Add llama jobs on Arm64 and reduce llama jobs on MacOS #9251
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -283,18 +283,72 @@ jobs: | |
| # Test ANE llama | ||
| ${CONDA_RUN} sh .ci/scripts/test_ane_static_llama.sh | ||
|
|
||
| test-llama-runner-linux: | ||
| # Test Both linux x86 and linux aarch64 | ||
| name: test-llama-runner-linux | ||
| uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main | ||
| permissions: | ||
| id-token: write | ||
| contents: read | ||
| strategy: | ||
| matrix: | ||
| dtype: [fp32] | ||
| mode: [portable, xnnpack+custom] | ||
|
There was a problem hiding this comment. @jackzhxng here |
||
| runner: [linux.2xlarge, linux.arm64.2xlarge] | ||
| docker-image: [executorch-ubuntu-22.04-clang12, executorch-ubuntu-22.04-gcc11-aarch64] | ||
| include: | ||
| - dtype: bf16 | ||
| mode: portable | ||
| runner: linux.2xlarge | ||
| docker-image: executorch-ubuntu-22.04-clang12 | ||
| - dtype: bf16 | ||
| mode: portable | ||
| runner: linux.arm64.2xlarge | ||
| docker-image: executorch-ubuntu-22.04-gcc11-aarch64 | ||
| - dtype: bf16 | ||
| mode: custom | ||
| runner: linux.arm64.2xlarge | ||
| docker-image: executorch-ubuntu-22.04-gcc11-aarch64 | ||
| # Excluding specific runner + docker image combinations that don't make sense: | ||
| # - Excluding the ARM64 gcc image on the x86 runner (linux.2xlarge) | ||
| # - Excluding the x86 clang image on the ARM64 runner (linux.arm64.2xlarge) | ||
| exclude: | ||
| - runner: linux.2xlarge | ||
| docker-image: executorch-ubuntu-22.04-gcc11-aarch64 | ||
| - runner: linux.arm64.2xlarge | ||
| docker-image: executorch-ubuntu-22.04-clang12 | ||
| fail-fast: false | ||
| with: | ||
| runner: ${{ matrix.runner }} | ||
| docker-image: ${{ matrix.docker-image }} | ||
| submodules: 'true' | ||
| ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }} | ||
| timeout: 900 | ||
| script: | | ||
| # The generic Linux job chooses to use base env, not the one setup by the image | ||
| CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]") | ||
| conda activate "${CONDA_ENV}" | ||
|
|
||
| DTYPE=${{ matrix.dtype }} | ||
| BUILD_TOOL="cmake" | ||
| MODE=${{ matrix.mode }} | ||
| ARTIFACTS_DIR_NAME="artifacts-to-be-uploaded/${DTYPE}-${MODE}" | ||
| ARTIFACTS_DIR_NAME="${ARTIFACTS_DIR_NAME/+/-}" | ||
|
|
||
| # Setup executorch | ||
| PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "${BUILD_TOOL}" | ||
| # Install requirements for export_llama | ||
| PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh | ||
| # Test llama2 | ||
| PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh -model stories110M -build_tool "${BUILD_TOOL}" -dtype "${DTYPE}" -mode "${MODE}" -upload "${ARTIFACTS_DIR_NAME}" | ||
|
|
||
| test-llama-runner-macos: | ||
| name: test-llama-runner-mac | ||
| uses: pytorch/test-infra/.github/workflows/macos_job.yml@main | ||
| strategy: | ||
| matrix: | ||
| dtype: [fp32] | ||
| mode: [mps, coreml, xnnpack+custom+quantize_kv] | ||
|
There was a problem hiding this comment. What about There was a problem hiding this comment. basically, i'm reducing the test coverage on iOS, and relying on Arm64 runners There was a problem hiding this comment. And it is tested on the pull job |
||
| fail-fast: false | ||
| with: | ||
| runner: macos-m1-stable | ||
|
|
||
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Wouldn't it be useful to test portable?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
It is part of the trunk job now