1289164Z       %aten_slice_copy_tensor_22 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_94, 4, 0, 1), kwargs = {})
2025-03-21T20:32:07.1289845Z       %aten_slice_copy_tensor_23 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_94, 4, 1, 2), kwargs = {})
2025-03-21T20:32:07.1290565Z       %aten_permute_copy_default_224 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_11, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1291211Z       %aten_permute_copy_default_225 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_11, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1291869Z       %aten_permute_copy_default_226 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_11, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1292515Z       %aten_permute_copy_default_227 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_11, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1293174Z       %aten_permute_copy_default_228 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_11, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1293816Z       %aten_permute_copy_default_229 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_11, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1294472Z       %aten_permute_copy_default_230 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_11, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1295112Z       %aten_permute_copy_default_231 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_11, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1295769Z       %aten_permute_copy_default_232 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_11, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1296412Z       %aten_permute_copy_default_233 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_11, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1297065Z       %aten_permute_copy_default_234 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_11, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1297709Z       %aten_permute_copy_default_235 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_11, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1298311Z       %aten_squeeze_copy_dims_58 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_20, [4]), kwargs = {})
2025-03-21T20:32:07.1298899Z       %aten_squeeze_copy_dims_59 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_21, [4]), kwargs = {})
2025-03-21T20:32:07.1299499Z       %aten_squeeze_copy_dims_60 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_22, [4]), kwargs = {})
2025-03-21T20:32:07.1300113Z       %aten_squeeze_copy_dims_61 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_23, [4]), kwargs = {})
2025-03-21T20:32:07.1300719Z       %aten_select_copy_int_264 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_224, 0, 0), kwargs = {})
2025-03-21T20:32:07.1301328Z       %aten_select_copy_int_266 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_225, 0, 0), kwargs = {})
2025-03-21T20:32:07.1301985Z       %aten_select_copy_int_268 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_226, 0, 0), kwargs = {})
2025-03-21T20:32:07.1302573Z       %aten_select_copy_int_270 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_227, 0, 0), kwargs = {})
2025-03-21T20:32:07.1303170Z       %aten_select_copy_int_272 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_228, 0, 0), kwargs = {})
2025-03-21T20:32:07.1303755Z       %aten_select_copy_int_274 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_229, 0, 0), kwargs = {})
2025-03-21T20:32:07.1304352Z       %aten_select_copy_int_276 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_230, 0, 0), kwargs = {})
2025-03-21T20:32:07.1304943Z       %aten_select_copy_int_278 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_231, 0, 0), kwargs = {})
2025-03-21T20:32:07.1305544Z       %aten_select_copy_int_280 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_232, 0, 0), kwargs = {})
2025-03-21T20:32:07.1306129Z       %aten_select_copy_int_282 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_233, 0, 0), kwargs = {})
2025-03-21T20:32:07.1306729Z       %aten_select_copy_int_284 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_234, 0, 0), kwargs = {})
2025-03-21T20:32:07.1307317Z       %aten_select_copy_int_286 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_235, 0, 0), kwargs = {})
2025-03-21T20:32:07.1307950Z       %aten_mul_tensor_77 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_58, %aten_view_copy_default_95), kwargs = {})
2025-03-21T20:32:07.1308563Z       %aten_mul_tensor_79 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_58, %aten_view_copy_default_96), kwargs = {})
2025-03-21T20:32:07.1309188Z       %aten_mul_tensor_78 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_59, %aten_view_copy_default_96), kwargs = {})
2025-03-21T20:32:07.1309798Z       %aten_mul_tensor_80 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_59, %aten_view_copy_default_95), kwargs = {})
2025-03-21T20:32:07.1310420Z       %aten_mul_tensor_81 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_60, %aten_view_copy_default_95), kwargs = {})
2025-03-21T20:32:07.1311028Z       %aten_mul_tensor_83 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_60, %aten_view_copy_default_96), kwargs = {})
2025-03-21T20:32:07.1311671Z       %aten_mul_tensor_82 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_61, %aten_view_copy_default_96), kwargs = {})
2025-03-21T20:32:07.1312302Z       %aten_mul_tensor_84 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_61, %aten_view_copy_default_95), kwargs = {})
2025-03-21T20:32:07.1312906Z       %aten_select_copy_int_265 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_264, 0, 0), kwargs = {})
2025-03-21T20:32:07.1313499Z       %aten_select_copy_int_267 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_266, 0, 1), kwargs = {})
2025-03-21T20:32:07.1314080Z       %aten_select_copy_int_269 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_268, 0, 2), kwargs = {})
2025-03-21T20:32:07.1314647Z       %aten_select_copy_int_271 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_270, 0, 3), kwargs = {})
2025-03-21T20:32:07.1315228Z       %aten_select_copy_int_273 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_272, 0, 4), kwargs = {})
2025-03-21T20:32:07.1315796Z       %aten_select_copy_int_275 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_274, 0, 5), kwargs = {})
2025-03-21T20:32:07.1316365Z       %aten_select_copy_int_277 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_276, 0, 6), kwargs = {})
2025-03-21T20:32:07.1316946Z       %aten_select_copy_int_279 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_278, 0, 7), kwargs = {})
2025-03-21T20:32:07.1317512Z       %aten_select_copy_int_281 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_280, 0, 8), kwargs = {})
2025-03-21T20:32:07.1318091Z       %aten_select_copy_int_283 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_282, 0, 9), kwargs = {})
2025-03-21T20:32:07.1318664Z       %aten_select_copy_int_285 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_284, 0, 10), kwargs = {})
2025-03-21T20:32:07.1319245Z       %aten_select_copy_int_287 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_286, 0, 11), kwargs = {})
2025-03-21T20:32:07.1319806Z       %aten_sub_tensor_10 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.sub.Tensor](args = (%aten_mul_tensor_77, %aten_mul_tensor_78), kwargs = {})
2025-03-21T20:32:07.1320371Z       %aten_add_tensor_25 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_mul_tensor_79, %aten_mul_tensor_80), kwargs = {})
2025-03-21T20:32:07.1320926Z       %aten_sub_tensor_11 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.sub.Tensor](args = (%aten_mul_tensor_81, %aten_mul_tensor_82), kwargs = {})
2025-03-21T20:32:07.1321495Z       %aten_add_tensor_26 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_mul_tensor_83, %aten_mul_tensor_84), kwargs = {})
2025-03-21T20:32:07.1322969Z       %aten_cat_default_23 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_select_copy_int_265, %aten_select_copy_int_267, %aten_select_copy_int_269, %aten_select_copy_int_271, %aten_select_copy_int_273, %aten_select_copy_int_275, %aten_select_copy_int_277, %aten_select_copy_int_279, %aten_select_copy_int_281, %aten_select_copy_int_283, %aten_select_copy_int_285, %aten_select_copy_int_287],), kwargs = {})
2025-03-21T20:32:07.1323616Z       %aten_unsqueeze_copy_default_58 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_sub_tensor_10, 4), kwargs = {})
2025-03-21T20:32:07.1324248Z       %aten_unsqueeze_copy_default_59 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_add_tensor_25, 4), kwargs = {})
2025-03-21T20:32:07.1324891Z       %aten_unsqueeze_copy_default_60 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_sub_tensor_11, 4), kwargs = {})
2025-03-21T20:32:07.1325498Z       %aten_unsqueeze_copy_default_61 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_add_tensor_26, 4), kwargs = {})
2025-03-21T20:32:07.1326111Z       %aten_view_copy_default_100 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_23, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:32:07.1326790Z       %aten_cat_default_20 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_unsqueeze_copy_default_58, %aten_unsqueeze_copy_default_59], -1), kwargs = {})
2025-03-21T20:32:07.1327477Z       %aten_cat_default_21 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_unsqueeze_copy_default_60, %aten_unsqueeze_copy_default_61], -1), kwargs = {})
2025-03-21T20:32:07.1328072Z       %aten_view_copy_default_97 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_20, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1328675Z       %aten_view_copy_default_98 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_21, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1329377Z       %aten_permute_copy_default_211 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_view_copy_default_97, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1330233Z       %aten_index_put_default_10 : [num_users=13] = call_function[target=executorch.exir.dialects.edge._ops.aten.index_put.default](args = (%b_layers_5_attention_kv_cache_past_k_caches, [None, %aten__to_copy_default_1], %aten_view_copy_default_98), kwargs = {})
2025-03-21T20:32:07.1330881Z       %aten_permute_copy_default_212 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_10, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1331537Z       %aten_permute_copy_default_213 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_10, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1332177Z       %aten_permute_copy_default_214 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_10, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1332957Z       %aten_permute_copy_default_215 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_10, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1333604Z       %aten_permute_copy_default_216 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_10, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1334311Z       %aten_permute_copy_default_217 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_10, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1334958Z       %aten_permute_copy_default_218 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_10, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1335646Z       %aten_permute_copy_default_219 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_10, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1336339Z       %aten_permute_copy_default_220 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_10, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1337022Z       %aten_permute_copy_default_221 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_10, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1337664Z       %aten_permute_copy_default_222 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_10, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1338321Z       %aten_permute_copy_default_223 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_10, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1338908Z       %aten_select_copy_int_240 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_212, 0, 0), kwargs = {})
2025-03-21T20:32:07.1339510Z       %aten_select_copy_int_242 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_213, 0, 0), kwargs = {})
2025-03-21T20:32:07.1340097Z       %aten_select_copy_int_244 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_214, 0, 0), kwargs = {})
2025-03-21T20:32:07.1340694Z       %aten_select_copy_int_246 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_215, 0, 0), kwargs = {})
2025-03-21T20:32:07.1341281Z       %aten_select_copy_int_248 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_216, 0, 0), kwargs = {})
2025-03-21T20:32:07.1341880Z       %aten_select_copy_int_250 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_217, 0, 0), kwargs = {})
2025-03-21T20:32:07.1342462Z       %aten_select_copy_int_252 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_218, 0, 0), kwargs = {})
2025-03-21T20:32:07.1343062Z       %aten_select_copy_int_254 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_219, 0, 0), kwargs = {})
2025-03-21T20:32:07.1343644Z       %aten_select_copy_int_256 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_220, 0, 0), kwargs = {})
2025-03-21T20:32:07.1344242Z       %aten_select_copy_int_258 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_221, 0, 0), kwargs = {})
2025-03-21T20:32:07.1344826Z       %aten_select_copy_int_260 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_222, 0, 0), kwargs = {})
2025-03-21T20:32:07.1345422Z       %aten_select_copy_int_262 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_223, 0, 0), kwargs = {})
2025-03-21T20:32:07.1346018Z       %aten_select_copy_int_241 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_240, 0, 0), kwargs = {})
2025-03-21T20:32:07.1346602Z       %aten_select_copy_int_243 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_242, 0, 1), kwargs = {})
2025-03-21T20:32:07.1347210Z       %aten_select_copy_int_245 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_244, 0, 2), kwargs = {})
2025-03-21T20:32:07.1347838Z       %aten_select_copy_int_247 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_246, 0, 3), kwargs = {})
2025-03-21T20:32:07.1348408Z       %aten_select_copy_int_249 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_248, 0, 4), kwargs = {})
2025-03-21T20:32:07.1348990Z       %aten_select_copy_int_251 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_250, 0, 5), kwargs = {})
2025-03-21T20:32:07.1349559Z       %aten_select_copy_int_253 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_252, 0, 6), kwargs = {})
2025-03-21T20:32:07.1350142Z       %aten_select_copy_int_255 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_254, 0, 7), kwargs = {})
2025-03-21T20:32:07.1350710Z       %aten_select_copy_int_257 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_256, 0, 8), kwargs = {})
2025-03-21T20:32:07.1351294Z       %aten_select_copy_int_259 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_258, 0, 9), kwargs = {})
2025-03-21T20:32:07.1351865Z       %aten_select_copy_int_261 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_260, 0, 10), kwargs = {})
2025-03-21T20:32:07.1352454Z       %aten_select_copy_int_263 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_262, 0, 11), kwargs = {})
2025-03-21T20:32:07.1353909Z       %aten_cat_default_22 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_select_copy_int_241, %aten_select_copy_int_243, %aten_select_copy_int_245, %aten_select_copy_int_247, %aten_select_copy_int_249, %aten_select_copy_int_251, %aten_select_copy_int_253, %aten_select_copy_int_255, %aten_select_copy_int_257, %aten_select_copy_int_259, %aten_select_copy_int_261, %aten_select_copy_int_263],), kwargs = {})
2025-03-21T20:32:07.1354526Z       %aten_view_copy_default_99 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_22, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:32:07.1355175Z       %aten_permute_copy_default_236 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_view_copy_default_99, [0, 1, 3, 2]), kwargs = {})
2025-03-21T20:32:07.1355872Z       %aten_matmul_default_10 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.matmul.default](args = (%aten_permute_copy_default_211, %aten_permute_copy_default_236), kwargs = {})
2025-03-21T20:32:07.1356454Z       %aten_mul_tensor_85 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_matmul_default_10, %b__frozen_param154), kwargs = {})
2025-03-21T20:32:07.1357030Z       %aten_add_tensor_27 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_mul_tensor_85, %aten_index_tensor_7), kwargs = {})
2025-03-21T20:32:07.1357635Z       %aten__softmax_default_5 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten._softmax.default](args = (%aten_add_tensor_27, -1, False), kwargs = {})
2025-03-21T20:32:07.1358328Z       %aten_matmul_default_11 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.matmul.default](args = (%aten__softmax_default_5, %aten_view_copy_default_100), kwargs = {})
2025-03-21T20:32:07.1359048Z       %aten_permute_copy_default_237 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_matmul_default_11, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1359709Z       %aten_view_copy_default_107 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_permute_copy_default_237, [1, 1, 768]), kwargs = {})
2025-03-21T20:32:07.1360349Z       %aten_unsqueeze_copy_default_62 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_view_copy_default_107, -1), kwargs = {})
2025-03-21T20:32:07.1361026Z       %aten_permute_copy_default_238 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_62, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1361848Z       %aten_convolution_default_38 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_238, %b__frozen_param50, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1362522Z       %aten_permute_copy_default_239 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_38, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1363127Z       %aten_squeeze_copy_dims_62 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_239, [-1]), kwargs = {})
2025-03-21T20:32:07.1363723Z       %aten_add_tensor_28 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_add_tensor_24, %aten_squeeze_copy_dims_62), kwargs = {})
2025-03-21T20:32:07.1364399Z       %aten_rms_norm_default_11 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.rms_norm.default](args = (%aten_add_tensor_28, [768], %b__frozen_param51, 9.999999747378752e-06), kwargs = {})
2025-03-21T20:32:07.1365049Z       %aten_unsqueeze_copy_default_63 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_11, -1), kwargs = {})
2025-03-21T20:32:07.1365679Z       %aten_unsqueeze_copy_default_64 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_11, -1), kwargs = {})
2025-03-21T20:32:07.1366361Z       %aten_permute_copy_default_240 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_63, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1367028Z       %aten_permute_copy_default_242 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_64, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1367862Z       %aten_convolution_default_39 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_240, %b__frozen_param52, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1368675Z       %aten_convolution_default_40 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_242, %b__frozen_param53, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1369435Z       %aten_permute_copy_default_241 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_39, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1370088Z       %aten_permute_copy_default_243 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_40, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1370754Z       %aten_squeeze_copy_dims_63 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_241, [-1]), kwargs = {})
2025-03-21T20:32:07.1371375Z       %aten_squeeze_copy_dims_64 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_243, [-1]), kwargs = {})
2025-03-21T20:32:07.1371965Z       %aten_sigmoid_default_5 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.sigmoid.default](args = (%aten_squeeze_copy_dims_63,), kwargs = {})
2025-03-21T20:32:07.1372563Z       %aten_mul_tensor_88 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_63, %aten_sigmoid_default_5), kwargs = {})
2025-03-21T20:32:07.1373157Z       %aten_mul_tensor_89 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_mul_tensor_88, %aten_squeeze_copy_dims_64), kwargs = {})
2025-03-21T20:32:07.1373770Z       %aten_unsqueeze_copy_default_65 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_mul_tensor_89, -1), kwargs = {})
2025-03-21T20:32:07.1374449Z       %aten_permute_copy_default_244 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_65, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1375266Z       %aten_convolution_default_41 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_244, %b__frozen_param54, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1375931Z       %aten_permute_copy_default_245 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_41, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1376534Z       %aten_squeeze_copy_dims_65 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_245, [-1]), kwargs = {})
2025-03-21T20:32:07.1377125Z       %aten_add_tensor_29 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_add_tensor_28, %aten_squeeze_copy_dims_65), kwargs = {})
2025-03-21T20:32:07.1377799Z       %aten_rms_norm_default_12 : [num_users=3] = call_function[target=executorch.exir.dialects.edge._ops.aten.rms_norm.default](args = (%aten_add_tensor_29, [768], %b__frozen_param55, 9.999999747378752e-06), kwargs = {})
2025-03-21T20:32:07.1378438Z       %aten_unsqueeze_copy_default_66 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_12, -1), kwargs = {})
2025-03-21T20:32:07.1379067Z       %aten_unsqueeze_copy_default_67 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_12, -1), kwargs = {})
2025-03-21T20:32:07.1379697Z       %aten_unsqueeze_copy_default_68 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_12, -1), kwargs = {})
2025-03-21T20:32:07.1380374Z       %aten_permute_copy_default_246 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_66, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1381064Z       %aten_permute_copy_default_248 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_67, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1381765Z       %aten_permute_copy_default_250 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_68, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1382603Z       %aten_convolution_default_42 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_246, %b__frozen_param56, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1383452Z       %aten_convolution_default_43 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_248, %b__frozen_param57, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1384277Z       %aten_convolution_default_44 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_250, %b__frozen_param58, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1384936Z       %aten_permute_copy_default_247 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_42, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1385608Z       %aten_permute_copy_default_249 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_43, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1386260Z       %aten_permute_copy_default_251 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_44, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1386875Z       %aten_squeeze_copy_dims_66 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_247, [-1]), kwargs = {})
2025-03-21T20:32:07.1387475Z       %aten_squeeze_copy_dims_67 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_249, [-1]), kwargs = {})
2025-03-21T20:32:07.1388077Z       %aten_squeeze_copy_dims_68 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_251, [-1]), kwargs = {})
2025-03-21T20:32:07.1388723Z       %aten_view_copy_default_108 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_squeeze_copy_dims_66, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1389344Z       %aten_view_copy_default_109 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_squeeze_copy_dims_67, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1389972Z       %aten_view_copy_default_110 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_squeeze_copy_dims_68, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1390603Z       %aten_view_copy_default_111 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_view_copy_default_108, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:32:07.1391243Z       %aten_view_copy_default_112 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_view_copy_default_109, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:32:07.1392120Z       %aten_index_put_default_13 : [num_users=13] = call_function[target=executorch.exir.dialects.edge._ops.aten.index_put.default](args = (%b_layers_6_attention_kv_cache_past_v_caches, [None, %aten__to_copy_default_1], %aten_view_copy_default_110), kwargs = {})
2025-03-21T20:32:07.1392733Z       %aten_slice_copy_tensor_24 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_111, 4, 0, 1), kwargs = {})
2025-03-21T20:32:07.1393355Z       %aten_slice_copy_tensor_25 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_111, 4, 1, 2), kwargs = {})
2025-03-21T20:32:07.1393984Z       %aten_slice_copy_tensor_26 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_112, 4, 0, 1), kwargs = {})
2025-03-21T20:32:07.1394602Z       %aten_slice_copy_tensor_27 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_112, 4, 1, 2), kwargs = {})
2025-03-21T20:32:07.1395259Z       %aten_permute_copy_default_265 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_13, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1395903Z       %aten_permute_copy_default_266 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_13, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1396556Z       %aten_permute_copy_default_267 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_13, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1397200Z       %aten_permute_copy_default_268 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_13, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1397850Z       %aten_permute_copy_default_269 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_13, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1398490Z       %aten_permute_copy_default_270 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_13, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1399145Z       %aten_permute_copy_default_271 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_13, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1399786Z       %aten_permute_copy_default_272 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_13, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1400440Z       %aten_permute_copy_default_273 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_13, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1401081Z       %aten_permute_copy_default_274 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_13, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1401732Z       %aten_permute_copy_default_275 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_13, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1402376Z       %aten_permute_copy_default_276 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_13, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1402984Z       %aten_squeeze_copy_dims_69 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_24, [4]), kwargs = {})
2025-03-21T20:32:07.1403576Z       %aten_squeeze_copy_dims_70 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_25, [4]), kwargs = {})
2025-03-21T20:32:07.1404203Z       %aten_squeeze_copy_dims_71 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_26, [4]), kwargs = {})
2025-03-21T20:32:07.1404815Z       %aten_squeeze_copy_dims_72 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_27, [4]), kwargs = {})
2025-03-21T20:32:07.1405441Z       %aten_select_copy_int_312 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_265, 0, 0), kwargs = {})
2025-03-21T20:32:07.1406058Z       %aten_select_copy_int_314 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_266, 0, 0), kwargs = {})
2025-03-21T20:32:07.1406657Z       %aten_select_copy_int_316 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_267, 0, 0), kwargs = {})
2025-03-21T20:32:07.1407242Z       %aten_select_copy_int_318 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_268, 0, 0), kwargs = {})
2025-03-21T20:32:07.1407844Z       %aten_select_copy_int_320 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_269, 0, 0), kwargs = {})
2025-03-21T20:32:07.1408432Z       %aten_select_copy_int_322 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_270, 0, 0), kwargs = {})
2025-03-21T20:32:07.1409029Z       %aten_select_copy_int_324 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_271, 0, 0), kwargs = {})
2025-03-21T20:32:07.1409672Z       %aten_select_copy_int_326 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_272, 0, 0), kwargs = {})
2025-03-21T20:32:07.1410271Z       %aten_select_copy_int_328 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_273, 0, 0), kwargs = {})
2025-03-21T20:32:07.1410855Z       %aten_select_copy_int_330 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_274, 0, 0), kwargs = {})
2025-03-21T20:32:07.1411456Z       %aten_select_copy_int_332 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_275, 0, 0), kwargs = {})
2025-03-21T20:32:07.1412041Z       %aten_select_copy_int_334 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_276, 0, 0), kwargs = {})
2025-03-21T20:32:07.1412669Z       %aten_mul_tensor_92 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_69, %aten_view_copy_default_113), kwargs = {})
2025-03-21T20:32:07.1413277Z       %aten_mul_tensor_94 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_69, %aten_view_copy_default_114), kwargs = {})
2025-03-21T20:32:07.1413902Z       %aten_mul_tensor_93 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_70, %aten_view_copy_default_114), kwargs = {})
2025-03-21T20:32:07.1414516Z       %aten_mul_tensor_95 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_70, %aten_view_copy_default_113), kwargs = {})
2025-03-21T20:32:07.1415164Z       %aten_mul_tensor_96 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_71, %aten_view_copy_default_113), kwargs = {})
2025-03-21T20:32:07.1415774Z       %aten_mul_tensor_98 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_71, %aten_view_copy_default_114), kwargs = {})
2025-03-21T20:32:07.1416419Z       %aten_mul_tensor_97 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_72, %aten_view_copy_default_114), kwargs = {})
2025-03-21T20:32:07.1417051Z       %aten_mul_tensor_99 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_72, %aten_view_copy_default_113), kwargs = {})
2025-03-21T20:32:07.1417657Z       %aten_select_copy_int_313 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_312, 0, 0), kwargs = {})
2025-03-21T20:32:07.1418227Z       %aten_select_copy_int_315 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_314, 0, 1), kwargs = {})
2025-03-21T20:32:07.1418809Z       %aten_select_copy_int_317 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_316, 0, 2), kwargs = {})
2025-03-21T20:32:07.1419378Z       %aten_select_copy_int_319 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_318, 0, 3), kwargs = {})
2025-03-21T20:32:07.1419961Z       %aten_select_copy_int_321 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_320, 0, 4), kwargs = {})
2025-03-21T20:32:07.1420528Z       %aten_select_copy_int_323 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_322, 0, 5), kwargs = {})
2025-03-21T20:32:07.1421110Z       %aten_select_copy_int_325 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_324, 0, 6), kwargs = {})
2025-03-21T20:32:07.1421676Z       %aten_select_copy_int_327 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_326, 0, 7), kwargs = {})
2025-03-21T20:32:07.1422257Z       %aten_select_copy_int_329 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_328, 0, 8), kwargs = {})
2025-03-21T20:32:07.1422828Z       %aten_select_copy_int_331 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_330, 0, 9), kwargs = {})
2025-03-21T20:32:07.1423401Z       %aten_select_copy_int_333 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_332, 0, 10), kwargs = {})
2025-03-21T20:32:07.1423986Z       %aten_select_copy_int_335 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_334, 0, 11), kwargs = {})
2025-03-21T20:32:07.1424545Z       %aten_sub_tensor_12 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.sub.Tensor](args = (%aten_mul_tensor_92, %aten_mul_tensor_93), kwargs = {})
2025-03-21T20:32:07.1425119Z       %aten_add_tensor_30 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_mul_tensor_94, %aten_mul_tensor_95), kwargs = {})
2025-03-21T20:32:07.1425676Z       %aten_sub_tensor_13 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.sub.Tensor](args = (%aten_mul_tensor_96, %aten_mul_tensor_97), kwargs = {})
2025-03-21T20:32:07.1426288Z       %aten_add_tensor_31 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_mul_tensor_98, %aten_mul_tensor_99), kwargs = {})
2025-03-21T20:32:07.1427746Z       %aten_cat_default_27 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_select_copy_int_313, %aten_select_copy_int_315, %aten_select_copy_int_317, %aten_select_copy_int_319, %aten_select_copy_int_321, %aten_select_copy_int_323, %aten_select_copy_int_325, %aten_select_copy_int_327, %aten_select_copy_int_329, %aten_select_copy_int_331, %aten_select_copy_int_333, %aten_select_copy_int_335],), kwargs = {})
2025-03-21T20:32:07.1428414Z       %aten_unsqueeze_copy_default_69 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_sub_tensor_12, 4), kwargs = {})
2025-03-21T20:32:07.1429074Z       %aten_unsqueeze_copy_default_70 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_add_tensor_30, 4), kwargs = {})
2025-03-21T20:32:07.1429682Z       %aten_unsqueeze_copy_default_71 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_sub_tensor_13, 4), kwargs = {})
2025-03-21T20:32:07.1430286Z       %aten_unsqueeze_copy_default_72 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_add_tensor_31, 4), kwargs = {})
2025-03-21T20:32:07.1430901Z       %aten_view_copy_default_118 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_27, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:32:07.1431579Z       %aten_cat_default_24 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_unsqueeze_copy_default_69, %aten_unsqueeze_copy_default_70], -1), kwargs = {})
2025-03-21T20:32:07.1432419Z       %aten_cat_default_25 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_unsqueeze_copy_default_71, %aten_unsqueeze_copy_default_72], -1), kwargs = {})
2025-03-21T20:32:07.1433020Z       %aten_view_copy_default_115 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_24, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1433631Z       %aten_view_copy_default_116 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_25, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1434283Z       %aten_permute_copy_default_252 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_view_copy_default_115, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1435136Z       %aten_index_put_default_12 : [num_users=13] = call_function[target=executorch.exir.dialects.edge._ops.aten.index_put.default](args = (%b_layers_6_attention_kv_cache_past_k_caches, [None, %aten__to_copy_default_1], %aten_view_copy_default_116), kwargs = {})
2025-03-21T20:32:07.1435782Z       %aten_permute_copy_default_253 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_12, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1436441Z       %aten_permute_copy_default_254 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_12, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1437082Z       %aten_permute_copy_default_255 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_12, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1437738Z       %aten_permute_copy_default_256 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_12, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1438427Z       %aten_permute_copy_default_257 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_12, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1439082Z       %aten_permute_copy_default_258 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_12, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1439757Z       %aten_permute_copy_default_259 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_12, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1440477Z       %aten_permute_copy_default_260 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_12, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1441123Z       %aten_permute_copy_default_261 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_12, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1441781Z       %aten_permute_copy_default_262 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_12, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1442423Z       %aten_permute_copy_default_263 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_12, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1443078Z       %aten_permute_copy_default_264 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_12, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1443668Z       %aten_select_copy_int_288 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_253, 0, 0), kwargs = {})
2025-03-21T20:32:07.1444268Z       %aten_select_copy_int_290 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_254, 0, 0), kwargs = {})
2025-03-21T20:32:07.1444853Z       %aten_select_copy_int_292 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_255, 0, 0), kwargs = {})
2025-03-21T20:32:07.1445454Z       %aten_select_copy_int_294 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_256, 0, 0), kwargs = {})
2025-03-21T20:32:07.1446040Z       %aten_select_copy_int_296 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_257, 0, 0), kwargs = {})
2025-03-21T20:32:07.1446637Z       %aten_select_copy_int_298 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_258, 0, 0), kwargs = {})
2025-03-21T20:32:07.1447223Z       %aten_select_copy_int_300 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_259, 0, 0), kwargs = {})
2025-03-21T20:32:07.1447815Z       %aten_select_copy_int_302 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_260, 0, 0), kwargs = {})
2025-03-21T20:32:07.1448398Z       %aten_select_copy_int_304 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_261, 0, 0), kwargs = {})
2025-03-21T20:32:07.1448993Z       %aten_select_copy_int_306 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_262, 0, 0), kwargs = {})
2025-03-21T20:32:07.1449709Z       %aten_select_copy_int_308 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_263, 0, 0), kwargs = {})
2025-03-21T20:32:07.1450309Z       %aten_select_copy_int_310 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_264, 0, 0), kwargs = {})
2025-03-21T20:32:07.1450903Z       %aten_select_copy_int_289 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_288, 0, 0), kwargs = {})
2025-03-21T20:32:07.1451511Z       %aten_select_copy_int_291 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_290, 0, 1), kwargs = {})
2025-03-21T20:32:07.1452105Z       %aten_select_copy_int_293 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_292, 0, 2), kwargs = {})
2025-03-21T20:32:07.1452690Z       %aten_select_copy_int_295 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_294, 0, 3), kwargs = {})
2025-03-21T20:32:07.1453256Z       %aten_select_copy_int_297 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_296, 0, 4), kwargs = {})
2025-03-21T20:32:07.1453838Z       %aten_select_copy_int_299 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_298, 0, 5), kwargs = {})
2025-03-21T20:32:07.1454411Z       %aten_select_copy_int_301 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_300, 0, 6), kwargs = {})
2025-03-21T20:32:07.1454993Z       %aten_select_copy_int_303 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_302, 0, 7), kwargs = {})
2025-03-21T20:32:07.1455560Z       %aten_select_copy_int_305 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_304, 0, 8), kwargs = {})
2025-03-21T20:32:07.1456141Z       %aten_select_copy_int_307 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_306, 0, 9), kwargs = {})
2025-03-21T20:32:07.1456715Z       %aten_select_copy_int_309 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_308, 0, 10), kwargs = {})
2025-03-21T20:32:07.1457304Z       %aten_select_copy_int_311 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_310, 0, 11), kwargs = {})
2025-03-21T20:32:07.1458761Z       %aten_cat_default_26 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_select_copy_int_289, %aten_select_copy_int_291, %aten_select_copy_int_293, %aten_select_copy_int_295, %aten_select_copy_int_297, %aten_select_copy_int_299, %aten_select_copy_int_301, %aten_select_copy_int_303, %aten_select_copy_int_305, %aten_select_copy_int_307, %aten_select_copy_int_309, %aten_select_copy_int_311],), kwargs = {})
2025-03-21T20:32:07.1459384Z       %aten_view_copy_default_117 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_26, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:32:07.1460033Z       %aten_permute_copy_default_277 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_view_copy_default_117, [0, 1, 3, 2]), kwargs = {})
2025-03-21T20:32:07.1460731Z       %aten_matmul_default_12 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.matmul.default](args = (%aten_permute_copy_default_252, %aten_permute_copy_default_277), kwargs = {})
2025-03-21T20:32:07.1461342Z       %aten_mul_tensor_100 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_matmul_default_12, %b__frozen_param155), kwargs = {})
2025-03-21T20:32:07.1461924Z       %aten_add_tensor_32 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_mul_tensor_100, %aten_index_tensor_8), kwargs = {})
2025-03-21T20:32:07.1462537Z       %aten__softmax_default_6 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten._softmax.default](args = (%aten_add_tensor_32, -1, False), kwargs = {})
2025-03-21T20:32:07.1463224Z       %aten_matmul_default_13 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.matmul.default](args = (%aten__softmax_default_6, %aten_view_copy_default_118), kwargs = {})
2025-03-21T20:32:07.1463884Z       %aten_permute_copy_default_278 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_matmul_default_13, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1464524Z       %aten_view_copy_default_125 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_permute_copy_default_278, [1, 1, 768]), kwargs = {})
2025-03-21T20:32:07.1465166Z       %aten_unsqueeze_copy_default_73 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_view_copy_default_125, -1), kwargs = {})
2025-03-21T20:32:07.1465851Z       %aten_permute_copy_default_279 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_73, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1466673Z       %aten_convolution_default_45 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_279, %b__frozen_param59, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1467344Z       %aten_permute_copy_default_280 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_45, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1467948Z       %aten_squeeze_copy_dims_73 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_280, [-1]), kwargs = {})
2025-03-21T20:32:07.1468545Z       %aten_add_tensor_33 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_add_tensor_29, %aten_squeeze_copy_dims_73), kwargs = {})
2025-03-21T20:32:07.1469221Z       %aten_rms_norm_default_13 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.rms_norm.default](args = (%aten_add_tensor_33, [768], %b__frozen_param60, 9.999999747378752e-06), kwargs = {})
2025-03-21T20:32:07.1469866Z       %aten_unsqueeze_copy_default_74 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_13, -1), kwargs = {})
2025-03-21T20:32:07.1470496Z       %aten_unsqueeze_copy_default_75 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_13, -1), kwargs = {})
2025-03-21T20:32:07.1471179Z       %aten_permute_copy_default_281 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_74, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1471849Z       %aten_permute_copy_default_283 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_75, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1472681Z       %aten_convolution_default_46 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_281, %b__frozen_param61, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1473518Z       %aten_convolution_default_47 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_283, %b__frozen_param62, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1474209Z       %aten_permute_copy_default_282 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_46, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1474899Z       %aten_permute_copy_default_284 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_47, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1475540Z       %aten_squeeze_copy_dims_74 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_282, [-1]), kwargs = {})
2025-03-21T20:32:07.1476140Z       %aten_squeeze_copy_dims_75 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_284, [-1]), kwargs = {})
2025-03-21T20:32:07.1476724Z       %aten_sigmoid_default_6 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.sigmoid.default](args = (%aten_squeeze_copy_dims_74,), kwargs = {})
2025-03-21T20:32:07.1477333Z       %aten_mul_tensor_103 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_74, %aten_sigmoid_default_6), kwargs = {})
2025-03-21T20:32:07.1477941Z       %aten_mul_tensor_104 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_mul_tensor_103, %aten_squeeze_copy_dims_75), kwargs = {})
2025-03-21T20:32:07.1478556Z       %aten_unsqueeze_copy_default_76 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_mul_tensor_104, -1), kwargs = {})
2025-03-21T20:32:07.1479235Z       %aten_permute_copy_default_285 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_76, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1480055Z       %aten_convolution_default_48 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_285, %b__frozen_param63, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1480723Z       %aten_permute_copy_default_286 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_48, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1481328Z       %aten_squeeze_copy_dims_76 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_286, [-1]), kwargs = {})
2025-03-21T20:32:07.1481922Z       %aten_add_tensor_34 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_add_tensor_33, %aten_squeeze_copy_dims_76), kwargs = {})
2025-03-21T20:32:07.1482591Z       %aten_rms_norm_default_14 : [num_users=3] = call_function[target=executorch.exir.dialects.edge._ops.aten.rms_norm.default](args = (%aten_add_tensor_34, [768], %b__frozen_param64, 9.999999747378752e-06), kwargs = {})
2025-03-21T20:32:07.1483233Z       %aten_unsqueeze_copy_default_77 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_14, -1), kwargs = {})
2025-03-21T20:32:07.1483864Z       %aten_unsqueeze_copy_default_78 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_14, -1), kwargs = {})
2025-03-21T20:32:07.1484526Z       %aten_unsqueeze_copy_default_79 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_14, -1), kwargs = {})
2025-03-21T20:32:07.1485192Z       %aten_permute_copy_default_287 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_77, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1485891Z       %aten_permute_copy_default_289 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_78, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1486581Z       %aten_permute_copy_default_291 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_79, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1487433Z       %aten_convolution_default_49 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_287, %b__frozen_param65, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1488243Z       %aten_convolution_default_50 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_289, %b__frozen_param66, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1489065Z       %aten_convolution_default_51 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_291, %b__frozen_param67, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1489786Z       %aten_permute_copy_default_288 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_49, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1490453Z       %aten_permute_copy_default_290 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_50, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1491104Z       %aten_permute_copy_default_292 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_51, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1491720Z       %aten_squeeze_copy_dims_77 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_288, [-1]), kwargs = {})
2025-03-21T20:32:07.1492323Z       %aten_squeeze_copy_dims_78 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_290, [-1]), kwargs = {})
2025-03-21T20:32:07.1492939Z       %aten_squeeze_copy_dims_79 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_292, [-1]), kwargs = {})
2025-03-21T20:32:07.1493566Z       %aten_view_copy_default_126 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_squeeze_copy_dims_77, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1494196Z       %aten_view_copy_default_127 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_squeeze_copy_dims_78, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1494815Z       %aten_view_copy_default_128 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_squeeze_copy_dims_79, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1495464Z       %aten_view_copy_default_129 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_view_copy_default_126, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:32:07.1496127Z       %aten_view_copy_default_130 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_view_copy_default_127, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:32:07.1496979Z       %aten_index_put_default_15 : [num_users=13] = call_function[target=executorch.exir.dialects.edge._ops.aten.index_put.default](args = (%b_layers_7_attention_kv_cache_past_v_caches, [None, %aten__to_copy_default_1], %aten_view_copy_default_128), kwargs = {})
2025-03-21T20:32:07.1497605Z       %aten_slice_copy_tensor_28 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_129, 4, 0, 1), kwargs = {})
2025-03-21T20:32:07.1498246Z       %aten_slice_copy_tensor_29 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_129, 4, 1, 2), kwargs = {})
2025-03-21T20:32:07.1498866Z       %aten_slice_copy_tensor_30 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_130, 4, 0, 1), kwargs = {})
2025-03-21T20:32:07.1499476Z       %aten_slice_copy_tensor_31 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_130, 4, 1, 2), kwargs = {})
2025-03-21T20:32:07.1500124Z       %aten_permute_copy_default_306 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_15, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1500786Z       %aten_permute_copy_default_307 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_15, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1501435Z       %aten_permute_copy_default_308 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_15, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1502093Z       %aten_permute_copy_default_309 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_15, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1502738Z       %aten_permute_copy_default_310 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_15, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1503396Z       %aten_permute_copy_default_311 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_15, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1504041Z       %aten_permute_copy_default_312 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_15, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1504684Z       %aten_permute_copy_default_313 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_15, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1505338Z       %aten_permute_copy_default_314 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_15, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1505983Z       %aten_permute_copy_default_315 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_15, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1506635Z       %aten_permute_copy_default_316 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_15, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1507277Z       %aten_permute_copy_default_317 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_15, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1507901Z       %aten_squeeze_copy_dims_80 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_28, [4]), kwargs = {})
2025-03-21T20:32:07.1508492Z       %aten_squeeze_copy_dims_81 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_29, [4]), kwargs = {})
2025-03-21T20:32:07.1509115Z       %aten_squeeze_copy_dims_82 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_30, [4]), kwargs = {})
2025-03-21T20:32:07.1509726Z       %aten_squeeze_copy_dims_83 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_31, [4]), kwargs = {})
2025-03-21T20:32:07.1510348Z       %aten_select_copy_int_360 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_306, 0, 0), kwargs = {})
2025-03-21T20:32:07.1510934Z       %aten_select_copy_int_362 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_307, 0, 0), kwargs = {})
2025-03-21T20:32:07.1511531Z       %aten_select_copy_int_364 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_308, 0, 0), kwargs = {})
2025-03-21T20:32:07.1512115Z       %aten_select_copy_int_366 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_309, 0, 0), kwargs = {})
2025-03-21T20:32:07.1512714Z       %aten_select_copy_int_368 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_310, 0, 0), kwargs = {})
2025-03-21T20:32:07.1513295Z       %aten_select_copy_int_370 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_311, 0, 0), kwargs = {})
2025-03-21T20:32:07.1513891Z       %aten_select_copy_int_372 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_312, 0, 0), kwargs = {})
2025-03-21T20:32:07.1514473Z       %aten_select_copy_int_374 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_313, 0, 0), kwargs = {})
2025-03-21T20:32:07.1515069Z       %aten_select_copy_int_376 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_314, 0, 0), kwargs = {})
2025-03-21T20:32:07.1515652Z       %aten_select_copy_int_378 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_315, 0, 0), kwargs = {})
2025-03-21T20:32:07.1516247Z       %aten_select_copy_int_380 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_316, 0, 0), kwargs = {})
2025-03-21T20:32:07.1516828Z       %aten_select_copy_int_382 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_317, 0, 0), kwargs = {})
2025-03-21T20:32:07.1517457Z       %aten_mul_tensor_107 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_80, %aten_view_copy_default_131), kwargs = {})
2025-03-21T20:32:07.1518072Z       %aten_mul_tensor_109 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_80, %aten_view_copy_default_132), kwargs = {})
2025-03-21T20:32:07.1518700Z       %aten_mul_tensor_108 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_81, %aten_view_copy_default_132), kwargs = {})
2025-03-21T20:32:07.1519337Z       %aten_mul_tensor_110 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_81, %aten_view_copy_default_131), kwargs = {})
2025-03-21T20:32:07.1519961Z       %aten_mul_tensor_111 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_82, %aten_view_copy_default_131), kwargs = {})
2025-03-21T20:32:07.1520608Z       %aten_mul_tensor_113 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_82, %aten_view_copy_default_132), kwargs = {})
2025-03-21T20:32:07.1521280Z       %aten_mul_tensor_112 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_83, %aten_view_copy_default_132), kwargs = {})
2025-03-21T20:32:07.1521894Z       %aten_mul_tensor_114 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_83, %aten_view_copy_default_131), kwargs = {})
2025-03-21T20:32:07.1522479Z       %aten_select_copy_int_361 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_360, 0, 0), kwargs = {})
2025-03-21T20:32:07.1523048Z       %aten_select_copy_int_363 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_362, 0, 1), kwargs = {})
2025-03-21T20:32:07.1523631Z       %aten_select_copy_int_365 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_364, 0, 2), kwargs = {})
2025-03-21T20:32:07.1524199Z       %aten_select_copy_int_367 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_366, 0, 3), kwargs = {})
2025-03-21T20:32:07.1524779Z       %aten_select_copy_int_369 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_368, 0, 4), kwargs = {})
2025-03-21T20:32:07.1525345Z       %aten_select_copy_int_371 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_370, 0, 5), kwargs = {})
2025-03-21T20:32:07.1525924Z       %aten_select_copy_int_373 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_372, 0, 6), kwargs = {})
2025-03-21T20:32:07.1526491Z       %aten_select_copy_int_375 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_374, 0, 7), kwargs = {})
2025-03-21T20:32:07.1527072Z       %aten_select_copy_int_377 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_376, 0, 8), kwargs = {})
2025-03-21T20:32:07.1527641Z       %aten_select_copy_int_379 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_378, 0, 9), kwargs = {})
2025-03-21T20:32:07.1528225Z       %aten_select_copy_int_381 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_380, 0, 10), kwargs = {})
2025-03-21T20:32:07.1528799Z       %aten_select_copy_int_383 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_382, 0, 11), kwargs = {})
2025-03-21T20:32:07.1529449Z       %aten_sub_tensor_14 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.sub.Tensor](args = (%aten_mul_tensor_107, %aten_mul_tensor_108), kwargs = {})
2025-03-21T20:32:07.1530015Z       %aten_add_tensor_35 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_mul_tensor_109, %aten_mul_tensor_110), kwargs = {})
2025-03-21T20:32:07.1530617Z       %aten_sub_tensor_15 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.sub.Tensor](args = (%aten_mul_tensor_111, %aten_mul_tensor_112), kwargs = {})
2025-03-21T20:32:07.1531177Z       %aten_add_tensor_36 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_mul_tensor_113, %aten_mul_tensor_114), kwargs = {})
2025-03-21T20:32:07.1532836Z       %aten_cat_default_31 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_select_copy_int_361, %aten_select_copy_int_363, %aten_select_copy_int_365, %aten_select_copy_int_367, %aten_select_copy_int_369, %aten_select_copy_int_371, %aten_select_copy_int_373, %aten_select_copy_int_375, %aten_select_copy_int_377, %aten_select_copy_int_379, %aten_select_copy_int_381, %aten_select_copy_int_383],), kwargs = {})
2025-03-21T20:32:07.1533489Z       %aten_unsqueeze_copy_default_80 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_sub_tensor_14, 4), kwargs = {})
2025-03-21T20:32:07.1534111Z       %aten_unsqueeze_copy_default_81 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_add_tensor_35, 4), kwargs = {})
2025-03-21T20:32:07.1534717Z       %aten_unsqueeze_copy_default_82 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_sub_tensor_15, 4), kwargs = {})
2025-03-21T20:32:07.1535338Z       %aten_unsqueeze_copy_default_83 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_add_tensor_36, 4), kwargs = {})
2025-03-21T20:32:07.1535945Z       %aten_view_copy_default_136 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_31, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:32:07.1536638Z       %aten_cat_default_28 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_unsqueeze_copy_default_80, %aten_unsqueeze_copy_default_81], -1), kwargs = {})
2025-03-21T20:32:07.1537313Z       %aten_cat_default_29 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_unsqueeze_copy_default_82, %aten_unsqueeze_copy_default_83], -1), kwargs = {})
2025-03-21T20:32:07.1537927Z       %aten_view_copy_default_133 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_28, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1538525Z       %aten_view_copy_default_134 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_29, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1539187Z       %aten_permute_copy_default_293 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_view_copy_default_133, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1540029Z       %aten_index_put_default_14 : [num_users=13] = call_function[target=executorch.exir.dialects.edge._ops.aten.index_put.default](args = (%b_layers_7_attention_kv_cache_past_k_caches, [None, %aten__to_copy_default_1], %aten_view_copy_default_134), kwargs = {})
2025-03-21T20:32:07.1540686Z       %aten_permute_copy_default_294 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_14, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1541335Z       %aten_permute_copy_default_295 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_14, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1541987Z       %aten_permute_copy_default_296 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_14, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1542658Z       %aten_permute_copy_default_297 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_14, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1543406Z       %aten_permute_copy_default_298 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_14, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1544069Z       %aten_permute_copy_default_299 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_14, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1544746Z       %aten_permute_copy_default_300 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_14, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1545386Z       %aten_permute_copy_default_301 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_14, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1546040Z       %aten_permute_copy_default_302 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_14, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1546680Z       %aten_permute_copy_default_303 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_14, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1547334Z       %aten_permute_copy_default_304 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_14, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1547974Z       %aten_permute_copy_default_305 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_14, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1548564Z       %aten_select_copy_int_336 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_294, 0, 0), kwargs = {})
2025-03-21T20:32:07.1549161Z       %aten_select_copy_int_338 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_295, 0, 0), kwargs = {})
2025-03-21T20:32:07.1549750Z       %aten_select_copy_int_340 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_296, 0, 0), kwargs = {})
2025-03-21T20:32:07.1550346Z       %aten_select_copy_int_342 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_297, 0, 0), kwargs = {})
2025-03-21T20:32:07.1550929Z       %aten_select_copy_int_344 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_298, 0, 0), kwargs = {})
2025-03-21T20:32:07.1551526Z       %aten_select_copy_int_346 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_299, 0, 0), kwargs = {})
2025-03-21T20:32:07.1552114Z       %aten_select_copy_int_348 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_300, 0, 0), kwargs = {})
2025-03-21T20:32:07.1552708Z       %aten_select_copy_int_350 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_301, 0, 0), kwargs = {})
2025-03-21T20:32:07.1553295Z       %aten_select_copy_int_352 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_302, 0, 0), kwargs = {})
2025-03-21T20:32:07.1553913Z       %aten_select_copy_int_354 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_303, 0, 0), kwargs = {})
2025-03-21T20:32:07.1554499Z       %aten_select_copy_int_356 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_304, 0, 0), kwargs = {})
2025-03-21T20:32:07.1555121Z       %aten_select_copy_int_358 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_305, 0, 0), kwargs = {})
2025-03-21T20:32:07.1555737Z       %aten_select_copy_int_337 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_336, 0, 0), kwargs = {})
2025-03-21T20:32:07.1556318Z       %aten_select_copy_int_339 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_338, 0, 1), kwargs = {})
2025-03-21T20:32:07.1556886Z       %aten_select_copy_int_341 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_340, 0, 2), kwargs = {})
2025-03-21T20:32:07.1557463Z       %aten_select_copy_int_343 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_342, 0, 3), kwargs = {})
2025-03-21T20:32:07.1558032Z       %aten_select_copy_int_345 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_344, 0, 4), kwargs = {})
2025-03-21T20:32:07.1558614Z       %aten_select_copy_int_347 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_346, 0, 5), kwargs = {})
2025-03-21T20:32:07.1559185Z       %aten_select_copy_int_349 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_348, 0, 6), kwargs = {})
2025-03-21T20:32:07.1559768Z       %aten_select_copy_int_351 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_350, 0, 7), kwargs = {})
2025-03-21T20:32:07.1560338Z       %aten_select_copy_int_353 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_352, 0, 8), kwargs = {})
2025-03-21T20:32:07.1560921Z       %aten_select_copy_int_355 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_354, 0, 9), kwargs = {})
2025-03-21T20:32:07.1561490Z       %aten_select_copy_int_357 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_356, 0, 10), kwargs = {})
2025-03-21T20:32:07.1562073Z       %aten_select_copy_int_359 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_358, 0, 11), kwargs = {})
2025-03-21T20:32:07.1563526Z       %aten_cat_default_30 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_select_copy_int_337, %aten_select_copy_int_339, %aten_select_copy_int_341, %aten_select_copy_int_343, %aten_select_copy_int_345, %aten_select_copy_int_347, %aten_select_copy_int_349, %aten_select_copy_int_351, %aten_select_copy_int_353, %aten_select_copy_int_355, %aten_select_copy_int_357, %aten_select_copy_int_359],), kwargs = {})
2025-03-21T20:32:07.1564143Z       %aten_view_copy_default_135 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_30, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:32:07.1564794Z       %aten_permute_copy_default_318 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_view_copy_default_135, [0, 1, 3, 2]), kwargs = {})
2025-03-21T20:32:07.1565523Z       %aten_matmul_default_14 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.matmul.default](args = (%aten_permute_copy_default_293, %aten_permute_copy_default_318), kwargs = {})
2025-03-21T20:32:07.1566130Z       %aten_mul_tensor_115 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_matmul_default_14, %b__frozen_param156), kwargs = {})
2025-03-21T20:32:07.1566733Z       %aten_add_tensor_37 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_mul_tensor_115, %aten_index_tensor_9), kwargs = {})
2025-03-21T20:32:07.1567335Z       %aten__softmax_default_7 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten._softmax.default](args = (%aten_add_tensor_37, -1, False), kwargs = {})
2025-03-21T20:32:07.1567998Z       %aten_matmul_default_15 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.matmul.default](args = (%aten__softmax_default_7, %aten_view_copy_default_136), kwargs = {})
2025-03-21T20:32:07.1568634Z       %aten_permute_copy_default_319 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_matmul_default_15, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1569331Z       %aten_view_copy_default_143 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_permute_copy_default_319, [1, 1, 768]), kwargs = {})
2025-03-21T20:32:07.1569973Z       %aten_unsqueeze_copy_default_84 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_view_copy_default_143, -1), kwargs = {})
2025-03-21T20:32:07.1570661Z       %aten_permute_copy_default_320 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_84, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1571484Z       %aten_convolution_default_52 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_320, %b__frozen_param68, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1572156Z       %aten_permute_copy_default_321 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_52, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1572762Z       %aten_squeeze_copy_dims_84 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_321, [-1]), kwargs = {})
2025-03-21T20:32:07.1573358Z       %aten_add_tensor_38 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_add_tensor_34, %aten_squeeze_copy_dims_84), kwargs = {})
2025-03-21T20:32:07.1574033Z       %aten_rms_norm_default_15 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.rms_norm.default](args = (%aten_add_tensor_38, [768], %b__frozen_param69, 9.999999747378752e-06), kwargs = {})
2025-03-21T20:32:07.1574676Z       %aten_unsqueeze_copy_default_85 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_15, -1), kwargs = {})
2025-03-21T20:32:07.1575305Z       %aten_unsqueeze_copy_default_86 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_15, -1), kwargs = {})
2025-03-21T20:32:07.1575983Z       %aten_permute_copy_default_322 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_85, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1576676Z       %aten_permute_copy_default_324 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_86, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1577510Z       %aten_convolution_default_53 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_322, %b__frozen_param70, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1578350Z       %aten_convolution_default_54 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_324, %b__frozen_param71, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1579066Z       %aten_permute_copy_default_323 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_53, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1579721Z       %aten_permute_copy_default_325 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_54, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1580332Z       %aten_squeeze_copy_dims_85 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_323, [-1]), kwargs = {})
2025-03-21T20:32:07.1580936Z       %aten_squeeze_copy_dims_86 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_325, [-1]), kwargs = {})
2025-03-21T20:32:07.1581525Z       %aten_sigmoid_default_7 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.sigmoid.default](args = (%aten_squeeze_copy_dims_85,), kwargs = {})
2025-03-21T20:32:07.1582131Z       %aten_mul_tensor_118 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_85, %aten_sigmoid_default_7), kwargs = {})
2025-03-21T20:32:07.1582736Z       %aten_mul_tensor_119 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_mul_tensor_118, %aten_squeeze_copy_dims_86), kwargs = {})
2025-03-21T20:32:07.1583347Z       %aten_unsqueeze_copy_default_87 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_mul_tensor_119, -1), kwargs = {})
2025-03-21T20:32:07.1584028Z       %aten_permute_copy_default_326 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_87, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1584845Z       %aten_convolution_default_55 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_326, %b__frozen_param72, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1585515Z       %aten_permute_copy_default_327 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_55, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1586115Z       %aten_squeeze_copy_dims_87 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_327, [-1]), kwargs = {})
2025-03-21T20:32:07.1586709Z       %aten_add_tensor_39 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_add_tensor_38, %aten_squeeze_copy_dims_87), kwargs = {})
2025-03-21T20:32:07.1587380Z       %aten_rms_norm_default_16 : [num_users=3] = call_function[target=executorch.exir.dialects.edge._ops.aten.rms_norm.default](args = (%aten_add_tensor_39, [768], %b__frozen_param73, 9.999999747378752e-06), kwargs = {})
2025-03-21T20:32:07.1588025Z       %aten_unsqueeze_copy_default_88 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_16, -1), kwargs = {})
2025-03-21T20:32:07.1588677Z       %aten_unsqueeze_copy_default_89 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_16, -1), kwargs = {})
2025-03-21T20:32:07.1589318Z       %aten_unsqueeze_copy_default_90 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_16, -1), kwargs = {})
2025-03-21T20:32:07.1590012Z       %aten_permute_copy_default_328 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_88, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1590734Z       %aten_permute_copy_default_330 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_89, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1591403Z       %aten_permute_copy_default_332 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_90, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1592232Z       %aten_convolution_default_56 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_328, %b__frozen_param74, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1593045Z       %aten_convolution_default_57 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_330, %b__frozen_param75, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1593871Z       %aten_convolution_default_58 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_332, %b__frozen_param76, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1594526Z       %aten_permute_copy_default_329 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_56, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1595191Z       %aten_permute_copy_default_331 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_57, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1595845Z       %aten_permute_copy_default_333 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_58, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1596463Z       %aten_squeeze_copy_dims_88 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_329, [-1]), kwargs = {})
2025-03-21T20:32:07.1597068Z       %aten_squeeze_copy_dims_89 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_331, [-1]), kwargs = {})
2025-03-21T20:32:07.1597683Z       %aten_squeeze_copy_dims_90 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_333, [-1]), kwargs = {})
2025-03-21T20:32:07.1598308Z       %aten_view_copy_default_144 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_squeeze_copy_dims_88, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1598945Z       %aten_view_copy_default_145 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_squeeze_copy_dims_89, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1599567Z       %aten_view_copy_default_146 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_squeeze_copy_dims_90, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1600237Z       %aten_view_copy_default_147 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_view_copy_default_144, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:32:07.1600870Z       %aten_view_copy_default_148 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_view_copy_default_145, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:32:07.1601776Z       %aten_index_put_default_17 : [num_users=13] = call_function[target=executorch.exir.dialects.edge._ops.aten.index_put.default](args = (%b_layers_8_attention_kv_cache_past_v_caches, [None, %aten__to_copy_default_1], %aten_view_copy_default_146), kwargs = {})
2025-03-21T20:32:07.1602413Z       %aten_slice_copy_tensor_32 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_147, 4, 0, 1), kwargs = {})
2025-03-21T20:32:07.1603027Z       %aten_slice_copy_tensor_33 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_147, 4, 1, 2), kwargs = {})
2025-03-21T20:32:07.1603621Z       %aten_slice_copy_tensor_34 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_148, 4, 0, 1), kwargs = {})
2025-03-21T20:32:07.1604229Z       %aten_slice_copy_tensor_35 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_148, 4, 1, 2), kwargs = {})
2025-03-21T20:32:07.1604874Z       %aten_permute_copy_default_347 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_17, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1605531Z       %aten_permute_copy_default_348 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_17, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1606176Z       %aten_permute_copy_default_349 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_17, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1606827Z       %aten_permute_copy_default_350 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_17, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1607471Z       %aten_permute_copy_default_351 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_17, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1608126Z       %aten_permute_copy_default_352 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_17, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1608768Z       %aten_permute_copy_default_353 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_17, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1609477Z       %aten_permute_copy_default_354 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_17, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1610120Z       %aten_permute_copy_default_355 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_17, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1610778Z       %aten_permute_copy_default_356 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_17, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1611420Z       %aten_permute_copy_default_357 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_17, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1612109Z       %aten_permute_copy_default_358 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_17, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1612724Z       %aten_squeeze_copy_dims_91 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_32, [4]), kwargs = {})
2025-03-21T20:32:07.1613324Z       %aten_squeeze_copy_dims_92 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_33, [4]), kwargs = {})
2025-03-21T20:32:07.1613961Z       %aten_squeeze_copy_dims_93 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_34, [4]), kwargs = {})
2025-03-21T20:32:07.1614562Z       %aten_squeeze_copy_dims_94 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_35, [4]), kwargs = {})
2025-03-21T20:32:07.1615149Z       %aten_select_copy_int_408 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_347, 0, 0), kwargs = {})
2025-03-21T20:32:07.1615734Z       %aten_select_copy_int_410 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_348, 0, 0), kwargs = {})
2025-03-21T20:32:07.1616334Z       %aten_select_copy_int_412 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_349, 0, 0), kwargs = {})
2025-03-21T20:32:07.1616917Z       %aten_select_copy_int_414 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_350, 0, 0), kwargs = {})
2025-03-21T20:32:07.1617511Z       %aten_select_copy_int_416 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_351, 0, 0), kwargs = {})
2025-03-21T20:32:07.1618094Z       %aten_select_copy_int_418 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_352, 0, 0), kwargs = {})
2025-03-21T20:32:07.1618689Z       %aten_select_copy_int_420 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_353, 0, 0), kwargs = {})
2025-03-21T20:32:07.1619271Z       %aten_select_copy_int_422 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_354, 0, 0), kwargs = {})
2025-03-21T20:32:07.1619867Z       %aten_select_copy_int_424 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_355, 0, 0), kwargs = {})
2025-03-21T20:32:07.1620453Z       %aten_select_copy_int_426 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_356, 0, 0), kwargs = {})
2025-03-21T20:32:07.1621049Z       %aten_select_copy_int_428 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_357, 0, 0), kwargs = {})
2025-03-21T20:32:07.1621636Z       %aten_select_copy_int_430 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_358, 0, 0), kwargs = {})
2025-03-21T20:32:07.1622270Z       %aten_mul_tensor_122 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_91, %aten_view_copy_default_149), kwargs = {})
2025-03-21T20:32:07.1622911Z       %aten_mul_tensor_124 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_91, %aten_view_copy_default_150), kwargs = {})
2025-03-21T20:32:07.1623536Z       %aten_mul_tensor_123 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_92, %aten_view_copy_default_150), kwargs = {})
2025-03-21T20:32:07.1624177Z       %aten_mul_tensor_125 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_92, %aten_view_copy_default_149), kwargs = {})
2025-03-21T20:32:07.1624824Z       %aten_mul_tensor_126 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_93, %aten_view_copy_default_149), kwargs = {})
2025-03-21T20:32:07.1625461Z       %aten_mul_tensor_128 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_93, %aten_view_copy_default_150), kwargs = {})
2025-03-21T20:32:07.1626088Z       %aten_mul_tensor_127 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_94, %aten_view_copy_default_150), kwargs = {})
2025-03-21T20:32:07.1626701Z       %aten_mul_tensor_129 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_94, %aten_view_copy_default_149), kwargs = {})
2025-03-21T20:32:07.1627282Z       %aten_select_copy_int_409 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_408, 0, 0), kwargs = {})
2025-03-21T20:32:07.1627949Z       %aten_select_copy_int_411 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_410, 0, 1), kwargs = {})
2025-03-21T20:32:07.1628536Z       %aten_select_copy_int_413 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_412, 0, 2), kwargs = {})
2025-03-21T20:32:07.1629109Z       %aten_select_copy_int_415 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_414, 0, 3), kwargs = {})
2025-03-21T20:32:07.1629688Z       %aten_select_copy_int_417 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_416, 0, 4), kwargs = {})
2025-03-21T20:32:07.1630257Z       %aten_select_copy_int_419 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_418, 0, 5), kwargs = {})
2025-03-21T20:32:07.1630846Z       %aten_select_copy_int_421 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_420, 0, 6), kwargs = {})
2025-03-21T20:32:07.1631412Z       %aten_select_copy_int_423 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_422, 0, 7), kwargs = {})
2025-03-21T20:32:07.1631995Z       %aten_select_copy_int_425 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_424, 0, 8), kwargs = {})
2025-03-21T20:32:07.1632685Z       %aten_select_copy_int_427 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_426, 0, 9), kwargs = {})
2025-03-21T20:32:07.1633276Z       %aten_select_copy_int_429 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_428, 0, 10), kwargs = {})
2025-03-21T20:32:07.1633848Z       %aten_select_copy_int_431 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_430, 0, 11), kwargs = {})
2025-03-21T20:32:07.1634475Z       %aten_sub_tensor_16 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.sub.Tensor](args = (%aten_mul_tensor_122, %aten_mul_tensor_123), kwargs = {})
2025-03-21T20:32:07.1635039Z       %aten_add_tensor_40 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_mul_tensor_124, %aten_mul_tensor_125), kwargs = {})
2025-03-21T20:32:07.1635651Z       %aten_sub_tensor_17 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.sub.Tensor](args = (%aten_mul_tensor_126, %aten_mul_tensor_127), kwargs = {})
2025-03-21T20:32:07.1636248Z       %aten_add_tensor_41 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_mul_tensor_128, %aten_mul_tensor_129), kwargs = {})
2025-03-21T20:32:07.1637748Z       %aten_cat_default_35 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_select_copy_int_409, %aten_select_copy_int_411, %aten_select_copy_int_413, %aten_select_copy_int_415, %aten_select_copy_int_417, %aten_select_copy_int_419, %aten_select_copy_int_421, %aten_select_copy_int_423, %aten_select_copy_int_425, %aten_select_copy_int_427, %aten_select_copy_int_429, %aten_select_copy_int_431],), kwargs = {})
2025-03-21T20:32:07.1638357Z       %aten_unsqueeze_copy_default_91 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_sub_tensor_16, 4), kwargs = {})
2025-03-21T20:32:07.1638980Z       %aten_unsqueeze_copy_default_92 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_add_tensor_40, 4), kwargs = {})
2025-03-21T20:32:07.1639590Z       %aten_unsqueeze_copy_default_93 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_sub_tensor_17, 4), kwargs = {})
2025-03-21T20:32:07.1640208Z       %aten_unsqueeze_copy_default_94 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_add_tensor_41, 4), kwargs = {})
2025-03-21T20:32:07.1640815Z       %aten_view_copy_default_154 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_35, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:32:07.1641513Z       %aten_cat_default_32 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_unsqueeze_copy_default_91, %aten_unsqueeze_copy_default_92], -1), kwargs = {})
2025-03-21T20:32:07.1642189Z       %aten_cat_default_33 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_unsqueeze_copy_default_93, %aten_unsqueeze_copy_default_94], -1), kwargs = {})
2025-03-21T20:32:07.1642802Z       %aten_view_copy_default_151 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_32, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1643404Z       %aten_view_copy_default_152 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_33, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1644062Z       %aten_permute_copy_default_334 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_view_copy_default_151, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1644907Z       %aten_index_put_default_16 : [num_users=13] = call_function[target=executorch.exir.dialects.edge._ops.aten.index_put.default](args = (%b_layers_8_attention_kv_cache_past_k_caches, [None, %aten__to_copy_default_1], %aten_view_copy_default_152), kwargs = {})
2025-03-21T20:32:07.1645570Z       %aten_permute_copy_default_335 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_16, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1646237Z       %aten_permute_copy_default_336 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_16, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1646890Z       %aten_permute_copy_default_337 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_16, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1647558Z       %aten_permute_copy_default_338 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_16, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1648249Z       %aten_permute_copy_default_339 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_16, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1648915Z       %aten_permute_copy_default_340 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_16, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1649625Z       %aten_permute_copy_default_341 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_16, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1650269Z       %aten_permute_copy_default_342 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_16, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1650923Z       %aten_permute_copy_default_343 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_16, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1651566Z       %aten_permute_copy_default_344 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_16, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1652219Z       %aten_permute_copy_default_345 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_16, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1652856Z       %aten_permute_copy_default_346 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_16, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1653458Z       %aten_select_copy_int_384 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_335, 0, 0), kwargs = {})
2025-03-21T20:32:07.1654050Z       %aten_select_copy_int_386 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_336, 0, 0), kwargs = {})
2025-03-21T20:32:07.1654649Z       %aten_select_copy_int_388 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_337, 0, 0), kwargs = {})
2025-03-21T20:32:07.1655233Z       %aten_select_copy_int_390 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_338, 0, 0), kwargs = {})
2025-03-21T20:32:07.1655827Z       %aten_select_copy_int_392 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_339, 0, 0), kwargs = {})
2025-03-21T20:32:07.1656411Z       %aten_select_copy_int_394 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_340, 0, 0), kwargs = {})
2025-03-21T20:32:07.1657000Z       %aten_select_copy_int_396 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_341, 0, 0), kwargs = {})
2025-03-21T20:32:07.1657621Z       %aten_select_copy_int_398 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_342, 0, 0), kwargs = {})
2025-03-21T20:32:07.1658205Z       %aten_select_copy_int_400 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_343, 0, 0), kwargs = {})
2025-03-21T20:32:07.1658825Z       %aten_select_copy_int_402 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_344, 0, 0), kwargs = {})
2025-03-21T20:32:07.1659428Z       %aten_select_copy_int_404 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_345, 0, 0), kwargs = {})
2025-03-21T20:32:07.1660047Z       %aten_select_copy_int_406 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_346, 0, 0), kwargs = {})
2025-03-21T20:32:07.1660623Z       %aten_select_copy_int_385 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_384, 0, 0), kwargs = {})
2025-03-21T20:32:07.1661204Z       %aten_select_copy_int_387 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_386, 0, 1), kwargs = {})
2025-03-21T20:32:07.1661774Z       %aten_select_copy_int_389 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_388, 0, 2), kwargs = {})
2025-03-21T20:32:07.1662359Z       %aten_select_copy_int_391 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_390, 0, 3), kwargs = {})
2025-03-21T20:32:07.1662929Z       %aten_select_copy_int_393 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_392, 0, 4), kwargs = {})
2025-03-21T20:32:07.1663513Z       %aten_select_copy_int_395 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_394, 0, 5), kwargs = {})
2025-03-21T20:32:07.1664080Z       %aten_select_copy_int_397 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_396, 0, 6), kwargs = {})
2025-03-21T20:32:07.1664659Z       %aten_select_copy_int_399 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_398, 0, 7), kwargs = {})
2025-03-21T20:32:07.1665230Z       %aten_select_copy_int_401 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_400, 0, 8), kwargs = {})
2025-03-21T20:32:07.1665814Z       %aten_select_copy_int_403 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_402, 0, 9), kwargs = {})
2025-03-21T20:32:07.1666385Z       %aten_select_copy_int_405 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_404, 0, 10), kwargs = {})
2025-03-21T20:32:07.1666966Z       %aten_select_copy_int_407 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_406, 0, 11), kwargs = {})
2025-03-21T20:32:07.1668419Z       %aten_cat_default_34 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_select_copy_int_385, %aten_select_copy_int_387, %aten_select_copy_int_389, %aten_select_copy_int_391, %aten_select_copy_int_393, %aten_select_copy_int_395, %aten_select_copy_int_397, %aten_select_copy_int_399, %aten_select_copy_int_401, %aten_select_copy_int_403, %aten_select_copy_int_405, %aten_select_copy_int_407],), kwargs = {})
2025-03-21T20:32:07.1669061Z       %aten_view_copy_default_153 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_34, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:32:07.1669709Z       %aten_permute_copy_default_359 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_view_copy_default_153, [0, 1, 3, 2]), kwargs = {})
2025-03-21T20:32:07.1670429Z       %aten_matmul_default_16 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.matmul.default](args = (%aten_permute_copy_default_334, %aten_permute_copy_default_359), kwargs = {})
2025-03-21T20:32:07.1671034Z       %aten_mul_tensor_130 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_matmul_default_16, %b__frozen_param157), kwargs = {})
2025-03-21T20:32:07.1671641Z       %aten_add_tensor_42 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_mul_tensor_130, %aten_index_tensor_10), kwargs = {})
2025-03-21T20:32:07.1672229Z       %aten__softmax_default_8 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten._softmax.default](args = (%aten_add_tensor_42, -1, False), kwargs = {})
2025-03-21T20:32:07.1672885Z       %aten_matmul_default_17 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.matmul.default](args = (%aten__softmax_default_8, %aten_view_copy_default_154), kwargs = {})
2025-03-21T20:32:07.1673522Z       %aten_permute_copy_default_360 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_matmul_default_17, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1674161Z       %aten_view_copy_default_161 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_permute_copy_default_360, [1, 1, 768]), kwargs = {})
2025-03-21T20:32:07.1674801Z       %aten_unsqueeze_copy_default_95 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_view_copy_default_161, -1), kwargs = {})
2025-03-21T20:32:07.1675484Z       %aten_permute_copy_default_361 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_95, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1676305Z       %aten_convolution_default_59 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_361, %b__frozen_param77, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1676971Z       %aten_permute_copy_default_362 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_59, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1677574Z       %aten_squeeze_copy_dims_95 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_362, [-1]), kwargs = {})
2025-03-21T20:32:07.1678168Z       %aten_add_tensor_43 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_add_tensor_39, %aten_squeeze_copy_dims_95), kwargs = {})
2025-03-21T20:32:07.1678845Z       %aten_rms_norm_default_17 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.rms_norm.default](args = (%aten_add_tensor_43, [768], %b__frozen_param78, 9.999999747378752e-06), kwargs = {})
2025-03-21T20:32:07.1679489Z       %aten_unsqueeze_copy_default_96 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_17, -1), kwargs = {})
2025-03-21T20:32:07.1680124Z       %aten_unsqueeze_copy_default_97 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_17, -1), kwargs = {})
2025-03-21T20:32:07.1680831Z       %aten_permute_copy_default_363 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_96, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1681498Z       %aten_permute_copy_default_365 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_97, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1682374Z       %aten_convolution_default_60 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_363, %b__frozen_param79, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1683212Z       %aten_convolution_default_61 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_365, %b__frozen_param80, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1683882Z       %aten_permute_copy_default_364 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_60, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1684538Z       %aten_permute_copy_default_366 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_61, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1685159Z       %aten_squeeze_copy_dims_96 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_364, [-1]), kwargs = {})
2025-03-21T20:32:07.1685763Z       %aten_squeeze_copy_dims_97 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_366, [-1]), kwargs = {})
2025-03-21T20:32:07.1686348Z       %aten_sigmoid_default_8 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.sigmoid.default](args = (%aten_squeeze_copy_dims_96,), kwargs = {})
2025-03-21T20:32:07.1686957Z       %aten_mul_tensor_133 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_96, %aten_sigmoid_default_8), kwargs = {})
2025-03-21T20:32:07.1687561Z       %aten_mul_tensor_134 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_mul_tensor_133, %aten_squeeze_copy_dims_97), kwargs = {})
2025-03-21T20:32:07.1688181Z       %aten_unsqueeze_copy_default_98 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_mul_tensor_134, -1), kwargs = {})
2025-03-21T20:32:07.1688862Z       %aten_permute_copy_default_367 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_98, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1689740Z       %aten_convolution_default_62 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_367, %b__frozen_param81, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1690409Z       %aten_permute_copy_default_368 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_62, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1691011Z       %aten_squeeze_copy_dims_98 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_368, [-1]), kwargs = {})
2025-03-21T20:32:07.1691608Z       %aten_add_tensor_44 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_add_tensor_43, %aten_squeeze_copy_dims_98), kwargs = {})
2025-03-21T20:32:07.1692305Z       %aten_rms_norm_default_18 : [num_users=3] = call_function[target=executorch.exir.dialects.edge._ops.aten.rms_norm.default](args = (%aten_add_tensor_44, [768], %b__frozen_param82, 9.999999747378752e-06), kwargs = {})
2025-03-21T20:32:07.1692955Z       %aten_unsqueeze_copy_default_99 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_18, -1), kwargs = {})
2025-03-21T20:32:07.1693624Z       %aten_unsqueeze_copy_default_100 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_18, -1), kwargs = {})
2025-03-21T20:32:07.1694296Z       %aten_unsqueeze_copy_default_101 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_18, -1), kwargs = {})
2025-03-21T20:32:07.1694990Z       %aten_permute_copy_default_369 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_99, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1695678Z       %aten_permute_copy_default_371 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_100, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1696347Z       %aten_permute_copy_default_373 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_101, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1697180Z       %aten_convolution_default_63 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_369, %b__frozen_param83, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1697996Z       %aten_convolution_default_64 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_371, %b__frozen_param84, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1698822Z       %aten_convolution_default_65 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_373, %b__frozen_param85, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1699484Z       %aten_permute_copy_default_370 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_63, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1700150Z       %aten_permute_copy_default_372 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_64, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1700805Z       %aten_permute_copy_default_374 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_65, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1701421Z       %aten_squeeze_copy_dims_99 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_370, [-1]), kwargs = {})
2025-03-21T20:32:07.1702024Z       %aten_squeeze_copy_dims_100 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_372, [-1]), kwargs = {})
2025-03-21T20:32:07.1702643Z       %aten_squeeze_copy_dims_101 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_374, [-1]), kwargs = {})
2025-03-21T20:32:07.1703266Z       %aten_view_copy_default_162 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_squeeze_copy_dims_99, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1703898Z       %aten_view_copy_default_163 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_squeeze_copy_dims_100, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1704543Z       %aten_view_copy_default_164 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_squeeze_copy_dims_101, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1705211Z       %aten_view_copy_default_165 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_view_copy_default_162, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:32:07.1705865Z       %aten_view_copy_default_166 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_view_copy_default_163, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:32:07.1706746Z       %aten_index_put_default_19 : [num_users=13] = call_function[target=executorch.exir.dialects.edge._ops.aten.index_put.default](args = (%b_layers_9_attention_kv_cache_past_v_caches, [None, %aten__to_copy_default_1], %aten_view_copy_default_164), kwargs = {})
2025-03-21T20:32:07.1707347Z       %aten_slice_copy_tensor_36 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_165, 4, 0, 1), kwargs = {})
2025-03-21T20:32:07.1707954Z       %aten_slice_copy_tensor_37 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_165, 4, 1, 2), kwargs = {})
2025-03-21T20:32:07.1708552Z       %aten_slice_copy_tensor_38 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_166, 4, 0, 1), kwargs = {})
2025-03-21T20:32:07.1709163Z       %aten_slice_copy_tensor_39 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_166, 4, 1, 2), kwargs = {})
2025-03-21T20:32:07.1709811Z       %aten_permute_copy_default_388 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_19, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1710463Z       %aten_permute_copy_default_389 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_19, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1711104Z       %aten_permute_copy_default_390 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_19, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1711757Z       %aten_permute_copy_default_391 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_19, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1712398Z       %aten_permute_copy_default_392 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_19, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1713051Z       %aten_permute_copy_default_393 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_19, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1713692Z       %aten_permute_copy_default_394 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_19, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1714348Z       %aten_permute_copy_default_395 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_19, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1714990Z       %aten_permute_copy_default_396 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_19, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1715669Z       %aten_permute_copy_default_397 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_19, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1716314Z       %aten_permute_copy_default_398 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_19, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1716996Z       %aten_permute_copy_default_399 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_19, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1717611Z       %aten_squeeze_copy_dims_102 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_36, [4]), kwargs = {})
2025-03-21T20:32:07.1718238Z       %aten_squeeze_copy_dims_103 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_37, [4]), kwargs = {})
2025-03-21T20:32:07.1718831Z       %aten_squeeze_copy_dims_104 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_38, [4]), kwargs = {})
2025-03-21T20:32:07.1719435Z       %aten_squeeze_copy_dims_105 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_39, [4]), kwargs = {})
2025-03-21T20:32:07.1720026Z       %aten_select_copy_int_456 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_388, 0, 0), kwargs = {})
2025-03-21T20:32:07.1720624Z       %aten_select_copy_int_458 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_389, 0, 0), kwargs = {})
2025-03-21T20:32:07.1721212Z       %aten_select_copy_int_460 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_390, 0, 0), kwargs = {})
2025-03-21T20:32:07.1721808Z       %aten_select_copy_int_462 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_391, 0, 0), kwargs = {})
2025-03-21T20:32:07.1722389Z       %aten_select_copy_int_464 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_392, 0, 0), kwargs = {})
2025-03-21T20:32:07.1722983Z       %aten_select_copy_int_466 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_393, 0, 0), kwargs = {})
2025-03-21T20:32:07.1723568Z       %aten_select_copy_int_468 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_394, 0, 0), kwargs = {})
2025-03-21T20:32:07.1724150Z       %aten_select_copy_int_470 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_395, 0, 0), kwargs = {})
2025-03-21T20:32:07.1724746Z       %aten_select_copy_int_472 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_396, 0, 0), kwargs = {})
2025-03-21T20:32:07.1725328Z       %aten_select_copy_int_474 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_397, 0, 0), kwargs = {})
2025-03-21T20:32:07.1725926Z       %aten_select_copy_int_476 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_398, 0, 0), kwargs = {})
2025-03-21T20:32:07.1726512Z       %aten_select_copy_int_478 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_399, 0, 0), kwargs = {})
2025-03-21T20:32:07.1727224Z       %aten_mul_tensor_137 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_102, %aten_view_copy_default_167), kwargs = {})
2025-03-21T20:32:07.1727847Z       %aten_mul_tensor_139 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_102, %aten_view_copy_default_168), kwargs = {})
2025-03-21T20:32:07.1728504Z       %aten_mul_tensor_138 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_103, %aten_view_copy_default_168), kwargs = {})
2025-03-21T20:32:07.1729171Z       %aten_mul_tensor_140 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_103, %aten_view_copy_default_167), kwargs = {})
2025-03-21T20:32:07.1729871Z       %aten_mul_tensor_141 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_104, %aten_view_copy_default_167), kwargs = {})
2025-03-21T20:32:07.1730486Z       %aten_mul_tensor_143 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_104, %aten_view_copy_default_168), kwargs = {})
2025-03-21T20:32:07.1731116Z       %aten_mul_tensor_142 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_105, %aten_view_copy_default_168), kwargs = {})
2025-03-21T20:32:07.1731730Z       %aten_mul_tensor_144 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_105, %aten_view_copy_default_167), kwargs = {})
2025-03-21T20:32:07.1732437Z       %aten_select_copy_int_457 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_456, 0, 0), kwargs = {})
2025-03-21T20:32:07.1733011Z       %aten_select_copy_int_459 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_458, 0, 1), kwargs = {})
2025-03-21T20:32:07.1733593Z       %aten_select_copy_int_461 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_460, 0, 2), kwargs = {})
2025-03-21T20:32:07.1734163Z       %aten_select_copy_int_463 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_462, 0, 3), kwargs = {})
2025-03-21T20:32:07.1734746Z       %aten_select_copy_int_465 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_464, 0, 4), kwargs = {})
2025-03-21T20:32:07.1735316Z       %aten_select_copy_int_467 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_466, 0, 5), kwargs = {})
2025-03-21T20:32:07.1735900Z       %aten_select_copy_int_469 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_468, 0, 6), kwargs = {})
2025-03-21T20:32:07.1736471Z       %aten_select_copy_int_471 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_470, 0, 7), kwargs = {})
2025-03-21T20:32:07.1737053Z       %aten_select_copy_int_473 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_472, 0, 8), kwargs = {})
2025-03-21T20:32:07.1737624Z       %aten_select_copy_int_475 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_474, 0, 9), kwargs = {})
2025-03-21T20:32:07.1738210Z       %aten_select_copy_int_477 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_476, 0, 10), kwargs = {})
2025-03-21T20:32:07.1738851Z       %aten_select_copy_int_479 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_478, 0, 11), kwargs = {})
2025-03-21T20:32:07.1739442Z       %aten_sub_tensor_18 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.sub.Tensor](args = (%aten_mul_tensor_137, %aten_mul_tensor_138), kwargs = {})
2025-03-21T20:32:07.1740036Z       %aten_add_tensor_45 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_mul_tensor_139, %aten_mul_tensor_140), kwargs = {})
2025-03-21T20:32:07.1740850Z       %aten_sub_tensor_19 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.sub.Tensor](args = (%aten_mul_tensor_141, %aten_mul_tensor_142), kwargs = {})
2025-03-21T20:32:07.1741413Z       %aten_add_tensor_46 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_mul_tensor_143, %aten_mul_tensor_144), kwargs = {})
2025-03-21T20:32:07.1742881Z       %aten_cat_default_39 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_select_copy_int_457, %aten_select_copy_int_459, %aten_select_copy_int_461, %aten_select_copy_int_463, %aten_select_copy_int_465, %aten_select_copy_int_467, %aten_select_copy_int_469, %aten_select_copy_int_471, %aten_select_copy_int_473, %aten_select_copy_int_475, %aten_select_copy_int_477, %aten_select_copy_int_479],), kwargs = {})
2025-03-21T20:32:07.1743503Z       %aten_unsqueeze_copy_default_102 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_sub_tensor_18, 4), kwargs = {})
2025-03-21T20:32:07.1744129Z       %aten_unsqueeze_copy_default_103 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_add_tensor_45, 4), kwargs = {})
2025-03-21T20:32:07.1744742Z       %aten_unsqueeze_copy_default_104 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_sub_tensor_19, 4), kwargs = {})
2025-03-21T20:32:07.1745361Z       %aten_unsqueeze_copy_default_105 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_add_tensor_46, 4), kwargs = {})
2025-03-21T20:32:07.1745964Z       %aten_view_copy_default_172 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_39, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:32:07.1746662Z       %aten_cat_default_36 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_unsqueeze_copy_default_102, %aten_unsqueeze_copy_default_103], -1), kwargs = {})
2025-03-21T20:32:07.1747344Z       %aten_cat_default_37 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_unsqueeze_copy_default_104, %aten_unsqueeze_copy_default_105], -1), kwargs = {})
2025-03-21T20:32:07.1747957Z       %aten_view_copy_default_169 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_36, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1748553Z       %aten_view_copy_default_170 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_37, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1749213Z       %aten_permute_copy_default_375 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_view_copy_default_169, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1750055Z       %aten_index_put_default_18 : [num_users=13] = call_function[target=executorch.exir.dialects.edge._ops.aten.index_put.default](args = (%b_layers_9_attention_kv_cache_past_k_caches, [None, %aten__to_copy_default_1], %aten_view_copy_default_170), kwargs = {})
2025-03-21T20:32:07.1750738Z       %aten_permute_copy_default_376 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_18, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1751407Z       %aten_permute_copy_default_377 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_18, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1752084Z       %aten_permute_copy_default_378 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_18, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1752747Z       %aten_permute_copy_default_379 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_18, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1753401Z       %aten_permute_copy_default_380 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_18, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1754039Z       %aten_permute_copy_default_381 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_18, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1754692Z       %aten_permute_copy_default_382 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_18, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1755335Z       %aten_permute_copy_default_383 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_18, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1755988Z       %aten_permute_copy_default_384 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_18, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1756630Z       %aten_permute_copy_default_385 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_18, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1757281Z       %aten_permute_copy_default_386 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_18, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1757921Z       %aten_permute_copy_default_387 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_18, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1758521Z       %aten_select_copy_int_432 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_376, 0, 0), kwargs = {})
2025-03-21T20:32:07.1759104Z       %aten_select_copy_int_434 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_377, 0, 0), kwargs = {})
2025-03-21T20:32:07.1759701Z       %aten_select_copy_int_436 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_378, 0, 0), kwargs = {})
2025-03-21T20:32:07.1760283Z       %aten_select_copy_int_438 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_379, 0, 0), kwargs = {})
2025-03-21T20:32:07.1760881Z       %aten_select_copy_int_440 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_380, 0, 0), kwargs = {})
2025-03-21T20:32:07.1761466Z       %aten_select_copy_int_442 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_381, 0, 0), kwargs = {})
2025-03-21T20:32:07.1762088Z       %aten_select_copy_int_444 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_382, 0, 0), kwargs = {})
2025-03-21T20:32:07.1762670Z       %aten_select_copy_int_446 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_383, 0, 0), kwargs = {})
2025-03-21T20:32:07.1763286Z       %aten_select_copy_int_448 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_384, 0, 0), kwargs = {})
2025-03-21T20:32:07.1763919Z       %aten_select_copy_int_450 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_385, 0, 0), kwargs = {})
2025-03-21T20:32:07.1764516Z       %aten_select_copy_int_452 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_386, 0, 0), kwargs = {})
2025-03-21T20:32:07.1765098Z       %aten_select_copy_int_454 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_387, 0, 0), kwargs = {})
2025-03-21T20:32:07.1765680Z       %aten_select_copy_int_433 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_432, 0, 0), kwargs = {})
2025-03-21T20:32:07.1766249Z       %aten_select_copy_int_435 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_434, 0, 1), kwargs = {})
2025-03-21T20:32:07.1766829Z       %aten_select_copy_int_437 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_436, 0, 2), kwargs = {})
2025-03-21T20:32:07.1767401Z       %aten_select_copy_int_439 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_438, 0, 3), kwargs = {})
2025-03-21T20:32:07.1767986Z       %aten_select_copy_int_441 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_440, 0, 4), kwargs = {})
2025-03-21T20:32:07.1768557Z       %aten_select_copy_int_443 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_442, 0, 5), kwargs = {})
2025-03-21T20:32:07.1769130Z       %aten_select_copy_int_445 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_444, 0, 6), kwargs = {})
2025-03-21T20:32:07.1769780Z       %aten_select_copy_int_447 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_446, 0, 7), kwargs = {})
2025-03-21T20:32:07.1770355Z       %aten_select_copy_int_449 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_448, 0, 8), kwargs = {})
2025-03-21T20:32:07.1770935Z       %aten_select_copy_int_451 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_450, 0, 9), kwargs = {})
2025-03-21T20:32:07.1771510Z       %aten_select_copy_int_453 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_452, 0, 10), kwargs = {})
2025-03-21T20:32:07.1772103Z       %aten_select_copy_int_455 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_454, 0, 11), kwargs = {})
2025-03-21T20:32:07.1773588Z       %aten_cat_default_38 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_select_copy_int_433, %aten_select_copy_int_435, %aten_select_copy_int_437, %aten_select_copy_int_439, %aten_select_copy_int_441, %aten_select_copy_int_443, %aten_select_copy_int_445, %aten_select_copy_int_447, %aten_select_copy_int_449, %aten_select_copy_int_451, %aten_select_copy_int_453, %aten_select_copy_int_455],), kwargs = {})
2025-03-21T20:32:07.1774208Z       %aten_view_copy_default_171 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_38, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:32:07.1774915Z       %aten_permute_copy_default_400 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_view_copy_default_171, [0, 1, 3, 2]), kwargs = {})
2025-03-21T20:32:07.1775631Z       %aten_matmul_default_18 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.matmul.default](args = (%aten_permute_copy_default_375, %aten_permute_copy_default_400), kwargs = {})
2025-03-21T20:32:07.1776225Z       %aten_mul_tensor_145 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_matmul_default_18, %b__frozen_param158), kwargs = {})
2025-03-21T20:32:07.1776793Z       %aten_add_tensor_47 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_mul_tensor_145, %aten_index_tensor_11), kwargs = {})
2025-03-21T20:32:07.1777374Z       %aten__softmax_default_9 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten._softmax.default](args = (%aten_add_tensor_47, -1, False), kwargs = {})
2025-03-21T20:32:07.1778033Z       %aten_matmul_default_19 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.matmul.default](args = (%aten__softmax_default_9, %aten_view_copy_default_172), kwargs = {})
2025-03-21T20:32:07.1787801Z       %aten_permute_copy_default_401 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_matmul_default_19, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1788575Z       %aten_view_copy_default_179 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_permute_copy_default_401, [1, 1, 768]), kwargs = {})
2025-03-21T20:32:07.1789227Z       %aten_unsqueeze_copy_default_106 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_view_copy_default_179, -1), kwargs = {})
2025-03-21T20:32:07.1789926Z       %aten_permute_copy_default_402 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_106, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1790751Z       %aten_convolution_default_66 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_402, %b__frozen_param86, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1791419Z       %aten_permute_copy_default_403 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_66, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1792028Z       %aten_squeeze_copy_dims_106 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_403, [-1]), kwargs = {})
2025-03-21T20:32:07.1792623Z       %aten_add_tensor_48 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_add_tensor_44, %aten_squeeze_copy_dims_106), kwargs = {})
2025-03-21T20:32:07.1793301Z       %aten_rms_norm_default_19 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.rms_norm.default](args = (%aten_add_tensor_48, [768], %b__frozen_param87, 9.999999747378752e-06), kwargs = {})
2025-03-21T20:32:07.1794044Z       %aten_unsqueeze_copy_default_107 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_19, -1), kwargs = {})
2025-03-21T20:32:07.1794679Z       %aten_unsqueeze_copy_default_108 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_19, -1), kwargs = {})
2025-03-21T20:32:07.1795400Z       %aten_permute_copy_default_404 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_107, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1796101Z       %aten_permute_copy_default_406 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_108, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1796959Z       %aten_convolution_default_67 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_404, %b__frozen_param88, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1797774Z       %aten_convolution_default_68 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_406, %b__frozen_param89, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1798443Z       %aten_permute_copy_default_405 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_67, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1799099Z       %aten_permute_copy_default_407 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_68, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1799718Z       %aten_squeeze_copy_dims_107 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_405, [-1]), kwargs = {})
2025-03-21T20:32:07.1800324Z       %aten_squeeze_copy_dims_108 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_407, [-1]), kwargs = {})
2025-03-21T20:32:07.1800910Z       %aten_sigmoid_default_9 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.sigmoid.default](args = (%aten_squeeze_copy_dims_107,), kwargs = {})
2025-03-21T20:32:07.1801520Z       %aten_mul_tensor_148 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_107, %aten_sigmoid_default_9), kwargs = {})
2025-03-21T20:32:07.1802129Z       %aten_mul_tensor_149 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_mul_tensor_148, %aten_squeeze_copy_dims_108), kwargs = {})
2025-03-21T20:32:07.1802751Z       %aten_unsqueeze_copy_default_109 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_mul_tensor_149, -1), kwargs = {})
2025-03-21T20:32:07.1803433Z       %aten_permute_copy_default_408 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_109, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1804248Z       %aten_convolution_default_69 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_408, %b__frozen_param90, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1804916Z       %aten_permute_copy_default_409 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_69, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1805522Z       %aten_squeeze_copy_dims_109 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_409, [-1]), kwargs = {})
2025-03-21T20:32:07.1806153Z       %aten_add_tensor_49 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_add_tensor_48, %aten_squeeze_copy_dims_109), kwargs = {})
2025-03-21T20:32:07.1806829Z       %aten_rms_norm_default_20 : [num_users=3] = call_function[target=executorch.exir.dialects.edge._ops.aten.rms_norm.default](args = (%aten_add_tensor_49, [768], %b__frozen_param91, 9.999999747378752e-06), kwargs = {})
2025-03-21T20:32:07.1807527Z       %aten_unsqueeze_copy_default_110 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_20, -1), kwargs = {})
2025-03-21T20:32:07.1808183Z       %aten_unsqueeze_copy_default_111 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_20, -1), kwargs = {})
2025-03-21T20:32:07.1808826Z       %aten_unsqueeze_copy_default_112 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_20, -1), kwargs = {})
2025-03-21T20:32:07.1809601Z       %aten_permute_copy_default_410 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_110, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1810286Z       %aten_permute_copy_default_412 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_111, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1810955Z       %aten_permute_copy_default_414 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_112, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1811791Z       %aten_convolution_default_70 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_410, %b__frozen_param92, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1812601Z       %aten_convolution_default_71 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_412, %b__frozen_param93, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1813427Z       %aten_convolution_default_72 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_414, %b__frozen_param94, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1814089Z       %aten_permute_copy_default_411 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_70, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1814758Z       %aten_permute_copy_default_413 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_71, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1815410Z       %aten_permute_copy_default_415 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_72, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1816031Z       %aten_squeeze_copy_dims_110 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_411, [-1]), kwargs = {})
2025-03-21T20:32:07.1816641Z       %aten_squeeze_copy_dims_111 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_413, [-1]), kwargs = {})
2025-03-21T20:32:07.1817258Z       %aten_squeeze_copy_dims_112 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_415, [-1]), kwargs = {})
2025-03-21T20:32:07.1817907Z       %aten_view_copy_default_180 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_squeeze_copy_dims_110, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1818544Z       %aten_view_copy_default_181 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_squeeze_copy_dims_111, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1819189Z       %aten_view_copy_default_182 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_squeeze_copy_dims_112, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1819880Z       %aten_view_copy_default_183 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_view_copy_default_180, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:32:07.1820510Z       %aten_view_copy_default_184 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_view_copy_default_181, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:32:07.1821363Z       %aten_index_put_default_21 : [num_users=13] = call_function[target=executorch.exir.dialects.edge._ops.aten.index_put.default](args = (%b_layers_10_attention_kv_cache_past_v_caches, [None, %aten__to_copy_default_1], %aten_view_copy_default_182), kwargs = {})
2025-03-21T20:32:07.1821965Z       %aten_slice_copy_tensor_40 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_183, 4, 0, 1), kwargs = {})
2025-03-21T20:32:07.1822577Z       %aten_slice_copy_tensor_41 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_183, 4, 1, 2), kwargs = {})
2025-03-21T20:32:07.1823174Z       %aten_slice_copy_tensor_42 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_184, 4, 0, 1), kwargs = {})
2025-03-21T20:32:07.1823782Z       %aten_slice_copy_tensor_43 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_184, 4, 1, 2), kwargs = {})
2025-03-21T20:32:07.1824424Z       %aten_permute_copy_default_429 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_21, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1825081Z       %aten_permute_copy_default_430 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_21, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1825723Z       %aten_permute_copy_default_431 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_21, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1826374Z       %aten_permute_copy_default_432 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_21, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1827011Z       %aten_permute_copy_default_433 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_21, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1827667Z       %aten_permute_copy_default_434 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_21, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1828309Z       %aten_permute_copy_default_435 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_21, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1828962Z       %aten_permute_copy_default_436 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_21, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1829626Z       %aten_permute_copy_default_437 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_21, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1830307Z       %aten_permute_copy_default_438 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_21, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1830982Z       %aten_permute_copy_default_439 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_21, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1831657Z       %aten_permute_copy_default_440 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_21, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1832470Z       %aten_squeeze_copy_dims_113 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_40, [4]), kwargs = {})
2025-03-21T20:32:07.1833076Z       %aten_squeeze_copy_dims_114 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_41, [4]), kwargs = {})
2025-03-21T20:32:07.1833669Z       %aten_squeeze_copy_dims_115 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_42, [4]), kwargs = {})
2025-03-21T20:32:07.1834270Z       %aten_squeeze_copy_dims_116 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_43, [4]), kwargs = {})
2025-03-21T20:32:07.1834855Z       %aten_select_copy_int_504 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_429, 0, 0), kwargs = {})
2025-03-21T20:32:07.1835450Z       %aten_select_copy_int_506 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_430, 0, 0), kwargs = {})
2025-03-21T20:32:07.1836032Z       %aten_select_copy_int_508 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_431, 0, 0), kwargs = {})
2025-03-21T20:32:07.1836627Z       %aten_select_copy_int_510 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_432, 0, 0), kwargs = {})
2025-03-21T20:32:07.1837212Z       %aten_select_copy_int_512 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_433, 0, 0), kwargs = {})
2025-03-21T20:32:07.1837811Z       %aten_select_copy_int_514 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_434, 0, 0), kwargs = {})
2025-03-21T20:32:07.1838390Z       %aten_select_copy_int_516 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_435, 0, 0), kwargs = {})
2025-03-21T20:32:07.1838983Z       %aten_select_copy_int_518 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_436, 0, 0), kwargs = {})
2025-03-21T20:32:07.1839566Z       %aten_select_copy_int_520 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_437, 0, 0), kwargs = {})
2025-03-21T20:32:07.1840162Z       %aten_select_copy_int_522 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_438, 0, 0), kwargs = {})
2025-03-21T20:32:07.1840808Z       %aten_select_copy_int_524 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_439, 0, 0), kwargs = {})
2025-03-21T20:32:07.1841402Z       %aten_select_copy_int_526 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_440, 0, 0), kwargs = {})
2025-03-21T20:32:07.1842079Z       %aten_mul_tensor_152 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_113, %aten_view_copy_default_185), kwargs = {})
2025-03-21T20:32:07.1842736Z       %aten_mul_tensor_154 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_113, %aten_view_copy_default_186), kwargs = {})
2025-03-21T20:32:07.1843401Z       %aten_mul_tensor_153 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_114, %aten_view_copy_default_186), kwargs = {})
2025-03-21T20:32:07.1844022Z       %aten_mul_tensor_155 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_114, %aten_view_copy_default_185), kwargs = {})
2025-03-21T20:32:07.1844656Z       %aten_mul_tensor_156 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_115, %aten_view_copy_default_185), kwargs = {})
2025-03-21T20:32:07.1845279Z       %aten_mul_tensor_158 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_115, %aten_view_copy_default_186), kwargs = {})
2025-03-21T20:32:07.1845913Z       %aten_mul_tensor_157 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_116, %aten_view_copy_default_186), kwargs = {})
2025-03-21T20:32:07.1846532Z       %aten_mul_tensor_159 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_116, %aten_view_copy_default_185), kwargs = {})
2025-03-21T20:32:07.1847121Z       %aten_select_copy_int_505 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_504, 0, 0), kwargs = {})
2025-03-21T20:32:07.1847699Z       %aten_select_copy_int_507 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_506, 0, 1), kwargs = {})
2025-03-21T20:32:07.1848286Z       %aten_select_copy_int_509 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_508, 0, 2), kwargs = {})
2025-03-21T20:32:07.1848931Z       %aten_select_copy_int_511 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_510, 0, 3), kwargs = {})
2025-03-21T20:32:07.1849713Z       %aten_select_copy_int_513 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_512, 0, 4), kwargs = {})
2025-03-21T20:32:07.1850315Z       %aten_select_copy_int_515 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_514, 0, 5), kwargs = {})
2025-03-21T20:32:07.1850902Z       %aten_select_copy_int_517 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_516, 0, 6), kwargs = {})
2025-03-21T20:32:07.1851471Z       %aten_select_copy_int_519 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_518, 0, 7), kwargs = {})
2025-03-21T20:32:07.1852050Z       %aten_select_copy_int_521 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_520, 0, 8), kwargs = {})
2025-03-21T20:32:07.1852655Z       %aten_select_copy_int_523 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_522, 0, 9), kwargs = {})
2025-03-21T20:32:07.1853235Z       %aten_select_copy_int_525 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_524, 0, 10), kwargs = {})
2025-03-21T20:32:07.1853837Z       %aten_select_copy_int_527 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_526, 0, 11), kwargs = {})
2025-03-21T20:32:07.1854464Z       %aten_sub_tensor_20 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.sub.Tensor](args = (%aten_mul_tensor_152, %aten_mul_tensor_153), kwargs = {})
2025-03-21T20:32:07.1855029Z       %aten_add_tensor_50 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_mul_tensor_154, %aten_mul_tensor_155), kwargs = {})
2025-03-21T20:32:07.1855602Z       %aten_sub_tensor_21 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.sub.Tensor](args = (%aten_mul_tensor_156, %aten_mul_tensor_157), kwargs = {})
2025-03-21T20:32:07.1856160Z       %aten_add_tensor_51 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_mul_tensor_158, %aten_mul_tensor_159), kwargs = {})
2025-03-21T20:32:07.1857625Z       %aten_cat_default_43 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_select_copy_int_505, %aten_select_copy_int_507, %aten_select_copy_int_509, %aten_select_copy_int_511, %aten_select_copy_int_513, %aten_select_copy_int_515, %aten_select_copy_int_517, %aten_select_copy_int_519, %aten_select_copy_int_521, %aten_select_copy_int_523, %aten_select_copy_int_525, %aten_select_copy_int_527],), kwargs = {})
2025-03-21T20:32:07.1858249Z       %aten_unsqueeze_copy_default_113 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_sub_tensor_20, 4), kwargs = {})
2025-03-21T20:32:07.1858876Z       %aten_unsqueeze_copy_default_114 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_add_tensor_50, 4), kwargs = {})
2025-03-21T20:32:07.1859491Z       %aten_unsqueeze_copy_default_115 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_sub_tensor_21, 4), kwargs = {})
2025-03-21T20:32:07.1860116Z       %aten_unsqueeze_copy_default_116 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_add_tensor_51, 4), kwargs = {})
2025-03-21T20:32:07.1860721Z       %aten_view_copy_default_190 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_43, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:32:07.1861425Z       %aten_cat_default_40 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_unsqueeze_copy_default_113, %aten_unsqueeze_copy_default_114], -1), kwargs = {})
2025-03-21T20:32:07.1862104Z       %aten_cat_default_41 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_unsqueeze_copy_default_115, %aten_unsqueeze_copy_default_116], -1), kwargs = {})
2025-03-21T20:32:07.1862717Z       %aten_view_copy_default_187 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_40, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1863318Z       %aten_view_copy_default_188 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_41, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1864002Z       %aten_permute_copy_default_416 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_view_copy_default_187, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1864849Z       %aten_index_put_default_20 : [num_users=13] = call_function[target=executorch.exir.dialects.edge._ops.aten.index_put.default](args = (%b_layers_10_attention_kv_cache_past_k_caches, [None, %aten__to_copy_default_1], %aten_view_copy_default_188), kwargs = {})
2025-03-21T20:32:07.1865531Z       %aten_permute_copy_default_417 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_20, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1866227Z       %aten_permute_copy_default_418 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_20, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1866881Z       %aten_permute_copy_default_419 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_20, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1867521Z       %aten_permute_copy_default_420 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_20, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1868176Z       %aten_permute_copy_default_421 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_20, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1868815Z       %aten_permute_copy_default_422 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_20, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1869470Z       %aten_permute_copy_default_423 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_20, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1870110Z       %aten_permute_copy_default_424 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_20, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1870762Z       %aten_permute_copy_default_425 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_20, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1871403Z       %aten_permute_copy_default_426 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_20, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1872060Z       %aten_permute_copy_default_427 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_20, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1872703Z       %aten_permute_copy_default_428 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_20, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1873301Z       %aten_select_copy_int_480 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_417, 0, 0), kwargs = {})
2025-03-21T20:32:07.1873887Z       %aten_select_copy_int_482 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_418, 0, 0), kwargs = {})
2025-03-21T20:32:07.1874482Z       %aten_select_copy_int_484 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_419, 0, 0), kwargs = {})
2025-03-21T20:32:07.1875065Z       %aten_select_copy_int_486 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_420, 0, 0), kwargs = {})
2025-03-21T20:32:07.1875684Z       %aten_select_copy_int_488 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_421, 0, 0), kwargs = {})
2025-03-21T20:32:07.1876268Z       %aten_select_copy_int_490 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_422, 0, 0), kwargs = {})
2025-03-21T20:32:07.1876897Z       %aten_select_copy_int_492 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_423, 0, 0), kwargs = {})
2025-03-21T20:32:07.1877506Z       %aten_select_copy_int_494 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_424, 0, 0), kwargs = {})
2025-03-21T20:32:07.1878128Z       %aten_select_copy_int_496 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_425, 0, 0), kwargs = {})
2025-03-21T20:32:07.1878713Z       %aten_select_copy_int_498 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_426, 0, 0), kwargs = {})
2025-03-21T20:32:07.1879305Z       %aten_select_copy_int_500 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_427, 0, 0), kwargs = {})
2025-03-21T20:32:07.1879890Z       %aten_select_copy_int_502 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_428, 0, 0), kwargs = {})
2025-03-21T20:32:07.1880475Z       %aten_select_copy_int_481 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_480, 0, 0), kwargs = {})
2025-03-21T20:32:07.1881043Z       %aten_select_copy_int_483 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_482, 0, 1), kwargs = {})
2025-03-21T20:32:07.1881626Z       %aten_select_copy_int_485 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_484, 0, 2), kwargs = {})
2025-03-21T20:32:07.1882193Z       %aten_select_copy_int_487 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_486, 0, 3), kwargs = {})
2025-03-21T20:32:07.1882775Z       %aten_select_copy_int_489 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_488, 0, 4), kwargs = {})
2025-03-21T20:32:07.1883341Z       %aten_select_copy_int_491 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_490, 0, 5), kwargs = {})
2025-03-21T20:32:07.1883923Z       %aten_select_copy_int_493 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_492, 0, 6), kwargs = {})
2025-03-21T20:32:07.1884489Z       %aten_select_copy_int_495 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_494, 0, 7), kwargs = {})
2025-03-21T20:32:07.1885056Z       %aten_select_copy_int_497 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_496, 0, 8), kwargs = {})
2025-03-21T20:32:07.1885634Z       %aten_select_copy_int_499 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_498, 0, 9), kwargs = {})
2025-03-21T20:32:07.1886206Z       %aten_select_copy_int_501 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_500, 0, 10), kwargs = {})
2025-03-21T20:32:07.1886812Z       %aten_select_copy_int_503 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_502, 0, 11), kwargs = {})
2025-03-21T20:32:07.1888264Z       %aten_cat_default_42 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_select_copy_int_481, %aten_select_copy_int_483, %aten_select_copy_int_485, %aten_select_copy_int_487, %aten_select_copy_int_489, %aten_select_copy_int_491, %aten_select_copy_int_493, %aten_select_copy_int_495, %aten_select_copy_int_497, %aten_select_copy_int_499, %aten_select_copy_int_501, %aten_select_copy_int_503],), kwargs = {})
2025-03-21T20:32:07.1888950Z       %aten_view_copy_default_189 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_42, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:32:07.1889686Z       %aten_permute_copy_default_441 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_view_copy_default_189, [0, 1, 3, 2]), kwargs = {})
2025-03-21T20:32:07.1890367Z       %aten_matmul_default_20 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.matmul.default](args = (%aten_permute_copy_default_416, %aten_permute_copy_default_441), kwargs = {})
2025-03-21T20:32:07.1890963Z       %aten_mul_tensor_160 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_matmul_default_20, %b__frozen_param159), kwargs = {})
2025-03-21T20:32:07.1891532Z       %aten_add_tensor_52 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_mul_tensor_160, %aten_index_tensor_12), kwargs = {})
2025-03-21T20:32:07.1892129Z       %aten__softmax_default_10 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten._softmax.default](args = (%aten_add_tensor_52, -1, False), kwargs = {})
2025-03-21T20:32:07.1892780Z       %aten_matmul_default_21 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.matmul.default](args = (%aten__softmax_default_10, %aten_view_copy_default_190), kwargs = {})
2025-03-21T20:32:07.1893413Z       %aten_permute_copy_default_442 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_matmul_default_21, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1894051Z       %aten_view_copy_default_197 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_permute_copy_default_442, [1, 1, 768]), kwargs = {})
2025-03-21T20:32:07.1894694Z       %aten_unsqueeze_copy_default_117 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_view_copy_default_197, -1), kwargs = {})
2025-03-21T20:32:07.1895376Z       %aten_permute_copy_default_443 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_117, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1896196Z       %aten_convolution_default_73 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_443, %b__frozen_param95, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1896867Z       %aten_permute_copy_default_444 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_73, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1897478Z       %aten_squeeze_copy_dims_117 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_444, [-1]), kwargs = {})
2025-03-21T20:32:07.1898072Z       %aten_add_tensor_53 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_add_tensor_49, %aten_squeeze_copy_dims_117), kwargs = {})
2025-03-21T20:32:07.1898773Z       %aten_rms_norm_default_21 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.rms_norm.default](args = (%aten_add_tensor_53, [768], %b__frozen_param96, 9.999999747378752e-06), kwargs = {})
2025-03-21T20:32:07.1899420Z       %aten_unsqueeze_copy_default_118 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_21, -1), kwargs = {})
2025-03-21T20:32:07.1900075Z       %aten_unsqueeze_copy_default_119 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_21, -1), kwargs = {})
2025-03-21T20:32:07.1900810Z       %aten_permute_copy_default_445 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_118, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1901480Z       %aten_permute_copy_default_447 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_119, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1902308Z       %aten_convolution_default_74 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_445, %b__frozen_param97, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1903128Z       %aten_convolution_default_75 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_447, %b__frozen_param98, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1903801Z       %aten_permute_copy_default_446 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_74, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1904455Z       %aten_permute_copy_default_448 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_75, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1905074Z       %aten_squeeze_copy_dims_118 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_446, [-1]), kwargs = {})
2025-03-21T20:32:07.1905682Z       %aten_squeeze_copy_dims_119 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_448, [-1]), kwargs = {})
2025-03-21T20:32:07.1906271Z       %aten_sigmoid_default_10 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.sigmoid.default](args = (%aten_squeeze_copy_dims_118,), kwargs = {})
2025-03-21T20:32:07.1906887Z       %aten_mul_tensor_163 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_118, %aten_sigmoid_default_10), kwargs = {})
2025-03-21T20:32:07.1907494Z       %aten_mul_tensor_164 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_mul_tensor_163, %aten_squeeze_copy_dims_119), kwargs = {})
2025-03-21T20:32:07.1908115Z       %aten_unsqueeze_copy_default_120 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_mul_tensor_164, -1), kwargs = {})
2025-03-21T20:32:07.1908797Z       %aten_permute_copy_default_449 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_120, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1909615Z       %aten_convolution_default_76 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_449, %b__frozen_param99, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1910304Z       %aten_permute_copy_default_450 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_76, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1910912Z       %aten_squeeze_copy_dims_120 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_450, [-1]), kwargs = {})
2025-03-21T20:32:07.1911537Z       %aten_add_tensor_54 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_add_tensor_53, %aten_squeeze_copy_dims_120), kwargs = {})
2025-03-21T20:32:07.1912239Z       %aten_rms_norm_default_22 : [num_users=3] = call_function[target=executorch.exir.dialects.edge._ops.aten.rms_norm.default](args = (%aten_add_tensor_54, [768], %b__frozen_param100, 9.999999747378752e-06), kwargs = {})
2025-03-21T20:32:07.1912968Z       %aten_unsqueeze_copy_default_121 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_22, -1), kwargs = {})
2025-03-21T20:32:07.1913612Z       %aten_unsqueeze_copy_default_122 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_22, -1), kwargs = {})
2025-03-21T20:32:07.1914260Z       %aten_unsqueeze_copy_default_123 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_22, -1), kwargs = {})
2025-03-21T20:32:07.1914934Z       %aten_permute_copy_default_451 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_121, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1915616Z       %aten_permute_copy_default_453 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_122, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1916288Z       %aten_permute_copy_default_455 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_123, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1917129Z       %aten_convolution_default_77 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_451, %b__frozen_param101, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1917952Z       %aten_convolution_default_78 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_453, %b__frozen_param102, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1918783Z       %aten_convolution_default_79 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_455, %b__frozen_param103, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.1919439Z       %aten_permute_copy_default_452 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_77, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1920103Z       %aten_permute_copy_default_454 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_78, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1920756Z       %aten_permute_copy_default_456 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_79, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1921377Z       %aten_squeeze_copy_dims_121 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_452, [-1]), kwargs = {})
2025-03-21T20:32:07.1922025Z       %aten_squeeze_copy_dims_122 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_454, [-1]), kwargs = {})
2025-03-21T20:32:07.1922646Z       %aten_squeeze_copy_dims_123 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_456, [-1]), kwargs = {})
2025-03-21T20:32:07.1923295Z       %aten_view_copy_default_198 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_squeeze_copy_dims_121, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1923955Z       %aten_view_copy_default_199 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_squeeze_copy_dims_122, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1924601Z       %aten_view_copy_default_200 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_squeeze_copy_dims_123, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1925250Z       %aten_view_copy_default_201 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_view_copy_default_198, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:32:07.1925882Z       %aten_view_copy_default_202 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_view_copy_default_199, [1, 1, 12, -1, 2]), kwargs = {})
2025-03-21T20:32:07.1926741Z       %aten_index_put_default_23 : [num_users=13] = call_function[target=executorch.exir.dialects.edge._ops.aten.index_put.default](args = (%b_layers_11_attention_kv_cache_past_v_caches, [None, %aten__to_copy_default_1], %aten_view_copy_default_200), kwargs = {})
2025-03-21T20:32:07.1927344Z       %aten_slice_copy_tensor_44 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_201, 4, 0, 1), kwargs = {})
2025-03-21T20:32:07.1927960Z       %aten_slice_copy_tensor_45 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_201, 4, 1, 2), kwargs = {})
2025-03-21T20:32:07.1928558Z       %aten_slice_copy_tensor_46 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_202, 4, 0, 1), kwargs = {})
2025-03-21T20:32:07.1929171Z       %aten_slice_copy_tensor_47 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.slice_copy.Tensor](args = (%aten_view_copy_default_202, 4, 1, 2), kwargs = {})
2025-03-21T20:32:07.1929879Z       %aten_permute_copy_default_470 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_23, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1930537Z       %aten_permute_copy_default_471 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_23, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1931180Z       %aten_permute_copy_default_472 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_23, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1931836Z       %aten_permute_copy_default_473 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_23, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1932653Z       %aten_permute_copy_default_474 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_23, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1933310Z       %aten_permute_copy_default_475 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_23, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1934018Z       %aten_permute_copy_default_476 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_23, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1934673Z       %aten_permute_copy_default_477 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_23, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1935349Z       %aten_permute_copy_default_478 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_23, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1936070Z       %aten_permute_copy_default_479 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_23, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1936714Z       %aten_permute_copy_default_480 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_23, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1937368Z       %aten_permute_copy_default_481 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_23, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1937965Z       %aten_squeeze_copy_dims_124 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_44, [4]), kwargs = {})
2025-03-21T20:32:07.1938575Z       %aten_squeeze_copy_dims_125 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_45, [4]), kwargs = {})
2025-03-21T20:32:07.1939167Z       %aten_squeeze_copy_dims_126 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_46, [4]), kwargs = {})
2025-03-21T20:32:07.1939769Z       %aten_squeeze_copy_dims_127 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_slice_copy_tensor_47, [4]), kwargs = {})
2025-03-21T20:32:07.1940355Z       %aten_select_copy_int_552 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_470, 0, 0), kwargs = {})
2025-03-21T20:32:07.1940953Z       %aten_select_copy_int_554 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_471, 0, 0), kwargs = {})
2025-03-21T20:32:07.1941543Z       %aten_select_copy_int_556 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_472, 0, 0), kwargs = {})
2025-03-21T20:32:07.1942142Z       %aten_select_copy_int_558 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_473, 0, 0), kwargs = {})
2025-03-21T20:32:07.1942730Z       %aten_select_copy_int_560 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_474, 0, 0), kwargs = {})
2025-03-21T20:32:07.1943327Z       %aten_select_copy_int_562 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_475, 0, 0), kwargs = {})
2025-03-21T20:32:07.1943914Z       %aten_select_copy_int_564 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_476, 0, 0), kwargs = {})
2025-03-21T20:32:07.1944517Z       %aten_select_copy_int_566 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_477, 0, 0), kwargs = {})
2025-03-21T20:32:07.1945128Z       %aten_select_copy_int_568 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_478, 0, 0), kwargs = {})
2025-03-21T20:32:07.1945725Z       %aten_select_copy_int_570 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_479, 0, 0), kwargs = {})
2025-03-21T20:32:07.1946335Z       %aten_select_copy_int_572 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_480, 0, 0), kwargs = {})
2025-03-21T20:32:07.1946954Z       %aten_select_copy_int_574 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_481, 0, 0), kwargs = {})
2025-03-21T20:32:07.1947607Z       %aten_mul_tensor_167 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_124, %aten_view_copy_default_203), kwargs = {})
2025-03-21T20:32:07.1948241Z       %aten_mul_tensor_169 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_124, %aten_view_copy_default_204), kwargs = {})
2025-03-21T20:32:07.1948857Z       %aten_mul_tensor_168 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_125, %aten_view_copy_default_204), kwargs = {})
2025-03-21T20:32:07.1949487Z       %aten_mul_tensor_170 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_125, %aten_view_copy_default_203), kwargs = {})
2025-03-21T20:32:07.1950105Z       %aten_mul_tensor_171 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_126, %aten_view_copy_default_203), kwargs = {})
2025-03-21T20:32:07.1950731Z       %aten_mul_tensor_173 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_126, %aten_view_copy_default_204), kwargs = {})
2025-03-21T20:32:07.1951346Z       %aten_mul_tensor_172 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_127, %aten_view_copy_default_204), kwargs = {})
2025-03-21T20:32:07.1951975Z       %aten_mul_tensor_174 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_127, %aten_view_copy_default_203), kwargs = {})
2025-03-21T20:32:07.1952547Z       %aten_select_copy_int_553 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_552, 0, 0), kwargs = {})
2025-03-21T20:32:07.1953132Z       %aten_select_copy_int_555 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_554, 0, 1), kwargs = {})
2025-03-21T20:32:07.1953702Z       %aten_select_copy_int_557 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_556, 0, 2), kwargs = {})
2025-03-21T20:32:07.1954281Z       %aten_select_copy_int_559 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_558, 0, 3), kwargs = {})
2025-03-21T20:32:07.1954853Z       %aten_select_copy_int_561 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_560, 0, 4), kwargs = {})
2025-03-21T20:32:07.1955421Z       %aten_select_copy_int_563 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_562, 0, 5), kwargs = {})
2025-03-21T20:32:07.1956004Z       %aten_select_copy_int_565 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_564, 0, 6), kwargs = {})
2025-03-21T20:32:07.1956597Z       %aten_select_copy_int_567 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_566, 0, 7), kwargs = {})
2025-03-21T20:32:07.1957175Z       %aten_select_copy_int_569 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_568, 0, 8), kwargs = {})
2025-03-21T20:32:07.1957768Z       %aten_select_copy_int_571 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_570, 0, 9), kwargs = {})
2025-03-21T20:32:07.1958378Z       %aten_select_copy_int_573 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_572, 0, 10), kwargs = {})
2025-03-21T20:32:07.1958987Z       %aten_select_copy_int_575 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_574, 0, 11), kwargs = {})
2025-03-21T20:32:07.1959571Z       %aten_sub_tensor_22 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.sub.Tensor](args = (%aten_mul_tensor_167, %aten_mul_tensor_168), kwargs = {})
2025-03-21T20:32:07.1960130Z       %aten_add_tensor_55 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_mul_tensor_169, %aten_mul_tensor_170), kwargs = {})
2025-03-21T20:32:07.1960702Z       %aten_sub_tensor_23 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.sub.Tensor](args = (%aten_mul_tensor_171, %aten_mul_tensor_172), kwargs = {})
2025-03-21T20:32:07.1961263Z       %aten_add_tensor_56 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_mul_tensor_173, %aten_mul_tensor_174), kwargs = {})
2025-03-21T20:32:07.1962728Z       %aten_cat_default_47 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_select_copy_int_553, %aten_select_copy_int_555, %aten_select_copy_int_557, %aten_select_copy_int_559, %aten_select_copy_int_561, %aten_select_copy_int_563, %aten_select_copy_int_565, %aten_select_copy_int_567, %aten_select_copy_int_569, %aten_select_copy_int_571, %aten_select_copy_int_573, %aten_select_copy_int_575],), kwargs = {})
2025-03-21T20:32:07.1963346Z       %aten_unsqueeze_copy_default_124 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_sub_tensor_22, 4), kwargs = {})
2025-03-21T20:32:07.1963971Z       %aten_unsqueeze_copy_default_125 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_add_tensor_55, 4), kwargs = {})
2025-03-21T20:32:07.1964582Z       %aten_unsqueeze_copy_default_126 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_sub_tensor_23, 4), kwargs = {})
2025-03-21T20:32:07.1965208Z       %aten_unsqueeze_copy_default_127 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_add_tensor_56, 4), kwargs = {})
2025-03-21T20:32:07.1965811Z       %aten_view_copy_default_208 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_47, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:32:07.1966511Z       %aten_cat_default_44 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_unsqueeze_copy_default_124, %aten_unsqueeze_copy_default_125], -1), kwargs = {})
2025-03-21T20:32:07.1967191Z       %aten_cat_default_45 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_unsqueeze_copy_default_126, %aten_unsqueeze_copy_default_127], -1), kwargs = {})
2025-03-21T20:32:07.1967803Z       %aten_view_copy_default_205 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_44, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1968428Z       %aten_view_copy_default_206 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_45, [1, 1, 12, 64]), kwargs = {})
2025-03-21T20:32:07.1969116Z       %aten_permute_copy_default_457 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_view_copy_default_205, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1970070Z       %aten_index_put_default_22 : [num_users=13] = call_function[target=executorch.exir.dialects.edge._ops.aten.index_put.default](args = (%b_layers_11_attention_kv_cache_past_k_caches, [None, %aten__to_copy_default_1], %aten_view_copy_default_206), kwargs = {})
2025-03-21T20:32:07.1970759Z       %aten_permute_copy_default_458 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_22, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1971406Z       %aten_permute_copy_default_459 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_22, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1972061Z       %aten_permute_copy_default_460 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_22, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1972708Z       %aten_permute_copy_default_461 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_22, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1973365Z       %aten_permute_copy_default_462 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_22, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1974006Z       %aten_permute_copy_default_463 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_22, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1974658Z       %aten_permute_copy_default_464 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_22, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1975301Z       %aten_permute_copy_default_465 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_22, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1975958Z       %aten_permute_copy_default_466 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_22, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1976600Z       %aten_permute_copy_default_467 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_22, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1977256Z       %aten_permute_copy_default_468 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_22, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1977896Z       %aten_permute_copy_default_469 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_index_put_default_22, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1978495Z       %aten_select_copy_int_528 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_458, 0, 0), kwargs = {})
2025-03-21T20:32:07.1979084Z       %aten_select_copy_int_530 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_459, 0, 0), kwargs = {})
2025-03-21T20:32:07.1979701Z       %aten_select_copy_int_532 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_460, 0, 0), kwargs = {})
2025-03-21T20:32:07.1980289Z       %aten_select_copy_int_534 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_461, 0, 0), kwargs = {})
2025-03-21T20:32:07.1980906Z       %aten_select_copy_int_536 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_462, 0, 0), kwargs = {})
2025-03-21T20:32:07.1981510Z       %aten_select_copy_int_538 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_463, 0, 0), kwargs = {})
2025-03-21T20:32:07.1982127Z       %aten_select_copy_int_540 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_464, 0, 0), kwargs = {})
2025-03-21T20:32:07.1982710Z       %aten_select_copy_int_542 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_465, 0, 0), kwargs = {})
2025-03-21T20:32:07.1983305Z       %aten_select_copy_int_544 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_466, 0, 0), kwargs = {})
2025-03-21T20:32:07.1983889Z       %aten_select_copy_int_546 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_467, 0, 0), kwargs = {})
2025-03-21T20:32:07.1984487Z       %aten_select_copy_int_548 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_468, 0, 0), kwargs = {})
2025-03-21T20:32:07.1985070Z       %aten_select_copy_int_550 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_permute_copy_default_469, 0, 0), kwargs = {})
2025-03-21T20:32:07.1985651Z       %aten_select_copy_int_529 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_528, 0, 0), kwargs = {})
2025-03-21T20:32:07.1986218Z       %aten_select_copy_int_531 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_530, 0, 1), kwargs = {})
2025-03-21T20:32:07.1986802Z       %aten_select_copy_int_533 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_532, 0, 2), kwargs = {})
2025-03-21T20:32:07.1987374Z       %aten_select_copy_int_535 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_534, 0, 3), kwargs = {})
2025-03-21T20:32:07.1987954Z       %aten_select_copy_int_537 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_536, 0, 4), kwargs = {})
2025-03-21T20:32:07.1988519Z       %aten_select_copy_int_539 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_538, 0, 5), kwargs = {})
2025-03-21T20:32:07.1989101Z       %aten_select_copy_int_541 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_540, 0, 6), kwargs = {})
2025-03-21T20:32:07.1989669Z       %aten_select_copy_int_543 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_542, 0, 7), kwargs = {})
2025-03-21T20:32:07.1990263Z       %aten_select_copy_int_545 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_544, 0, 8), kwargs = {})
2025-03-21T20:32:07.1990967Z       %aten_select_copy_int_547 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_546, 0, 9), kwargs = {})
2025-03-21T20:32:07.1991552Z       %aten_select_copy_int_549 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_548, 0, 10), kwargs = {})
2025-03-21T20:32:07.1992148Z       %aten_select_copy_int_551 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_select_copy_int_550, 0, 11), kwargs = {})
2025-03-21T20:32:07.1993637Z       %aten_cat_default_46 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.cat.default](args = ([%aten_select_copy_int_529, %aten_select_copy_int_531, %aten_select_copy_int_533, %aten_select_copy_int_535, %aten_select_copy_int_537, %aten_select_copy_int_539, %aten_select_copy_int_541, %aten_select_copy_int_543, %aten_select_copy_int_545, %aten_select_copy_int_547, %aten_select_copy_int_549, %aten_select_copy_int_551],), kwargs = {})
2025-03-21T20:32:07.1994266Z       %aten_view_copy_default_207 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_cat_default_46, [1, 12, 128, 64]), kwargs = {})
2025-03-21T20:32:07.1994924Z       %aten_permute_copy_default_482 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_view_copy_default_207, [0, 1, 3, 2]), kwargs = {})
2025-03-21T20:32:07.1995607Z       %aten_matmul_default_22 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.matmul.default](args = (%aten_permute_copy_default_457, %aten_permute_copy_default_482), kwargs = {})
2025-03-21T20:32:07.1996205Z       %aten_mul_tensor_175 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_matmul_default_22, %b__frozen_param160), kwargs = {})
2025-03-21T20:32:07.1996773Z       %aten_add_tensor_57 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_mul_tensor_175, %aten_index_tensor_13), kwargs = {})
2025-03-21T20:32:07.1997365Z       %aten__softmax_default_11 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten._softmax.default](args = (%aten_add_tensor_57, -1, False), kwargs = {})
2025-03-21T20:32:07.1998013Z       %aten_matmul_default_23 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.matmul.default](args = (%aten__softmax_default_11, %aten_view_copy_default_208), kwargs = {})
2025-03-21T20:32:07.1998663Z       %aten_permute_copy_default_483 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_matmul_default_23, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.1999287Z       %aten_view_copy_default_215 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_permute_copy_default_483, [1, 1, 768]), kwargs = {})
2025-03-21T20:32:07.1999941Z       %aten_unsqueeze_copy_default_128 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_view_copy_default_215, -1), kwargs = {})
2025-03-21T20:32:07.2000609Z       %aten_permute_copy_default_484 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_128, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.2001446Z       %aten_convolution_default_80 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_484, %b__frozen_param104, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.2002102Z       %aten_permute_copy_default_485 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_80, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.2002745Z       %aten_squeeze_copy_dims_128 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_485, [-1]), kwargs = {})
2025-03-21T20:32:07.2003329Z       %aten_add_tensor_58 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_add_tensor_54, %aten_squeeze_copy_dims_128), kwargs = {})
2025-03-21T20:32:07.2004044Z       %aten_rms_norm_default_23 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.rms_norm.default](args = (%aten_add_tensor_58, [768], %b__frozen_param105, 9.999999747378752e-06), kwargs = {})
2025-03-21T20:32:07.2004740Z       %aten_unsqueeze_copy_default_129 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_23, -1), kwargs = {})
2025-03-21T20:32:07.2005385Z       %aten_unsqueeze_copy_default_130 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_rms_norm_default_23, -1), kwargs = {})
2025-03-21T20:32:07.2006057Z       %aten_permute_copy_default_486 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_129, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.2006741Z       %aten_permute_copy_default_488 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_130, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.2007561Z       %aten_convolution_default_81 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_486, %b__frozen_param106, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.2008392Z       %aten_convolution_default_82 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_488, %b__frozen_param107, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.2009047Z       %aten_permute_copy_default_487 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_81, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.2009766Z       %aten_permute_copy_default_489 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_82, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.2010379Z       %aten_squeeze_copy_dims_129 : [num_users=2] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_487, [-1]), kwargs = {})
2025-03-21T20:32:07.2010997Z       %aten_squeeze_copy_dims_130 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_489, [-1]), kwargs = {})
2025-03-21T20:32:07.2011574Z       %aten_sigmoid_default_11 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.sigmoid.default](args = (%aten_squeeze_copy_dims_129,), kwargs = {})
2025-03-21T20:32:07.2012200Z       %aten_mul_tensor_178 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_squeeze_copy_dims_129, %aten_sigmoid_default_11), kwargs = {})
2025-03-21T20:32:07.2012797Z       %aten_mul_tensor_179 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.mul.Tensor](args = (%aten_mul_tensor_178, %aten_squeeze_copy_dims_130), kwargs = {})
2025-03-21T20:32:07.2013432Z       %aten_unsqueeze_copy_default_131 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.unsqueeze_copy.default](args = (%aten_mul_tensor_179, -1), kwargs = {})
2025-03-21T20:32:07.2014106Z       %aten_permute_copy_default_490 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_unsqueeze_copy_default_131, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.2014967Z       %aten_convolution_default_83 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_490, %b__frozen_param108, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.2015647Z       %aten_permute_copy_default_491 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_83, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.2016287Z       %aten_squeeze_copy_dims_131 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.squeeze_copy.dims](args = (%aten_permute_copy_default_491, [-1]), kwargs = {})
2025-03-21T20:32:07.2016896Z       %aten_add_tensor_59 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.add.Tensor](args = (%aten_add_tensor_58, %aten_squeeze_copy_dims_131), kwargs = {})
2025-03-21T20:32:07.2017465Z       %aten_select_copy_int_576 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.select_copy.int](args = (%aten_add_tensor_59, 1, -1), kwargs = {})
2025-03-21T20:32:07.2018168Z       %aten_rms_norm_default_24 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.rms_norm.default](args = (%aten_select_copy_int_576, [768], %b__frozen_param109, 9.999999747378752e-06), kwargs = {})
2025-03-21T20:32:07.2018798Z       %aten_view_copy_default_216 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_rms_norm_default_24, [1, 1, 768, 1]), kwargs = {})
2025-03-21T20:32:07.2019450Z       %aten_permute_copy_default_492 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_view_copy_default_216, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.2020285Z       %aten_convolution_default_84 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.convolution.default](args = (%aten_permute_copy_default_492, %b__frozen_param110, None, [1, 1], [0, 0], [1, 1], False, [0, 0], 1), kwargs = {})
2025-03-21T20:32:07.2020941Z       %aten_permute_copy_default_493 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.permute_copy.default](args = (%aten_convolution_default_84, [0, 2, 1, 3]), kwargs = {})
2025-03-21T20:32:07.2021578Z       %aten_view_copy_default_217 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.view_copy.default](args = (%aten_permute_copy_default_493, [1, 32000]), kwargs = {})
2025-03-21T20:32:07.2023752Z       return [aten_index_put_default_1, aten_index_put_default, aten_index_put_default_3, aten_index_put_default_2, aten_index_put_default_5, aten_index_put_default_4, aten_index_put_default_7, aten_index_put_default_6, aten_index_put_default_9, aten_index_put_default_8, aten_index_put_default_11, aten_index_put_default_10, aten_index_put_default_13, aten_index_put_default_12, aten_index_put_default_15, aten_index_put_default_14, aten_index_put_default_17, aten_index_put_default_16, aten_index_put_default_19, aten_index_put_default_18, aten_index_put_default_21, aten_index_put_default_20, aten_index_put_default_23, aten_index_put_default_22, aten_view_copy_default_217]
2025-03-21T20:32:07.2028100Z   %executorch_call_delegate : [num_users=25] = call_function[target=torch.ops.higher_order.executorch_call_delegate](args = (%lowered_module_0, %b_layers_0_attention_kv_cache_past_v_caches, %b_layers_0_attention_kv_cache_past_k_caches, %b_layers_1_attention_kv_cache_past_v_caches, %b_layers_1_attention_kv_cache_past_k_caches, %b_layers_2_attention_kv_cache_past_v_caches, %b_layers_2_attention_kv_cache_past_k_caches, %b_layers_3_attention_kv_cache_past_v_caches, %b_layers_3_attention_kv_cache_past_k_caches, %b_layers_4_attention_kv_cache_past_v_caches, %b_layers_4_attention_kv_cache_past_k_caches, %b_layers_5_attention_kv_cache_past_v_caches, %b_layers_5_attention_kv_cache_past_k_caches, %b_layers_6_attention_kv_cache_past_v_caches, %b_layers_6_attention_kv_cache_past_k_caches, %b_layers_7_attention_kv_cache_past_v_caches, %b_layers_7_attention_kv_cache_past_k_caches, %b_layers_8_attention_kv_cache_past_v_caches, %b_layers_8_attention_kv_cache_past_k_caches, %b_layers_9_attention_kv_cache_past_v_caches, %b_layers_9_attention_kv_cache_past_k_caches, %b_layers_10_attention_kv_cache_past_v_caches, %b_layers_10_attention_kv_cache_past_k_caches, %b_layers_11_attention_kv_cache_past_v_caches, %b_layers_11_attention_kv_cache_past_k_caches, %tokens, %attn_options_input_pos), kwargs = {})
2025-03-21T20:32:07.2028534Z   %getitem : [num_users=1] = call_function[target=operator.getitem](args = (%executorch_call_delegate, 0), kwargs = {})
2025-03-21T20:32:07.2028942Z   %getitem_1 : [num_users=1] = call_function[target=operator.getitem](args = (%executorch_call_delegate, 1), kwargs = {})
2025-03-21T20:32:07.2029304Z   %getitem_2 : [num_users=1] = call_function[target=operator.getitem](args = (%executorch_call_delegate, 2), kwargs = {})
2025-03-21T20:32:07.2029672Z   %getitem_3 : [num_users=1] = call_function[target=operator.getitem](args = (%executorch_call_delegate, 3), kwargs = {})
2025-03-21T20:32:07.2030043Z   %getitem_4 : [num_users=1] = call_function[target=operator.getitem](args = (%executorch_call_delegate, 4), kwargs = {})
2025-03-21T20:32:07.2030403Z   %getitem_5 : [num_users=1] = call_function[target=operator.getitem](args = (%executorch_call_delegate, 5), kwargs = {})
2025-03-21T20:32:07.2030773Z   %getitem_6 : [num_users=1] = call_function[target=operator.getitem](args = (%executorch_call_delegate, 6), kwargs = {})
2025-03-21T20:32:07.2031216Z   %getitem_7 : [num_users=1] = call_function[target=operator.getitem](args = (%executorch_call_delegate, 7), kwargs = {})
2025-03-21T20:32:07.2031590Z   %getitem_8 : [num_users=1] = call_function[target=operator.getitem](args = (%executorch_call_delegate, 8), kwargs = {})
2025-03-21T20:32:07.2031948Z   %getitem_9 : [num_users=1] = call_function[target=operator.getitem](args = (%executorch_call_delegate, 9), kwargs = {})
2025-03-21T20:32:07.2032481Z   %getitem_10 : [num_users=1] = call_function[target=operator.getitem](args = (%executorch_call_delegate, 10), kwargs = {})
2025-03-21T20:32:07.2032849Z   %getitem_11 : [num_users=1] = call_function[target=operator.getitem](args = (%executorch_call_delegate, 11), kwargs = {})
2025-03-21T20:32:07.2033226Z   %getitem_12 : [num_users=1] = call_function[target=operator.getitem](args = (%executorch_call_delegate, 12), kwargs = {})
2025-03-21T20:32:07.2033589Z   %getitem_13 : [num_users=1] = call_function[target=operator.getitem](args = (%executorch_call_delegate, 13), kwargs = {})
2025-03-21T20:32:07.2033957Z   %getitem_14 : [num_users=1] = call_function[target=operator.getitem](args = (%executorch_call_delegate, 14), kwargs = {})
2025-03-21T20:32:07.2034332Z   %getitem_15 : [num_users=1] = call_function[target=operator.getitem](args = (%executorch_call_delegate, 15), kwargs = {})
2025-03-21T20:32:07.2034694Z   %getitem_16 : [num_users=1] = call_function[target=operator.getitem](args = (%executorch_call_delegate, 16), kwargs = {})
2025-03-21T20:32:07.2035069Z   %getitem_17 : [num_users=1] = call_function[target=operator.getitem](args = (%executorch_call_delegate, 17), kwargs = {})
2025-03-21T20:32:07.2035431Z   %getitem_18 : [num_users=1] = call_function[target=operator.getitem](args = (%executorch_call_delegate, 18), kwargs = {})
2025-03-21T20:32:07.2035803Z   %getitem_19 : [num_users=1] = call_function[target=operator.getitem](args = (%executorch_call_delegate, 19), kwargs = {})
2025-03-21T20:32:07.2036167Z   %getitem_20 : [num_users=1] = call_function[target=operator.getitem](args = (%executorch_call_delegate, 20), kwargs = {})
2025-03-21T20:32:07.2036542Z   %getitem_21 : [num_users=1] = call_function[target=operator.getitem](args = (%executorch_call_delegate, 21), kwargs = {})
2025-03-21T20:32:07.2036905Z   %getitem_22 : [num_users=1] = call_function[target=operator.getitem](args = (%executorch_call_delegate, 22), kwargs = {})
2025-03-21T20:32:07.2037344Z   %getitem_23 : [num_users=1] = call_function[target=operator.getitem](args = (%executorch_call_delegate, 23), kwargs = {})
2025-03-21T20:32:07.2037709Z   %getitem_24 : [num_users=1] = call_function[target=operator.getitem](args = (%executorch_call_delegate, 24), kwargs = {})
2025-03-21T20:32:07.2038398Z   %aten_copy_default_1 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.copy.default](args = (%b_layers_0_attention_kv_cache_past_v_caches, %getitem), kwargs = {})
2025-03-21T20:32:07.2039076Z   %aten_copy_default : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.copy.default](args = (%b_layers_0_attention_kv_cache_past_k_caches, %getitem_1), kwargs = {})
2025-03-21T20:32:07.2039770Z   %aten_copy_default_3 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.copy.default](args = (%b_layers_1_attention_kv_cache_past_v_caches, %getitem_2), kwargs = {})
2025-03-21T20:32:07.2040414Z   %aten_copy_default_2 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.copy.default](args = (%b_layers_1_attention_kv_cache_past_k_caches, %getitem_3), kwargs = {})
2025-03-21T20:32:07.2041061Z   %aten_copy_default_5 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.copy.default](args = (%b_layers_2_attention_kv_cache_past_v_caches, %getitem_4), kwargs = {})
2025-03-21T20:32:07.2041695Z   %aten_copy_default_4 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.copy.default](args = (%b_layers_2_attention_kv_cache_past_k_caches, %getitem_5), kwargs = {})
2025-03-21T20:32:07.2042335Z   %aten_copy_default_7 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.copy.default](args = (%b_layers_3_attention_kv_cache_past_v_caches, %getitem_6), kwargs = {})
2025-03-21T20:32:07.2042983Z   %aten_copy_default_6 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.copy.default](args = (%b_layers_3_attention_kv_cache_past_k_caches, %getitem_7), kwargs = {})
2025-03-21T20:32:07.2043619Z   %aten_copy_default_9 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.copy.default](args = (%b_layers_4_attention_kv_cache_past_v_caches, %getitem_8), kwargs = {})
2025-03-21T20:32:07.2044271Z   %aten_copy_default_8 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.copy.default](args = (%b_layers_4_attention_kv_cache_past_k_caches, %getitem_9), kwargs = {})
2025-03-21T20:32:07.2044913Z   %aten_copy_default_11 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.copy.default](args = (%b_layers_5_attention_kv_cache_past_v_caches, %getitem_10), kwargs = {})
2025-03-21T20:32:07.2045570Z   %aten_copy_default_10 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.copy.default](args = (%b_layers_5_attention_kv_cache_past_k_caches, %getitem_11), kwargs = {})
2025-03-21T20:32:07.2046204Z   %aten_copy_default_13 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.copy.default](args = (%b_layers_6_attention_kv_cache_past_v_caches, %getitem_12), kwargs = {})
2025-03-21T20:32:07.2046854Z   %aten_copy_default_12 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.copy.default](args = (%b_layers_6_attention_kv_cache_past_k_caches, %getitem_13), kwargs = {})
2025-03-21T20:32:07.2047492Z   %aten_copy_default_15 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.copy.default](args = (%b_layers_7_attention_kv_cache_past_v_caches, %getitem_14), kwargs = {})
2025-03-21T20:32:07.2048140Z   %aten_copy_default_14 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.copy.default](args = (%b_layers_7_attention_kv_cache_past_k_caches, %getitem_15), kwargs = {})
2025-03-21T20:32:07.2048775Z   %aten_copy_default_17 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.copy.default](args = (%b_layers_8_attention_kv_cache_past_v_caches, %getitem_16), kwargs = {})
2025-03-21T20:32:07.2049541Z   %aten_copy_default_16 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.copy.default](args = (%b_layers_8_attention_kv_cache_past_k_caches, %getitem_17), kwargs = {})
2025-03-21T20:32:07.2050218Z   %aten_copy_default_19 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.copy.default](args = (%b_layers_9_attention_kv_cache_past_v_caches, %getitem_18), kwargs = {})
2025-03-21T20:32:07.2050895Z   %aten_copy_default_18 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.copy.default](args = (%b_layers_9_attention_kv_cache_past_k_caches, %getitem_19), kwargs = {})
2025-03-21T20:32:07.2051569Z   %aten_copy_default_21 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.copy.default](args = (%b_layers_10_attention_kv_cache_past_v_caches, %getitem_20), kwargs = {})
2025-03-21T20:32:07.2052222Z   %aten_copy_default_20 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.copy.default](args = (%b_layers_10_attention_kv_cache_past_k_caches, %getitem_21), kwargs = {})
2025-03-21T20:32:07.2052858Z   %aten_copy_default_23 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.copy.default](args = (%b_layers_11_attention_kv_cache_past_v_caches, %getitem_22), kwargs = {})
2025-03-21T20:32:07.2053508Z   %aten_copy_default_22 : [num_users=1] = call_function[target=executorch.exir.dialects.edge._ops.aten.copy.default](args = (%b_layers_11_attention_kv_cache_past_k_caches, %getitem_23), kwargs = {})
2025-03-21T20:32:07.2055234Z   return (aten_copy_default, aten_copy_default_1, aten_copy_default_2, aten_copy_default_3, aten_copy_default_4, aten_copy_default_5, aten_copy_default_6, aten_copy_default_7, aten_copy_default_8, aten_copy_default_9, aten_copy_default_10, aten_copy_default_11, aten_copy_default_12, aten_copy_default_13, aten_copy_default_14, aten_copy_default_15, aten_copy_default_16, aten_copy_default_17, aten_copy_default_18, aten_copy_default_19, aten_copy_default_20, aten_copy_default_21, aten_copy_default_22, aten_copy_default_23, getitem_24)
2025-03-21T20:32:07.2055254Z 
2025-03-21T20:32:07.2055837Z [INFO 2025-03-21 20:32:06,999 builder.py:448] Applied partitioners: <executorch.backends.qualcomm.partition.qnn_partitioner.QnnPartitioner object at 0x7fa85c1487f0>
2025-03-21T20:32:07.2055963Z Total delegated subgraphs: 1
2025-03-21T20:32:07.2056072Z Number of delegated nodes: 1992
2025-03-21T20:32:07.2056184Z Number of non-delegated nodes: 49
2025-03-21T20:32:07.2056189Z 
2025-03-21T20:32:07.2096343Z ╒════╤═════════════════════════════╤═══════════════════════════════════╤═══════════════════════════════════════╕
2025-03-21T20:32:07.2096748Z │    │ op_type                     │   occurrences_in_delegated_graphs │   occurrences_in_non_delegated_graphs │
2025-03-21T20:32:07.2097127Z ╞════╪═════════════════════════════╪═══════════════════════════════════╪═══════════════════════════════════════╡
2025-03-21T20:32:07.2097462Z │  0 │ aten__softmax_default       │                                12 │                                     0 │
2025-03-21T20:32:07.2097815Z ├────┼─────────────────────────────┼───────────────────────────────────┼───────────────────────────────────────┤
2025-03-21T20:32:07.2098126Z │  1 │ aten__to_copy_default       │                                 2 │                                     0 │
2025-03-21T20:32:07.2098480Z ├────┼─────────────────────────────┼───────────────────────────────────┼───────────────────────────────────────┤
2025-03-21T20:32:07.2098830Z │  2 │ aten_add_tensor             │                                60 │                                     0 │
2025-03-21T20:32:07.2099211Z ├────┼─────────────────────────────┼───────────────────────────────────┼───────────────────────────────────────┤
2025-03-21T20:32:07.2099517Z │  3 │ aten_cat_default            │                                48 │                                     0 │
2025-03-21T20:32:07.2099894Z ├────┼─────────────────────────────┼───────────────────────────────────┼───────────────────────────────────────┤
2025-03-21T20:32:07.2100235Z │  4 │ aten_convolution_default    │                                85 │                                     0 │
2025-03-21T20:32:07.2100613Z ├────┼─────────────────────────────┼───────────────────────────────────┼───────────────────────────────────────┤
2025-03-21T20:32:07.2100922Z │  5 │ aten_copy_default           │                                 0 │                                    24 │
2025-03-21T20:32:07.2101259Z ├────┼─────────────────────────────┼───────────────────────────────────┼───────────────────────────────────────┤
2025-03-21T20:32:07.2101609Z │  6 │ aten_embedding_default      │                                 1 │                                     0 │
2025-03-21T20:32:07.2101950Z ├────┼─────────────────────────────┼───────────────────────────────────┼───────────────────────────────────────┤
2025-03-21T20:32:07.2102272Z │  7 │ aten_index_put_default      │                                24 │                                     0 │
2025-03-21T20:32:07.2102626Z ├────┼─────────────────────────────┼───────────────────────────────────┼───────────────────────────────────────┤
2025-03-21T20:32:07.2102921Z │  8 │ aten_index_tensor           │                                14 │                                     0 │
2025-03-21T20:32:07.2103284Z ├────┼─────────────────────────────┼───────────────────────────────────┼───────────────────────────────────────┤
2025-03-21T20:32:07.2103587Z │  9 │ aten_matmul_default         │                                24 │                                     0 │
2025-03-21T20:32:07.2104054Z ├────┼─────────────────────────────┼───────────────────────────────────┼───────────────────────────────────────┤
2025-03-21T20:32:07.2104351Z │ 10 │ aten_mul_tensor             │                               132 │                                     0 │
2025-03-21T20:32:07.2104700Z ├────┼─────────────────────────────┼───────────────────────────────────┼───────────────────────────────────────┤
2025-03-21T20:32:07.2105063Z │ 11 │ aten_permute_copy_default   │                               494 │                                     0 │
2025-03-21T20:32:07.2105416Z ├────┼─────────────────────────────┼───────────────────────────────────┼───────────────────────────────────────┤
2025-03-21T20:32:07.2105757Z │ 12 │ aten_rms_norm_default       │                                25 │                                     0 │
2025-03-21T20:32:07.2106098Z ├────┼─────────────────────────────┼───────────────────────────────────┼───────────────────────────────────────┤
2025-03-21T20:32:07.2106441Z │ 13 │ aten_select_copy_int        │                               577 │                                     0 │
2025-03-21T20:32:07.2106783Z ├────┼─────────────────────────────┼───────────────────────────────────┼───────────────────────────────────────┤
2025-03-21T20:32:07.2107103Z │ 14 │ aten_sigmoid_default        │                                12 │                                     0 │
2025-03-21T20:32:07.2107453Z ├────┼─────────────────────────────┼───────────────────────────────────┼───────────────────────────────────────┤
2025-03-21T20:32:07.2107775Z │ 15 │ aten_slice_copy_tensor      │                                48 │                                     0 │
2025-03-21T20:32:07.2108127Z ├────┼─────────────────────────────┼───────────────────────────────────┼───────────────────────────────────────┤
2025-03-21T20:32:07.2108448Z │ 16 │ aten_squeeze_copy_dims      │                               132 │                                     0 │
2025-03-21T20:32:07.2108829Z ├────┼─────────────────────────────┼───────────────────────────────────┼───────────────────────────────────────┤
2025-03-21T20:32:07.2109125Z │ 17 │ aten_sub_tensor             │                                24 │                                     0 │
2025-03-21T20:32:07.2109480Z ├────┼─────────────────────────────┼───────────────────────────────────┼───────────────────────────────────────┤
2025-03-21T20:32:07.2109849Z │ 18 │ aten_unsqueeze_copy_default │                               132 │                                     0 │
2025-03-21T20:32:07.2110202Z ├────┼─────────────────────────────┼───────────────────────────────────┼───────────────────────────────────────┤
2025-03-21T20:32:07.2110547Z │ 19 │ aten_view_copy_default      │                               146 │                                     0 │
2025-03-21T20:32:07.2110898Z ├────┼─────────────────────────────┼───────────────────────────────────┼───────────────────────────────────────┤
2025-03-21T20:32:07.2111173Z │ 20 │ getitem                     │                                 0 │                                    25 │
2025-03-21T20:32:18.0541287Z ├────┼─────────────────────────────┼───────────────────────────────────┼───────────────────────────────────────┤
2025-03-21T20:32:18.0542082Z │ 21 │ Total                       │                              1992 │                                    49 │
2025-03-21T20:32:18.0542848Z ╘════╧═════════════════════════════╧═══════════════════════════════════╧═══════════════════════════════════════╛
2025-03-21T20:32:18.0544525Z /pytorch/executorch/exir/emit/_emitter.py:1592: UserWarning: Mutation on a buffer in the model is detected. ExecuTorch assumes buffers that are mutated in the graph have a meaningless initial state, only the shape and dtype will be serialized, unless a pass which sets meta["et_init_buffer"] to True such as InitializedMutableBufferPass is run.
2025-03-21T20:32:18.0546261Z   warnings.warn(
2025-03-21T20:32:18.0546756Z [INFO 2025-03-21 20:32:10,599 builder.py:507] Required memory for activation in bytes: [0, 19395584]
2025-03-21T20:32:18.0547343Z modelname: tinyllama_qnn_fp32
2025-03-21T20:32:18.0547665Z output_file: tinyllama_qnn_fp32.pte
2025-03-21T20:32:18.0548193Z [INFO 2025-03-21 20:32:10,694 utils.py:141] Saved exported program to tinyllama_qnn_fp32.pte
2025-03-21T20:32:18.0548678Z + echo 'Creating tokenizer.bin'
2025-03-21T20:32:18.0549040Z Creating tokenizer.bin
2025-03-21T20:32:18.0549490Z + python -m extension.llm.tokenizer.tokenizer -t tokenizer.model -o tokenizer.bin
2025-03-21T20:32:18.0550408Z + RUNTIME_ARGS='--model_path=tinyllama_qnn_fp32.pte --tokenizer_path=tokenizer.bin --prompt=Once --temperature=0 --seq_len=10 --warmup=1'
2025-03-21T20:32:18.0551160Z + echo 'Running tinyllama_qnn_fp32.pte in portable mode'
2025-03-21T20:32:18.0551580Z Running tinyllama_qnn_fp32.pte in portable mode
2025-03-21T20:32:18.0551941Z + [[ cmake == \b\u\c\k\2 ]]
2025-03-21T20:32:18.0552220Z + [[ cmake == \c\m\a\k\e ]]
2025-03-21T20:32:18.0552563Z + cmake_install_executorch_libraries
2025-03-21T20:32:18.0553347Z + echo 'Installing libexecutorch.a, libextension_module.so, libportable_ops_lib.a'
2025-03-21T20:32:18.0553986Z Installing libexecutorch.a, libextension_module.so, libportable_ops_lib.a
2025-03-21T20:32:18.0554448Z + rm -rf cmake-out
2025-03-21T20:32:18.0556596Z + retry cmake -DCMAKE_INSTALL_PREFIX=cmake-out -DCMAKE_BUILD_TYPE=Release -DEXECUTORCH_BUILD_EXTENSION_DATA_LOADER=ON -DEXECUTORCH_BUILD_EXTENSION_MODULE=ON -DEXECUTORCH_BUILD_EXTENSION_TENSOR=ON -DEXECUTORCH_BUILD_KERNELS_CUSTOM=OFF -DEXECUTORCH_BUILD_KERNELS_OPTIMIZED=ON -DEXECUTORCH_BUILD_KERNELS_QUANTIZED=ON -DEXECUTORCH_BUILD_XNNPACK=OFF -DEXECUTORCH_BUILD_MPS=OFF -DEXECUTORCH_BUILD_COREML=OFF -DEXECUTORCH_BUILD_QNN=ON -DQNN_SDK_ROOT=/tmp/qnn/2.28.0.241029 -DPYTHON_EXECUTABLE=python -Bcmake-out .
2025-03-21T20:32:18.0560437Z + cmake -DCMAKE_INSTALL_PREFIX=cmake-out -DCMAKE_BUILD_TYPE=Release -DEXECUTORCH_BUILD_EXTENSION_DATA_LOADER=ON -DEXECUTORCH_BUILD_EXTENSION_MODULE=ON -DEXECUTORCH_BUILD_EXTENSION_TENSOR=ON -DEXECUTORCH_BUILD_KERNELS_CUSTOM=OFF -DEXECUTORCH_BUILD_KERNELS_OPTIMIZED=ON -DEXECUTORCH_BUILD_KERNELS_QUANTIZED=ON -DEXECUTORCH_BUILD_XNNPACK=OFF -DEXECUTORCH_BUILD_MPS=OFF -DEXECUTORCH_BUILD_COREML=OFF -DEXECUTORCH_BUILD_QNN=ON -DQNN_SDK_ROOT=/tmp/qnn/2.28.0.241029 -DPYTHON_EXECUTABLE=python -Bcmake-out .
2025-03-21T20:32:18.0562512Z -- The C compiler identification is Clang 12.0.1
2025-03-21T20:32:18.0562912Z -- The CXX compiler identification is Clang 12.0.1
2025-03-21T20:32:18.0563347Z -- Detecting C compiler ABI info
2025-03-21T20:32:18.0563680Z -- Detecting C compiler ABI info - done
2025-03-21T20:32:18.0564071Z -- Check for working C compiler: /opt/cache/bin/cc - skipped
2025-03-21T20:32:18.0564473Z -- Detecting C compile features
2025-03-21T20:32:18.0564795Z -- Detecting C compile features - done
2025-03-21T20:32:18.0565130Z -- Detecting CXX compiler ABI info
2025-03-21T20:32:18.0565460Z -- Detecting CXX compiler ABI info - done
2025-03-21T20:32:18.0565863Z -- Check for working CXX compiler: /opt/cache/bin/c++ - skipped
2025-03-21T20:32:18.0566276Z -- Detecting CXX compile features
2025-03-21T20:32:18.0566602Z -- Detecting CXX compile features - done
2025-03-21T20:32:18.0567391Z CMake Deprecation Warning at backends/xnnpack/third-party/FXdiv/CMakeLists.txt:1 (CMAKE_MINIMUM_REQUIRED):
2025-03-21T20:32:18.0568133Z   Compatibility with CMake < 3.10 will be removed from a future version of
2025-03-21T20:32:18.0568557Z   CMake.
2025-03-21T20:32:18.0568695Z 
2025-03-21T20:32:18.0568925Z   Update the VERSION argument <min> value.  Or, use the <min>...<max> syntax
2025-03-21T20:32:18.0569591Z   to tell CMake that the project requires at least <min> but has been updated
2025-03-21T20:32:18.0570098Z   to work with policies introduced by <max> or earlier.
2025-03-21T20:32:18.0570356Z 
2025-03-21T20:32:18.0570493Z 
2025-03-21T20:32:18.0571115Z CMake Deprecation Warning at backends/xnnpack/third-party/cpuinfo/CMakeLists.txt:1 (CMAKE_MINIMUM_REQUIRED):
2025-03-21T20:32:18.0571852Z   Compatibility with CMake < 3.10 will be removed from a future version of
2025-03-21T20:32:18.0572287Z   CMake.
2025-03-21T20:32:18.0572419Z 
2025-03-21T20:32:18.0572646Z   Update the VERSION argument <min> value.  Or, use the <min>...<max> syntax
2025-03-21T20:32:18.0573209Z   to tell CMake that the project requires at least <min> but has been updated
2025-03-21T20:32:18.0573718Z   to work with policies introduced by <max> or earlier.
2025-03-21T20:32:18.0573978Z 
2025-03-21T20:32:18.0574102Z 
2025-03-21T20:32:18.0574354Z -- Performing Test CMAKE_HAVE_LIBC_PTHREAD
2025-03-21T20:32:18.0574734Z -- Performing Test CMAKE_HAVE_LIBC_PTHREAD - Success
2025-03-21T20:32:18.0575102Z -- Found Threads: TRUE
2025-03-21T20:32:18.0575803Z CMake Deprecation Warning at backends/xnnpack/third-party/pthreadpool/CMakeLists.txt:1 (CMAKE_MINIMUM_REQUIRED):
2025-03-21T20:32:18.0576619Z   Compatibility with CMake < 3.10 will be removed from a future version of
2025-03-21T20:32:18.0577080Z   CMake.
2025-03-21T20:32:18.0577202Z 
2025-03-21T20:32:18.0577509Z   Update the VERSION argument <min> value.  Or, use the <min>...<max> syntax
2025-03-21T20:32:18.0578098Z   to tell CMake that the project requires at least <min> but has been updated
2025-03-21T20:32:18.0578606Z   to work with policies introduced by <max> or earlier.
2025-03-21T20:32:18.0578878Z 
2025-03-21T20:32:18.0579002Z 
2025-03-21T20:32:18.0579246Z -- Using python executable 'python'
2025-03-21T20:32:18.0579576Z -- Resolved buck2 as buck2.
2025-03-21T20:32:18.0579890Z -- Killing buck2 daemon
2025-03-21T20:32:18.0580159Z 'buck2 killall'
2025-03-21T20:32:18.0580431Z -- executorch: Generating source lists
2025-03-21T20:32:18.0580965Z -- executorch: Generating source file list /pytorch/executorch/cmake-out/executorch_srcs.cmake
2025-03-21T20:32:18.0581693Z -- executorch: Using sources file /pytorch/executorch/cmake-out/executorch_srcs.cmake
2025-03-21T20:32:18.0582192Z -- executorch: Using PAL default 'posix'
2025-03-21T20:32:18.0582531Z -- Generating operator lib:
2025-03-21T20:32:18.0582825Z --   LIB_NAME: portable_ops_lib
2025-03-21T20:32:18.0583251Z --   OPS_SCHEMA_YAML: /pytorch/executorch/kernels/portable/functions.yaml
2025-03-21T20:32:18.0583681Z --   ROOT_OPS: 
2025-03-21T20:32:18.0583914Z --   INCLUDE_ALL_OPS: 
2025-03-21T20:32:18.0585156Z Command - python;-m;codegen.tools.gen_oplist;--output_path=/pytorch/executorch/cmake-out/kernels/portable/portable_ops_lib/selected_operators.yaml;--ops_schema_yaml_path="/pytorch/executorch/kernels/portable/functions.yaml"
2025-03-21T20:32:18.0586269Z -- Generating kernel bindings:
2025-03-21T20:32:18.0586571Z --   LIB_NAME: portable_ops_lib
2025-03-21T20:32:18.0586986Z --   FUNCTIONS_YAML: /pytorch/executorch/kernels/portable/functions.yaml
2025-03-21T20:32:18.0587423Z --   CUSTOM_OPS_YAML: 
2025-03-21T20:32:18.0587692Z --   ADD_EXCEPTION_BOUNDARY: FALSE
2025-03-21T20:32:18.0589421Z Generated files /pytorch/executorch/cmake-out/kernels/portable/portable_ops_lib/RegisterCodegenUnboxedKernelsEverything.cpp;/pytorch/executorch/cmake-out/kernels/portable/portable_ops_lib/Functions.h;/pytorch/executorch/cmake-out/kernels/portable/portable_ops_lib/NativeFunctions.h
2025-03-21T20:32:18.0590889Z -- Generating operator lib:
2025-03-21T20:32:18.0591192Z --   LIB_NAME: portable_ops_lib
2025-03-21T20:32:18.0591500Z --   KERNEL_LIBS: portable_kernels
2025-03-21T20:32:18.0591809Z --   DEPS: executorch
2025-03-21T20:32:18.0592324Z 'python' '-c' 'import importlib.util; print(importlib.util.find_spec('torch').submodule_search_locations[0])'
2025-03-21T20:32:18.0592903Z -- Generating operator lib:
2025-03-21T20:32:18.0593198Z --   LIB_NAME: optimized_ops_lib
2025-03-21T20:32:18.0593626Z --   OPS_SCHEMA_YAML: /pytorch/executorch/kernels/optimized/optimized.yaml
2025-03-21T20:32:18.0594066Z --   ROOT_OPS: 
2025-03-21T20:32:18.0594299Z --   INCLUDE_ALL_OPS: 
2025-03-21T20:32:18.0595551Z Command - python;-m;codegen.tools.gen_oplist;--output_path=/pytorch/executorch/cmake-out/kernels/optimized/optimized_ops_lib/selected_operators.yaml;--ops_schema_yaml_path="/pytorch/executorch/kernels/optimized/optimized.yaml"
2025-03-21T20:32:18.0596679Z -- Generating kernel bindings:
2025-03-21T20:32:18.0596987Z --   LIB_NAME: optimized_ops_lib
2025-03-21T20:32:18.0597414Z --   FUNCTIONS_YAML: /pytorch/executorch/kernels/optimized/optimized.yaml
2025-03-21T20:32:18.0597856Z --   CUSTOM_OPS_YAML: 
2025-03-21T20:32:18.0598123Z --   ADD_EXCEPTION_BOUNDARY: TRUE
2025-03-21T20:32:18.0599836Z Generated files /pytorch/executorch/cmake-out/kernels/optimized/optimized_ops_lib/RegisterCodegenUnboxedKernelsEverything.cpp;/pytorch/executorch/cmake-out/kernels/optimized/optimized_ops_lib/Functions.h;/pytorch/executorch/cmake-out/kernels/optimized/optimized_ops_lib/NativeFunctions.h
2025-03-21T20:32:18.0601332Z -- Generating operator lib:
2025-03-21T20:32:18.0601630Z --   LIB_NAME: optimized_ops_lib
2025-03-21T20:32:18.0601943Z --   KERNEL_LIBS: optimized_kernels
2025-03-21T20:32:18.0602236Z --   DEPS: executorch
2025-03-21T20:32:18.0602508Z -- Merging kernel yaml files:
2025-03-21T20:32:18.0603146Z --   FUNCTIONS_YAML: /pytorch/executorch/configurations/../kernels/optimized/optimized.yaml
2025-03-21T20:32:18.0603910Z --   FALLBACK_YAML: /pytorch/executorch/configurations/../kernels/portable/functions.yaml
2025-03-21T20:32:18.0604508Z --   OUTPUT_DIR: /pytorch/executorch/cmake-out/configurations
2025-03-21T20:32:18.0604909Z -- Generating operator lib:
2025-03-21T20:32:18.0605209Z --   LIB_NAME: optimized_native_cpu_ops_lib
2025-03-21T20:32:18.0605709Z --   OPS_SCHEMA_YAML: /pytorch/executorch/cmake-out/configurations/merged.yaml
2025-03-21T20:32:18.0606160Z --   ROOT_OPS: 
2025-03-21T20:32:18.0606405Z --   INCLUDE_ALL_OPS: 
2025-03-21T20:32:18.0607720Z Command - python;-m;codegen.tools.gen_oplist;--output_path=/pytorch/executorch/cmake-out/configurations/optimized_native_cpu_ops_lib/selected_operators.yaml;--ops_schema_yaml_path="/pytorch/executorch/cmake-out/configurations/merged.yaml"
2025-03-21T20:32:20.5555336Z -- Generating kernel bindings:
2025-03-21T20:32:20.5556027Z --   LIB_NAME: optimized_native_cpu_ops_lib
2025-03-21T20:32:20.5556918Z --   FUNCTIONS_YAML: /pytorch/executorch/cmake-out/configurations/merged.yaml
2025-03-21T20:32:20.5557737Z --   CUSTOM_OPS_YAML: 
2025-03-21T20:32:20.5558210Z --   ADD_EXCEPTION_BOUNDARY: TRUE
2025-03-21T20:32:20.5561704Z Generated files /pytorch/executorch/cmake-out/configurations/optimized_native_cpu_ops_lib/RegisterCodegenUnboxedKernelsEverything.cpp;/pytorch/executorch/cmake-out/configurations/optimized_native_cpu_ops_lib/Functions.h;/pytorch/executorch/cmake-out/configurations/optimized_native_cpu_ops_lib/NativeFunctions.h
2025-03-21T20:32:20.5564792Z -- Generating operator lib:
2025-03-21T20:32:20.5565385Z --   LIB_NAME: optimized_native_cpu_ops_lib
2025-03-21T20:32:20.5566105Z --   KERNEL_LIBS: optimized_kernels;optimized_portable_kernels
2025-03-21T20:32:20.5566767Z --   DEPS: executorch
2025-03-21T20:32:20.5567935Z CMake Deprecation Warning at third-party/gflags/CMakeLists.txt:73 (cmake_minimum_required):
2025-03-21T20:32:20.5569123Z   Compatibility with CMake < 3.10 will be removed from a future version of
2025-03-21T20:32:20.5570033Z   CMake.
2025-03-21T20:32:20.5570249Z 
2025-03-21T20:32:20.5570637Z   Update the VERSION argument <min> value.  Or, use the <min>...<max> syntax
2025-03-21T20:32:20.5571695Z   to tell CMake that the project requires at least <min> but has been updated
2025-03-21T20:32:20.5572584Z   to work with policies introduced by <max> or earlier.
2025-03-21T20:32:20.5573058Z 
2025-03-21T20:32:20.5573314Z 
2025-03-21T20:32:20.5573696Z -- Looking for C++ include unistd.h
2025-03-21T20:32:20.5574259Z -- Looking for C++ include unistd.h - found
2025-03-21T20:32:20.5574854Z -- Looking for C++ include stdint.h
2025-03-21T20:32:20.5575429Z -- Looking for C++ include stdint.h - found
2025-03-21T20:32:20.5576035Z -- Looking for C++ include inttypes.h
2025-03-21T20:32:20.5576623Z -- Looking for C++ include inttypes.h - found
2025-03-21T20:32:20.5577209Z -- Looking for C++ include sys/types.h
2025-03-21T20:32:20.5577799Z -- Looking for C++ include sys/types.h - found
2025-03-21T20:32:20.5578402Z -- Looking for C++ include sys/stat.h
2025-03-21T20:32:20.5578979Z -- Looking for C++ include sys/stat.h - found
2025-03-21T20:32:20.5579546Z -- Looking for C++ include fnmatch.h
2025-03-21T20:32:20.5580138Z -- Looking for C++ include fnmatch.h - found
2025-03-21T20:32:20.5580776Z -- Looking for C++ include stddef.h
2025-03-21T20:32:20.5581347Z -- Looking for C++ include stddef.h - found
2025-03-21T20:32:20.5581929Z -- Check size of uint32_t
2025-03-21T20:32:20.5582411Z -- Check size of uint32_t - done
2025-03-21T20:32:20.5582935Z -- Looking for strtoll
2025-03-21T20:32:20.5583399Z -- Looking for strtoll - found
2025-03-21T20:32:20.5583958Z -- Using qnn sdk root /tmp/qnn/2.28.0.241029
2025-03-21T20:32:20.5584618Z -- Using EXECUTORCH_SOURCE_DIR /pytorch/executorch
2025-03-21T20:32:20.5585902Z CMake Deprecation Warning at third-party/pybind11/CMakeLists.txt:13 (cmake_minimum_required):
2025-03-21T20:32:20.5587134Z   Compatibility with CMake < 3.10 will be removed from a future version of
2025-03-21T20:32:20.5588210Z   CMake.
2025-03-21T20:32:20.5588411Z 
2025-03-21T20:32:20.5588819Z   Update the VERSION argument <min> value.  Or, use the <min>...<max> syntax
2025-03-21T20:32:20.5589829Z   to tell CMake that the project requires at least <min> but has been updated
2025-03-21T20:32:20.5590676Z   to work with policies introduced by <max> or earlier.
2025-03-21T20:32:20.5591112Z 
2025-03-21T20:32:20.5591461Z 
2025-03-21T20:32:20.5591835Z -- pybind11 v2.13.6 
2025-03-21T20:32:20.5592658Z -- Found PythonInterp: python (found suitable version "3.10.16", minimum required is "3.7")
2025-03-21T20:32:20.5594284Z -- Found PythonLibs: /opt/conda/envs/py_3.10/lib/libpython3.10.so
2025-03-21T20:32:20.5595035Z -- Performing Test HAS_FLTO_THIN
2025-03-21T20:32:20.5595581Z -- Performing Test HAS_FLTO_THIN - Success
2025-03-21T20:32:20.5596190Z -- Generating operator lib:
2025-03-21T20:32:20.5596716Z --   LIB_NAME: quantized_ops_lib
2025-03-21T20:32:20.5597483Z --   OPS_SCHEMA_YAML: /pytorch/executorch/kernels/quantized/quantized.yaml
2025-03-21T20:32:20.5598277Z --   ROOT_OPS: 
2025-03-21T20:32:20.5598694Z --   INCLUDE_ALL_OPS: 
2025-03-21T20:32:20.5601107Z Command - python;-m;codegen.tools.gen_oplist;--output_path=/pytorch/executorch/cmake-out/kernels/quantized/quantized_ops_lib/selected_operators.yaml;--ops_schema_yaml_path="/pytorch/executorch/kernels/quantized/quantized.yaml"
2025-03-21T20:32:20.5603265Z -- Generating kernel bindings:
2025-03-21T20:32:20.5603810Z --   LIB_NAME: quantized_ops_lib
2025-03-21T20:32:20.5604334Z --   FUNCTIONS_YAML: 
2025-03-21T20:32:20.5605041Z --   CUSTOM_OPS_YAML: /pytorch/executorch/kernels/quantized/quantized.yaml
2025-03-21T20:32:20.5605831Z --   ADD_EXCEPTION_BOUNDARY: FALSE
2025-03-21T20:32:20.5611805Z Generated files /pytorch/executorch/cmake-out/kernels/quantized/quantized_ops_lib/RegisterCodegenUnboxedKernelsEverything.cpp;/pytorch/executorch/cmake-out/kernels/quantized/quantized_ops_lib/Functions.h;/pytorch/executorch/cmake-out/kernels/quantized/quantized_ops_lib/NativeFunctions.h;/pytorch/executorch/cmake-out/kernels/quantized/quantized_ops_lib/RegisterCPUCustomOps.cpp;/pytorch/executorch/cmake-out/kernels/quantized/quantized_ops_lib/RegisterSchema.cpp;/pytorch/executorch/cmake-out/kernels/quantized/quantized_ops_lib/CustomOpsNativeFunctions.h
2025-03-21T20:32:20.5617037Z -- Generating operator lib:
2025-03-21T20:32:20.5617589Z --   LIB_NAME: quantized_ops_lib
2025-03-21T20:32:20.5618156Z --   KERNEL_LIBS: quantized_kernels
2025-03-21T20:32:20.5618705Z --   DEPS: executorch
2025-03-21T20:32:20.5619128Z -- 
2025-03-21T20:32:20.5619480Z -- ******** Summary ********
2025-03-21T20:32:20.5620014Z --   CMAKE_BUILD_TYPE              : Release
2025-03-21T20:32:20.5620602Z --   CMAKE_CXX_STANDARD            : 17
2025-03-21T20:32:20.5621166Z --   CMAKE_CXX_COMPILER_ID         : Clang
2025-03-21T20:32:20.5621704Z --   CMAKE_TOOLCHAIN_FILE          : 
2025-03-21T20:32:20.5622256Z --   BUCK2                         : buck2
2025-03-21T20:32:20.5622858Z --   PYTHON_EXECUTABLE             : python
2025-03-21T20:32:20.5623749Z --   FLATC_EXECUTABLE              : /pytorch/executorch/cmake-out/third-party/flatbuffers/flatc
2025-03-21T20:32:20.5624688Z --   EXECUTORCH_ENABLE_LOGGING              : OFF
2025-03-21T20:32:20.5625378Z --   EXECUTORCH_ENABLE_PROGRAM_VERIFICATION : OFF
2025-03-21T20:32:20.5626026Z --   EXECUTORCH_LOG_LEVEL                   : Info
2025-03-21T20:32:20.5626629Z --   EXECUTORCH_BUILD_ANDROID_JNI           : OFF
2025-03-21T20:32:20.5627258Z --   EXECUTORCH_BUILD_ARM_BAREMETAL         : OFF
2025-03-21T20:32:20.5627875Z --   EXECUTORCH_BUILD_CADENCE               : OFF
2025-03-21T20:32:20.5628494Z --   EXECUTORCH_BUILD_COREML                : OFF
2025-03-21T20:32:20.5629074Z --   EXECUTORCH_BUILD_CPUINFO               : ON
2025-03-21T20:32:20.5629725Z --   EXECUTORCH_BUILD_DEVTOOLS              : OFF
2025-03-21T20:32:20.5630342Z --   EXECUTORCH_BUILD_EXECUTOR_RUNNER       : ON
2025-03-21T20:32:20.5630961Z --   EXECUTORCH_BUILD_EXTENSION_DATA_LOADER : ON
2025-03-21T20:32:20.5631777Z --   EXECUTORCH_BUILD_EXTENSION_FLAT_TENSOR : ON
2025-03-21T20:32:20.5632565Z --   EXECUTORCH_BUILD_EXTENSION_LLM : OFF
2025-03-21T20:32:20.5633174Z --   EXECUTORCH_BUILD_EXTENSION_MODULE      : ON
2025-03-21T20:32:20.5633826Z --   EXECUTORCH_BUILD_EXTENSION_RUNNER_UTIL : OFF
2025-03-21T20:32:20.5634454Z --   EXECUTORCH_BUILD_EXTENSION_TENSOR      : ON
2025-03-21T20:32:20.5635187Z --   EXECUTORCH_BUILD_EXTENSION_TRAINING    : OFF
2025-03-21T20:32:20.5635795Z --   EXECUTORCH_BUILD_FLATC                 : ON
2025-03-21T20:32:20.5636396Z --   EXECUTORCH_BUILD_GFLAGS                : ON
2025-03-21T20:32:20.5637133Z --   EXECUTORCH_BUILD_HOST_TARGETS          : ON
2025-03-21T20:32:20.5637779Z --   EXECUTORCH_BUILD_KERNELS_CUSTOM        : OFF
2025-03-21T20:32:20.5638430Z --   EXECUTORCH_BUILD_KERNELS_CUSTOM_AOT    : OFF
2025-03-21T20:32:20.5639049Z --   EXECUTORCH_BUILD_KERNELS_OPTIMIZED     : ON
2025-03-21T20:32:20.5639667Z --   EXECUTORCH_BUILD_KERNELS_QUANTIZED     : ON
2025-03-21T20:32:20.5640338Z --   EXECUTORCH_BUILD_MPS                   : OFF
2025-03-21T20:32:20.5640973Z --   EXECUTORCH_BUILD_NEURON                : OFF
2025-03-21T20:32:20.5641657Z --   EXECUTORCH_BUILD_PTHREADPOOL           : ON
2025-03-21T20:32:20.5642303Z --   EXECUTORCH_BUILD_PYBIND                : OFF
2025-03-21T20:32:20.5642948Z --   EXECUTORCH_BUILD_QNN                   : ON
2025-03-21T20:32:20.5643573Z --   EXECUTORCH_BUILD_SIZE_TEST             : OFF
2025-03-21T20:32:20.5644213Z --   EXECUTORCH_BUILD_TESTS                 : OFF
2025-03-21T20:32:20.5644847Z --   EXECUTORCH_BUILD_VULKAN                : OFF
2025-03-21T20:32:20.5645480Z --   EXECUTORCH_BUILD_XNNPACK               : OFF
2025-03-21T20:32:20.5646049Z -- Configuring done (5.5s)
2025-03-21T20:32:20.5646541Z -- Generating done (0.2s)
2025-03-21T20:32:20.5647188Z -- Build files have been written to: /pytorch/executorch/cmake-out
2025-03-21T20:32:20.5648029Z + cmake --build cmake-out -j9 --target install --config Release
2025-03-21T20:32:20.5649503Z [  0%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/api.c.o
2025-03-21T20:32:20.5651014Z [  0%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/cache.c.o
2025-03-21T20:32:20.5652562Z [  0%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/init.c.o
2025-03-21T20:32:20.5654244Z [  0%] Building C object backends/xnnpack/third-party/pthreadpool/CMakeFiles/pthreadpool.dir/src/legacy-api.c.o
2025-03-21T20:32:20.5655890Z [  1%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/log.c.o
2025-03-21T20:32:20.5657443Z [  1%] Building CXX object third-party/gflags/CMakeFiles/gflags_nothreads_static.dir/src/gflags.cc.o
2025-03-21T20:32:20.5659068Z [  1%] Building CXX object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/single.cpp.o
2025-03-21T20:32:20.5660299Z [  1%] Creating directories for 'flatbuffers'
2025-03-21T20:32:20.5661571Z [  2%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/api.c.o
2025-03-21T20:32:20.5662764Z [  3%] No download step for 'flatbuffers'
2025-03-21T20:32:20.5663497Z [  3%] No update step for 'flatbuffers'
2025-03-21T20:32:20.5664215Z [  3%] No patch step for 'flatbuffers'
2025-03-21T20:32:20.5664988Z [  3%] Performing configure step for 'flatbuffers'
2025-03-21T20:32:20.5665656Z CMake Warning:
2025-03-21T20:32:20.5666191Z   Ignoring empty string ("") provided on the command line.
2025-03-21T20:32:20.5666660Z 
2025-03-21T20:32:20.5666862Z 
2025-03-21T20:32:20.5667315Z fatal: No names found, cannot describe anything.
2025-03-21T20:32:20.5668084Z CMake Warning at CMake/Version.cmake:32 (message):
2025-03-21T20:32:20.5668739Z   git describe failed with exit code: 128
2025-03-21T20:32:20.5669125Z 
2025-03-21T20:32:20.5669672Z   Make sure you cloned with tags or run 'git fetch --tags'.
2025-03-21T20:32:20.5670325Z Call Stack (most recent call first):
2025-03-21T20:32:20.5670864Z   CMakeLists.txt:5 (include)
2025-03-21T20:32:20.5671166Z 
2025-03-21T20:32:20.5671372Z 
2025-03-21T20:32:20.5671772Z -- Proceeding with version: 24.3.25.0
2025-03-21T20:32:20.5673008Z [  3%] Building CXX object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/double.cpp.o
2025-03-21T20:32:20.5674704Z [  3%] Building CXX object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/complex_single.cpp.o
2025-03-21T20:32:20.5676507Z [  3%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/cache.c.o
2025-03-21T20:32:20.5678511Z [  4%] Building C object backends/xnnpack/third-party/pthreadpool/CMakeFiles/pthreadpool.dir/src/portable-api.c.o
2025-03-21T20:32:20.5680287Z [  4%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/init.c.o
2025-03-21T20:32:21.7166641Z [  4%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/init.c.o
2025-03-21T20:32:21.7168576Z [  5%] Building CXX object third-party/gflags/CMakeFiles/gflags_nothreads_static.dir/src/gflags_reporting.cc.o
2025-03-21T20:32:21.7170612Z [  5%] Building CXX object third-party/gflags/CMakeFiles/gflags_nothreads_static.dir/src/gflags_completions.cc.o
2025-03-21T20:32:21.7172524Z [  5%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/log.c.o
2025-03-21T20:32:21.7174225Z [  5%] Building C object backends/xnnpack/third-party/pthreadpool/CMakeFiles/pthreadpool.dir/src/memory.c.o
2025-03-21T20:32:21.7175906Z [  5%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/info.c.o
2025-03-21T20:32:21.7176962Z -- The CXX compiler identification is Clang 12.0.1
2025-03-21T20:32:21.7177608Z -- Detecting CXX compiler ABI info
2025-03-21T20:32:21.7178856Z [  5%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/vendor.c.o
2025-03-21T20:32:21.7180682Z [  5%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/x86/init.c.o
2025-03-21T20:32:21.7182579Z [  5%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/x86/info.c.o
2025-03-21T20:32:21.7184436Z [  5%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/uarch.c.o
2025-03-21T20:32:21.7186201Z [  5%] Building C object backends/xnnpack/third-party/pthreadpool/CMakeFiles/pthreadpool.dir/src/pthreads.c.o
2025-03-21T20:32:21.7187598Z [  5%] Linking CXX static library libgflags_nothreads.a
2025-03-21T20:32:21.7188364Z [  5%] Built target gflags_nothreads_static
2025-03-21T20:32:21.7189682Z [  5%] Building C object backends/xnnpack/third-party/pthreadpool/CMakeFiles/pthreadpool.dir/src/fastpath.c.o
2025-03-21T20:32:21.7191525Z [  6%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/x86/vendor.c.o
2025-03-21T20:32:21.7193212Z [  6%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/name.c.o
2025-03-21T20:32:21.7194930Z [  7%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/topology.c.o
2025-03-21T20:32:21.7196805Z [  7%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/x86/uarch.c.o
2025-03-21T20:32:21.7198758Z [  7%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/x86/name.c.o
2025-03-21T20:32:21.7200621Z [  8%] Building CXX object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/complex_double.cpp.o
2025-03-21T20:32:21.7202767Z [  8%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/isa.c.o
2025-03-21T20:32:21.7203698Z [  8%] Linking C static library libpthreadpool.a
2025-03-21T20:32:21.7204570Z [  8%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/cache/init.c.o
2025-03-21T20:32:21.7205285Z [  8%] Built target pthreadpool
2025-03-21T20:32:21.7206454Z [  8%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/cache/descriptor.c.o
2025-03-21T20:32:21.7208286Z [  8%] Building CXX object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/xerbla.cpp.o
2025-03-21T20:32:21.7210326Z [  8%] Building C object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/f2c/srotm.c.o
2025-03-21T20:32:21.7212288Z [  8%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/cache/deterministic.c.o
2025-03-21T20:32:21.7214217Z [  8%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/linux/init.c.o
2025-03-21T20:32:21.7216124Z [  8%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/x86/topology.c.o
2025-03-21T20:32:21.7218063Z [  8%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/x86/isa.c.o
2025-03-21T20:32:21.7219237Z -- Detecting CXX compiler ABI info - done
2025-03-21T20:32:21.7220672Z [  8%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/x86/cache/init.c.o
2025-03-21T20:32:21.7222898Z [  9%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/x86/cache/descriptor.c.o
2025-03-21T20:32:21.7224357Z -- Check for working CXX compiler: /opt/cache/bin/c++ - skipped
2025-03-21T20:32:21.7225100Z -- Detecting CXX compile features
2025-03-21T20:32:21.7225672Z -- Detecting CXX compile features - done
2025-03-21T20:32:21.7227093Z [  9%] Building C object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/f2c/srotmg.c.o
2025-03-21T20:32:21.7228996Z [ 10%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/linux/cpuinfo.c.o
2025-03-21T20:32:21.7230146Z -- Looking for strtof_l
2025-03-21T20:32:21.7231353Z [ 10%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/linux/smallfile.c.o
2025-03-21T20:32:21.7233452Z [ 10%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/linux/multiline.c.o
2025-03-21T20:32:21.7235567Z [ 10%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/x86/cache/deterministic.c.o
2025-03-21T20:32:21.7237849Z [ 10%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/x86/linux/init.c.o
2025-03-21T20:32:21.7240021Z [ 10%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/x86/linux/cpuinfo.c.o
2025-03-21T20:32:21.7242073Z [ 10%] Building C object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/f2c/drotm.c.o
2025-03-21T20:32:21.7244023Z [ 10%] Building C object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/f2c/drotmg.c.o
2025-03-21T20:32:21.7245909Z [ 10%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/linux/cpulist.c.o
2025-03-21T20:32:21.7247674Z [ 10%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo.dir/src/linux/processors.c.o
2025-03-21T20:32:21.7249546Z [ 11%] Building C object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/f2c/lsame.c.o
2025-03-21T20:32:21.7251280Z [ 11%] Building C object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/f2c/dspmv.c.o
2025-03-21T20:32:21.7253301Z [ 11%] Building C object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/f2c/ssbmv.c.o
2025-03-21T20:32:21.7255228Z [ 11%] Building C object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/f2c/chbmv.c.o
2025-03-21T20:32:21.7257206Z [ 11%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/linux/smallfile.c.o
2025-03-21T20:32:21.7259421Z [ 11%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/linux/multiline.c.o
2025-03-21T20:32:21.7261334Z [ 11%] Building C object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/f2c/sspmv.c.o
2025-03-21T20:32:21.7263501Z [ 12%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/linux/cpulist.c.o
2025-03-21T20:32:21.7264876Z [ 12%] Linking C static library libcpuinfo.a
2025-03-21T20:32:21.7266207Z [ 12%] Building C object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/f2c/zhbmv.c.o
2025-03-21T20:32:21.7268053Z [ 13%] Building C object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/f2c/chpmv.c.o
2025-03-21T20:32:21.7269832Z [ 13%] Building C object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/f2c/dsbmv.c.o
2025-03-21T20:32:21.7271861Z [ 13%] Building C object backends/xnnpack/third-party/cpuinfo/CMakeFiles/cpuinfo_internals.dir/src/linux/processors.c.o
2025-03-21T20:32:21.7273166Z -- Looking for strtof_l - found
2025-03-21T20:32:21.7273706Z -- Looking for strtoull_l
2025-03-21T20:32:21.7274988Z [ 13%] Building C object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/f2c/zhpmv.c.o
2025-03-21T20:32:21.7276132Z [ 13%] Built target cpuinfo
2025-03-21T20:32:21.7277370Z [ 13%] Building C object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/f2c/dtbmv.c.o
2025-03-21T20:32:21.7279198Z [ 13%] Building C object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/f2c/stbmv.c.o
2025-03-21T20:32:21.7280968Z [ 13%] Building C object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/f2c/ctbmv.c.o
2025-03-21T20:32:21.7282760Z [ 14%] Building C object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/f2c/ztbmv.c.o
2025-03-21T20:32:21.7284693Z [ 14%] Building C object kernels/optimized/CMakeFiles/eigen_blas.dir/third-party/eigen/blas/f2c/complexdots.c.o
2025-03-21T20:32:21.7286171Z [ 14%] Linking C static library libcpuinfo_internals.a
2025-03-21T20:32:21.7287178Z [ 14%] Linking CXX static library libeigen_blas.a
2025-03-21T20:32:21.7287922Z [ 14%] Built target cpuinfo_internals
2025-03-21T20:32:21.7288526Z [ 14%] Built target eigen_blas
2025-03-21T20:32:21.7289066Z -- Looking for strtoull_l - found
2025-03-21T20:32:21.7289702Z -- Looking for realpath
2025-03-21T20:32:21.7290212Z -- Looking for realpath - found
2025-03-21T20:32:21.7290861Z -- CMAKE_CXX_FLAGS: "-DFLATBUFFERS_MAX_ALIGNMENT=1024"
2025-03-21T20:32:21.7291568Z -- Configuring done (1.2s)
2025-03-21T20:32:21.7292060Z -- Generating done (0.0s)
2025-03-21T20:32:21.7292908Z -- Build files have been written to: /pytorch/executorch/cmake-out/third-party/flatbuffers
2025-03-21T20:32:21.7294100Z [ 14%] Performing build step for 'flatbuffers'
2025-03-21T20:32:21.7295123Z [  2%] Building CXX object CMakeFiles/flatc.dir/src/idl_parser.cpp.o
2025-03-21T20:32:24.2473496Z [  5%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_text.cpp.o
2025-03-21T20:32:24.2474561Z [  7%] Building CXX object CMakeFiles/flatc.dir/src/reflection.cpp.o
2025-03-21T20:32:24.2475340Z [ 10%] Building CXX object CMakeFiles/flatc.dir/src/util.cpp.o
2025-03-21T20:32:24.2476067Z [ 13%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_cpp.cpp.o
2025-03-21T20:32:24.2476794Z [ 15%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_binary.cpp.o
2025-03-21T20:32:24.2477755Z [ 18%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_csharp.cpp.o
2025-03-21T20:32:24.2478465Z [ 21%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_dart.cpp.o
2025-03-21T20:32:24.2479230Z [ 23%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_kotlin.cpp.o
2025-03-21T20:32:24.2480256Z [ 26%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_kotlin_kmp.cpp.o
2025-03-21T20:32:24.2481084Z [ 28%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_go.cpp.o
2025-03-21T20:32:24.2481745Z [ 31%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_java.cpp.o
2025-03-21T20:32:24.2482436Z [ 34%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_ts.cpp.o
2025-03-21T20:32:24.2483114Z [ 36%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_php.cpp.o
2025-03-21T20:32:24.2484191Z [ 39%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_python.cpp.o
2025-03-21T20:32:24.2485079Z [ 42%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_lobster.cpp.o
2025-03-21T20:32:24.2485826Z [ 44%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_rust.cpp.o
2025-03-21T20:32:24.2486617Z [ 47%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_fbs.cpp.o
2025-03-21T20:32:24.2487329Z [ 50%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_grpc.cpp.o
2025-03-21T20:32:24.2488075Z [ 52%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_json_schema.cpp.o
2025-03-21T20:32:24.2488820Z [ 55%] Building CXX object CMakeFiles/flatc.dir/src/idl_gen_swift.cpp.o
2025-03-21T20:32:24.2489682Z [ 57%] Building CXX object CMakeFiles/flatc.dir/src/file_name_saving_file_manager.cpp.o
2025-03-21T20:32:24.2490494Z [ 60%] Building CXX object CMakeFiles/flatc.dir/src/file_binary_writer.cpp.o
2025-03-21T20:32:24.2491231Z [ 63%] Building CXX object CMakeFiles/flatc.dir/src/file_writer.cpp.o
2025-03-21T20:32:24.2491905Z [ 65%] Building CXX object CMakeFiles/flatc.dir/src/flatc.cpp.o
2025-03-21T20:32:24.2492774Z [ 68%] Building CXX object CMakeFiles/flatc.dir/src/flatc_main.cpp.o
2025-03-21T20:32:24.2493947Z [ 71%] Building CXX object CMakeFiles/flatc.dir/src/binary_annotator.cpp.o
2025-03-21T20:32:24.2495225Z [ 73%] Building CXX object CMakeFiles/flatc.dir/src/annotated_binary_text_gen.cpp.o
2025-03-21T20:32:24.2496569Z [ 76%] Building CXX object CMakeFiles/flatc.dir/src/bfbs_gen_lua.cpp.o
2025-03-21T20:32:24.2497759Z [ 78%] Building CXX object CMakeFiles/flatc.dir/src/bfbs_gen_nim.cpp.o
2025-03-21T20:32:24.2498961Z [ 81%] Building CXX object CMakeFiles/flatc.dir/src/code_generators.cpp.o
2025-03-21T20:32:24.2500245Z [ 84%] Building CXX object CMakeFiles/flatc.dir/grpc/src/compiler/cpp_generator.cc.o
2025-03-21T20:32:24.2501042Z [ 86%] Building CXX object CMakeFiles/flatc.dir/grpc/src/compiler/go_generator.cc.o
2025-03-21T20:32:24.2501898Z [ 89%] Building CXX object CMakeFiles/flatc.dir/grpc/src/compiler/java_generator.cc.o
2025-03-21T20:32:24.2502707Z [ 92%] Building CXX object CMakeFiles/flatc.dir/grpc/src/compiler/python_generator.cc.o
2025-03-21T20:32:24.2503506Z [ 94%] Building CXX object CMakeFiles/flatc.dir/grpc/src/compiler/swift_generator.cc.o
2025-03-21T20:32:24.2504283Z [ 97%] Building CXX object CMakeFiles/flatc.dir/grpc/src/compiler/ts_generator.cc.o
2025-03-21T20:32:24.2504885Z [100%] Linking CXX executable flatc
2025-03-21T20:32:24.2505264Z [100%] Built target flatc
2025-03-21T20:32:24.2505637Z [ 14%] No install step for 'flatbuffers'
2025-03-21T20:32:24.2506063Z [ 14%] Completed 'flatbuffers'
2025-03-21T20:32:24.2506400Z [ 14%] Built target flatbuffers
2025-03-21T20:32:24.2506777Z [ 14%] Generating common_schema headers
2025-03-21T20:32:24.2507231Z [ 14%] Generating qualcomm ir schema headers
2025-03-21T20:32:24.2507665Z [ 14%] Generating qnn_schema headers
2025-03-21T20:32:24.2508227Z [ 14%] Generating scalar_type_schema headers
2025-03-21T20:32:24.2508595Z [ 14%] Built target common_schema
2025-03-21T20:32:24.2508899Z [ 14%] Built target scalar_type_schema
2025-03-21T20:32:24.2509214Z [ 14%] Built target qcir
2025-03-21T20:32:24.2509499Z [ 14%] Built target qnn_schema
2025-03-21T20:32:24.2509886Z [ 14%] Generating program_schema headers
2025-03-21T20:32:24.2510371Z [ 14%] Generating flat_tensor_schema headers
2025-03-21T20:32:24.2511051Z [ 15%] Building CXX object backends/qualcomm/CMakeFiles/qcir_utils.dir/aot/ir/qcir_utils.cpp.o
2025-03-21T20:32:24.2512063Z [ 15%] Building CXX object backends/qualcomm/CMakeFiles/qnn_executorch_logging.dir/runtime/Logging.cpp.o
2025-03-21T20:32:24.2512715Z [ 15%] Built target flat_tensor_schema
2025-03-21T20:32:24.2513041Z [ 15%] Built target program_schema
2025-03-21T20:32:24.2513656Z [ 15%] Building CXX object CMakeFiles/executorch_core.dir/runtime/backend/interface.cpp.o
2025-03-21T20:32:24.2514462Z [ 15%] Building CXX object CMakeFiles/executorch_core.dir/runtime/core/evalue.cpp.o
2025-03-21T20:32:24.2515374Z [ 15%] Building CXX object CMakeFiles/executorch_core.dir/runtime/core/exec_aten/util/tensor_util_portable.cpp.o
2025-03-21T20:32:24.2516434Z [ 15%] Building CXX object CMakeFiles/executorch_core.dir/runtime/core/exec_aten/util/tensor_shape_to_c_string.cpp.o
2025-03-21T20:32:24.2517324Z [ 16%] Building CXX object CMakeFiles/executorch_core.dir/runtime/core/tag.cpp.o
2025-03-21T20:32:24.2518120Z [ 16%] Building CXX object CMakeFiles/executorch_core.dir/runtime/core/tensor_layout.cpp.o
2025-03-21T20:32:24.2519105Z [ 16%] Building CXX object CMakeFiles/executorch_core.dir/runtime/core/portable_type/tensor_impl.cpp.o
2025-03-21T20:32:24.2519986Z [ 16%] Building CXX object CMakeFiles/executorch_core.dir/runtime/executor/method.cpp.o
2025-03-21T20:32:24.2521029Z [ 16%] Building CXX object CMakeFiles/executorch_core.dir/runtime/executor/method_meta.cpp.o
2025-03-21T20:32:24.2522291Z [ 16%] Linking CXX static library libqnn_executorch_logging.a
2025-03-21T20:32:24.2523027Z [ 16%] Built target qnn_executorch_logging
2025-03-21T20:32:24.2524128Z [ 16%] Building CXX object CMakeFiles/executorch_core.dir/runtime/executor/program.cpp.o
2025-03-21T20:32:24.2525285Z [ 16%] Linking CXX static library libqcir_utils.a
2025-03-21T20:32:24.2525984Z [ 16%] Built target qcir_utils
2025-03-21T20:32:24.2527082Z [ 16%] Building CXX object CMakeFiles/executorch_core.dir/runtime/executor/pte_data_map.cpp.o
2025-03-21T20:32:24.2528848Z [ 17%] Building CXX object CMakeFiles/executorch_core.dir/runtime/executor/tensor_parser_exec_aten.cpp.o
2025-03-21T20:32:24.2530951Z [ 17%] Building CXX object backends/qualcomm/CMakeFiles/qnn_implementation.dir/runtime/backends/QnnImplementation.cpp.o
2025-03-21T20:32:24.2533462Z [ 17%] Building CXX object CMakeFiles/executorch_core.dir/runtime/executor/tensor_parser_portable.cpp.o
2025-03-21T20:32:24.2535180Z [ 17%] Building CXX object CMakeFiles/executorch_core.dir/runtime/kernel/operator_registry.cpp.o
2025-03-21T20:32:24.2536697Z [ 17%] Building CXX object CMakeFiles/executorch_core.dir/runtime/platform/abort.cpp.o
2025-03-21T20:32:24.2538048Z [ 17%] Building CXX object CMakeFiles/executorch_core.dir/runtime/platform/log.cpp.o
2025-03-21T20:32:24.2539862Z [ 17%] Building CXX object backends/qualcomm/CMakeFiles/qnn_sys_implementation.dir/runtime/backends/QnnSysImplementation.cpp.o
2025-03-21T20:32:24.2541418Z [ 18%] Linking CXX static library libqnn_implementation.a
2025-03-21T20:32:24.2542684Z [ 18%] Building CXX object CMakeFiles/executorch_core.dir/runtime/platform/profiler.cpp.o
2025-03-21T20:32:24.2544469Z [ 18%] Building CXX object backends/qualcomm/CMakeFiles/qnn_custom_protocol.dir/runtime/backends/QnnCustomProtocol.cpp.o
2025-03-21T20:32:24.2545883Z [ 18%] Built target qnn_implementation
2025-03-21T20:32:24.2546958Z [ 19%] Building CXX object CMakeFiles/executorch_core.dir/runtime/platform/runtime.cpp.o
2025-03-21T20:32:24.2548388Z [ 19%] Building CXX object CMakeFiles/executorch_core.dir/schema/extended_header.cpp.o
2025-03-21T20:32:24.2549832Z [ 19%] Building CXX object CMakeFiles/executorch_core.dir/runtime/platform/default/posix.cpp.o
2025-03-21T20:32:24.2551567Z [ 19%] Building CXX object backends/qualcomm/CMakeFiles/qnn_profiler.dir/runtime/backends/QnnProfiler.cpp.o
2025-03-21T20:32:24.2552570Z [ 19%] Building CXX object backends/qualcomm/CMakeFiles/utils.dir/runtime/Utils.cpp.o
2025-03-21T20:32:24.2553516Z [ 19%] Building CXX object backends/qualcomm/CMakeFiles/shared_buffer.dir/runtime/SharedBuffer.cpp.o
2025-03-21T20:32:24.2554284Z [ 20%] Linking CXX static library libqnn_sys_implementation.a
2025-03-21T20:32:24.2555080Z [ 20%] Building CXX object backends/qualcomm/CMakeFiles/wrappers.dir/aot/wrappers/TensorWrapper.cpp.o
2025-03-21T20:32:24.2555709Z [ 20%] Built target qnn_sys_implementation
2025-03-21T20:32:24.2556470Z [ 20%] Building CXX object backends/qualcomm/CMakeFiles/wrappers.dir/aot/wrappers/QuantizeParamsWrapper.cpp.o
2025-03-21T20:32:24.2557485Z [ 20%] Building CXX object backends/qualcomm/CMakeFiles/qnn_logger.dir/runtime/backends/QnnLogger.cpp.o
2025-03-21T20:32:24.2558512Z [ 20%] Building CXX object backends/qualcomm/CMakeFiles/qnn_backend_cache.dir/runtime/backends/QnnBackendCache.cpp.o
2025-03-21T20:32:24.2559435Z [ 20%] Linking CXX static library libexecutorch_core.a
2025-03-21T20:32:24.2560101Z [ 20%] Built target executorch_core
2025-03-21T20:32:24.2561228Z [ 20%] Building CXX object backends/qualcomm/CMakeFiles/wrappers.dir/aot/wrappers/OpWrapper.cpp.o
2025-03-21T20:32:24.2562207Z [ 20%] Linking CXX static library libutils.a
2025-03-21T20:32:24.2563026Z [ 21%] Linking CXX static library libqnn_custom_protocol.a
2025-03-21T20:32:24.2563609Z [ 21%] Built target utils
2025-03-21T20:32:24.2564026Z [ 21%] Built target qnn_custom_protocol
2025-03-21T20:32:24.2564909Z [ 21%] Building CXX object CMakeFiles/executorch.dir/kernels/prim_ops/et_copy_index.cpp.o
2025-03-21T20:32:25.8427845Z [ 21%] Building CXX object CMakeFiles/executorch.dir/kernels/prim_ops/et_view.cpp.o
2025-03-21T20:32:25.8429596Z [ 21%] Building CXX object extension/threadpool/CMakeFiles/extension_threadpool.dir/threadpool.cpp.o
2025-03-21T20:32:25.8430942Z [ 21%] Linking CXX static library libqnn_logger.a
2025-03-21T20:32:25.8431889Z [ 21%] Linking CXX static library libqnn_profiler.a
2025-03-21T20:32:25.8433466Z [ 21%] Built target qnn_logger
2025-03-21T20:32:25.8434266Z [ 22%] Linking CXX static library libshared_buffer.a
2025-03-21T20:32:25.8435583Z [ 23%] Building CXX object CMakeFiles/executorch.dir/kernels/prim_ops/register_prim_ops.cpp.o
2025-03-21T20:32:25.8436632Z [ 23%] Built target qnn_profiler
2025-03-21T20:32:25.8437808Z [ 24%] Building CXX object extension/tensor/CMakeFiles/extension_tensor.dir/tensor_ptr.cpp.o
2025-03-21T20:32:25.8439852Z [ 24%] Building CXX object backends/qualcomm/CMakeFiles/qnn_backend_cache.dir/runtime/backends/htpbackend/HtpBackendCache.cpp.o
2025-03-21T20:32:25.8441208Z [ 24%] Built target shared_buffer
2025-03-21T20:32:25.8442593Z [ 24%] Building CXX object backends/qualcomm/CMakeFiles/qnn_backend.dir/runtime/backends/QnnBackendCommon.cpp.o
2025-03-21T20:32:25.8444559Z [ 24%] Building CXX object backends/qualcomm/CMakeFiles/qnn_device.dir/runtime/backends/QnnDeviceCommon.cpp.o
2025-03-21T20:32:25.8445939Z [ 25%] Linking CXX static library libwrappers.a
2025-03-21T20:32:25.8446633Z [ 25%] Built target wrappers
2025-03-21T20:32:25.8447942Z [ 25%] Building CXX object extension/threadpool/CMakeFiles/extension_threadpool.dir/threadpool_guard.cpp.o
2025-03-21T20:32:25.8450279Z [ 25%] Building CXX object extension/threadpool/CMakeFiles/extension_threadpool.dir/thread_parallel.cpp.o
2025-03-21T20:32:25.8452134Z [ 26%] Building CXX object extension/threadpool/CMakeFiles/extension_threadpool.dir/cpuinfo_utils.cpp.o
2025-03-21T20:32:25.8453950Z [ 26%] Building CXX object extension/tensor/CMakeFiles/extension_tensor.dir/tensor_ptr_maker.cpp.o
2025-03-21T20:32:25.8455988Z [ 26%] Building CXX object backends/qualcomm/CMakeFiles/qnn_device.dir/runtime/backends/htpbackend/HtpDevice.cpp.o
2025-03-21T20:32:25.8457438Z [ 26%] Linking CXX static library libexecutorch.a
2025-03-21T20:32:25.8458223Z [ 26%] Built target executorch
2025-03-21T20:32:25.8459873Z [ 26%] Building CXX object backends/qualcomm/CMakeFiles/qnn_device.dir/runtime/backends/htpbackend/x86_64/HtpDevicePlatformInfoConfig.cpp.o
2025-03-21T20:32:25.8462283Z [ 26%] Building CXX object backends/qualcomm/CMakeFiles/PyQnnWrapperAdaptor.dir/aot/python/PyQnnWrapperAdaptor.cpp.o
2025-03-21T20:32:25.8463852Z [ 27%] Linking CXX static library libqnn_backend_cache.a
2025-03-21T20:32:25.8465508Z [ 27%] Building CXX object backends/qualcomm/CMakeFiles/PyQnnWrapperAdaptor.dir/aot/wrappers/TensorWrapper.cpp.o
2025-03-21T20:32:25.8467052Z [ 27%] Linking CXX static library libqnn_backend.a
2025-03-21T20:32:25.8468837Z [ 27%] Building CXX object backends/qualcomm/CMakeFiles/qnn_device.dir/runtime/backends/htpbackend/x86_64/HtpDeviceCustomConfig.cpp.o
2025-03-21T20:32:25.8470266Z [ 27%] Built target qnn_backend_cache
2025-03-21T20:32:25.8471636Z [ 27%] Building CXX object extension/data_loader/CMakeFiles/extension_data_loader.dir/file_data_loader.cpp.o
2025-03-21T20:32:25.8472796Z [ 27%] Built target qnn_backend
2025-03-21T20:32:25.8474050Z [ 27%] Building CXX object kernels/quantized/CMakeFiles/quantized_kernels.dir/cpu/embeddingxb.cpp.o
2025-03-21T20:32:25.8475511Z [ 27%] Linking CXX static library libextension_threadpool.a
2025-03-21T20:32:25.8486226Z [ 27%] Building CXX object kernels/quantized/CMakeFiles/quantized_kernels.dir/cpu/op_add.cpp.o
2025-03-21T20:32:25.8487832Z [ 27%] Linking CXX static library libextension_tensor.a
2025-03-21T20:32:25.8488611Z [ 27%] Built target extension_threadpool
2025-03-21T20:32:25.8490050Z [ 27%] Building CXX object kernels/quantized/CMakeFiles/quantized_kernels.dir/cpu/op_choose_qparams.cpp.o
2025-03-21T20:32:25.8491211Z [ 27%] Built target extension_tensor
2025-03-21T20:32:25.8492557Z [ 27%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op__empty_dim_order.cpp.o
2025-03-21T20:32:25.8494418Z [ 27%] Building CXX object extension/data_loader/CMakeFiles/extension_data_loader.dir/mmap_data_loader.cpp.o
2025-03-21T20:32:25.8496323Z [ 27%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op__to_dim_order_copy.cpp.o
2025-03-21T20:32:25.8498191Z [ 27%] Building CXX object kernels/quantized/CMakeFiles/quantized_kernels.dir/cpu/op_dequantize.cpp.o
2025-03-21T20:32:25.8499571Z [ 27%] Linking CXX static library libqnn_device.a
2025-03-21T20:32:25.8500260Z [ 27%] Built target qnn_device
2025-03-21T20:32:25.8501576Z [ 27%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op__empty_dim_order.cpp.o
2025-03-21T20:32:25.8503090Z [ 28%] Linking CXX static library libextension_data_loader.a
2025-03-21T20:32:25.8504514Z [ 28%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_abs.cpp.o
2025-03-21T20:32:25.8505605Z [ 28%] Built target extension_data_loader
2025-03-21T20:32:25.8506932Z [ 28%] Building CXX object kernels/quantized/CMakeFiles/quantized_kernels.dir/cpu/op_embedding.cpp.o
2025-03-21T20:32:25.8508779Z [ 29%] Building CXX object kernels/quantized/CMakeFiles/quantized_kernels.dir/cpu/op_embedding2b.cpp.o
2025-03-21T20:32:25.8510810Z [ 29%] Building CXX object kernels/quantized/CMakeFiles/quantized_kernels.dir/cpu/op_embedding4b.cpp.o
2025-03-21T20:32:25.8512448Z [ 29%] Building CXX object kernels/quantized/CMakeFiles/quantized_kernels.dir/cpu/op_mixed_linear.cpp.o
2025-03-21T20:32:25.8514169Z [ 30%] Building CXX object kernels/optimized/CMakeFiles/cpublas.dir/blas/BlasKernel.cpp.o
2025-03-21T20:32:25.8515705Z [ 30%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_acos.cpp.o
2025-03-21T20:32:25.8517113Z [ 30%] Linking CXX shared module PyQnnWrapperAdaptor.cpython-310-x86_64-linux-gnu.so
2025-03-21T20:32:25.8518714Z [ 31%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op__to_dim_order_copy.cpp.o
2025-03-21T20:32:25.8520304Z [ 31%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_abs.cpp.o
2025-03-21T20:32:25.8521630Z [ 31%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_acos.cpp.o
2025-03-21T20:32:25.8522925Z [ 31%] Building CXX object kernels/quantized/CMakeFiles/quantized_kernels.dir/cpu/op_mixed_mm.cpp.o
2025-03-21T20:32:25.8524240Z [ 31%] Building CXX object kernels/quantized/CMakeFiles/quantized_kernels.dir/cpu/op_quantize.cpp.o
2025-03-21T20:32:25.8525569Z [ 31%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_acosh.cpp.o
2025-03-21T20:32:25.8526830Z [ 32%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_acosh.cpp.o
2025-03-21T20:32:25.8527935Z [ 32%] Building CXX object kernels/optimized/CMakeFiles/cpublas.dir/blas/CPUBlas.cpp.o
2025-03-21T20:32:25.8529353Z [ 32%] Building CXX object backends/qualcomm/CMakeFiles/qnn_context.dir/runtime/backends/QnnContextCommon.cpp.o
2025-03-21T20:32:25.8530810Z [ 32%] Building CXX object backends/qualcomm/CMakeFiles/qnn_context.dir/runtime/backends/htpbackend/HtpContext.cpp.o
2025-03-21T20:32:25.8532384Z [ 32%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_add.cpp.o
2025-03-21T20:32:25.8533455Z [ 32%] Linking CXX static library libquantized_kernels.a
2025-03-21T20:32:25.8534046Z [ 32%] Built target quantized_kernels
2025-03-21T20:32:25.8535024Z [ 32%] Building CXX object extension/flat_tensor/CMakeFiles/extension_flat_tensor.dir/flat_tensor_data_map.cpp.o
2025-03-21T20:32:25.8536385Z [ 32%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_addmm.cpp.o
2025-03-21T20:32:25.8537632Z [ 32%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_add.cpp.o
2025-03-21T20:32:25.8538522Z [ 32%] Linking CXX static library libcpublas.a
2025-03-21T20:32:25.8539035Z [ 32%] Built target cpublas
2025-03-21T20:32:25.8539857Z [ 32%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_addmm.cpp.o
2025-03-21T20:32:25.8541076Z [ 32%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_alias_copy.cpp.o
2025-03-21T20:32:25.8542396Z [ 32%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_alias_copy.cpp.o
2025-03-21T20:32:25.8543989Z [ 32%] Building CXX object backends/qualcomm/CMakeFiles/qnn_context.dir/runtime/backends/htpbackend/x86_64/HtpContextCustomConfig.cpp.o
2025-03-21T20:32:25.8545562Z [ 33%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_allclose.cpp.o
2025-03-21T20:32:25.8547040Z [ 33%] Building CXX object extension/flat_tensor/CMakeFiles/extension_flat_tensor.dir/serialize/flat_tensor_header.cpp.o
2025-03-21T20:32:25.8548399Z [ 33%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_allclose.cpp.o
2025-03-21T20:32:25.8549770Z [ 33%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_amax.cpp.o
2025-03-21T20:32:25.8551394Z [ 33%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_amax.cpp.o
2025-03-21T20:32:25.8552677Z [ 34%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_amin.cpp.o
2025-03-21T20:32:25.8554109Z [ 34%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_amin.cpp.o
2025-03-21T20:32:25.8555454Z [ 34%] Linking CXX static library libextension_flat_tensor.a
2025-03-21T20:32:25.8556235Z [ 34%] Built target extension_flat_tensor
2025-03-21T20:32:25.8557158Z [ 34%] Generating selected_operators.yaml for quantized_ops_lib
2025-03-21T20:32:25.8558273Z [ 34%] Linking CXX static library libqnn_context.a
2025-03-21T20:32:29.1766018Z [ 34%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_any.cpp.o
2025-03-21T20:32:29.1767240Z [ 34%] Built target qnn_context
2025-03-21T20:32:29.1768503Z [ 34%] Building CXX object kernels/optimized/CMakeFiles/optimized_kernels.dir/cpu/op_add.cpp.o
2025-03-21T20:32:29.1770485Z [ 35%] Building CXX object backends/qualcomm/CMakeFiles/qnn_graph.dir/runtime/backends/QnnGraphCommon.cpp.o
2025-03-21T20:32:29.1772542Z [ 35%] Building CXX object backends/qualcomm/CMakeFiles/qnn_graph.dir/runtime/backends/htpbackend/HtpGraph.cpp.o
2025-03-21T20:32:29.1774961Z [ 35%] Building CXX object backends/qualcomm/CMakeFiles/qnn_graph.dir/runtime/backends/htpbackend/HtpGraphCustomConfig.cpp.o
2025-03-21T20:32:29.1776984Z [ 35%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_any.cpp.o
2025-03-21T20:32:29.1778804Z [ 35%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_arange.cpp.o
2025-03-21T20:32:29.1780212Z [ 36%] Generating code for kernel registration
2025-03-21T20:32:29.1781572Z [ 36%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_arange.cpp.o
2025-03-21T20:32:29.1783309Z [ 36%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_argmax.cpp.o
2025-03-21T20:32:29.1784993Z [ 36%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_argmin.cpp.o
2025-03-21T20:32:29.1787130Z [ 36%] Building CXX object backends/qualcomm/CMakeFiles/qnn_graph.dir/runtime/backends/htpbackend/x86_64/HtpGraphCustomConfig.cpp.o
2025-03-21T20:32:29.1789325Z [ 36%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_argmax.cpp.o
2025-03-21T20:32:29.1791224Z [ 36%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_as_strided_copy.cpp.o
2025-03-21T20:32:29.1792984Z [ 37%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_asin.cpp.o
2025-03-21T20:32:29.1794692Z [ 37%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_asinh.cpp.o
2025-03-21T20:32:29.1796007Z [ 37%] Linking CXX static library libqnn_graph.a
2025-03-21T20:32:29.1797316Z [ 37%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_atan.cpp.o
2025-03-21T20:32:29.1798995Z [ 37%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_atan2.cpp.o
2025-03-21T20:32:29.1800776Z [ 38%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_argmin.cpp.o
2025-03-21T20:32:29.1801941Z [ 38%] Built target qnn_graph
2025-03-21T20:32:29.1803292Z [ 39%] Building CXX object backends/qualcomm/CMakeFiles/qnn_mem_manager.dir/runtime/backends/QnnMemManager.cpp.o
2025-03-21T20:32:29.1805126Z [ 39%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_atanh.cpp.o
2025-03-21T20:32:29.1806803Z [ 39%] Building CXX object kernels/optimized/CMakeFiles/optimized_kernels.dir/cpu/op_bmm.cpp.o
2025-03-21T20:32:29.1808703Z [ 39%] Building CXX object kernels/optimized/CMakeFiles/optimized_kernels.dir/cpu/op_div.cpp.o
2025-03-21T20:32:29.1810654Z [ 39%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_avg_pool2d.cpp.o
2025-03-21T20:32:29.1812941Z [ 39%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_as_strided_copy.cpp.o
2025-03-21T20:32:29.1815048Z [ 40%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_bitwise_and.cpp.o
2025-03-21T20:32:29.1816529Z [ 40%] Linking CXX static library libqnn_mem_manager.a
2025-03-21T20:32:29.1817353Z [ 40%] Built target qnn_mem_manager
2025-03-21T20:32:29.1818937Z [ 40%] Building CXX object extension/module/CMakeFiles/extension_module.dir/__/flat_tensor/flat_tensor_data_map.cpp.o
2025-03-21T20:32:29.1820872Z [ 41%] Building CXX object kernels/optimized/CMakeFiles/optimized_kernels.dir/cpu/op_exp.cpp.o
2025-03-21T20:32:29.1822781Z [ 41%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_bitwise_not.cpp.o
2025-03-21T20:32:29.1824716Z [ 41%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_asin.cpp.o
2025-03-21T20:32:29.1826612Z [ 41%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_bitwise_or.cpp.o
2025-03-21T20:32:29.1828728Z [ 41%] Building CXX object extension/module/CMakeFiles/extension_module.dir/__/flat_tensor/serialize/flat_tensor_header.cpp.o
2025-03-21T20:32:29.1830745Z [ 42%] Building CXX object extension/module/CMakeFiles/extension_module.dir/module.cpp.o
2025-03-21T20:32:29.1836048Z [ 42%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_asinh.cpp.o
2025-03-21T20:32:29.1838065Z [ 42%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_atan.cpp.o
2025-03-21T20:32:29.1839884Z [ 42%] Building CXX object kernels/optimized/CMakeFiles/optimized_kernels.dir/cpu/op_fft_r2c.cpp.o
2025-03-21T20:32:29.1841659Z [ 42%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_bitwise_xor.cpp.o
2025-03-21T20:32:29.1843051Z [ 42%] Linking CXX shared library libextension_module.so
2025-03-21T20:32:29.1844482Z [ 42%] Building CXX object kernels/optimized/CMakeFiles/optimized_kernels.dir/cpu/op_gelu.cpp.o
2025-03-21T20:32:29.1846307Z [ 42%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_atan2.cpp.o
2025-03-21T20:32:29.1847458Z [ 42%] Built target extension_module
2025-03-21T20:32:29.1848763Z [ 43%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_atanh.cpp.o
2025-03-21T20:32:29.1850580Z [ 43%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_bmm.cpp.o
2025-03-21T20:32:29.1852447Z [ 43%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_avg_pool2d.cpp.o
2025-03-21T20:32:29.1854283Z [ 43%] Building CXX object kernels/optimized/CMakeFiles/optimized_kernels.dir/cpu/op_le.cpp.o
2025-03-21T20:32:29.1856143Z [ 43%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_bitwise_and.cpp.o
2025-03-21T20:32:29.1858124Z [ 43%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_bitwise_not.cpp.o
2025-03-21T20:32:29.1859978Z [ 43%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_cat.cpp.o
2025-03-21T20:32:29.1861701Z [ 43%] Building CXX object kernels/optimized/CMakeFiles/optimized_kernels.dir/cpu/op_linear.cpp.o
2025-03-21T20:32:29.1863945Z [ 43%] Building CXX object kernels/quantized/CMakeFiles/quantized_ops_lib.dir/quantized_ops_lib/RegisterCodegenUnboxedKernelsEverything.cpp.o
2025-03-21T20:32:29.1866231Z [ 43%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_bitwise_or.cpp.o
2025-03-21T20:32:29.1868415Z [ 44%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_cdist_forward.cpp.o
2025-03-21T20:32:29.1870462Z [ 44%] Building CXX object extension/module/CMakeFiles/extension_module_static.dir/__/flat_tensor/flat_tensor_data_map.cpp.o
2025-03-21T20:32:29.1874021Z [ 44%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_ceil.cpp.o
2025-03-21T20:32:29.1875390Z [ 44%] Linking CXX static library libquantized_ops_lib.a
2025-03-21T20:32:29.1876134Z [ 44%] Built target quantized_ops_lib
2025-03-21T20:32:29.1877638Z [ 44%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_clamp.cpp.o
2025-03-21T20:32:29.1879453Z [ 44%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_bitwise_xor.cpp.o
2025-03-21T20:32:29.1881356Z [ 45%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_bmm.cpp.o
2025-03-21T20:32:29.1883460Z [ 45%] Building CXX object extension/module/CMakeFiles/extension_module_static.dir/__/flat_tensor/serialize/flat_tensor_header.cpp.o
2025-03-21T20:32:29.1885560Z [ 45%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_cat.cpp.o
2025-03-21T20:32:29.1887365Z [ 45%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_clone.cpp.o
2025-03-21T20:32:29.1889130Z [ 45%] Building CXX object kernels/optimized/CMakeFiles/optimized_kernels.dir/cpu/op_log_softmax.cpp.o
2025-03-21T20:32:29.1890973Z [ 45%] Building CXX object extension/module/CMakeFiles/extension_module_static.dir/module.cpp.o
2025-03-21T20:32:29.1892882Z [ 45%] Building CXX object backends/qualcomm/CMakeFiles/qnn_factory.dir/runtime/backends/QnnBackendFactory.cpp.o
2025-03-21T20:32:29.1894952Z [ 45%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_cdist_forward.cpp.o
2025-03-21T20:32:29.1896883Z [ 45%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_constant_pad_nd.cpp.o
2025-03-21T20:32:29.1898343Z [ 45%] Linking CXX static library libextension_module_static.a
2025-03-21T20:32:29.1899167Z [ 45%] Built target extension_module_static
2025-03-21T20:32:29.1900427Z [ 46%] Building CXX object kernels/optimized/CMakeFiles/optimized_kernels.dir/cpu/op_mm.cpp.o
2025-03-21T20:32:29.1902148Z [ 46%] Building CXX object kernels/optimized/CMakeFiles/optimized_kernels.dir/cpu/op_mul.cpp.o
2025-03-21T20:32:29.1903436Z [ 46%] Linking CXX static library libqnn_factory.a
2025-03-21T20:32:29.1904859Z [ 46%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_ceil.cpp.o
2025-03-21T20:32:29.1905962Z [ 46%] Built target qnn_factory
2025-03-21T20:32:29.1907144Z [ 46%] Building CXX object backends/qualcomm/CMakeFiles/qnn_manager.dir/runtime/QnnManager.cpp.o
2025-03-21T20:32:33.1736412Z [ 46%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_convolution.cpp.o
2025-03-21T20:32:33.1738404Z [ 46%] Building CXX object kernels/optimized/CMakeFiles/optimized_kernels.dir/cpu/op_native_layer_norm.cpp.o
2025-03-21T20:32:33.1740403Z [ 46%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_clamp.cpp.o
2025-03-21T20:32:33.1742315Z [ 46%] Building CXX object backends/qualcomm/CMakeFiles/qnn_manager.dir/aot/wrappers/TensorWrapper.cpp.o
2025-03-21T20:32:33.1744279Z [ 47%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_convolution_backward.cpp.o
2025-03-21T20:32:33.1746246Z [ 47%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_clone.cpp.o
2025-03-21T20:32:33.1748020Z [ 47%] Building CXX object kernels/optimized/CMakeFiles/optimized_kernels.dir/cpu/op_neg.cpp.o
2025-03-21T20:32:33.1749618Z [ 47%] Linking CXX static library libqnn_manager.a
2025-03-21T20:32:33.1750336Z [ 47%] Built target qnn_manager
2025-03-21T20:32:33.1751722Z [ 48%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_constant_pad_nd.cpp.o
2025-03-21T20:32:33.1753557Z [ 48%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_copy.cpp.o
2025-03-21T20:32:33.1755489Z [ 48%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_convolution.cpp.o
2025-03-21T20:32:33.1757358Z [ 48%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_cos.cpp.o
2025-03-21T20:32:33.1759184Z [ 48%] Building CXX object kernels/optimized/CMakeFiles/optimized_kernels.dir/cpu/op_sigmoid.cpp.o
2025-03-21T20:32:33.1760933Z [ 48%] Building CXX object kernels/optimized/CMakeFiles/optimized_kernels.dir/cpu/op_sub.cpp.o
2025-03-21T20:32:33.1762919Z [ 48%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_convolution_backward.cpp.o
2025-03-21T20:32:33.1764970Z [ 48%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_copy.cpp.o
2025-03-21T20:32:33.1766758Z [ 48%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_cosh.cpp.o
2025-03-21T20:32:33.1768555Z [ 48%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_cos.cpp.o
2025-03-21T20:32:33.1770433Z [ 49%] Building CXX object kernels/optimized/CMakeFiles/optimized_kernels.dir/cpu/op_where.cpp.o
2025-03-21T20:32:33.1772171Z [ 49%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_cosh.cpp.o
2025-03-21T20:32:33.1773907Z [ 49%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_cumsum.cpp.o
2025-03-21T20:32:33.1775690Z [ 49%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_detach_copy.cpp.o
2025-03-21T20:32:33.1777533Z [ 50%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_diagonal_copy.cpp.o
2025-03-21T20:32:33.1779425Z [ 51%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_cumsum.cpp.o
2025-03-21T20:32:33.1781224Z [ 51%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_div.cpp.o
2025-03-21T20:32:33.1782937Z [ 51%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_embedding.cpp.o
2025-03-21T20:32:33.1784817Z [ 51%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_detach_copy.cpp.o
2025-03-21T20:32:33.1786864Z [ 52%] Building CXX object backends/qualcomm/CMakeFiles/qnn_executorch_backend.dir/runtime/QnnExecuTorchBackend.cpp.o
2025-03-21T20:32:33.1788779Z [ 52%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_empty.cpp.o
2025-03-21T20:32:33.1790284Z [ 52%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_eq.cpp.o
2025-03-21T20:32:33.1791852Z [ 52%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_diagonal_copy.cpp.o
2025-03-21T20:32:33.1793429Z [ 52%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_erf.cpp.o
2025-03-21T20:32:33.1794656Z [ 52%] Linking CXX shared library libqnn_executorch_backend.so
2025-03-21T20:32:33.1795919Z [ 53%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_exp.cpp.o
2025-03-21T20:32:33.1797561Z [ 53%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_div.cpp.o
2025-03-21T20:32:33.1798726Z [ 53%] Built target qnn_executorch_backend
2025-03-21T20:32:33.1800248Z [ 53%] Building CXX object backends/qualcomm/CMakeFiles/PyQnnManagerAdaptor.dir/aot/python/PyQnnManagerAdaptor.cpp.o
2025-03-21T20:32:33.1802275Z [ 53%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_expand_copy.cpp.o
2025-03-21T20:32:33.1803858Z [ 53%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_expm1.cpp.o
2025-03-21T20:32:33.1805486Z [ 53%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_embedding.cpp.o
2025-03-21T20:32:33.1807109Z [ 53%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_fill.cpp.o
2025-03-21T20:32:33.1808556Z [ 53%] Linking CXX shared module PyQnnManagerAdaptor.cpython-310-x86_64-linux-gnu.so
2025-03-21T20:32:33.1810177Z [ 53%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_flip.cpp.o
2025-03-21T20:32:33.1811729Z [ 53%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_empty.cpp.o
2025-03-21T20:32:33.1813377Z [ 54%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_eq.cpp.o
2025-03-21T20:32:33.1814978Z [ 54%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_erf.cpp.o
2025-03-21T20:32:33.1816610Z [ 54%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_floor.cpp.o
2025-03-21T20:32:33.1818303Z [ 54%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_exp.cpp.o
2025-03-21T20:32:33.1820253Z [ 54%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_expand_copy.cpp.o
2025-03-21T20:32:33.1822095Z [ 54%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_expm1.cpp.o
2025-03-21T20:32:33.1823941Z [ 55%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_floor_divide.cpp.o
2025-03-21T20:32:33.1825093Z [ 55%] Built target PyQnnWrapperAdaptor
2025-03-21T20:32:33.1826346Z [ 55%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_fmod.cpp.o
2025-03-21T20:32:33.1828041Z [ 55%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_full.cpp.o
2025-03-21T20:32:33.1829833Z [ 55%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_fill.cpp.o
2025-03-21T20:32:33.1831701Z [ 55%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_floor.cpp.o
2025-03-21T20:32:33.1834763Z [ 56%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_flip.cpp.o
2025-03-21T20:32:33.1836630Z [ 56%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_floor_divide.cpp.o
2025-03-21T20:32:33.1838539Z [ 56%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_full_like.cpp.o
2025-03-21T20:32:33.1873487Z [ 56%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_gather.cpp.o
2025-03-21T20:32:33.1875100Z [ 56%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_ge.cpp.o
2025-03-21T20:32:33.1876857Z [ 56%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_fmod.cpp.o
2025-03-21T20:32:33.1878715Z [ 56%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_full.cpp.o
2025-03-21T20:32:33.1880601Z [ 56%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_full_like.cpp.o
2025-03-21T20:32:33.1882473Z [ 57%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_gather.cpp.o
2025-03-21T20:32:33.1884217Z [ 58%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_gelu.cpp.o
2025-03-21T20:32:33.1885832Z [ 58%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_glu.cpp.o
2025-03-21T20:32:33.1887757Z [ 58%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_gt.cpp.o
2025-03-21T20:32:33.1889597Z [ 58%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_ge.cpp.o
2025-03-21T20:32:33.1891457Z [ 58%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_gelu.cpp.o
2025-03-21T20:32:33.1892957Z [ 58%] Linking CXX static library liboptimized_kernels.a
2025-03-21T20:32:33.1894430Z [ 58%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_glu.cpp.o
2025-03-21T20:32:33.1896304Z [ 58%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_hardtanh.cpp.o
2025-03-21T20:32:33.1898032Z [ 58%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_index.cpp.o
2025-03-21T20:32:33.1899750Z [ 58%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_gt.cpp.o
2025-03-21T20:32:33.1901631Z [ 58%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_hardtanh.cpp.o
2025-03-21T20:32:35.5076760Z [ 59%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_index.cpp.o
2025-03-21T20:32:35.5077980Z [ 59%] Built target optimized_kernels
2025-03-21T20:32:35.5079462Z [ 59%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_index_put.cpp.o
2025-03-21T20:32:35.5081032Z [ 59%] Generating selected_operators.yaml for optimized_ops_lib
2025-03-21T20:32:35.5082560Z [ 59%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_index_put.cpp.o
2025-03-21T20:32:35.5084371Z [ 59%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_index_select.cpp.o
2025-03-21T20:32:35.5086197Z [ 60%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_index_select.cpp.o
2025-03-21T20:32:35.5088010Z [ 60%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_isinf.cpp.o
2025-03-21T20:32:35.5089506Z [ 60%] Generating code for kernel registration
2025-03-21T20:32:35.5090878Z [ 60%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_isnan.cpp.o
2025-03-21T20:32:35.5092766Z [ 60%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_le.cpp.o
2025-03-21T20:32:35.5094710Z [ 61%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_leaky_relu.cpp.o
2025-03-21T20:32:35.5096556Z [ 61%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_isinf.cpp.o
2025-03-21T20:32:35.5098486Z [ 61%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_lift_fresh_copy.cpp.o
2025-03-21T20:32:35.5100354Z [ 61%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_isnan.cpp.o
2025-03-21T20:32:35.5102322Z [ 61%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_linear_scratch_example.cpp.o
2025-03-21T20:32:35.5104313Z [ 61%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_log.cpp.o
2025-03-21T20:32:35.5106215Z [ 61%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_log10.cpp.o
2025-03-21T20:32:35.5107987Z [ 61%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_le.cpp.o
2025-03-21T20:32:35.5109739Z [ 61%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_log1p.cpp.o
2025-03-21T20:32:35.5111580Z [ 61%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_leaky_relu.cpp.o
2025-03-21T20:32:35.5113620Z [ 62%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_log2.cpp.o
2025-03-21T20:32:35.5115723Z [ 62%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_log_softmax.cpp.o
2025-03-21T20:32:35.5117723Z [ 62%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_logical_and.cpp.o
2025-03-21T20:32:35.5119819Z [ 62%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_logical_not.cpp.o
2025-03-21T20:32:35.5121797Z [ 62%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_lift_fresh_copy.cpp.o
2025-03-21T20:32:35.5123783Z [ 62%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_logical_or.cpp.o
2025-03-21T20:32:35.5125692Z [ 63%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_linear_scratch_example.cpp.o
2025-03-21T20:32:35.5127687Z [ 63%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_logical_xor.cpp.o
2025-03-21T20:32:35.5129674Z [ 64%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_logit.cpp.o
2025-03-21T20:32:35.5131400Z [ 64%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_lt.cpp.o
2025-03-21T20:32:35.5133500Z [ 64%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_masked_fill.cpp.o
2025-03-21T20:32:35.5135344Z [ 64%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_log.cpp.o
2025-03-21T20:32:35.5137141Z [ 64%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_masked_scatter.cpp.o
2025-03-21T20:32:35.5139001Z [ 64%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_log10.cpp.o
2025-03-21T20:32:35.5140887Z [ 64%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_masked_select.cpp.o
2025-03-21T20:32:35.5142596Z [ 64%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_max.cpp.o
2025-03-21T20:32:35.5144572Z [ 65%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_max_pool2d_with_indices.cpp.o
2025-03-21T20:32:35.5146382Z [ 65%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_log1p.cpp.o
2025-03-21T20:32:35.5148939Z [ 65%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_max_pool2d_with_indices_backward.cpp.o
2025-03-21T20:32:35.5151078Z [ 65%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_maximum.cpp.o
2025-03-21T20:32:35.5152850Z [ 65%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_log2.cpp.o
2025-03-21T20:32:35.5154656Z [ 65%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_mean.cpp.o
2025-03-21T20:32:35.5156499Z [ 65%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_min.cpp.o
2025-03-21T20:32:35.5158399Z [ 65%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_minimum.cpp.o
2025-03-21T20:32:35.5160266Z [ 65%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_log_softmax.cpp.o
2025-03-21T20:32:35.5162118Z [ 65%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_mm.cpp.o
2025-03-21T20:32:35.5163960Z [ 66%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_mul.cpp.o
2025-03-21T20:32:35.5165817Z [ 67%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_logical_and.cpp.o
2025-03-21T20:32:35.5167941Z [ 67%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_narrow_copy.cpp.o
2025-03-21T20:32:35.5170173Z [ 67%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_native_batch_norm.cpp.o
2025-03-21T20:32:35.5172214Z [ 67%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_native_group_norm.cpp.o
2025-03-21T20:32:35.5174414Z [ 67%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_native_layer_norm.cpp.o
2025-03-21T20:32:35.5176363Z [ 67%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_ne.cpp.o
2025-03-21T20:32:35.5178278Z [ 67%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_logical_not.cpp.o
2025-03-21T20:32:35.5180094Z [ 68%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_neg.cpp.o
2025-03-21T20:32:35.5181920Z [ 68%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_logical_or.cpp.o
2025-03-21T20:32:35.5183793Z [ 68%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_nonzero.cpp.o
2025-03-21T20:32:35.5185663Z [ 68%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_ones.cpp.o
2025-03-21T20:32:35.5187627Z [ 68%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_pdist_forward.cpp.o
2025-03-21T20:32:35.5189666Z [ 68%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_permute_copy.cpp.o
2025-03-21T20:32:35.5191538Z [ 68%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_logical_xor.cpp.o
2025-03-21T20:32:35.5193454Z [ 68%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_pixel_shuffle.cpp.o
2025-03-21T20:32:35.5195328Z [ 68%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_logit.cpp.o
2025-03-21T20:32:35.5197282Z [ 69%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_pixel_unshuffle.cpp.o
2025-03-21T20:32:35.5199256Z [ 69%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_pow.cpp.o
2025-03-21T20:32:35.5201137Z [ 69%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_prod.cpp.o
2025-03-21T20:32:35.5202909Z [ 69%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_lt.cpp.o
2025-03-21T20:32:35.5204676Z [ 70%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_masked_fill.cpp.o
2025-03-21T20:32:35.5206547Z [ 70%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_masked_scatter.cpp.o
2025-03-21T20:32:35.5208889Z [ 70%] Building CXX object kernels/optimized/CMakeFiles/optimized_ops_lib.dir/optimized_ops_lib/RegisterCodegenUnboxedKernelsEverything.cpp.o
2025-03-21T20:32:35.5211267Z [ 70%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_masked_select.cpp.o
2025-03-21T20:32:37.4303666Z [ 70%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_reciprocal.cpp.o
2025-03-21T20:32:37.4305800Z [ 70%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_reflection_pad1d.cpp.o
2025-03-21T20:32:37.4307711Z [ 70%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_max.cpp.o
2025-03-21T20:32:37.4309602Z [ 70%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_max_pool2d_with_indices.cpp.o
2025-03-21T20:32:37.4311810Z [ 70%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_max_pool2d_with_indices_backward.cpp.o
2025-03-21T20:32:37.4313762Z [ 70%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_maximum.cpp.o
2025-03-21T20:32:37.4315428Z [ 70%] Linking CXX static library liboptimized_ops_lib.a
2025-03-21T20:32:37.4317051Z [ 70%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_reflection_pad2d.cpp.o
2025-03-21T20:32:37.4318280Z [ 70%] Built target optimized_ops_lib
2025-03-21T20:32:37.4319815Z [ 71%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_reflection_pad3d.cpp.o
2025-03-21T20:32:37.4321759Z [ 71%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_relu.cpp.o
2025-03-21T20:32:37.4323847Z [ 71%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_remainder.cpp.o
2025-03-21T20:32:37.4325581Z [ 72%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_mean.cpp.o
2025-03-21T20:32:37.4327249Z [ 72%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_min.cpp.o
2025-03-21T20:32:37.4328955Z [ 72%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_minimum.cpp.o
2025-03-21T20:32:37.4330899Z [ 72%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_repeat.cpp.o
2025-03-21T20:32:37.4333121Z [ 72%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_replication_pad1d.cpp.o
2025-03-21T20:32:37.4335264Z [ 72%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_repeat_interleave.cpp.o
2025-03-21T20:32:37.4337337Z [ 73%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_replication_pad2d.cpp.o
2025-03-21T20:32:37.4338559Z [ 73%] Built target PyQnnManagerAdaptor
2025-03-21T20:32:37.4340022Z [ 73%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_replication_pad3d.cpp.o
2025-03-21T20:32:37.4342014Z [ 73%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_roll.cpp.o
2025-03-21T20:32:37.4343736Z [ 73%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_mm.cpp.o
2025-03-21T20:32:37.4345348Z [ 73%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_mul.cpp.o
2025-03-21T20:32:37.4347147Z [ 73%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_round.cpp.o
2025-03-21T20:32:37.4348994Z [ 73%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_rsqrt.cpp.o
2025-03-21T20:32:37.4350842Z [ 73%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_rsub.cpp.o
2025-03-21T20:32:37.4352633Z [ 73%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_narrow_copy.cpp.o
2025-03-21T20:32:37.4354591Z [ 74%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_scalar_tensor.cpp.o
2025-03-21T20:32:37.4356508Z [ 74%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_scatter.cpp.o
2025-03-21T20:32:37.4358476Z [ 74%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_scatter_add.cpp.o
2025-03-21T20:32:37.4360468Z [ 75%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_native_batch_norm.cpp.o
2025-03-21T20:32:37.4362441Z [ 75%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_select_copy.cpp.o
2025-03-21T20:32:37.4364480Z [ 75%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_select_scatter.cpp.o
2025-03-21T20:32:37.4366496Z [ 75%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_sigmoid.cpp.o
2025-03-21T20:32:37.4368602Z [ 75%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_native_group_norm.cpp.o
2025-03-21T20:32:37.4370726Z [ 75%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_native_layer_norm.cpp.o
2025-03-21T20:32:37.4372643Z [ 76%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_sign.cpp.o
2025-03-21T20:32:37.4374459Z [ 76%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_ne.cpp.o
2025-03-21T20:32:37.4376156Z [ 76%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_sin.cpp.o
2025-03-21T20:32:37.4378057Z [ 76%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_sinh.cpp.o
2025-03-21T20:32:37.4379956Z [ 76%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_slice_copy.cpp.o
2025-03-21T20:32:37.4381999Z [ 76%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_slice_scatter.cpp.o
2025-03-21T20:32:37.4383871Z [ 76%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_neg.cpp.o
2025-03-21T20:32:37.4385701Z [ 76%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_softmax.cpp.o
2025-03-21T20:32:37.4387591Z [ 76%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_nonzero.cpp.o
2025-03-21T20:32:37.4389388Z [ 77%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_split_copy.cpp.o
2025-03-21T20:32:37.4391459Z [ 77%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_split_with_sizes_copy.cpp.o
2025-03-21T20:32:37.4393386Z [ 78%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_ones.cpp.o
2025-03-21T20:32:37.4395177Z [ 78%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_sqrt.cpp.o
2025-03-21T20:32:37.4397056Z [ 78%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_squeeze_copy.cpp.o
2025-03-21T20:32:37.4398999Z [ 78%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_pdist_forward.cpp.o
2025-03-21T20:32:37.4400908Z [ 78%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_stack.cpp.o
2025-03-21T20:32:37.4402796Z [ 78%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_sub.cpp.o
2025-03-21T20:32:37.4404666Z [ 78%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_permute_copy.cpp.o
2025-03-21T20:32:37.4406448Z [ 78%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_pixel_shuffle.cpp.o
2025-03-21T20:32:37.4408361Z [ 78%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_pixel_unshuffle.cpp.o
2025-03-21T20:32:37.4410357Z [ 79%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_sum.cpp.o
2025-03-21T20:32:37.4412260Z [ 79%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_t_copy.cpp.o
2025-03-21T20:32:37.4414021Z [ 79%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_pow.cpp.o
2025-03-21T20:32:37.4415808Z [ 79%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_tan.cpp.o
2025-03-21T20:32:37.4417559Z [ 80%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_prod.cpp.o
2025-03-21T20:32:37.4419355Z [ 80%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_tanh.cpp.o
2025-03-21T20:32:37.4421223Z [ 80%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_reciprocal.cpp.o
2025-03-21T20:32:37.4423199Z [ 80%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_reflection_pad1d.cpp.o
2025-03-21T20:32:37.4425178Z [ 80%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_reflection_pad2d.cpp.o
2025-03-21T20:32:37.4427119Z [ 80%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_to_copy.cpp.o
2025-03-21T20:32:37.4429114Z [ 80%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_reflection_pad3d.cpp.o
2025-03-21T20:32:37.4430911Z [ 80%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_relu.cpp.o
2025-03-21T20:32:37.4434475Z [ 80%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_topk.cpp.o
2025-03-21T20:32:37.4436554Z [ 81%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_transpose_copy.cpp.o
2025-03-21T20:32:37.4438508Z [ 82%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_remainder.cpp.o
2025-03-21T20:32:37.4440182Z [ 82%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_repeat.cpp.o
2025-03-21T20:32:39.3498178Z [ 82%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_repeat_interleave.cpp.o
2025-03-21T20:32:39.3500105Z [ 82%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_replication_pad1d.cpp.o
2025-03-21T20:32:39.3502013Z [ 82%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_replication_pad2d.cpp.o
2025-03-21T20:32:39.3503872Z [ 82%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_replication_pad3d.cpp.o
2025-03-21T20:32:39.3505519Z [ 83%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_roll.cpp.o
2025-03-21T20:32:39.3506530Z [ 83%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_tril.cpp.o
2025-03-21T20:32:39.3507478Z [ 83%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_round.cpp.o
2025-03-21T20:32:39.3508365Z [ 83%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_rsqrt.cpp.o
2025-03-21T20:32:39.3509303Z [ 83%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_trunc.cpp.o
2025-03-21T20:32:39.3510229Z [ 83%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_rsub.cpp.o
2025-03-21T20:32:39.3511146Z [ 83%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_scalar_tensor.cpp.o
2025-03-21T20:32:39.3512702Z [ 83%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_scatter.cpp.o
2025-03-21T20:32:39.3514445Z [ 83%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_unbind_copy.cpp.o
2025-03-21T20:32:39.3516324Z [ 84%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_scatter_add.cpp.o
2025-03-21T20:32:39.3518080Z [ 84%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_select_copy.cpp.o
2025-03-21T20:32:39.3519776Z [ 84%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_select_scatter.cpp.o
2025-03-21T20:32:39.3521538Z [ 84%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_sigmoid.cpp.o
2025-03-21T20:32:39.3523325Z [ 84%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_unfold_copy.cpp.o
2025-03-21T20:32:39.3525126Z [ 84%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_sign.cpp.o
2025-03-21T20:32:39.3526746Z [ 84%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_sin.cpp.o
2025-03-21T20:32:39.3528642Z [ 85%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_sinh.cpp.o
2025-03-21T20:32:39.3530598Z [ 85%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_slice_copy.cpp.o
2025-03-21T20:32:39.3532685Z [ 85%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_unsqueeze_copy.cpp.o
2025-03-21T20:32:39.3534691Z [ 85%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_slice_scatter.cpp.o
2025-03-21T20:32:39.3536525Z [ 86%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_upsample_bilinear2d.cpp.o
2025-03-21T20:32:39.3538528Z [ 86%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_upsample_nearest2d.cpp.o
2025-03-21T20:32:39.3540428Z [ 86%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_var.cpp.o
2025-03-21T20:32:39.3542313Z [ 86%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_view_copy.cpp.o
2025-03-21T20:32:39.3544193Z [ 86%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_where.cpp.o
2025-03-21T20:32:39.3545970Z [ 86%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_softmax.cpp.o
2025-03-21T20:32:39.3547726Z [ 86%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_split_copy.cpp.o
2025-03-21T20:32:39.3549529Z [ 86%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/op_zeros.cpp.o
2025-03-21T20:32:39.3551472Z [ 87%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/pattern/unary_ufunc_realh.cpp.o
2025-03-21T20:32:39.3553169Z [ 87%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_split_with_sizes_copy.cpp.o
2025-03-21T20:32:39.3554518Z [ 87%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/pattern/unary_ufunc_realhb_to_bool.cpp.o
2025-03-21T20:32:39.3555595Z [ 88%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_sqrt.cpp.o
2025-03-21T20:32:39.3556580Z [ 88%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_squeeze_copy.cpp.o
2025-03-21T20:32:39.3558257Z [ 88%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_stack.cpp.o
2025-03-21T20:32:39.3560125Z [ 88%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_sub.cpp.o
2025-03-21T20:32:39.3562484Z [ 88%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/pattern/unary_ufunc_realhbbf16_to_floathbf16.cpp.o
2025-03-21T20:32:39.3564756Z [ 88%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/activation_ops_util.cpp.o
2025-03-21T20:32:39.3565947Z [ 88%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_sum.cpp.o
2025-03-21T20:32:39.3566984Z [ 88%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_t_copy.cpp.o
2025-03-21T20:32:39.3568172Z [ 88%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/advanced_index_util.cpp.o
2025-03-21T20:32:39.3569511Z [ 89%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_tan.cpp.o
2025-03-21T20:32:39.3570392Z [ 89%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_tanh.cpp.o
2025-03-21T20:32:39.3571294Z [ 89%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_to_copy.cpp.o
2025-03-21T20:32:39.3572176Z [ 89%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_topk.cpp.o
2025-03-21T20:32:39.3573162Z [ 89%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/broadcast_util.cpp.o
2025-03-21T20:32:39.3574433Z [ 90%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/copy_ops_util.cpp.o
2025-03-21T20:32:39.3575454Z [ 90%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_transpose_copy.cpp.o
2025-03-21T20:32:39.3576540Z [ 90%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/delinearize_index.cpp.o
2025-03-21T20:32:39.3577633Z [ 90%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/distance_util.cpp.o
2025-03-21T20:32:39.3579048Z [ 90%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_tril.cpp.o
2025-03-21T20:32:39.3580709Z [ 90%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/dtype_util.cpp.o
2025-03-21T20:32:39.3582088Z [ 90%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/index_util.cpp.o
2025-03-21T20:32:39.3583773Z [ 91%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_trunc.cpp.o
2025-03-21T20:32:39.3585266Z [ 91%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/kernel_ops_util.cpp.o
2025-03-21T20:32:39.3587105Z [ 92%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/matmul_ops_util.cpp.o
2025-03-21T20:32:39.3588756Z [ 92%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_unbind_copy.cpp.o
2025-03-21T20:32:39.3590548Z [ 92%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/normalization_ops_util.cpp.o
2025-03-21T20:32:39.3592488Z [ 92%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/padding_util.cpp.o
2025-03-21T20:32:39.3593607Z [ 92%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_unfold_copy.cpp.o
2025-03-21T20:32:39.3595144Z [ 92%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/reduce_util.cpp.o
2025-03-21T20:32:39.3596908Z [ 92%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_unsqueeze_copy.cpp.o
2025-03-21T20:32:39.3598769Z [ 92%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_upsample_bilinear2d.cpp.o
2025-03-21T20:32:39.3600729Z [ 92%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/repeat_util.cpp.o
2025-03-21T20:32:39.3602418Z [ 92%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_upsample_nearest2d.cpp.o
2025-03-21T20:32:39.3603428Z [ 93%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_var.cpp.o
2025-03-21T20:32:39.3604339Z [ 93%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_view_copy.cpp.o
2025-03-21T20:32:39.3605369Z [ 93%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/select_copy_util.cpp.o
2025-03-21T20:32:42.6552136Z [ 93%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_where.cpp.o
2025-03-21T20:32:42.6553473Z [ 93%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_zeros.cpp.o
2025-03-21T20:32:42.6554666Z [ 93%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/pattern/unary_ufunc_realh.cpp.o
2025-03-21T20:32:42.6555838Z [ 94%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/slice_util.cpp.o
2025-03-21T20:32:42.6557039Z [ 94%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/pattern/unary_ufunc_realhb_to_bool.cpp.o
2025-03-21T20:32:42.6558526Z [ 95%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/pattern/unary_ufunc_realhbbf16_to_floathbf16.cpp.o
2025-03-21T20:32:42.6560165Z [ 95%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/activation_ops_util.cpp.o
2025-03-21T20:32:42.6561463Z [ 95%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/advanced_index_util.cpp.o
2025-03-21T20:32:42.6562961Z [ 95%] Building CXX object kernels/portable/CMakeFiles/optimized_portable_kernels.dir/cpu/util/upsample_util.cpp.o
2025-03-21T20:32:42.6564342Z [ 95%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/broadcast_util.cpp.o
2025-03-21T20:32:42.6565686Z [ 95%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/copy_ops_util.cpp.o
2025-03-21T20:32:42.6567030Z [ 95%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/delinearize_index.cpp.o
2025-03-21T20:32:42.6568260Z [ 96%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/distance_util.cpp.o
2025-03-21T20:32:42.6569588Z [ 96%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/dtype_util.cpp.o
2025-03-21T20:32:42.6570806Z [ 96%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/index_util.cpp.o
2025-03-21T20:32:42.6572042Z [ 96%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/kernel_ops_util.cpp.o
2025-03-21T20:32:42.6573237Z [ 96%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/matmul_ops_util.cpp.o
2025-03-21T20:32:42.6574292Z [ 96%] Linking CXX static library liboptimized_portable_kernels.a
2025-03-21T20:32:42.6575265Z [ 96%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/normalization_ops_util.cpp.o
2025-03-21T20:32:42.6576511Z [ 96%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/padding_util.cpp.o
2025-03-21T20:32:42.6577660Z [ 97%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/reduce_util.cpp.o
2025-03-21T20:32:42.6578811Z [ 97%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/select_copy_util.cpp.o
2025-03-21T20:32:42.6580049Z [ 97%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/repeat_util.cpp.o
2025-03-21T20:32:42.6581265Z [ 97%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/slice_util.cpp.o
2025-03-21T20:32:42.6582532Z [ 97%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/util/upsample_util.cpp.o
2025-03-21T20:32:42.6583217Z [ 97%] Built target optimized_portable_kernels
2025-03-21T20:32:42.6583749Z [ 97%] Merging kernel yaml files
2025-03-21T20:32:42.6584396Z [ 97%] Generating selected_operators.yaml for optimized_native_cpu_ops_lib
2025-03-21T20:32:42.6585178Z [ 97%] Linking CXX static library libportable_kernels.a
2025-03-21T20:32:42.6585731Z [ 97%] Built target portable_kernels
2025-03-21T20:32:42.6586327Z [ 97%] Generating selected_operators.yaml for portable_ops_lib
2025-03-21T20:32:42.6587085Z [ 97%] Generating code for kernel registration
2025-03-21T20:32:42.6587602Z [ 98%] Generating code for kernel registration
2025-03-21T20:32:42.6588901Z [ 98%] Building CXX object configurations/CMakeFiles/optimized_native_cpu_ops_lib.dir/optimized_native_cpu_ops_lib/RegisterCodegenUnboxedKernelsEverything.cpp.o
2025-03-21T20:32:42.6590234Z [ 99%] Linking CXX static library liboptimized_native_cpu_ops_lib.a
2025-03-21T20:32:42.6591584Z [ 99%] Building CXX object kernels/portable/CMakeFiles/portable_ops_lib.dir/portable_ops_lib/RegisterCodegenUnboxedKernelsEverything.cpp.o
2025-03-21T20:32:42.6592554Z [ 99%] Built target optimized_native_cpu_ops_lib
2025-03-21T20:32:42.6593574Z [ 99%] Building CXX object CMakeFiles/executor_runner.dir/examples/portable/executor_runner/executor_runner.cpp.o
2025-03-21T20:32:42.6594911Z [ 99%] Building CXX object CMakeFiles/executor_runner.dir/extension/data_loader/file_data_loader.cpp.o
2025-03-21T20:32:42.6596097Z [ 99%] Building CXX object CMakeFiles/executor_runner.dir/extension/evalue_util/print_evalue.cpp.o
2025-03-21T20:32:42.6597251Z [100%] Building CXX object CMakeFiles/executor_runner.dir/extension/runner_util/inputs.cpp.o
2025-03-21T20:32:42.6598521Z [100%] Building CXX object CMakeFiles/executor_runner.dir/runtime/executor/test/test_backend_compiler_lib.cpp.o
2025-03-21T20:32:42.6599849Z [100%] Building CXX object CMakeFiles/executor_runner.dir/extension/runner_util/inputs_portable.cpp.o
2025-03-21T20:32:42.6600632Z [100%] Linking CXX static library libportable_ops_lib.a
2025-03-21T20:32:42.6601164Z [100%] Built target portable_ops_lib
2025-03-21T20:32:42.6601700Z [100%] Linking CXX executable executor_runner
2025-03-21T20:32:42.6602210Z [100%] Built target executor_runner
2025-03-21T20:32:42.6602690Z Install the project...
2025-03-21T20:32:42.6603045Z -- Install configuration: "Release"
2025-03-21T20:32:42.6603618Z -- Installing: /pytorch/executorch/cmake-out/include/fxdiv.h
2025-03-21T20:32:42.6604247Z -- Installing: /pytorch/executorch/cmake-out/share/cpuinfo/cpuinfo-config.cmake
2025-03-21T20:32:42.6604994Z -- Installing: /pytorch/executorch/cmake-out/lib/libcpuinfo.a
2025-03-21T20:32:42.6605608Z -- Installing: /pytorch/executorch/cmake-out/include/cpuinfo.h
2025-03-21T20:32:42.6606293Z -- Installing: /pytorch/executorch/cmake-out/share/cpuinfo/cpuinfo-targets.cmake
2025-03-21T20:32:42.6607179Z -- Installing: /pytorch/executorch/cmake-out/share/cpuinfo/cpuinfo-targets-release.cmake
2025-03-21T20:32:42.6607981Z -- Installing: /pytorch/executorch/cmake-out/lib/pkgconfig/libcpuinfo.pc
2025-03-21T20:32:42.6608608Z -- Installing: /pytorch/executorch/cmake-out/include/pthreadpool.h
2025-03-21T20:32:42.6609222Z -- Installing: /pytorch/executorch/cmake-out/lib/libpthreadpool.a
2025-03-21T20:32:42.6610006Z -- Installing: /pytorch/executorch/cmake-out/lib/liboptimized_portable_kernels.a
2025-03-21T20:32:42.6610858Z -- Installing: /pytorch/executorch/cmake-out/lib/libportable_kernels.a
2025-03-21T20:32:42.6611495Z -- Installing: /pytorch/executorch/cmake-out/lib/libportable_ops_lib.a
2025-03-21T20:32:42.6612290Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/kernels/portable/Functions.h
2025-03-21T20:32:42.6613254Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/kernels/portable/NativeFunctions.h
2025-03-21T20:32:42.6614034Z -- Installing: /pytorch/executorch/cmake-out/lib/libeigen_blas.a
2025-03-21T20:32:42.6614604Z -- Installing: /pytorch/executorch/cmake-out/lib/libcpublas.a
2025-03-21T20:32:42.6615258Z -- Installing: /pytorch/executorch/cmake-out/lib/liboptimized_kernels.a
2025-03-21T20:32:42.6615886Z -- Installing: /pytorch/executorch/cmake-out/lib/liboptimized_ops_lib.a
2025-03-21T20:32:42.6616727Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/kernels/optimized/Functions.h
2025-03-21T20:32:42.6617662Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/kernels/optimized/NativeFunctions.h
2025-03-21T20:32:42.6618551Z -- Up-to-date: /pytorch/executorch/cmake-out/lib/libcpublas.a
2025-03-21T20:32:42.6619264Z -- Installing: /pytorch/executorch/cmake-out/lib/liboptimized_native_cpu_ops_lib.a
2025-03-21T20:32:42.6619938Z -- Installing: /pytorch/executorch/cmake-out/lib/Functions.h
2025-03-21T20:32:42.6620593Z -- Installing: /pytorch/executorch/cmake-out/lib/NativeFunctions.h
2025-03-21T20:32:42.6621271Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core
2025-03-21T20:32:42.6622116Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/array_ref.h
2025-03-21T20:32:42.6623069Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/data_loader.h
2025-03-21T20:32:42.6623982Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/defines.h
2025-03-21T20:32:42.6624807Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/error.h
2025-03-21T20:32:42.6625683Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/evalue.h
2025-03-21T20:32:42.6626396Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/event_tracer.h
2025-03-21T20:32:42.6627397Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/event_tracer_hooks.h
2025-03-21T20:32:42.6628504Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/event_tracer_hooks_delegate.h
2025-03-21T20:32:42.6629527Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/exec_aten
2025-03-21T20:32:42.6630514Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/exec_aten/exec_aten.h
2025-03-21T20:32:42.6631661Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/exec_aten/testing_util
2025-03-21T20:32:42.6632889Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/exec_aten/testing_util/tensor_factory.h
2025-03-21T20:32:42.6634210Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/exec_aten/testing_util/tensor_util.h
2025-03-21T20:32:42.6635355Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/exec_aten/testing_util/test
2025-03-21T20:32:42.6636386Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/exec_aten/util
2025-03-21T20:32:42.6637440Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/exec_aten/util/dim_order_util.h
2025-03-21T20:32:42.6643573Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/exec_aten/util/scalar_type_util.h
2025-03-21T20:32:42.6644965Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/exec_aten/util/tensor_dimension_limit.h
2025-03-21T20:32:42.6646071Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/exec_aten/util/tensor_shape_to_c_string.h
2025-03-21T20:32:42.6647005Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/exec_aten/util/tensor_util.h
2025-03-21T20:32:42.6647910Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/exec_aten/util/test
2025-03-21T20:32:42.6648689Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/freeable_buffer.h
2025-03-21T20:32:42.6649562Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/hierarchical_allocator.h
2025-03-21T20:32:42.6650361Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/memory_allocator.h
2025-03-21T20:32:42.6651133Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/named_data_map.h
2025-03-21T20:32:42.6651875Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/portable_type
2025-03-21T20:32:42.6652667Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/portable_type/bfloat16.h
2025-03-21T20:32:42.6653535Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/portable_type/bfloat16_math.h
2025-03-21T20:32:42.6654405Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/portable_type/bits_types.h
2025-03-21T20:32:42.6655363Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/portable_type/c10
2025-03-21T20:32:42.6656235Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/portable_type/c10/c10
2025-03-21T20:32:42.6657067Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/portable_type/c10/c10/macros
2025-03-21T20:32:42.6657981Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/portable_type/c10/c10/macros/Export.h
2025-03-21T20:32:42.6658931Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/portable_type/c10/c10/macros/Macros.h
2025-03-21T20:32:42.6659979Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/portable_type/c10/c10/util
2025-03-21T20:32:42.6660908Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/portable_type/c10/c10/util/BFloat16-inl.h
2025-03-21T20:32:42.6661958Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/portable_type/c10/c10/util/BFloat16-math.h
2025-03-21T20:32:42.6662936Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/portable_type/c10/c10/util/BFloat16.h
2025-03-21T20:32:42.6663880Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/portable_type/c10/c10/util/Half-inl.h
2025-03-21T20:32:42.6664861Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/portable_type/c10/c10/util/Half.h
2025-03-21T20:32:42.6665839Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/portable_type/c10/c10/util/TypeSafeSignMath.h
2025-03-21T20:32:42.6666838Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/portable_type/c10/c10/util/bit_cast.h
2025-03-21T20:32:42.6667848Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/portable_type/c10/c10/util/floating_point_utils.h
2025-03-21T20:32:42.6668853Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/portable_type/c10/c10/util/irange.h
2025-03-21T20:32:42.6669746Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/portable_type/complex.h
2025-03-21T20:32:42.6670563Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/portable_type/device.h
2025-03-21T20:32:42.6671379Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/portable_type/half.h
2025-03-21T20:32:42.6672294Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/portable_type/optional.h
2025-03-21T20:32:42.6673288Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/portable_type/qint_types.h
2025-03-21T20:32:42.6674127Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/portable_type/scalar.h
2025-03-21T20:32:42.6674971Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/portable_type/scalar_type.h
2025-03-21T20:32:42.6675836Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/portable_type/string_view.h
2025-03-21T20:32:42.6676668Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/portable_type/tensor.h
2025-03-21T20:32:42.6677511Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/portable_type/tensor_impl.h
2025-03-21T20:32:42.6678576Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/portable_type/tensor_options.h
2025-03-21T20:32:42.6679415Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/portable_type/test
2025-03-21T20:32:42.6680141Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/result.h
2025-03-21T20:32:42.6680850Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/span.h
2025-03-21T20:32:42.6681553Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/tag.h
2025-03-21T20:32:42.6682257Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/tensor_layout.h
2025-03-21T20:32:42.6683042Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/tensor_shape_dynamism.h
2025-03-21T20:32:42.6683782Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/core/test
2025-03-21T20:32:42.6684422Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/kernel
2025-03-21T20:32:42.6685268Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/kernel/kernel_includes.h
2025-03-21T20:32:42.6686207Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/kernel/kernel_runtime_context.h
2025-03-21T20:32:42.6687143Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/kernel/operator_registry.h
2025-03-21T20:32:42.6687892Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/kernel/test
2025-03-21T20:32:42.6688617Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/kernel/test/test_util.h
2025-03-21T20:32:42.6689551Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/kernel/thread_parallel_interface.h
2025-03-21T20:32:42.6690327Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/platform
2025-03-21T20:32:42.6691034Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/platform/abort.h
2025-03-21T20:32:42.6691742Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/platform/assert.h
2025-03-21T20:32:42.6692465Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/platform/clock.h
2025-03-21T20:32:42.6693226Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/platform/compat_unistd.h
2025-03-21T20:32:42.6693995Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/platform/compiler.h
2025-03-21T20:32:42.6694722Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/platform/default
2025-03-21T20:32:42.6695422Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/platform/log.h
2025-03-21T20:32:42.6696275Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/platform/platform.h
2025-03-21T20:32:42.6697007Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/platform/profiler.h
2025-03-21T20:32:42.6697894Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/platform/runtime.h
2025-03-21T20:32:42.6698725Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/platform/system.h
2025-03-21T20:32:42.6699426Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/platform/test
2025-03-21T20:32:42.6700193Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/platform/test/stub_platform.h
2025-03-21T20:32:42.6701095Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/runtime/platform/types.h
2025-03-21T20:32:42.6701872Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/extension/kernel_util
2025-03-21T20:32:42.6702723Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/extension/kernel_util/make_boxed_from_unboxed_functor.h
2025-03-21T20:32:42.6703767Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/extension/kernel_util/meta_programming.h
2025-03-21T20:32:42.6704674Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/extension/kernel_util/test
2025-03-21T20:32:42.6705446Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/extension/kernel_util/type_list.h
2025-03-21T20:32:42.6706161Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/extension/tensor
2025-03-21T20:32:42.6706990Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/extension/tensor/tensor.h
2025-03-21T20:32:42.6707841Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/extension/tensor/tensor_accessor.h
2025-03-21T20:32:42.6708847Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/extension/tensor/tensor_ptr.h
2025-03-21T20:32:42.6709660Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/extension/tensor/tensor_ptr_maker.h
2025-03-21T20:32:42.6710640Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/extension/tensor/test
2025-03-21T20:32:42.6711392Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/extension/threadpool
2025-03-21T20:32:42.6712195Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/extension/threadpool/cpuinfo_utils.h
2025-03-21T20:32:42.6713042Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/extension/threadpool/test
2025-03-21T20:32:44.3910229Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/extension/threadpool/threadpool.h
2025-03-21T20:32:44.3911818Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/extension/threadpool/threadpool_guard.h
2025-03-21T20:32:44.3913023Z -- Installing: /pytorch/executorch/cmake-out/lib/libexecutorch.a
2025-03-21T20:32:44.3913921Z -- Installing: /pytorch/executorch/cmake-out/lib/libexecutorch_core.a
2025-03-21T20:32:44.3915158Z -- Installing: /pytorch/executorch/cmake-out/lib/cmake/ExecuTorch/executorch-config.cmake
2025-03-21T20:32:44.3916466Z -- Installing: /pytorch/executorch/cmake-out/lib/libqnn_executorch_backend.so
2025-03-21T20:32:44.3917701Z -- Installing: /pytorch/executorch/cmake-out/lib/libextension_data_loader.a
2025-03-21T20:32:44.3918757Z -- Installing: /pytorch/executorch/cmake-out/lib/libextension_flat_tensor.a
2025-03-21T20:32:44.3919772Z -- Installing: /pytorch/executorch/cmake-out/lib/libextension_module.so
2025-03-21T20:32:44.3920814Z -- Installing: /pytorch/executorch/cmake-out/lib/libextension_module_static.a
2025-03-21T20:32:44.3921903Z -- Installing: /pytorch/executorch/cmake-out/lib/libextension_tensor.a
2025-03-21T20:32:44.3922871Z -- Installing: /pytorch/executorch/cmake-out/lib/libextension_threadpool.a
2025-03-21T20:32:44.3923859Z -- Installing: /pytorch/executorch/cmake-out/lib/libquantized_kernels.a
2025-03-21T20:32:44.3924820Z -- Installing: /pytorch/executorch/cmake-out/lib/libquantized_ops_lib.a
2025-03-21T20:32:44.3926008Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/kernels/quantized/Functions.h
2025-03-21T20:32:44.3927464Z -- Installing: /pytorch/executorch/cmake-out/include/executorch/kernels/quantized/NativeFunctions.h
2025-03-21T20:32:44.3928538Z + cmake_build_llama_runner
2025-03-21T20:32:44.3929040Z + echo 'Building llama runner'
2025-03-21T20:32:44.3929626Z Building llama runner
2025-03-21T20:32:44.3930108Z + pushd extension/llm/tokenizers
2025-03-21T20:32:44.3930846Z /pytorch/executorch/extension/llm/tokenizers /pytorch/executorch
2025-03-21T20:32:44.3931692Z + echo 'Updating tokenizers submodule'
2025-03-21T20:32:44.3932461Z Updating tokenizers submodule
2025-03-21T20:32:44.3932969Z + git submodule update --init
2025-03-21T20:32:44.3933436Z + popd
2025-03-21T20:32:44.3933809Z /pytorch/executorch
2025-03-21T20:32:44.3934242Z + dir=examples/models/llama
2025-03-21T20:32:44.3936327Z + retry cmake -DCMAKE_INSTALL_PREFIX=cmake-out -DCMAKE_BUILD_TYPE=Release -DEXECUTORCH_BUILD_KERNELS_CUSTOM=OFF -DEXECUTORCH_BUILD_KERNELS_OPTIMIZED=ON -DEXECUTORCH_BUILD_XNNPACK=OFF -DPYTHON_EXECUTABLE=python -Bcmake-out/examples/models/llama examples/models/llama
2025-03-21T20:32:44.3940079Z + cmake -DCMAKE_INSTALL_PREFIX=cmake-out -DCMAKE_BUILD_TYPE=Release -DEXECUTORCH_BUILD_KERNELS_CUSTOM=OFF -DEXECUTORCH_BUILD_KERNELS_OPTIMIZED=ON -DEXECUTORCH_BUILD_XNNPACK=OFF -DPYTHON_EXECUTABLE=python -Bcmake-out/examples/models/llama examples/models/llama
2025-03-21T20:32:44.3942265Z -- The C compiler identification is Clang 12.0.1
2025-03-21T20:32:44.3942984Z -- The CXX compiler identification is Clang 12.0.1
2025-03-21T20:32:44.3943654Z -- Detecting C compiler ABI info
2025-03-21T20:32:44.3944237Z -- Detecting C compiler ABI info - done
2025-03-21T20:32:44.3944979Z -- Check for working C compiler: /opt/cache/bin/cc - skipped
2025-03-21T20:32:44.3945708Z -- Detecting C compile features
2025-03-21T20:32:44.3946278Z -- Detecting C compile features - done
2025-03-21T20:32:44.3946874Z -- Detecting CXX compiler ABI info
2025-03-21T20:32:44.3947466Z -- Detecting CXX compiler ABI info - done
2025-03-21T20:32:44.3948199Z -- Check for working CXX compiler: /opt/cache/bin/c++ - skipped
2025-03-21T20:32:44.3948954Z -- Detecting CXX compile features
2025-03-21T20:32:44.3949552Z -- Detecting CXX compile features - done
2025-03-21T20:32:44.3950622Z CMake Warning (dev) at CMakeLists.txt:82 (find_package):
2025-03-21T20:32:44.3951602Z   Policy CMP0144 is not set: find_package uses upper-case <PACKAGENAME>_ROOT
2025-03-21T20:32:44.3952684Z   variables.  Run "cmake --help-policy CMP0144" for policy details.  Use the
2025-03-21T20:32:44.3953918Z   cmake_policy command to set the policy and suppress this warning.
2025-03-21T20:32:44.3954441Z 
2025-03-21T20:32:44.3954666Z   CMake variable EXECUTORCH_ROOT is set to:
2025-03-21T20:32:44.3955022Z 
2025-03-21T20:32:44.3955290Z     /pytorch/executorch/examples/models/llama/../../..
2025-03-21T20:32:44.3955728Z 
2025-03-21T20:32:44.3956050Z   Environment variable EXECUTORCH_ROOT is set to:
2025-03-21T20:32:44.3956469Z 
2025-03-21T20:32:44.3956652Z     /pytorch/executorch/.ci
2025-03-21T20:32:44.3956975Z 
2025-03-21T20:32:44.3957377Z   For compatibility, find_package is ignoring the variable, but code in a
2025-03-21T20:32:44.3958239Z   .cmake module might still use it.
2025-03-21T20:32:44.3958973Z This warning is for project developers.  Use -Wno-dev to suppress it.
2025-03-21T20:32:44.3959797Z 
2025-03-21T20:32:44.3960262Z etdump library is not found.
2025-03-21T20:32:44.3961172Z             If needed rebuild with the proper options in CMakeLists.txt
2025-03-21T20:32:44.3962078Z bundled_program library is not found.
2025-03-21T20:32:44.3962972Z             If needed rebuild with the proper options in CMakeLists.txt
2025-03-21T20:32:44.3963790Z flatccrt library is not found.
2025-03-21T20:32:44.3964637Z             If needed rebuild with the proper options in CMakeLists.txt
2025-03-21T20:32:44.3965513Z coremldelegate library is not found.
2025-03-21T20:32:44.3966393Z             If needed rebuild with the proper options in CMakeLists.txt
2025-03-21T20:32:44.3967177Z mpsdelegate library is not found.
2025-03-21T20:32:44.3968037Z             If needed rebuild with the proper options in CMakeLists.txt
2025-03-21T20:32:44.3968850Z neuron_backend library is not found.
2025-03-21T20:32:44.3969816Z             If needed rebuild with the proper options in CMakeLists.txt
2025-03-21T20:32:44.3970683Z custom_ops library is not found.
2025-03-21T20:32:44.3971572Z             If needed rebuild with the proper options in CMakeLists.txt
2025-03-21T20:32:44.3972520Z extension_runner_util library is not found.
2025-03-21T20:32:44.3973464Z             If needed rebuild with the proper options in CMakeLists.txt
2025-03-21T20:32:44.3974408Z extension_training library is not found.
2025-03-21T20:32:44.3975347Z             If needed rebuild with the proper options in CMakeLists.txt
2025-03-21T20:32:44.3976218Z xnnpack_backend library is not found.
2025-03-21T20:32:44.3977107Z             If needed rebuild with the proper options in CMakeLists.txt
2025-03-21T20:32:44.3977955Z XNNPACK library is not found.
2025-03-21T20:32:44.3978786Z             If needed rebuild with the proper options in CMakeLists.txt
2025-03-21T20:32:44.3979659Z microkernels-prod library is not found.
2025-03-21T20:32:44.3980561Z             If needed rebuild with the proper options in CMakeLists.txt
2025-03-21T20:32:44.3981431Z kleidiai library is not found.
2025-03-21T20:32:44.3982298Z             If needed rebuild with the proper options in CMakeLists.txt
2025-03-21T20:32:44.3983121Z vulkan_backend library is not found.
2025-03-21T20:32:44.3983937Z             If needed rebuild with the proper options in CMakeLists.txt
2025-03-21T20:32:44.3984811Z quantized_ops_aot_lib library is not found.
2025-03-21T20:32:44.3985690Z             If needed rebuild with the proper options in CMakeLists.txt
2025-03-21T20:32:44.3987182Z -- executorch: Using source file list /pytorch/executorch/cmake-out/examples/models/llama/runner/../../../../executorch_srcs.cmake
2025-03-21T20:32:44.3988520Z -- Performing Test ABSL_INTERNAL_AT_LEAST_CXX17
2025-03-21T20:32:44.3989283Z -- Performing Test ABSL_INTERNAL_AT_LEAST_CXX17 - Success
2025-03-21T20:32:44.3990054Z -- Performing Test ABSL_INTERNAL_AT_LEAST_CXX20
2025-03-21T20:32:44.3990784Z -- Performing Test ABSL_INTERNAL_AT_LEAST_CXX20 - Failed
2025-03-21T20:32:44.3991486Z -- Performing Test CMAKE_HAVE_LIBC_PTHREAD
2025-03-21T20:32:44.3992159Z -- Performing Test CMAKE_HAVE_LIBC_PTHREAD - Success
2025-03-21T20:32:44.3992944Z -- Found Threads: TRUE
2025-03-21T20:32:44.3993363Z -- 
2025-03-21T20:32:44.3993735Z -- ******** Summary ********
2025-03-21T20:32:44.3994250Z --   CMAKE_BUILD_TYPE              : Release
2025-03-21T20:32:44.3994827Z --   CMAKE_CXX_STANDARD            : 17
2025-03-21T20:32:44.3995365Z --   CMAKE_CXX_COMPILER_ID         : Clang
2025-03-21T20:32:44.3996012Z --   CMAKE_TOOLCHAIN_FILE          : 
2025-03-21T20:32:44.3996564Z --   BUCK2                         : 
2025-03-21T20:32:44.3997103Z --   PYTHON_EXECUTABLE             : python
2025-03-21T20:32:44.3997653Z --   FLATC_EXECUTABLE              : 
2025-03-21T20:32:44.3998252Z --   EXECUTORCH_ENABLE_LOGGING              : 
2025-03-21T20:32:44.3998856Z --   EXECUTORCH_ENABLE_PROGRAM_VERIFICATION : 
2025-03-21T20:32:44.3999450Z --   EXECUTORCH_LOG_LEVEL                   : 
2025-03-21T20:32:44.4000043Z --   EXECUTORCH_BUILD_ANDROID_JNI           : 
2025-03-21T20:32:44.4000685Z --   EXECUTORCH_BUILD_ARM_BAREMETAL         : 
2025-03-21T20:32:44.4001285Z --   EXECUTORCH_BUILD_CADENCE               : 
2025-03-21T20:32:44.4001877Z --   EXECUTORCH_BUILD_COREML                : 
2025-03-21T20:32:44.4002505Z --   EXECUTORCH_BUILD_CPUINFO               : ON
2025-03-21T20:32:44.4003145Z --   EXECUTORCH_BUILD_DEVTOOLS              : 
2025-03-21T20:32:44.4003758Z --   EXECUTORCH_BUILD_EXECUTOR_RUNNER       : 
2025-03-21T20:32:44.4004367Z --   EXECUTORCH_BUILD_EXTENSION_DATA_LOADER : 
2025-03-21T20:32:44.4005009Z --   EXECUTORCH_BUILD_EXTENSION_FLAT_TENSOR : 
2025-03-21T20:32:44.4005631Z --   EXECUTORCH_BUILD_EXTENSION_LLM : 
2025-03-21T20:32:44.4006214Z --   EXECUTORCH_BUILD_EXTENSION_MODULE      : 
2025-03-21T20:32:44.4006813Z --   EXECUTORCH_BUILD_EXTENSION_RUNNER_UTIL : 
2025-03-21T20:32:44.4007407Z --   EXECUTORCH_BUILD_EXTENSION_TENSOR      : 
2025-03-21T20:32:44.4008000Z --   EXECUTORCH_BUILD_EXTENSION_TRAINING    : 
2025-03-21T20:32:44.4008576Z --   EXECUTORCH_BUILD_FLATC                 : 
2025-03-21T20:32:44.4009171Z --   EXECUTORCH_BUILD_GFLAGS                : 
2025-03-21T20:32:44.4009854Z --   EXECUTORCH_BUILD_HOST_TARGETS          : 
2025-03-21T20:32:44.4010462Z --   EXECUTORCH_BUILD_KERNELS_CUSTOM        : OFF
2025-03-21T20:32:44.4011076Z --   EXECUTORCH_BUILD_KERNELS_CUSTOM_AOT    : 
2025-03-21T20:32:44.4011716Z --   EXECUTORCH_BUILD_KERNELS_OPTIMIZED     : ON
2025-03-21T20:32:44.4012350Z --   EXECUTORCH_BUILD_KERNELS_QUANTIZED     : 
2025-03-21T20:32:44.4012944Z --   EXECUTORCH_BUILD_MPS                   : 
2025-03-21T20:32:44.4013521Z --   EXECUTORCH_BUILD_NEURON                : 
2025-03-21T20:32:44.4014139Z --   EXECUTORCH_BUILD_PTHREADPOOL           : ON
2025-03-21T20:32:44.4014783Z --   EXECUTORCH_BUILD_PYBIND                : 
2025-03-21T20:32:44.4015394Z --   EXECUTORCH_BUILD_QNN                   : 
2025-03-21T20:32:44.4015994Z --   EXECUTORCH_BUILD_SIZE_TEST             : 
2025-03-21T20:32:44.4016597Z --   EXECUTORCH_BUILD_TESTS                 : 
2025-03-21T20:32:44.4017195Z --   EXECUTORCH_BUILD_VULKAN                : 
2025-03-21T20:32:44.4017570Z --   EXECUTORCH_BUILD_XNNPACK               : OFF
2025-03-21T20:32:44.4017922Z -- Configuring done (1.2s)
2025-03-21T20:32:44.4018219Z -- Generating done (0.3s)
2025-03-21T20:32:44.4019159Z -- Build files have been written to: /pytorch/executorch/cmake-out/examples/models/llama
2025-03-21T20:32:44.4020138Z + cmake --build cmake-out/examples/models/llama -j9 --config Release
2025-03-21T20:32:44.4021612Z [  0%] Building CXX object runner/abseil-cpp/absl/base/CMakeFiles/log_severity.dir/log_severity.cc.o
2025-03-21T20:32:44.4023497Z [  0%] Building CXX object runner/abseil-cpp/absl/base/CMakeFiles/spinlock_wait.dir/internal/spinlock_wait.cc.o
2025-03-21T20:32:44.4025320Z [  0%] Building CXX object runner/abseil-cpp/absl/base/CMakeFiles/strerror.dir/internal/strerror.cc.o
2025-03-21T20:32:44.4026944Z [  0%] Building CXX object runner/abseil-cpp/absl/debugging/CMakeFiles/utf8_for_code_point.dir/internal/utf8_for_code_point.cc.o
2025-03-21T20:32:45.2268971Z [  1%] Building CXX object runner/abseil-cpp/absl/time/CMakeFiles/civil_time.dir/internal/cctz/src/civil_time_detail.cc.o
2025-03-21T20:32:45.2271338Z [  1%] Building CXX object runner/abseil-cpp/absl/profiling/CMakeFiles/exponential_biased.dir/internal/exponential_biased.cc.o
2025-03-21T20:32:45.2273473Z [  1%] Building CXX object runner/abseil-cpp/absl/debugging/CMakeFiles/leak_check.dir/leak_check.cc.o
2025-03-21T20:32:45.2275437Z [  1%] Building CXX object runner/abseil-cpp/absl/time/CMakeFiles/time_zone.dir/internal/cctz/src/time_zone_fixed.cc.o
2025-03-21T20:32:45.2277269Z [  2%] Building CXX object runner/abseil-cpp/absl/numeric/CMakeFiles/int128.dir/int128.cc.o
2025-03-21T20:32:45.2278653Z [  3%] Linking CXX static library libabsl_leak_check.a
2025-03-21T20:32:45.2279699Z [  4%] Linking CXX static library libabsl_utf8_for_code_point.a
2025-03-21T20:32:45.2280783Z [  4%] Linking CXX static library libabsl_spinlock_wait.a
2025-03-21T20:32:45.2281572Z [  4%] Built target leak_check
2025-03-21T20:32:45.2282084Z [  4%] Built target utf8_for_code_point
2025-03-21T20:32:45.2283527Z [  5%] Building CXX object runner/abseil-cpp/absl/time/CMakeFiles/time_zone.dir/internal/cctz/src/time_zone_format.cc.o
2025-03-21T20:32:45.2285772Z [  5%] Building CXX object runner/abseil-cpp/absl/flags/CMakeFiles/flags_commandlineflag_internal.dir/internal/commandlineflag.cc.o
2025-03-21T20:32:45.2297008Z [  6%] Linking CXX static library libabsl_log_severity.a
2025-03-21T20:32:45.2297886Z [  6%] Built target spinlock_wait
2025-03-21T20:32:45.2299348Z [  6%] Building CXX object runner/abseil-cpp/absl/log/CMakeFiles/log_internal_nullguard.dir/internal/nullguard.cc.o
2025-03-21T20:32:45.2300819Z [  6%] Linking CXX static library libabsl_strerror.a
2025-03-21T20:32:45.2301528Z [  6%] Built target log_severity
2025-03-21T20:32:45.2302987Z [  7%] Building CXX object runner/abseil-cpp/absl/random/CMakeFiles/random_seed_gen_exception.dir/seed_gen_exception.cc.o
2025-03-21T20:32:45.2304267Z [  7%] Built target strerror
2025-03-21T20:32:45.2305022Z [  7%] Linking CXX static library libabsl_civil_time.a
2025-03-21T20:32:45.2306690Z [  8%] Building CXX object runner/abseil-cpp/absl/random/CMakeFiles/random_internal_platform.dir/internal/randen_round_keys.cc.o
2025-03-21T20:32:45.2308376Z [  9%] Linking CXX static library libabsl_exponential_biased.a
2025-03-21T20:32:45.2309178Z [  9%] Built target civil_time
2025-03-21T20:32:45.2310552Z [ 10%] Building CXX object runner/abseil-cpp/absl/base/CMakeFiles/raw_logging_internal.dir/internal/raw_logging.cc.o
2025-03-21T20:32:45.2311715Z [ 10%] Built target exponential_biased
2025-03-21T20:32:45.2313221Z [ 11%] Building CXX object runner/abseil-cpp/absl/debugging/CMakeFiles/decode_rust_punycode.dir/internal/decode_rust_punycode.cc.o
2025-03-21T20:32:45.2315007Z [ 12%] Linking CXX static library libabsl_flags_commandlineflag_internal.a
2025-03-21T20:32:45.2315966Z [ 12%] Built target flags_commandlineflag_internal
2025-03-21T20:32:45.2317407Z [ 12%] Building CXX object runner/abseil-cpp/absl/time/CMakeFiles/time_zone.dir/internal/cctz/src/time_zone_if.cc.o
2025-03-21T20:32:45.2319565Z [ 12%] Building CXX object runner/abseil-cpp/absl/profiling/CMakeFiles/periodic_sampler.dir/internal/periodic_sampler.cc.o
2025-03-21T20:32:45.2321240Z [ 12%] Linking CXX static library libabsl_log_internal_nullguard.a
2025-03-21T20:32:45.2322443Z [ 12%] Linking CXX static library libabsl_random_internal_platform.a
2025-03-21T20:32:45.2323300Z [ 12%] Built target log_internal_nullguard
2025-03-21T20:32:45.2324742Z [ 12%] Building CXX object runner/abseil-cpp/absl/time/CMakeFiles/time_zone.dir/internal/cctz/src/time_zone_impl.cc.o
2025-03-21T20:32:45.2325993Z [ 12%] Built target random_internal_platform
2025-03-21T20:32:45.2327700Z [ 13%] Building CXX object runner/abseil-cpp/absl/time/CMakeFiles/time_zone.dir/internal/cctz/src/time_zone_info.cc.o
2025-03-21T20:32:45.2329875Z [ 13%] Building CXX object runner/abseil-cpp/absl/time/CMakeFiles/time_zone.dir/internal/cctz/src/time_zone_libc.cc.o
2025-03-21T20:32:45.2331494Z [ 13%] Linking CXX static library libabsl_random_seed_gen_exception.a
2025-03-21T20:32:45.2335258Z [ 13%] Linking CXX static library libabsl_int128.a
2025-03-21T20:32:45.2336031Z [ 13%] Built target random_seed_gen_exception
2025-03-21T20:32:45.2337564Z [ 13%] Building CXX object runner/abseil-cpp/absl/time/CMakeFiles/time_zone.dir/internal/cctz/src/time_zone_lookup.cc.o
2025-03-21T20:32:45.2338886Z [ 13%] Built target int128
2025-03-21T20:32:45.2339760Z [ 13%] Linking CXX static library libabsl_raw_logging_internal.a
2025-03-21T20:32:45.2340890Z [ 13%] Linking CXX static library libabsl_periodic_sampler.a
2025-03-21T20:32:45.2342550Z [ 13%] Building CXX object runner/abseil-cpp/absl/random/CMakeFiles/random_internal_randen_hwaes_impl.dir/internal/randen_hwaes.cc.o
2025-03-21T20:32:45.2343426Z [ 13%] Built target raw_logging_internal
2025-03-21T20:32:45.2343766Z [ 13%] Built target periodic_sampler
2025-03-21T20:32:45.2344282Z [ 13%] Linking CXX static library libabsl_decode_rust_punycode.a
2025-03-21T20:32:45.2345199Z [ 13%] Building CXX object runner/abseil-cpp/absl/random/CMakeFiles/random_internal_randen_slow.dir/internal/randen_slow.cc.o
2025-03-21T20:32:45.2346404Z [ 13%] Building CXX object runner/abseil-cpp/absl/types/CMakeFiles/bad_any_cast_impl.dir/bad_any_cast.cc.o
2025-03-21T20:32:45.2347085Z [ 13%] Built target decode_rust_punycode
2025-03-21T20:32:45.2347885Z [ 14%] Building CXX object runner/abseil-cpp/absl/time/CMakeFiles/time_zone.dir/internal/cctz/src/time_zone_posix.cc.o
2025-03-21T20:32:45.2349083Z [ 14%] Building CXX object runner/abseil-cpp/absl/time/CMakeFiles/time_zone.dir/internal/cctz/src/zone_info_source.cc.o
2025-03-21T20:32:45.2349915Z [ 14%] Linking CXX static library libabsl_bad_any_cast_impl.a
2025-03-21T20:32:45.2350868Z [ 14%] Building CXX object runner/abseil-cpp/absl/base/CMakeFiles/base.dir/internal/cycleclock.cc.o
2025-03-21T20:32:45.2351863Z [ 14%] Building CXX object runner/abseil-cpp/absl/types/CMakeFiles/bad_variant_access.dir/bad_variant_access.cc.o
2025-03-21T20:32:45.2352514Z [ 14%] Built target bad_any_cast_impl
2025-03-21T20:32:45.2353302Z [ 14%] Building CXX object runner/abseil-cpp/absl/base/CMakeFiles/throw_delegate.dir/internal/throw_delegate.cc.o
2025-03-21T20:32:45.2354707Z [ 14%] Building CXX object runner/abseil-cpp/absl/debugging/CMakeFiles/debugging_internal.dir/internal/address_is_readable.cc.o
2025-03-21T20:32:45.2355863Z [ 14%] Building CXX object runner/abseil-cpp/absl/debugging/CMakeFiles/demangle_rust.dir/internal/demangle_rust.cc.o
2025-03-21T20:32:45.2356986Z [ 15%] Building CXX object runner/abseil-cpp/absl/debugging/CMakeFiles/debugging_internal.dir/internal/elf_mem_image.cc.o
2025-03-21T20:32:45.2358007Z [ 15%] Building CXX object runner/abseil-cpp/absl/base/CMakeFiles/base.dir/internal/spinlock.cc.o
2025-03-21T20:32:45.2358789Z [ 16%] Linking CXX static library libabsl_random_internal_randen_slow.a
2025-03-21T20:32:45.2359474Z [ 17%] Linking CXX static library libabsl_random_internal_randen_hwaes_impl.a
2025-03-21T20:32:45.2360350Z [ 18%] Linking CXX static library libabsl_bad_variant_access.a
2025-03-21T20:32:45.2360867Z [ 18%] Built target random_internal_randen_slow
2025-03-21T20:32:45.2361554Z [ 19%] Building CXX object runner/abseil-cpp/absl/base/CMakeFiles/base.dir/internal/sysinfo.cc.o
2025-03-21T20:32:45.2362165Z [ 19%] Built target random_internal_randen_hwaes_impl
2025-03-21T20:32:45.2362537Z [ 19%] Built target bad_variant_access
2025-03-21T20:32:45.2363384Z [ 20%] Building CXX object runner/abseil-cpp/absl/types/CMakeFiles/bad_optional_access.dir/bad_optional_access.cc.o
2025-03-21T20:32:45.2364851Z [ 20%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/cordz_functions.dir/internal/cordz_functions.cc.o
2025-03-21T20:32:45.2366853Z [ 20%] Building CXX object runner/abseil-cpp/absl/debugging/CMakeFiles/debugging_internal.dir/internal/vdso_support.cc.o
2025-03-21T20:32:45.2368473Z [ 21%] Linking CXX static library libabsl_throw_delegate.a
2025-03-21T20:32:45.2369219Z [ 21%] Linking CXX static library libabsl_time_zone.a
2025-03-21T20:32:45.2369722Z [ 21%] Built target throw_delegate
2025-03-21T20:32:45.2370899Z [ 21%] Building CXX object runner/abseil-cpp/absl/base/CMakeFiles/scoped_set_env.dir/internal/scoped_set_env.cc.o
2025-03-21T20:32:45.2372141Z [ 22%] Linking CXX static library libabsl_demangle_rust.a
2025-03-21T20:32:45.2372762Z [ 22%] Built target time_zone
2025-03-21T20:32:45.2373149Z [ 22%] Built target demangle_rust
2025-03-21T20:32:45.2374234Z [ 23%] Building CXX object runner/abseil-cpp/absl/random/CMakeFiles/random_internal_randen_hwaes.dir/internal/randen_detect.cc.o
2025-03-21T20:32:45.2375749Z [ 23%] Building CXX object runner/abseil-cpp/absl/debugging/CMakeFiles/demangle_internal.dir/internal/demangle.cc.o
2025-03-21T20:32:45.2376787Z [ 23%] Building CXX object runner/abseil-cpp/absl/base/CMakeFiles/base.dir/internal/thread_identity.cc.o
2025-03-21T20:32:45.2377797Z [ 23%] Building CXX object runner/abseil-cpp/absl/base/CMakeFiles/base.dir/internal/unscaledcycleclock.cc.o
2025-03-21T20:32:45.2378646Z [ 23%] Linking CXX static library libabsl_bad_optional_access.a
2025-03-21T20:32:45.2379658Z [ 23%] Linking CXX static library libabsl_random_internal_randen_hwaes.a
2025-03-21T20:32:45.2380452Z [ 23%] Linking CXX static library libabsl_debugging_internal.a
2025-03-21T20:32:45.2380897Z [ 23%] Built target bad_optional_access
2025-03-21T20:32:45.2381408Z [ 23%] Built target random_internal_randen_hwaes
2025-03-21T20:32:45.2381961Z [ 23%] Built target debugging_internal
2025-03-21T20:32:45.2382978Z [ 23%] Building CXX object runner/abseil-cpp/absl/random/CMakeFiles/random_internal_randen.dir/internal/randen.cc.o
2025-03-21T20:32:45.2384003Z [ 24%] Building CXX object runner/abseil-cpp/absl/debugging/CMakeFiles/stacktrace.dir/stacktrace.cc.o
2025-03-21T20:32:45.2384766Z [ 25%] Linking CXX static library libabsl_cordz_functions.a
2025-03-21T20:32:45.2385189Z [ 25%] Built target cordz_functions
2025-03-21T20:32:46.4790025Z [ 27%] Linking CXX static library libabsl_scoped_set_env.a
2025-03-21T20:32:46.4790690Z [ 27%] Linking CXX static library libabsl_base.a
2025-03-21T20:32:46.4791262Z [ 28%] Linking CXX static library libabsl_demangle_internal.a
2025-03-21T20:32:46.4791814Z [ 28%] Built target scoped_set_env
2025-03-21T20:32:46.4792227Z [ 28%] Built target base
2025-03-21T20:32:46.4793071Z [ 28%] Building CXX object runner/abseil-cpp/absl/base/CMakeFiles/malloc_internal.dir/internal/low_level_alloc.cc.o
2025-03-21T20:32:46.4794128Z [ 29%] Building CXX object runner/abseil-cpp/absl/base/CMakeFiles/tracing_internal.dir/internal/tracing.cc.o
2025-03-21T20:32:46.4795103Z [ 30%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/string_view.dir/string_view.cc.o
2025-03-21T20:32:46.4796263Z [ 31%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/strings_internal.dir/internal/ostringstream.cc.o
2025-03-21T20:32:46.4798138Z [ 32%] Building CXX object runner/abseil-cpp/absl/crc/CMakeFiles/crc_cpu_detect.dir/internal/cpu_detect.cc.o
2025-03-21T20:32:46.4799757Z [ 32%] Building CXX object runner/abseil-cpp/absl/hash/CMakeFiles/city.dir/internal/city.cc.o
2025-03-21T20:32:46.4800732Z [ 32%] Built target demangle_internal
2025-03-21T20:32:46.4802264Z [ 32%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/strings_internal.dir/internal/utf8.cc.o
2025-03-21T20:32:46.4803791Z [ 32%] Linking CXX static library libabsl_stacktrace.a
2025-03-21T20:32:46.4804866Z [ 32%] Linking CXX static library libabsl_random_internal_randen.a
2025-03-21T20:32:46.4805659Z [ 32%] Built target stacktrace
2025-03-21T20:32:46.4806936Z [ 33%] Building CXX object runner/abseil-cpp/absl/hash/CMakeFiles/low_level_hash.dir/internal/low_level_hash.cc.o
2025-03-21T20:32:46.4808103Z [ 33%] Built target random_internal_randen
2025-03-21T20:32:46.4809601Z [ 34%] Building CXX object runner/abseil-cpp/absl/log/CMakeFiles/log_internal_conditions.dir/internal/conditions.cc.o
2025-03-21T20:32:46.4811232Z [ 34%] Linking CXX static library libabsl_tracing_internal.a
2025-03-21T20:32:46.4812745Z [ 34%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/strings_internal.dir/internal/escaping.cc.o
2025-03-21T20:32:46.4814103Z [ 34%] Built target tracing_internal
2025-03-21T20:32:46.4815016Z [ 35%] Linking CXX static library libabsl_malloc_internal.a
2025-03-21T20:32:46.4815811Z [ 35%] Built target malloc_internal
2025-03-21T20:32:46.4816585Z [ 35%] Linking CXX static library libabsl_city.a
2025-03-21T20:32:46.4818193Z [ 35%] Building CXX object runner/abseil-cpp/absl/synchronization/CMakeFiles/graphcycles_internal.dir/internal/graphcycles.cc.o
2025-03-21T20:32:46.4820112Z [ 36%] Building CXX object runner/abseil-cpp/absl/base/CMakeFiles/poison.dir/internal/poison.cc.o
2025-03-21T20:32:46.4821505Z [ 36%] Linking CXX static library libabsl_log_internal_conditions.a
2025-03-21T20:32:46.4822571Z [ 36%] Linking CXX static library libabsl_string_view.a
2025-03-21T20:32:46.4823281Z [ 36%] Built target city
2025-03-21T20:32:46.4823801Z [ 36%] Built target log_internal_conditions
2025-03-21T20:32:46.4824379Z [ 36%] Built target string_view
2025-03-21T20:32:46.4825236Z [ 36%] Linking CXX static library libabsl_crc_cpu_detect.a
2025-03-21T20:32:46.4825994Z [ 36%] Linking CXX static library libabsl_low_level_hash.a
2025-03-21T20:32:46.4826504Z [ 36%] Built target crc_cpu_detect
2025-03-21T20:32:46.4827298Z [ 37%] Linking CXX static library libabsl_strings_internal.a
2025-03-21T20:32:46.4828824Z [ 38%] Building CXX object runner/abseil-cpp/absl/crc/CMakeFiles/crc_internal.dir/internal/crc_x86_arm_combined.cc.o
2025-03-21T20:32:46.4830721Z [ 38%] Building CXX object runner/abseil-cpp/absl/crc/CMakeFiles/crc_internal.dir/internal/crc.cc.o
2025-03-21T20:32:46.4831814Z [ 38%] Built target low_level_hash
2025-03-21T20:32:46.4832801Z [ 38%] Built target strings_internal
2025-03-21T20:32:46.4834030Z [ 39%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/strings.dir/ascii.cc.o
2025-03-21T20:32:46.4835658Z [ 39%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/strings.dir/escaping.cc.o
2025-03-21T20:32:46.4837331Z [ 39%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/strings.dir/charconv.cc.o
2025-03-21T20:32:46.4839202Z [ 40%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/strings.dir/internal/charconv_bigint.cc.o
2025-03-21T20:32:46.4841051Z [ 40%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/strings.dir/internal/charconv_parse.cc.o
2025-03-21T20:32:46.4842398Z [ 40%] Linking CXX static library libabsl_poison.a
2025-03-21T20:32:46.4843062Z [ 40%] Built target poison
2025-03-21T20:32:46.4844444Z [ 40%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/strings.dir/internal/damerau_levenshtein_distance.cc.o
2025-03-21T20:32:46.4846049Z [ 41%] Linking CXX static library libabsl_graphcycles_internal.a
2025-03-21T20:32:46.4846851Z [ 41%] Built target graphcycles_internal
2025-03-21T20:32:46.4848138Z [ 42%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/strings.dir/internal/memutil.cc.o
2025-03-21T20:32:46.4850341Z [ 42%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/strings.dir/internal/stringify_sink.cc.o
2025-03-21T20:32:46.4852054Z [ 42%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/strings.dir/match.cc.o
2025-03-21T20:32:46.4853631Z [ 43%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/strings.dir/numbers.cc.o
2025-03-21T20:32:46.4855050Z [ 43%] Linking CXX static library libabsl_crc_internal.a
2025-03-21T20:32:46.4855504Z [ 43%] Built target crc_internal
2025-03-21T20:32:46.4856134Z [ 43%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/strings.dir/str_cat.cc.o
2025-03-21T20:32:46.4857608Z [ 43%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/strings.dir/str_replace.cc.o
2025-03-21T20:32:46.4858528Z [ 44%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/strings.dir/str_split.cc.o
2025-03-21T20:32:46.4859530Z [ 44%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/strings.dir/substitute.cc.o
2025-03-21T20:32:46.4860236Z [ 44%] Linking CXX static library libabsl_strings.a
2025-03-21T20:32:46.4860626Z [ 44%] Built target strings
2025-03-21T20:32:46.4861260Z [ 44%] Building CXX object runner/abseil-cpp/absl/debugging/CMakeFiles/symbolize.dir/symbolize.cc.o
2025-03-21T20:32:46.4862146Z [ 44%] Building CXX object runner/abseil-cpp/absl/time/CMakeFiles/time.dir/civil_time.cc.o
2025-03-21T20:32:46.4862996Z [ 45%] Building CXX object runner/abseil-cpp/absl/hash/CMakeFiles/hash.dir/internal/hash.cc.o
2025-03-21T20:32:46.4863999Z [ 45%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/str_format_internal.dir/internal/str_format/arg.cc.o
2025-03-21T20:32:46.4865097Z [ 46%] Building CXX object runner/abseil-cpp/absl/flags/CMakeFiles/flags_commandlineflag.dir/commandlineflag.cc.o
2025-03-21T20:32:46.4866394Z [ 47%] Building CXX object runner/abseil-cpp/absl/log/CMakeFiles/log_internal_proto.dir/internal/proto.cc.o
2025-03-21T20:32:46.4867835Z [ 47%] Building CXX object runner/abseil-cpp/absl/random/CMakeFiles/random_internal_seed_material.dir/internal/seed_material.cc.o
2025-03-21T20:32:46.4869269Z [ 47%] Building CXX object runner/abseil-cpp/absl/log/CMakeFiles/log_internal_fnmatch.dir/internal/fnmatch.cc.o
2025-03-21T20:32:46.4871022Z [ 48%] Building CXX object runner/abseil-cpp/absl/random/CMakeFiles/random_distributions.dir/discrete_distribution.cc.o
2025-03-21T20:32:46.4872288Z [ 49%] Linking CXX static library libabsl_symbolize.a
2025-03-21T20:32:46.4873102Z [ 49%] Linking CXX static library libabsl_flags_commandlineflag.a
2025-03-21T20:32:46.4873750Z [ 50%] Linking CXX static library libabsl_log_internal_fnmatch.a
2025-03-21T20:32:46.4874187Z [ 50%] Built target symbolize
2025-03-21T20:32:46.4874644Z [ 50%] Linking CXX static library libabsl_log_internal_proto.a
2025-03-21T20:32:46.4875847Z [ 50%] Building CXX object runner/abseil-cpp/absl/random/CMakeFiles/random_distributions.dir/gaussian_distribution.cc.o
2025-03-21T20:32:46.4877077Z [ 50%] Built target flags_commandlineflag
2025-03-21T20:32:46.4877648Z [ 50%] Built target log_internal_fnmatch
2025-03-21T20:32:46.4878704Z [ 50%] Building CXX object runner/abseil-cpp/absl/time/CMakeFiles/time.dir/clock.cc.o
2025-03-21T20:32:46.4880415Z [ 51%] Building CXX object runner/abseil-cpp/absl/debugging/CMakeFiles/examine_stack.dir/internal/examine_stack.cc.o
2025-03-21T20:32:46.4882720Z [ 51%] Building CXX object runner/abseil-cpp/absl/flags/CMakeFiles/flags_private_handle_accessor.dir/internal/private_handle_accessor.cc.o
2025-03-21T20:32:46.4884159Z [ 51%] Built target log_internal_proto
2025-03-21T20:32:46.4885353Z [ 52%] Building CXX object runner/abseil-cpp/absl/time/CMakeFiles/time.dir/duration.cc.o
2025-03-21T20:32:46.4887234Z [ 52%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/str_format_internal.dir/internal/str_format/bind.cc.o
2025-03-21T20:32:46.4888741Z [ 52%] Linking CXX static library libabsl_hash.a
2025-03-21T20:32:46.4890416Z [ 52%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/str_format_internal.dir/internal/str_format/extension.cc.o
2025-03-21T20:32:46.4891671Z [ 52%] Built target hash
2025-03-21T20:32:46.4893294Z [ 53%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/str_format_internal.dir/internal/str_format/float_conversion.cc.o
2025-03-21T20:32:46.4895140Z [ 53%] Linking CXX static library libabsl_random_internal_seed_material.a
2025-03-21T20:32:46.4896491Z [ 53%] Linking CXX static library libabsl_flags_private_handle_accessor.a
2025-03-21T20:32:46.4897645Z [ 53%] Linking CXX static library libabsl_examine_stack.a
2025-03-21T20:32:46.4898411Z [ 53%] Built target random_internal_seed_material
2025-03-21T20:32:46.4899407Z [ 53%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/str_format_internal.dir/internal/str_format/output.cc.o
2025-03-21T20:32:46.4900140Z [ 53%] Built target flags_private_handle_accessor
2025-03-21T20:32:48.0667171Z [ 53%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/str_format_internal.dir/internal/str_format/parser.cc.o
2025-03-21T20:32:48.0668421Z [ 53%] Linking CXX static library libabsl_random_distributions.a
2025-03-21T20:32:48.0669158Z [ 53%] Building CXX object runner/abseil-cpp/absl/time/CMakeFiles/time.dir/format.cc.o
2025-03-21T20:32:48.0669690Z [ 53%] Built target examine_stack
2025-03-21T20:32:48.0670283Z [ 54%] Building CXX object runner/abseil-cpp/absl/time/CMakeFiles/time.dir/time.cc.o
2025-03-21T20:32:48.0670805Z [ 54%] Built target random_distributions
2025-03-21T20:32:48.0671594Z [ 54%] Building CXX object runner/abseil-cpp/absl/random/CMakeFiles/random_internal_pool_urbg.dir/internal/pool_urbg.cc.o
2025-03-21T20:32:48.0672465Z [ 55%] Linking CXX static library libabsl_str_format_internal.a
2025-03-21T20:32:48.0672910Z [ 55%] Built target str_format_internal
2025-03-21T20:32:48.0673773Z [ 56%] Building CXX object runner/abseil-cpp/absl/random/CMakeFiles/random_internal_distribution_test_util.dir/internal/chi_square.cc.o
2025-03-21T20:32:48.0674797Z [ 57%] Building CXX object runner/abseil-cpp/absl/crc/CMakeFiles/crc32c.dir/crc32c.cc.o
2025-03-21T20:32:48.0675703Z [ 57%] Building CXX object runner/abseil-cpp/absl/flags/CMakeFiles/flags_marshalling.dir/marshalling.cc.o
2025-03-21T20:32:48.0676742Z [ 57%] Building CXX object runner/abseil-cpp/absl/crc/CMakeFiles/crc32c.dir/internal/crc_memcpy_x86_arm_combined.cc.o
2025-03-21T20:32:48.0677800Z [ 57%] Building CXX object runner/abseil-cpp/absl/crc/CMakeFiles/crc32c.dir/internal/crc_memcpy_fallback.cc.o
2025-03-21T20:32:48.0678911Z [ 57%] Building CXX object runner/abseil-cpp/absl/debugging/CMakeFiles/failure_signal_handler.dir/failure_signal_handler.cc.o
2025-03-21T20:32:48.0680030Z [ 57%] Building CXX object runner/abseil-cpp/absl/crc/CMakeFiles/crc32c.dir/internal/crc_non_temporal_memcpy.cc.o
2025-03-21T20:32:48.0680872Z [ 58%] Linking CXX static library libabsl_random_internal_pool_urbg.a
2025-03-21T20:32:48.0681446Z [ 58%] Linking CXX static library libabsl_time.a
2025-03-21T20:32:48.0681826Z [ 58%] Built target time
2025-03-21T20:32:48.0682110Z [ 58%] Built target random_internal_pool_urbg
2025-03-21T20:32:48.0683051Z [ 58%] Building CXX object runner/abseil-cpp/absl/random/CMakeFiles/random_internal_distribution_test_util.dir/internal/distribution_test_util.cc.o
2025-03-21T20:32:48.0684385Z [ 59%] Building CXX object runner/abseil-cpp/absl/synchronization/CMakeFiles/kernel_timeout_internal.dir/internal/kernel_timeout.cc.o
2025-03-21T20:32:48.0685311Z [ 59%] Linking CXX static library libabsl_failure_signal_handler.a
2025-03-21T20:32:48.0685773Z [ 59%] Built target failure_signal_handler
2025-03-21T20:32:48.0686705Z [ 60%] Building CXX object runner/abseil-cpp/absl/log/CMakeFiles/log_internal_globals.dir/internal/globals.cc.o
2025-03-21T20:32:48.0687694Z [ 60%] Building CXX object runner/abseil-cpp/absl/log/CMakeFiles/log_entry.dir/log_entry.cc.o
2025-03-21T20:32:48.0688717Z [ 60%] Building CXX object runner/abseil-cpp/absl/random/CMakeFiles/random_seed_sequences.dir/seed_sequences.cc.o
2025-03-21T20:32:48.0689575Z [ 61%] Linking CXX static library libabsl_crc32c.a
2025-03-21T20:32:48.0689960Z [ 61%] Built target crc32c
2025-03-21T20:32:48.0690650Z [ 61%] Building CXX object runner/abseil-cpp/absl/crc/CMakeFiles/crc_cord_state.dir/internal/crc_cord_state.cc.o
2025-03-21T20:32:48.0691505Z [ 62%] Linking CXX static library libabsl_flags_marshalling.a
2025-03-21T20:32:48.0692190Z [ 62%] Linking CXX static library libabsl_random_internal_distribution_test_util.a
2025-03-21T20:32:48.0692837Z [ 62%] Built target random_internal_distribution_test_util
2025-03-21T20:32:48.0693359Z [ 62%] Built target flags_marshalling
2025-03-21T20:32:48.0693996Z [ 62%] Linking CXX static library libabsl_kernel_timeout_internal.a
2025-03-21T20:32:48.0694510Z [ 62%] Built target kernel_timeout_internal
2025-03-21T20:32:48.0695273Z [ 62%] Building CXX object runner/abseil-cpp/absl/synchronization/CMakeFiles/synchronization.dir/barrier.cc.o
2025-03-21T20:32:48.0696466Z [ 63%] Building CXX object runner/abseil-cpp/absl/synchronization/CMakeFiles/synchronization.dir/internal/create_thread_identity.cc.o
2025-03-21T20:32:48.0697710Z [ 63%] Building CXX object runner/abseil-cpp/absl/synchronization/CMakeFiles/synchronization.dir/internal/futex_waiter.cc.o
2025-03-21T20:32:48.0698858Z [ 63%] Building CXX object runner/abseil-cpp/absl/synchronization/CMakeFiles/synchronization.dir/blocking_counter.cc.o
2025-03-21T20:32:48.0700048Z [ 63%] Building CXX object runner/abseil-cpp/absl/synchronization/CMakeFiles/synchronization.dir/internal/per_thread_sem.cc.o
2025-03-21T20:32:48.0700947Z [ 64%] Linking CXX static library libabsl_random_seed_sequences.a
2025-03-21T20:32:48.0701398Z [ 64%] Built target random_seed_sequences
2025-03-21T20:32:48.0702239Z [ 65%] Building CXX object runner/abseil-cpp/absl/synchronization/CMakeFiles/synchronization.dir/internal/pthread_waiter.cc.o
2025-03-21T20:32:48.0703135Z [ 65%] Linking CXX static library libabsl_log_internal_globals.a
2025-03-21T20:32:48.0703696Z [ 66%] Linking CXX static library libabsl_log_entry.a
2025-03-21T20:32:48.0704098Z [ 66%] Built target log_entry
2025-03-21T20:32:48.0704408Z [ 66%] Built target log_internal_globals
2025-03-21T20:32:48.0705158Z [ 66%] Building CXX object runner/abseil-cpp/absl/log/CMakeFiles/log_internal_format.dir/internal/log_format.cc.o
2025-03-21T20:32:48.0706093Z [ 66%] Building CXX object runner/abseil-cpp/absl/log/CMakeFiles/log_sink.dir/log_sink.cc.o
2025-03-21T20:32:48.0706791Z [ 66%] Linking CXX static library libabsl_crc_cord_state.a
2025-03-21T20:32:48.0707197Z [ 66%] Built target crc_cord_state
2025-03-21T20:32:48.0707930Z [ 66%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/cord_internal.dir/internal/cord_internal.cc.o
2025-03-21T20:32:48.0709056Z [ 66%] Building CXX object runner/abseil-cpp/absl/synchronization/CMakeFiles/synchronization.dir/internal/sem_waiter.cc.o
2025-03-21T20:32:48.0710249Z [ 66%] Building CXX object runner/abseil-cpp/absl/synchronization/CMakeFiles/synchronization.dir/internal/stdcpp_waiter.cc.o
2025-03-21T20:32:48.0711439Z [ 67%] Building CXX object runner/abseil-cpp/absl/synchronization/CMakeFiles/synchronization.dir/internal/waiter_base.cc.o
2025-03-21T20:32:48.0712620Z [ 67%] Building CXX object runner/abseil-cpp/absl/synchronization/CMakeFiles/synchronization.dir/internal/win32_waiter.cc.o
2025-03-21T20:32:48.0713833Z [ 67%] Building CXX object runner/abseil-cpp/absl/synchronization/CMakeFiles/synchronization.dir/notification.cc.o
2025-03-21T20:32:48.0714934Z [ 68%] Building CXX object runner/abseil-cpp/absl/synchronization/CMakeFiles/synchronization.dir/mutex.cc.o
2025-03-21T20:32:48.0715748Z [ 68%] Linking CXX static library libabsl_log_internal_format.a
2025-03-21T20:32:48.0716348Z [ 68%] Linking CXX static library libabsl_log_sink.a
2025-03-21T20:32:48.0716747Z [ 68%] Built target log_internal_format
2025-03-21T20:32:48.0717499Z [ 68%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/cord_internal.dir/internal/cord_rep_btree.cc.o
2025-03-21T20:32:48.0718182Z [ 68%] Built target log_sink
2025-03-21T20:32:48.0718939Z [ 69%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/cord_internal.dir/internal/cord_rep_btree_navigator.cc.o
2025-03-21T20:32:48.0720089Z [ 69%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/cord_internal.dir/internal/cord_rep_btree_reader.cc.o
2025-03-21T20:32:48.0721186Z [ 69%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/cord_internal.dir/internal/cord_rep_crc.cc.o
2025-03-21T20:32:48.0722256Z [ 70%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/cord_internal.dir/internal/cord_rep_consume.cc.o
2025-03-21T20:32:48.0723078Z [ 70%] Linking CXX static library libabsl_synchronization.a
2025-03-21T20:32:48.0723507Z [ 70%] Built target synchronization
2025-03-21T20:32:48.0724431Z [ 70%] Building CXX object runner/abseil-cpp/absl/container/CMakeFiles/hashtablez_sampler.dir/internal/hashtablez_sampler_force_weak_definition.cc.o
2025-03-21T20:32:48.0725747Z [ 71%] Building CXX object runner/abseil-cpp/absl/container/CMakeFiles/hashtablez_sampler.dir/internal/hashtablez_sampler.cc.o
2025-03-21T20:32:48.0726987Z [ 71%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/cordz_handle.dir/internal/cordz_handle.cc.o
2025-03-21T20:32:48.0728241Z [ 71%] Building CXX object runner/abseil-cpp/absl/log/CMakeFiles/vlog_config_internal.dir/internal/vlog_config.cc.o
2025-03-21T20:32:48.0729799Z [ 72%] Building CXX object runner/abseil-cpp/absl/flags/CMakeFiles/flags_program_name.dir/internal/program_name.cc.o
2025-03-21T20:32:48.0730911Z [ 72%] Linking CXX static library libabsl_cord_internal.a
2025-03-21T20:32:48.0731585Z [ 72%] Built target cord_internal
2025-03-21T20:32:48.0732074Z [ 72%] Linking CXX static library libabsl_hashtablez_sampler.a
2025-03-21T20:32:48.0733049Z [ 72%] Built target hashtablez_sampler
2025-03-21T20:32:48.0733621Z [ 73%] Linking CXX static library libabsl_vlog_config_internal.a
2025-03-21T20:32:48.0734072Z [ 73%] Built target vlog_config_internal
2025-03-21T20:32:48.0734572Z [ 73%] Linking CXX static library libabsl_flags_program_name.a
2025-03-21T20:32:48.0735306Z [ 74%] Building CXX object runner/abseil-cpp/absl/log/CMakeFiles/log_globals.dir/globals.cc.o
2025-03-21T20:32:48.0735885Z [ 74%] Built target flags_program_name
2025-03-21T20:32:48.0736566Z [ 74%] Building CXX object runner/abseil-cpp/absl/flags/CMakeFiles/flags_config.dir/usage_config.cc.o
2025-03-21T20:32:48.0737302Z [ 74%] Linking CXX static library libabsl_cordz_handle.a
2025-03-21T20:32:48.0737710Z [ 74%] Built target cordz_handle
2025-03-21T20:32:48.0738414Z [ 75%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/cordz_info.dir/internal/cordz_info.cc.o
2025-03-21T20:32:48.0739169Z [ 75%] Linking CXX static library libabsl_flags_config.a
2025-03-21T20:32:48.0739583Z [ 75%] Built target flags_config
2025-03-21T20:32:51.0429245Z [ 76%] Building CXX object runner/abseil-cpp/absl/flags/CMakeFiles/flags_internal.dir/internal/flag.cc.o
2025-03-21T20:32:51.0430080Z [ 76%] Linking CXX static library libabsl_log_globals.a
2025-03-21T20:32:51.0430494Z [ 76%] Built target log_globals
2025-03-21T20:32:51.0431597Z [ 77%] Building CXX object runner/abseil-cpp/absl/log/CMakeFiles/log_internal_log_sink_set.dir/internal/log_sink_set.cc.o
2025-03-21T20:32:51.0432816Z [ 77%] Building CXX object runner/abseil-cpp/absl/log/CMakeFiles/log_initialize.dir/initialize.cc.o
2025-03-21T20:32:51.0433552Z [ 77%] Linking CXX static library libabsl_cordz_info.a
2025-03-21T20:32:51.0434025Z [ 77%] Built target cordz_info
2025-03-21T20:32:51.0434624Z [ 77%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/cord.dir/cord.cc.o
2025-03-21T20:32:51.0435483Z [ 78%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/cord.dir/cord_analysis.cc.o
2025-03-21T20:32:51.0436467Z [ 78%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/cord.dir/cord_buffer.cc.o
2025-03-21T20:32:51.0437504Z [ 78%] Building CXX object runner/abseil-cpp/absl/strings/CMakeFiles/cordz_sample_token.dir/internal/cordz_sample_token.cc.o
2025-03-21T20:32:51.0438360Z [ 78%] Linking CXX static library libabsl_flags_internal.a
2025-03-21T20:32:51.0438769Z [ 78%] Built target flags_internal
2025-03-21T20:32:51.0439282Z [ 78%] Linking CXX static library libabsl_log_internal_log_sink_set.a
2025-03-21T20:32:51.0439758Z [ 78%] Built target log_internal_log_sink_set
2025-03-21T20:32:51.0440257Z [ 79%] Linking CXX static library libabsl_log_initialize.a
2025-03-21T20:32:51.0441098Z [ 79%] Building CXX object runner/abseil-cpp/absl/log/CMakeFiles/log_internal_message.dir/internal/log_message.cc.o
2025-03-21T20:32:51.0441748Z [ 79%] Built target log_initialize
2025-03-21T20:32:51.0442220Z [ 80%] Linking CXX static library libabsl_cordz_sample_token.a
2025-03-21T20:32:51.0442657Z [ 80%] Built target cordz_sample_token
2025-03-21T20:32:51.0443092Z [ 81%] Linking CXX static library libabsl_cord.a
2025-03-21T20:32:51.0443462Z [ 81%] Built target cord
2025-03-21T20:32:51.0444163Z [ 81%] Building CXX object runner/abseil-cpp/absl/container/CMakeFiles/raw_hash_set.dir/internal/raw_hash_set.cc.o
2025-03-21T20:32:51.0445206Z [ 82%] Building CXX object runner/abseil-cpp/absl/status/CMakeFiles/status.dir/internal/status_internal.cc.o
2025-03-21T20:32:51.0446206Z [ 82%] Building CXX object runner/abseil-cpp/absl/status/CMakeFiles/status.dir/status_payload_printer.cc.o
2025-03-21T20:32:51.0447167Z [ 82%] Building CXX object runner/abseil-cpp/absl/status/CMakeFiles/status.dir/status.cc.o
2025-03-21T20:32:51.0447876Z [ 83%] Linking CXX static library libabsl_log_internal_message.a
2025-03-21T20:32:51.0448324Z [ 83%] Built target log_internal_message
2025-03-21T20:32:51.0449074Z [ 83%] Building CXX object runner/abseil-cpp/absl/log/CMakeFiles/log_internal_check_op.dir/internal/check_op.cc.o
2025-03-21T20:32:51.0450140Z [ 83%] Building CXX object runner/abseil-cpp/absl/log/CMakeFiles/die_if_null.dir/die_if_null.cc.o
2025-03-21T20:32:51.0450859Z [ 83%] Linking CXX static library libabsl_raw_hash_set.a
2025-03-21T20:32:51.0451276Z [ 83%] Built target raw_hash_set
2025-03-21T20:32:51.0451701Z [ 84%] Linking CXX static library libabsl_status.a
2025-03-21T20:32:51.0452459Z [ 84%] Building CXX object runner/abseil-cpp/absl/flags/CMakeFiles/flags_reflection.dir/reflection.cc.o
2025-03-21T20:32:51.0453209Z [ 84%] Linking CXX static library libabsl_die_if_null.a
2025-03-21T20:32:51.0453606Z [ 84%] Built target status
2025-03-21T20:32:51.0454072Z [ 84%] Linking CXX static library libabsl_log_internal_check_op.a
2025-03-21T20:32:51.0454822Z [ 84%] Building CXX object runner/abseil-cpp/absl/status/CMakeFiles/statusor.dir/statusor.cc.o
2025-03-21T20:32:51.0455394Z [ 84%] Built target die_if_null
2025-03-21T20:32:51.0455708Z [ 84%] Built target log_internal_check_op
2025-03-21T20:32:51.0456173Z [ 84%] Linking CXX static library libabsl_statusor.a
2025-03-21T20:32:51.0456560Z [ 84%] Built target statusor
2025-03-21T20:32:51.0457153Z [ 85%] Linking CXX static library libabsl_flags_reflection.a
2025-03-21T20:32:51.0457578Z [ 85%] Built target flags_reflection
2025-03-21T20:32:51.0458310Z [ 86%] Building CXX object runner/abseil-cpp/absl/flags/CMakeFiles/flags_usage_internal.dir/internal/usage.cc.o
2025-03-21T20:32:51.0459270Z [ 86%] Building CXX object runner/abseil-cpp/absl/log/CMakeFiles/log_flags.dir/flags.cc.o
2025-03-21T20:32:51.0460036Z [ 86%] Building CXX object runner/re2/CMakeFiles/re2.dir/re2/bitmap256.cc.o
2025-03-21T20:32:51.0460717Z [ 87%] Building CXX object runner/re2/CMakeFiles/re2.dir/re2/compile.cc.o
2025-03-21T20:32:51.0461433Z [ 87%] Building CXX object runner/re2/CMakeFiles/re2.dir/re2/bitstate.cc.o
2025-03-21T20:32:51.0462078Z [ 87%] Building CXX object runner/re2/CMakeFiles/re2.dir/re2/dfa.cc.o
2025-03-21T20:32:51.0462748Z [ 87%] Building CXX object runner/re2/CMakeFiles/re2.dir/re2/mimics_pcre.cc.o
2025-03-21T20:32:51.0463418Z [ 87%] Building CXX object runner/re2/CMakeFiles/re2.dir/re2/nfa.cc.o
2025-03-21T20:32:51.0464104Z [ 88%] Building CXX object runner/re2/CMakeFiles/re2.dir/re2/filtered_re2.cc.o
2025-03-21T20:32:51.0464799Z [ 89%] Building CXX object runner/re2/CMakeFiles/re2.dir/re2/onepass.cc.o
2025-03-21T20:32:51.0465468Z [ 89%] Building CXX object runner/re2/CMakeFiles/re2.dir/re2/parse.cc.o
2025-03-21T20:32:51.0466045Z [ 89%] Linking CXX static library libabsl_log_flags.a
2025-03-21T20:32:51.0466616Z [ 89%] Linking CXX static library libabsl_flags_usage_internal.a
2025-03-21T20:32:51.0467052Z [ 89%] Built target log_flags
2025-03-21T20:32:51.0467577Z [ 90%] Building CXX object runner/re2/CMakeFiles/re2.dir/re2/perl_groups.cc.o
2025-03-21T20:32:51.0468283Z [ 90%] Building CXX object runner/re2/CMakeFiles/re2.dir/re2/prefilter.cc.o
2025-03-21T20:32:51.0468757Z [ 90%] Built target flags_usage_internal
2025-03-21T20:32:51.0469338Z [ 90%] Building CXX object runner/re2/CMakeFiles/re2.dir/re2/prefilter_tree.cc.o
2025-03-21T20:32:51.0470029Z [ 91%] Building CXX object runner/re2/CMakeFiles/re2.dir/re2/prog.cc.o
2025-03-21T20:32:51.0470670Z [ 91%] Building CXX object runner/re2/CMakeFiles/re2.dir/re2/re2.cc.o
2025-03-21T20:32:51.0471316Z [ 91%] Building CXX object runner/re2/CMakeFiles/re2.dir/re2/regexp.cc.o
2025-03-21T20:32:51.0471963Z [ 92%] Building CXX object runner/re2/CMakeFiles/re2.dir/re2/set.cc.o
2025-03-21T20:32:51.0472610Z [ 92%] Building CXX object runner/re2/CMakeFiles/re2.dir/re2/simplify.cc.o
2025-03-21T20:32:51.0473292Z [ 92%] Building CXX object runner/re2/CMakeFiles/re2.dir/re2/tostring.cc.o
2025-03-21T20:32:51.0474010Z [ 93%] Building CXX object runner/re2/CMakeFiles/re2.dir/re2/unicode_casefold.cc.o
2025-03-21T20:32:51.0474763Z [ 93%] Building CXX object runner/re2/CMakeFiles/re2.dir/re2/unicode_groups.cc.o
2025-03-21T20:32:51.0475471Z [ 93%] Building CXX object runner/re2/CMakeFiles/re2.dir/util/rune.cc.o
2025-03-21T20:32:51.0476139Z [ 94%] Building CXX object runner/re2/CMakeFiles/re2.dir/util/strutil.cc.o
2025-03-21T20:32:51.0476925Z [ 94%] Building CXX object runner/abseil-cpp/absl/flags/CMakeFiles/flags_usage.dir/usage.cc.o
2025-03-21T20:32:51.0477583Z [ 94%] Linking CXX static library libre2.a
2025-03-21T20:32:51.0477938Z [ 94%] Built target re2
2025-03-21T20:32:51.0478431Z [ 95%] Building CXX object runner/CMakeFiles/llama_runner.dir/runner.cpp.o
2025-03-21T20:32:51.0479230Z [ 95%] Building CXX object runner/CMakeFiles/llama_runner.dir/__/tokenizer/llama_tiktoken.cpp.o
2025-03-21T20:32:51.0480266Z [ 95%] Building CXX object runner/CMakeFiles/llama_runner.dir/pytorch/executorch/extension/evalue_util/print_evalue.cpp.o
2025-03-21T20:32:51.0481395Z [ 96%] Building CXX object runner/CMakeFiles/llama_runner.dir/pytorch/executorch/extension/llm/sampler/sampler.cpp.o
2025-03-21T20:32:51.0482644Z [ 96%] Building CXX object runner/CMakeFiles/llama_runner.dir/pytorch/executorch/extension/llm/runner/text_decoder_runner.cpp.o
2025-03-21T20:32:51.0483827Z [ 96%] Building CXX object runner/CMakeFiles/llama_runner.dir/pytorch/executorch/extension/llm/runner/text_prefiller.cpp.o
2025-03-21T20:32:51.0485013Z [ 97%] Building CXX object runner/CMakeFiles/llama_runner.dir/pytorch/executorch/extension/llm/tokenizer/tiktoken.cpp.o
2025-03-21T20:32:51.0486240Z [ 97%] Building CXX object runner/CMakeFiles/llama_runner.dir/pytorch/executorch/extension/llm/tokenizers/src/bpe_tokenizer_base.cpp.o
2025-03-21T20:32:51.0487174Z [ 97%] Linking CXX static library libabsl_flags_usage.a
2025-03-21T20:32:51.0487579Z [ 97%] Built target flags_usage
2025-03-21T20:32:51.0488202Z [ 97%] Building CXX object runner/abseil-cpp/absl/flags/CMakeFiles/flags_parse.dir/parse.cc.o
2025-03-21T20:32:51.0489392Z [ 97%] Building CXX object runner/CMakeFiles/llama_runner.dir/pytorch/executorch/extension/llm/tokenizers/src/llama2c_tokenizer.cpp.o
2025-03-21T20:32:51.0490631Z [ 98%] Building CXX object runner/CMakeFiles/llama_runner.dir/pytorch/executorch/extension/llm/tokenizers/src/tiktoken.cpp.o
2025-03-21T20:32:51.0491757Z [ 98%] Building CXX object runner/CMakeFiles/llama_runner.dir/pytorch/executorch/extension/tensor/tensor_ptr.cpp.o
2025-03-21T20:32:51.0492870Z [ 99%] Building CXX object runner/CMakeFiles/llama_runner.dir/pytorch/executorch/extension/tensor/tensor_ptr_maker.cpp.o
2025-03-21T20:32:51.0493704Z [100%] Linking CXX static library libabsl_flags_parse.a
2025-03-21T20:32:51.0494115Z [100%] Built target flags_parse
2025-03-21T20:32:51.0494553Z [100%] Linking CXX shared library libllama_runner.so
2025-03-21T20:32:51.0494937Z [100%] Built target llama_runner
2025-03-21T20:32:51.0495414Z [100%] Building CXX object CMakeFiles/llama_main.dir/main.cpp.o
2025-03-21T20:32:51.0495943Z [100%] Linking CXX executable llama_main
2025-03-21T20:32:51.0496302Z [100%] Built target llama_main
2025-03-21T20:32:51.0496591Z ++ date +%H:%M:%S
2025-03-21T20:32:51.0496816Z + NOW=20:32:50
2025-03-21T20:32:51.0497090Z + echo 'Starting to run llama runner at 20:32:50'
2025-03-21T20:32:51.0497457Z Starting to run llama runner at 20:32:50
2025-03-21T20:32:51.0498293Z + cmake-out/examples/models/llama/llama_main --model_path=tinyllama_qnn_fp32.pte --tokenizer_path=tokenizer.bin --prompt=Once --temperature=0 --seq_len=10 --warmup=1
2025-03-21T20:44:23.8924591Z [INFO] [Qnn ExecuTorch]: Deserializing processed data using QnnContextCustomProtocol
2025-03-21T20:44:23.8925279Z [INFO] [Qnn ExecuTorch]: create QNN Logger with log_level 2
2025-03-21T20:44:23.8925770Z [WARNING] [Qnn ExecuTorch]: QnnDsp <W> Initializing HtpProvider
2025-03-21T20:44:23.8926079Z 
2025-03-21T20:44:23.8926390Z [INFO] [Qnn ExecuTorch]: Initialize Qnn backend parameters for Qnn executorch backend type 2
2025-03-21T20:44:23.8926993Z [INFO] [Qnn ExecuTorch]: Caching: Caching is in RESTORE MODE.
2025-03-21T20:44:23.8927617Z [INFO] [Qnn ExecuTorch]: QnnContextCustomProtocol expected magic number: 0x5678abcd but get: 0x2000000
2025-03-21T20:44:23.8928302Z [WARNING] [Qnn ExecuTorch]: QnnDsp <W> Performance Estimates unsupported
2025-03-21T20:44:23.8928649Z 
2025-03-21T20:44:23.8929089Z [WARNING] [Qnn ExecuTorch]: QnnDsp <W> Arch 68 set by custom config is different from arch associated with SoC 57, will overwrite it to 75
2025-03-21T20:44:23.8929723Z 
2025-03-21T20:44:23.8929882Z [INFO] [Qnn ExecuTorch]: Running level=3 optimization.
2025-03-21T20:44:23.8930356Z invalid char[INFO] [Qnn ExecuTorch]: Destroy Qnn backend parameters
2025-03-21T20:44:23.8930808Z [INFO] [Qnn ExecuTorch]: Destroy Qnn context
2025-03-21T20:44:23.8931155Z [INFO] [Qnn ExecuTorch]: Destroy Qnn device
2025-03-21T20:44:23.8931514Z [INFO] [Qnn ExecuTorch]: Destroy Qnn backend
2025-03-21T20:44:23.8931843Z ++ date +%H:%M:%S
2025-03-21T20:44:23.8932078Z + NOW=20:44:23
2025-03-21T20:44:23.8932921Z + echo 'Finished at 20:44:23'
2025-03-21T20:44:23.8933206Z Finished at 20:44:23
2025-03-21T20:44:23.8933462Z ++ cat result.txt
2025-03-21T20:44:23.8933757Z + RESULT='Once upon a time, there was a little girl
2025-03-21T20:44:23.8935220Z PyTorchObserver {"prompt_tokens":1,"generated_tokens":8,"model_load_start_ms":1742589170898,"model_load_end_ms":1742589171248,"inference_start_ms":1742589533644,"inference_end_ms":1742589863821,"prompt_eval_end_ms":1742589559828,"first_token_ms":1742589559828,"aggregate_sampling_time_ms":0,"SCALING_FACTOR_UNITS_PER_SECOND":1000}'
2025-03-21T20:44:23.8936595Z + EXPECTED_PREFIX='Once upon a time,'
2025-03-21T20:44:23.8937017Z + [[ Once upon a time, there was a little girl
2025-03-21T20:44:23.8938505Z PyTorchObserver {"prompt_tokens":1,"generated_tokens":8,"model_load_start_ms":1742589170898,"model_load_end_ms":1742589171248,"inference_start_ms":1742589533644,"inference_end_ms":1742589863821,"prompt_eval_end_ms":1742589559828,"first_token_ms":1742589559828,"aggregate_sampling_time_ms":0,"SCALING_FACTOR_UNITS_PER_SECOND":1000} == \O\n\c\e\ \u\p\o\n\ \a\ \t\i\m\e\,* ]]
2025-03-21T20:44:23.8940000Z + echo 'Expected result prefix: Once upon a time,'
2025-03-21T20:44:23.8940368Z Expected result prefix: Once upon a time,
2025-03-21T20:44:23.8940789Z + echo 'Actual result: Once upon a time, there was a little girl
2025-03-21T20:44:23.8942206Z PyTorchObserver {"prompt_tokens":1,"generated_tokens":8,"model_load_start_ms":1742589170898,"model_load_end_ms":1742589171248,"inference_start_ms":1742589533644,"inference_end_ms":1742589863821,"prompt_eval_end_ms":1742589559828,"first_token_ms":1742589559828,"aggregate_sampling_time_ms":0,"SCALING_FACTOR_UNITS_PER_SECOND":1000}'
2025-03-21T20:44:23.8943605Z Actual result: Once upon a time, there was a little girl
2025-03-21T20:44:23.8944994Z PyTorchObserver {"prompt_tokens":1,"generated_tokens":8,"model_load_start_ms":1742589170898,"model_load_end_ms":1742589171248,"inference_start_ms":1742589533644,"inference_end_ms":1742589863821,"prompt_eval_end_ms":1742589559828,"first_token_ms":1742589559828,"aggregate_sampling_time_ms":0,"SCALING_FACTOR_UNITS_PER_SECOND":1000}
2025-03-21T20:44:23.8946309Z + echo Success
2025-03-21T20:44:23.8946540Z Success
2025-03-21T20:44:23.8946760Z + prepare_artifacts_upload
2025-03-21T20:44:23.8947043Z + '[' -n '' ']'
2025-03-21T20:44:23.8947284Z + cleanup_files
2025-03-21T20:44:23.8947569Z + echo 'Deleting downloaded and generated files'
2025-03-21T20:44:23.8947944Z Deleting downloaded and generated files
2025-03-21T20:44:23.8948261Z + rm stories110M.pt
2025-03-21T20:44:23.8948517Z + rm tokenizer.model
2025-03-21T20:44:23.8948777Z + rm tokenizer.bin
2025-03-21T20:44:23.8949032Z + rm tinyllama_qnn_fp32.pte
2025-03-21T20:44:23.8949298Z + rm result.txt
2025-03-21T20:44:23.8949538Z + rm params.json
2025-03-21T20:44:23.9028892Z ##[group]Run pmeier/pytest-results-action@v0.3.0
2025-03-21T20:44:23.9029274Z with:
2025-03-21T20:44:23.9029601Z   path: /home/ec2-user/actions-runner/_work/_temp/test-results
2025-03-21T20:44:23.9030020Z   fail-on-empty: false
2025-03-21T20:44:23.9030275Z env:
2025-03-21T20:44:23.9030532Z   DOCKER_IMAGE: executorch-ubuntu-22.04-qnn-sdk
2025-03-21T20:44:23.9030896Z   REPOSITORY: pytorch/executorch
2025-03-21T20:44:23.9031191Z   PR_NUMBER: 
2025-03-21T20:44:23.9034468Z   SCRIPT: # The generic Linux job chooses to use base env, not the one setup by the image
CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
conda activate "${CONDA_ENV}"

DTYPE=fp32
BUILD_TOOL="cmake"
MODE=qnn
PT2E_QUANTIZE=qnn_16a16w

./install_requirements.sh --use-pt-pinned-commit
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh

# Setup executorch
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "${BUILD_TOOL}"
# Install requirements for export_llama
PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
# Test llama2
PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh -model stories110M -build_tool "${BUILD_TOOL}" -mode "${MODE}" -dtype "${DTYPE}" -pt2e_quantize "${PT2E_QUANTIZE}"

2025-03-21T20:44:23.9037781Z   RUNNER_ARTIFACT_DIR: /home/ec2-user/actions-runner/_work/_temp/artifacts
2025-03-21T20:44:23.9038380Z   RUNNER_TEST_RESULTS_DIR: /home/ec2-user/actions-runner/_work/_temp/test-results
2025-03-21T20:44:23.9038934Z   RUNNER_DOCS_DIR: /home/ec2-user/actions-runner/_work/_temp/docs
2025-03-21T20:44:23.9039316Z ##[endgroup]
2025-03-21T20:44:23.9594499Z Prepare all required actions
2025-03-21T20:44:23.9631972Z ##[group]Run ./test-infra/.github/actions/chown-directory
2025-03-21T20:44:23.9632713Z with:
2025-03-21T20:44:23.9633090Z   directory: /home/ec2-user/actions-runner/_work/executorch/executorch/
2025-03-21T20:44:23.9633766Z   ALPINE_IMAGE: 308535385114.dkr.ecr.us-east-1.amazonaws.com/tool/alpine
2025-03-21T20:44:23.9634203Z env:
2025-03-21T20:44:23.9634455Z   DOCKER_IMAGE: executorch-ubuntu-22.04-qnn-sdk
2025-03-21T20:44:23.9634821Z   REPOSITORY: pytorch/executorch
2025-03-21T20:44:23.9635126Z   PR_NUMBER: 
2025-03-21T20:44:23.9638199Z   SCRIPT: # The generic Linux job chooses to use base env, not the one setup by the image
CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
conda activate "${CONDA_ENV}"

DTYPE=fp32
BUILD_TOOL="cmake"
MODE=qnn
PT2E_QUANTIZE=qnn_16a16w

./install_requirements.sh --use-pt-pinned-commit
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh

# Setup executorch
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "${BUILD_TOOL}"
# Install requirements for export_llama
PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
# Test llama2
PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh -model stories110M -build_tool "${BUILD_TOOL}" -mode "${MODE}" -dtype "${DTYPE}" -pt2e_quantize "${PT2E_QUANTIZE}"

2025-03-21T20:44:23.9641426Z   RUNNER_ARTIFACT_DIR: /home/ec2-user/actions-runner/_work/_temp/artifacts
2025-03-21T20:44:23.9642014Z   RUNNER_TEST_RESULTS_DIR: /home/ec2-user/actions-runner/_work/_temp/test-results
2025-03-21T20:44:23.9642571Z   RUNNER_DOCS_DIR: /home/ec2-user/actions-runner/_work/_temp/docs
2025-03-21T20:44:23.9642967Z ##[endgroup]
2025-03-21T20:44:23.9675769Z ##[group]Run docker run --rm -v "${DIRECTORY}":/v -w /v "${ALPINE_IMAGE}" chown -R "$(id -u):$(id -g)" .
2025-03-21T20:44:23.9676491Z docker run --rm -v "${DIRECTORY}":/v -w /v "${ALPINE_IMAGE}" chown -R "$(id -u):$(id -g)" .
2025-03-21T20:44:23.9685285Z shell: /usr/bin/bash --noprofile --norc -e -o pipefail {0}
2025-03-21T20:44:23.9685676Z env:
2025-03-21T20:44:23.9685948Z   DOCKER_IMAGE: executorch-ubuntu-22.04-qnn-sdk
2025-03-21T20:44:23.9686332Z   REPOSITORY: pytorch/executorch
2025-03-21T20:44:23.9686628Z   PR_NUMBER: 
2025-03-21T20:44:23.9689767Z   SCRIPT: # The generic Linux job chooses to use base env, not the one setup by the image
CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
conda activate "${CONDA_ENV}"

DTYPE=fp32
BUILD_TOOL="cmake"
MODE=qnn
PT2E_QUANTIZE=qnn_16a16w

./install_requirements.sh --use-pt-pinned-commit
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh

# Setup executorch
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "${BUILD_TOOL}"
# Install requirements for export_llama
PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
# Test llama2
PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh -model stories110M -build_tool "${BUILD_TOOL}" -mode "${MODE}" -dtype "${DTYPE}" -pt2e_quantize "${PT2E_QUANTIZE}"

2025-03-21T20:44:23.9692991Z   RUNNER_ARTIFACT_DIR: /home/ec2-user/actions-runner/_work/_temp/artifacts
2025-03-21T20:44:23.9693586Z   RUNNER_TEST_RESULTS_DIR: /home/ec2-user/actions-runner/_work/_temp/test-results
2025-03-21T20:44:23.9694142Z   RUNNER_DOCS_DIR: /home/ec2-user/actions-runner/_work/_temp/docs
2025-03-21T20:44:23.9694670Z   ALPINE_IMAGE: 308535385114.dkr.ecr.us-east-1.amazonaws.com/tool/alpine
2025-03-21T20:44:23.9695327Z   DIRECTORY: /home/ec2-user/actions-runner/_work/executorch/executorch/
2025-03-21T20:44:23.9695764Z ##[endgroup]
2025-03-21T20:44:24.0011446Z Unable to find image '308535385114.dkr.ecr.us-east-1.amazonaws.com/tool/alpine:latest' locally
2025-03-21T20:44:24.2438494Z latest: Pulling from tool/alpine
2025-03-21T20:44:24.2438924Z 540db60ca938: Pulling fs layer
2025-03-21T20:44:24.3397060Z 540db60ca938: Download complete
2025-03-21T20:44:24.4183256Z 540db60ca938: Pull complete
2025-03-21T20:44:24.4287976Z Digest: sha256:def822f9851ca422481ec6fee59a9966f12b351c62ccb9aca841526ffaa9f748
2025-03-21T20:44:24.4327543Z Status: Downloaded newer image for 308535385114.dkr.ecr.us-east-1.amazonaws.com/tool/alpine:latest
2025-03-21T20:44:25.7860427Z Prepare all required actions
2025-03-21T20:44:25.7886724Z ##[group]Run ./test-infra/.github/actions/chown-directory
2025-03-21T20:44:25.7887100Z with:
2025-03-21T20:44:25.7887392Z   directory: /home/ec2-user/actions-runner/_work/_temp
2025-03-21T20:44:25.7887886Z   ALPINE_IMAGE: 308535385114.dkr.ecr.us-east-1.amazonaws.com/tool/alpine
2025-03-21T20:44:25.7888312Z env:
2025-03-21T20:44:25.7888577Z   DOCKER_IMAGE: executorch-ubuntu-22.04-qnn-sdk
2025-03-21T20:44:25.7888945Z   REPOSITORY: pytorch/executorch
2025-03-21T20:44:25.7889340Z   PR_NUMBER: 
2025-03-21T20:44:25.7892406Z   SCRIPT: # The generic Linux job chooses to use base env, not the one setup by the image
CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
conda activate "${CONDA_ENV}"

DTYPE=fp32
BUILD_TOOL="cmake"
MODE=qnn
PT2E_QUANTIZE=qnn_16a16w

./install_requirements.sh --use-pt-pinned-commit
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh

# Setup executorch
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "${BUILD_TOOL}"
# Install requirements for export_llama
PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
# Test llama2
PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh -model stories110M -build_tool "${BUILD_TOOL}" -mode "${MODE}" -dtype "${DTYPE}" -pt2e_quantize "${PT2E_QUANTIZE}"

2025-03-21T20:44:25.7895631Z   RUNNER_ARTIFACT_DIR: /home/ec2-user/actions-runner/_work/_temp/artifacts
2025-03-21T20:44:25.7896226Z   RUNNER_TEST_RESULTS_DIR: /home/ec2-user/actions-runner/_work/_temp/test-results
2025-03-21T20:44:25.7896783Z   RUNNER_DOCS_DIR: /home/ec2-user/actions-runner/_work/_temp/docs
2025-03-21T20:44:25.7897180Z ##[endgroup]
2025-03-21T20:44:25.7915361Z ##[group]Run docker run --rm -v "${DIRECTORY}":/v -w /v "${ALPINE_IMAGE}" chown -R "$(id -u):$(id -g)" .
2025-03-21T20:44:25.7916081Z docker run --rm -v "${DIRECTORY}":/v -w /v "${ALPINE_IMAGE}" chown -R "$(id -u):$(id -g)" .
2025-03-21T20:44:25.7922476Z shell: /usr/bin/bash --noprofile --norc -e -o pipefail {0}
2025-03-21T20:44:25.7922862Z env:
2025-03-21T20:44:25.7923134Z   DOCKER_IMAGE: executorch-ubuntu-22.04-qnn-sdk
2025-03-21T20:44:25.7923510Z   REPOSITORY: pytorch/executorch
2025-03-21T20:44:25.7923810Z   PR_NUMBER: 
2025-03-21T20:44:25.7926848Z   SCRIPT: # The generic Linux job chooses to use base env, not the one setup by the image
CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
conda activate "${CONDA_ENV}"

DTYPE=fp32
BUILD_TOOL="cmake"
MODE=qnn
PT2E_QUANTIZE=qnn_16a16w

./install_requirements.sh --use-pt-pinned-commit
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh

# Setup executorch
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "${BUILD_TOOL}"
# Install requirements for export_llama
PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
# Test llama2
PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh -model stories110M -build_tool "${BUILD_TOOL}" -mode "${MODE}" -dtype "${DTYPE}" -pt2e_quantize "${PT2E_QUANTIZE}"

2025-03-21T20:44:25.7930175Z   RUNNER_ARTIFACT_DIR: /home/ec2-user/actions-runner/_work/_temp/artifacts
2025-03-21T20:44:25.7930775Z   RUNNER_TEST_RESULTS_DIR: /home/ec2-user/actions-runner/_work/_temp/test-results
2025-03-21T20:44:25.7931434Z   RUNNER_DOCS_DIR: /home/ec2-user/actions-runner/_work/_temp/docs
2025-03-21T20:44:25.7931970Z   ALPINE_IMAGE: 308535385114.dkr.ecr.us-east-1.amazonaws.com/tool/alpine
2025-03-21T20:44:25.7932687Z   DIRECTORY: /home/ec2-user/actions-runner/_work/_temp
2025-03-21T20:44:25.7933059Z ##[endgroup]
2025-03-21T20:44:26.6469726Z ##[group]Run # Only do these steps if we actually want to upload an artifact
2025-03-21T20:44:26.6470348Z # Only do these steps if we actually want to upload an artifact
2025-03-21T20:44:26.6470813Z if [[ -n "${UPLOAD_ARTIFACT_NAME}" ]]; then
2025-03-21T20:44:26.6471434Z   # If the default execution path is followed then we should get a wheel in the dist/ folder
2025-03-21T20:44:26.6472056Z   # attempt to just grab whatever is in there and scoop it all up
2025-03-21T20:44:26.6472561Z   if find "dist/" -name "*.whl" >/dev/null 2>/dev/null; then
2025-03-21T20:44:26.6473018Z     mv -v dist/*.whl "${RUNNER_ARTIFACT_DIR}/"
2025-03-21T20:44:26.6473371Z   fi
2025-03-21T20:44:26.6473666Z   if [[ -d "artifacts-to-be-uploaded" ]]; then
2025-03-21T20:44:26.6474123Z     mv -v artifacts-to-be-uploaded/* "${RUNNER_ARTIFACT_DIR}/"
2025-03-21T20:44:26.6474531Z   fi
2025-03-21T20:44:26.6474806Z fi
2025-03-21T20:44:26.6475033Z 
2025-03-21T20:44:26.6475253Z upload_docs=0
2025-03-21T20:44:26.6475677Z # Check if there are files in the documentation folder to upload, note that
2025-03-21T20:44:26.6476152Z # empty folders do not count
2025-03-21T20:44:26.6476623Z if find "${RUNNER_DOCS_DIR}" -mindepth 1 -maxdepth 1 -type f | read -r; then
2025-03-21T20:44:26.6477232Z   # TODO: Add a check here to test if on ec2 because if we're not on ec2 then this
2025-03-21T20:44:26.6477738Z   # upload will probably not work correctly
2025-03-21T20:44:26.6478092Z   upload_docs=1
2025-03-21T20:44:26.6478360Z fi
2025-03-21T20:44:26.6478687Z echo "upload-docs=${upload_docs}" >> "${GITHUB_OUTPUT}"
2025-03-21T20:44:26.6485568Z shell: /usr/bin/bash -e {0}
2025-03-21T20:44:26.6485861Z env:
2025-03-21T20:44:26.6486127Z   DOCKER_IMAGE: executorch-ubuntu-22.04-qnn-sdk
2025-03-21T20:44:26.6486512Z   REPOSITORY: pytorch/executorch
2025-03-21T20:44:26.6486808Z   PR_NUMBER: 
2025-03-21T20:44:26.6489947Z   SCRIPT: # The generic Linux job chooses to use base env, not the one setup by the image
CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
conda activate "${CONDA_ENV}"

DTYPE=fp32
BUILD_TOOL="cmake"
MODE=qnn
PT2E_QUANTIZE=qnn_16a16w

./install_requirements.sh --use-pt-pinned-commit
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh

# Setup executorch
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "${BUILD_TOOL}"
# Install requirements for export_llama
PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
# Test llama2
PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh -model stories110M -build_tool "${BUILD_TOOL}" -mode "${MODE}" -dtype "${DTYPE}" -pt2e_quantize "${PT2E_QUANTIZE}"

2025-03-21T20:44:26.6493191Z   RUNNER_ARTIFACT_DIR: /home/ec2-user/actions-runner/_work/_temp/artifacts
2025-03-21T20:44:26.6493792Z   RUNNER_TEST_RESULTS_DIR: /home/ec2-user/actions-runner/_work/_temp/test-results
2025-03-21T20:44:26.6494347Z   RUNNER_DOCS_DIR: /home/ec2-user/actions-runner/_work/_temp/docs
2025-03-21T20:44:26.6494755Z   UPLOAD_ARTIFACT_NAME: 
2025-03-21T20:44:26.6495026Z ##[endgroup]
2025-03-21T20:44:26.6650654Z Prepare all required actions
2025-03-21T20:44:26.6700781Z ##[group]Run ./test-infra/.github/actions/teardown-linux
2025-03-21T20:44:26.6701420Z with:
2025-03-21T20:44:26.6701770Z env:
2025-03-21T20:44:26.6702219Z   DOCKER_IMAGE: executorch-ubuntu-22.04-qnn-sdk
2025-03-21T20:44:26.6702842Z   REPOSITORY: pytorch/executorch
2025-03-21T20:44:26.6703495Z   PR_NUMBER: 
2025-03-21T20:44:26.6709061Z   SCRIPT: # The generic Linux job chooses to use base env, not the one setup by the image
CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
conda activate "${CONDA_ENV}"

DTYPE=fp32
BUILD_TOOL="cmake"
MODE=qnn
PT2E_QUANTIZE=qnn_16a16w

./install_requirements.sh --use-pt-pinned-commit
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh

# Setup executorch
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "${BUILD_TOOL}"
# Install requirements for export_llama
PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
# Test llama2
PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh -model stories110M -build_tool "${BUILD_TOOL}" -mode "${MODE}" -dtype "${DTYPE}" -pt2e_quantize "${PT2E_QUANTIZE}"

2025-03-21T20:44:26.6715299Z   RUNNER_ARTIFACT_DIR: /home/ec2-user/actions-runner/_work/_temp/artifacts
2025-03-21T20:44:26.6716364Z   RUNNER_TEST_RESULTS_DIR: /home/ec2-user/actions-runner/_work/_temp/test-results
2025-03-21T20:44:26.6717261Z   RUNNER_DOCS_DIR: /home/ec2-user/actions-runner/_work/_temp/docs
2025-03-21T20:44:26.6717900Z ##[endgroup]
2025-03-21T20:44:26.6747234Z ##[group]Run set -eou pipefail
2025-03-21T20:44:26.6747745Z set -eou pipefail
2025-03-21T20:44:26.6748180Z 
2025-03-21T20:44:26.6748797Z echo "Holding runner for 2 hours until all ssh sessions have logged out"
2025-03-21T20:44:26.6749558Z for _ in $(seq 1440); do
2025-03-21T20:44:26.6750117Z     # Break if no ssh session exists anymore
2025-03-21T20:44:26.6750751Z     if [ "$(who)" = "" ]; then
2025-03-21T20:44:26.6751243Z       break
2025-03-21T20:44:26.6751658Z     fi
2025-03-21T20:44:26.6752052Z     echo "."
2025-03-21T20:44:26.6752477Z     sleep 5
2025-03-21T20:44:26.6752876Z done
2025-03-21T20:44:26.6760550Z shell: /usr/bin/bash --noprofile --norc -e -o pipefail {0}
2025-03-21T20:44:26.6761221Z env:
2025-03-21T20:44:26.6761674Z   DOCKER_IMAGE: executorch-ubuntu-22.04-qnn-sdk
2025-03-21T20:44:26.6762303Z   REPOSITORY: pytorch/executorch
2025-03-21T20:44:26.6762791Z   PR_NUMBER: 
2025-03-21T20:44:26.6768274Z   SCRIPT: # The generic Linux job chooses to use base env, not the one setup by the image
CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
conda activate "${CONDA_ENV}"

DTYPE=fp32
BUILD_TOOL="cmake"
MODE=qnn
PT2E_QUANTIZE=qnn_16a16w

./install_requirements.sh --use-pt-pinned-commit
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh

# Setup executorch
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "${BUILD_TOOL}"
# Install requirements for export_llama
PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
# Test llama2
PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh -model stories110M -build_tool "${BUILD_TOOL}" -mode "${MODE}" -dtype "${DTYPE}" -pt2e_quantize "${PT2E_QUANTIZE}"

2025-03-21T20:44:26.6774333Z   RUNNER_ARTIFACT_DIR: /home/ec2-user/actions-runner/_work/_temp/artifacts
2025-03-21T20:44:26.6775318Z   RUNNER_TEST_RESULTS_DIR: /home/ec2-user/actions-runner/_work/_temp/test-results
2025-03-21T20:44:26.6776241Z   RUNNER_DOCS_DIR: /home/ec2-user/actions-runner/_work/_temp/docs
2025-03-21T20:44:26.6776911Z ##[endgroup]
2025-03-21T20:44:26.6804354Z Holding runner for 2 hours until all ssh sessions have logged out
2025-03-21T20:44:26.6880453Z ##[group]Run # ignore expansion of "docker ps -q" since it could be empty
2025-03-21T20:44:26.6881164Z # ignore expansion of "docker ps -q" since it could be empty
2025-03-21T20:44:26.6881609Z # shellcheck disable=SC2046
2025-03-21T20:44:26.6881957Z docker stop $(docker ps -q) || true
2025-03-21T20:44:26.6882328Z # Prune all of the docker images
2025-03-21T20:44:26.6882686Z docker system prune -af
2025-03-21T20:44:26.6887733Z shell: /usr/bin/bash --noprofile --norc -e -o pipefail {0}
2025-03-21T20:44:26.6888119Z env:
2025-03-21T20:44:26.6888397Z   DOCKER_IMAGE: executorch-ubuntu-22.04-qnn-sdk
2025-03-21T20:44:26.6888773Z   REPOSITORY: pytorch/executorch
2025-03-21T20:44:26.6889079Z   PR_NUMBER: 
2025-03-21T20:44:26.6892225Z   SCRIPT: # The generic Linux job chooses to use base env, not the one setup by the image
CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
conda activate "${CONDA_ENV}"

DTYPE=fp32
BUILD_TOOL="cmake"
MODE=qnn
PT2E_QUANTIZE=qnn_16a16w

./install_requirements.sh --use-pt-pinned-commit
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh

# Setup executorch
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "${BUILD_TOOL}"
# Install requirements for export_llama
PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
# Test llama2
PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh -model stories110M -build_tool "${BUILD_TOOL}" -mode "${MODE}" -dtype "${DTYPE}" -pt2e_quantize "${PT2E_QUANTIZE}"

2025-03-21T20:44:26.6895570Z   RUNNER_ARTIFACT_DIR: /home/ec2-user/actions-runner/_work/_temp/artifacts
2025-03-21T20:44:26.6896166Z   RUNNER_TEST_RESULTS_DIR: /home/ec2-user/actions-runner/_work/_temp/test-results
2025-03-21T20:44:26.6896721Z   RUNNER_DOCS_DIR: /home/ec2-user/actions-runner/_work/_temp/docs
2025-03-21T20:44:26.6897115Z ##[endgroup]
2025-03-21T20:44:37.4510138Z e4535af01bce
2025-03-21T20:44:38.2457424Z Deleted Containers:
2025-03-21T20:44:38.2457990Z e4535af01bcec20a70eace7fee6b4cd457f84d9eb152ff3bc4c2d5a7ab85cc60
2025-03-21T20:44:38.2458425Z 
2025-03-21T20:44:40.9219898Z Deleted Images:
2025-03-21T20:44:40.9220842Z untagged: 308535385114.dkr.ecr.us-east-1.amazonaws.com/executorch/executorch-ubuntu-22.04-qnn-sdk:2abd9b1bd42f655b7d130222db4a0cdbc04da8a4
2025-03-21T20:44:40.9222194Z untagged: 308535385114.dkr.ecr.us-east-1.amazonaws.com/executorch/executorch-ubuntu-22.04-qnn-sdk@sha256:d38559c98aeb82552e009bbb7b17d76adfa19c8f3fb874ea99a5e76d87757f76
2025-03-21T20:44:40.9223865Z deleted: sha256:a30343f4b72f0dce49d6d4823ed055cd99145a3bc06228740f811eb1decc1863
2025-03-21T20:44:40.9224608Z deleted: sha256:dcbb28d0046263c2430b67be3aa47d5eeae988406651c479166a85d1f2dc5352
2025-03-21T20:44:40.9225280Z deleted: sha256:9eb84eff28220b78ca23a97d30406ba503bed179b002ea84bf7374f638729e3d
2025-03-21T20:44:40.9225939Z deleted: sha256:1e08d848f7a107eb88f5b1a9b4514efc7f1c8dcd0851dd1522bf5910c9a64b6e
2025-03-21T20:44:40.9226570Z deleted: sha256:338177c78bc0a768d9773592fdf8b7b0698a67566a991a8b485100213ca9fbc4
2025-03-21T20:44:40.9227221Z deleted: sha256:1735d6e22433f10e5a460ac53455294f66b52df308d6b6be04dd20bba3bc489b
2025-03-21T20:44:40.9227963Z deleted: sha256:e916ccba91a2ab63063cc7db425ff08ff4285196cf9b87316350e73b07ee4a38
2025-03-21T20:44:40.9228618Z deleted: sha256:50076809f40f30d632e24ddc5aed1a5bd9a9865dd2866c1ab23c86bf633e7962
2025-03-21T20:44:40.9229276Z deleted: sha256:f9be2a6a76147aff49d05a4ea9ab782cc03d178fcdc373fd1823e47d21271049
2025-03-21T20:44:40.9229953Z deleted: sha256:bcff32a2d3890e40a7d4fbff9b5e94b9990921f0d31050cc14aed0fbce2bdabc
2025-03-21T20:44:40.9230598Z deleted: sha256:d109d4f8538bf72481f92b4c500c92c077bca0bc829e607b2641e0012f982281
2025-03-21T20:44:40.9231256Z deleted: sha256:5a0315aad41e328783b21378a977b58eeafc0b12176c2a92ce6261d80cdb9f8a
2025-03-21T20:44:40.9231897Z deleted: sha256:953c2404ccf647ae6e90833a37a6d33d737a6db8d7654ba8673e7b27869c69d6
2025-03-21T20:44:40.9232742Z deleted: sha256:e3927df9fd6d09d5eec7a59563f028e532d8a8c26857d96d10c4ddb6d653d53c
2025-03-21T20:44:40.9233714Z deleted: sha256:6bf53b8ff77bb357c14b6f6bed501f1faaff14318f94a6c4266d4d490a3085d9
2025-03-21T20:44:40.9234376Z deleted: sha256:e35d013dc9b6638d165d3f99a5c52f826f791f536f8f6242b265fbc67198c58f
2025-03-21T20:44:40.9235018Z deleted: sha256:9056d4457c2cf08797efc71f8cd27c48415253e4b8f43b5f5229881a048ae27a
2025-03-21T20:44:40.9235669Z deleted: sha256:11466fda95e0deac6f947a330c64148f8b0901ed5a5aafacb4beff8f8a3eee77
2025-03-21T20:44:40.9236400Z deleted: sha256:af1d6fff7fd2699d5467ebd83e5684a43ec168b096cff174e142bb765c8aabed
2025-03-21T20:44:40.9237116Z deleted: sha256:d19e5d441e9eb9eb6a2f7e2087900b02fe702f38a119aa24f8302fbf0c6d21c0
2025-03-21T20:44:40.9237770Z deleted: sha256:2eedf60c8f92b92c908ecdb9ab484b4fafbd3e58496f78811a34b47b64563a6b
2025-03-21T20:44:40.9238551Z deleted: sha256:a9978fc0edbcd2becaca7b1bc439a65f8d08deb93a495259e35e44b80aa1fbbe
2025-03-21T20:44:40.9239284Z deleted: sha256:aca89b930d690a03dce5a887ffaba51a668ebfc78e187c476b2ef4d0fd155f42
2025-03-21T20:44:40.9239948Z deleted: sha256:0e562d3843f56b21d2a87df5932a674a1c3da44b539183db41db607ee862817c
2025-03-21T20:44:40.9240694Z deleted: sha256:5bb4fc3398f4c242cdf92cd40e1381d1ff68b7167fc08d3d889ce557e50631d0
2025-03-21T20:44:40.9241340Z deleted: sha256:27624496153d316bfdc2939bf156e557c1513ecf739d17b1e5d3a750d68951b8
2025-03-21T20:44:40.9241967Z deleted: sha256:06d9bc783b214f17c850d3800e14a626f030ed2e0bdbecba98bf84129643b204
2025-03-21T20:44:40.9242626Z deleted: sha256:b4c64f2492fcc5ffd8ecb88e3dc75478d137ed1c9b2f629b94ce38ce3a5da7b8
2025-03-21T20:44:40.9243281Z deleted: sha256:39f0c825984bef7310d3c956fa942850179360a59ef4db07a36b1379624fff28
2025-03-21T20:44:40.9243919Z deleted: sha256:8309096811fc40ec15e13afb5f2a7bd53ba41cdfb537065276e069a989fe0224
2025-03-21T20:44:40.9244573Z deleted: sha256:5dff339fb9ea5cfce15eaa54001cae3192a999789f66f4b950961082706b004b
2025-03-21T20:44:40.9245298Z deleted: sha256:21f790bc6db4d962af416145b9dba556aaff3c063b5c0f6cc14d14b053296c3c
2025-03-21T20:44:40.9245936Z deleted: sha256:56efc65dc265db39000751855e04b0ca0e56235bdfd19e74c9831a26e9548135
2025-03-21T20:44:40.9246583Z deleted: sha256:30b5876aa699f37563aa1e3f719d1e7866d1496062d1583c55ab4c59038ac044
2025-03-21T20:44:40.9247227Z deleted: sha256:8a672d95f0bde22559bbc58ae56f509b8c988c5af6e6fcd3442a6478126ad730
2025-03-21T20:44:40.9247878Z deleted: sha256:4fe3e21828f67217155c5bf58ec5ce3d6f6e39648b9ee84cd1f7492f8773a235
2025-03-21T20:44:40.9248517Z deleted: sha256:270a1170e7e398434ff1b31e17e233f7d7b71aa99a40473615860068e86720af
2025-03-21T20:44:40.9249141Z untagged: 308535385114.dkr.ecr.us-east-1.amazonaws.com/tool/alpine:latest
2025-03-21T20:44:40.9250089Z untagged: 308535385114.dkr.ecr.us-east-1.amazonaws.com/tool/alpine@sha256:def822f9851ca422481ec6fee59a9966f12b351c62ccb9aca841526ffaa9f748
2025-03-21T20:44:40.9250982Z deleted: sha256:6dbb9cc54074106d46d4ccb330f2a40a682d49dda5f4844962b7dce9fe44aaec
2025-03-21T20:44:40.9251656Z deleted: sha256:b2d5eeeaba3a22b9b8aa97261957974a6bd65274ebd43e1d81d0a7b8b752b116
2025-03-21T20:44:40.9252059Z 
2025-03-21T20:44:40.9262842Z Total reclaimed space: 18.35GB
2025-03-21T20:44:40.9311640Z ##[group]Run set +e
2025-03-21T20:44:40.9312073Z set +e
2025-03-21T20:44:40.9312442Z if [[ "${NO_SUDO}" == "false" ]]; then
2025-03-21T20:44:40.9313023Z   sudo rm -rf "${GITHUB_WORKSPACE:?}/${REPOSITORY:?}"
2025-03-21T20:44:40.9313457Z else
2025-03-21T20:44:40.9313821Z   rm -rf "${GITHUB_WORKSPACE:?}/${REPOSITORY:?}"
2025-03-21T20:44:40.9314313Z fi
2025-03-21T20:44:40.9314638Z set -e
2025-03-21T20:44:40.9320832Z shell: /usr/bin/bash -e {0}
2025-03-21T20:44:40.9321214Z env:
2025-03-21T20:44:40.9321563Z   DOCKER_IMAGE: executorch-ubuntu-22.04-qnn-sdk
2025-03-21T20:44:40.9322050Z   REPOSITORY: pytorch/executorch
2025-03-21T20:44:40.9322476Z   PR_NUMBER: 
2025-03-21T20:44:40.9325738Z   SCRIPT: # The generic Linux job chooses to use base env, not the one setup by the image
CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
conda activate "${CONDA_ENV}"

DTYPE=fp32
BUILD_TOOL="cmake"
MODE=qnn
PT2E_QUANTIZE=qnn_16a16w

./install_requirements.sh --use-pt-pinned-commit
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh

# Setup executorch
PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "${BUILD_TOOL}"
# Install requirements for export_llama
PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
# Test llama2
PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh -model stories110M -build_tool "${BUILD_TOOL}" -mode "${MODE}" -dtype "${DTYPE}" -pt2e_quantize "${PT2E_QUANTIZE}"

2025-03-21T20:44:40.9329112Z   RUNNER_ARTIFACT_DIR: /home/ec2-user/actions-runner/_work/_temp/artifacts
2025-03-21T20:44:40.9329940Z   RUNNER_TEST_RESULTS_DIR: /home/ec2-user/actions-runner/_work/_temp/test-results
2025-03-21T20:44:40.9330592Z   RUNNER_DOCS_DIR: /home/ec2-user/actions-runner/_work/_temp/docs
2025-03-21T20:44:40.9331055Z   NO_SUDO: false
2025-03-21T20:44:40.9331439Z ##[endgroup]
2025-03-21T20:44:42.2255065Z Post job cleanup.
2025-03-21T20:44:42.3251362Z Post job cleanup.
2025-03-21T20:44:42.4172607Z [command]/usr/bin/git version
2025-03-21T20:44:42.4229474Z git version 2.47.1
2025-03-21T20:44:42.4269176Z Temporarily overriding HOME='/home/ec2-user/actions-runner/_work/_temp/dbf76e65-469e-4521-bbf0-91d473269fa0' before making global git config changes
2025-03-21T20:44:42.4270128Z Adding repository directory to the temporary git global config as a safe directory
2025-03-21T20:44:42.4273787Z [command]/usr/bin/git config --global --add safe.directory /home/ec2-user/actions-runner/_work/executorch/executorch/test-infra
2025-03-21T20:44:42.4302286Z [command]/usr/bin/git config --local --name-only --get-regexp core\.sshCommand
2025-03-21T20:44:42.4336455Z [command]/usr/bin/git submodule foreach --recursive sh -c "git config --local --name-only --get-regexp 'core\.sshCommand' && git config --local --unset-all 'core.sshCommand' || :"
2025-03-21T20:44:42.4608993Z [command]/usr/bin/git config --local --name-only --get-regexp http\.https\:\/\/github\.com\/\.extraheader
2025-03-21T20:44:42.4625294Z http.https://github.com/.extraheader
2025-03-21T20:44:42.4634152Z [command]/usr/bin/git config --local --unset-all http.https://github.com/.extraheader
2025-03-21T20:44:42.4658524Z [command]/usr/bin/git submodule foreach --recursive sh -c "git config --local --name-only --get-regexp 'http\.https\:\/\/github\.com\/\.extraheader' && git config --local --unset-all 'http.https://github.com/.extraheader' || :"
2025-03-21T20:44:42.4958001Z A job completed hook has been configured by the self-hosted runner administrator
2025-03-21T20:44:42.4983056Z ##[group]Run '/home/ec2-user/runner-scripts/after_job.sh'
2025-03-21T20:44:42.4988187Z shell: /usr/bin/bash --noprofile --norc -e -o pipefail {0}
2025-03-21T20:44:42.4988588Z ##[endgroup]
2025-03-21T20:44:48.0121740Z Cleaning up orphan processes