[Misc] Support quantization of MllamaForCausalLM (#8822) #58
Workflow file for this run
This file contains 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 workflow will upload a Python Package to Release asset | |
| # For more information see: https://help.github.com/en/actions/language-and-framework-guides/using-python-with-github-actions | |
| name: Create Release | |
| on: | |
| push: | |
| tags: | |
| - v* | |
| # Needed to create release and upload assets | |
| permissions: | |
| contents: write | |
| jobs: | |
| release: | |
| # Retrieve tag and create release | |
| name: Create Release | |
| runs-on: ubuntu-latest | |
| outputs: | |
| upload_url: ${{ steps.create_release.outputs.upload_url }} | |
| steps: | |
| - name: Checkout | |
| uses: actions/checkout@v3 | |
| - name: Extract branch info | |
| shell: bash | |
| run: | | |
| echo "release_tag=${GITHUB_REF#refs/*/}" >> $GITHUB_ENV | |
| - name: Create Release | |
| id: create_release | |
| uses: "actions/github-script@v6" | |
| env: | |
| RELEASE_TAG: ${{ env.release_tag }} | |
| with: | |
| github-token: "${{ secrets.GITHUB_TOKEN }}" | |
| script: | | |
| const script = require('.github/workflows/scripts/create_release.js') | |
| await script(github, context, core) | |
| wheel: | |
| name: Build Wheel | |
| runs-on: ${{ matrix.os }} | |
| needs: release | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| os: ['ubuntu-20.04'] | |
| python-version: ['3.8', '3.9', '3.10', '3.11', '3.12'] | |
| pytorch-version: ['2.4.0'] # Must be the most recent version that meets requirements-cuda.txt. | |
| cuda-version: ['11.8', '12.1'] | |
| steps: | |
| - name: Checkout | |
| uses: actions/checkout@v3 | |
| - name: Setup ccache | |
| uses: hendrikmuhs/[email protected] | |
| with: | |
| create-symlink: true | |
| key: ${{ github.job }}-${{ matrix.python-version }}-${{ matrix.cuda-version }} | |
| - name: Set up Linux Env | |
| if: ${{ runner.os == 'Linux' }} | |
| run: | | |
| bash -x .github/workflows/scripts/env.sh | |
| - name: Set up Python | |
| uses: actions/setup-python@v4 | |
| with: | |
| python-version: ${{ matrix.python-version }} | |
| - name: Install CUDA ${{ matrix.cuda-version }} | |
| run: | | |
| bash -x .github/workflows/scripts/cuda-install.sh ${{ matrix.cuda-version }} ${{ matrix.os }} | |
| - name: Install PyTorch ${{ matrix.pytorch-version }} with CUDA ${{ matrix.cuda-version }} | |
| run: | | |
| bash -x .github/workflows/scripts/pytorch-install.sh ${{ matrix.python-version }} ${{ matrix.pytorch-version }} ${{ matrix.cuda-version }} | |
| - name: Build wheel | |
| shell: bash | |
| env: | |
| CMAKE_BUILD_TYPE: Release # do not compile with debug symbol to reduce wheel size | |
| run: | | |
| bash -x .github/workflows/scripts/build.sh ${{ matrix.python-version }} ${{ matrix.cuda-version }} | |
| wheel_name=$(ls dist/*whl | xargs -n 1 basename) | |
| asset_name=${wheel_name//"linux"/"manylinux1"} | |
| echo "wheel_name=${wheel_name}" >> $GITHUB_ENV | |
| echo "asset_name=${asset_name}" >> $GITHUB_ENV | |
| - name: Upload Release Asset | |
| uses: actions/upload-release-asset@v1 | |
| env: | |
| GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} | |
| with: | |
| upload_url: ${{ needs.release.outputs.upload_url }} | |
| asset_path: ./dist/${{ env.wheel_name }} | |
| asset_name: ${{ env.asset_name }} | |
| asset_content_type: application/* | |
| # (Danielkinz): This last step will publish the .whl to pypi. Warning: untested | |
| # - name: Publish package | |
| # uses: pypa/gh-action-pypi-publish@release/v1.8 | |
| # with: | |
| # repository-url: https://test.pypi.org/legacy/ | |
| # password: ${{ secrets.PYPI_API_TOKEN }} | |
| # skip-existing: true |