[CI] Add automated monthly PyPI release plan with hotfix support (#1588) #4
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
| name: Monthly Release | ||
| on: | ||
| schedule: | ||
| # Run on the 1st of every month at 00:00 UTC | ||
| - cron: '0 0 1 * *' | ||
| workflow_dispatch: | ||
| inputs: | ||
| version_type: | ||
| description: 'Version type (major, minor, patch)' | ||
| required: true | ||
| default: 'minor' | ||
| type: choice | ||
| options: | ||
| - major | ||
| - minor | ||
| - patch | ||
| env: | ||
| SCCACHE_GHA_ENABLED: "true" | ||
| jobs: | ||
| prepare-release: | ||
| runs-on: ubuntu-22.04 | ||
| permissions: | ||
| contents: write | ||
| outputs: | ||
| new_version: ${{ steps.bump_version.outputs.new_version }} | ||
| release_tag: ${{ steps.bump_version.outputs.release_tag }} | ||
| steps: | ||
| - name: Checkout source | ||
| uses: actions/checkout@v4 | ||
| with: | ||
| fetch-depth: 0 | ||
| token: ${{ secrets.GITHUB_TOKEN }} | ||
| - name: Set up Python | ||
| uses: actions/setup-python@v5 | ||
| with: | ||
| python-version: '3.10' | ||
| - name: Install dependencies | ||
| run: | | ||
| pip install packaging | ||
| - name: Bump version | ||
| id: bump_version | ||
| run: | | ||
| # Read current version from pyproject.toml | ||
| CURRENT_VERSION=$(grep -oP 'version = "\K[^"]+' mooncake-wheel/pyproject.toml) | ||
| echo "Current version: $CURRENT_VERSION" | ||
| # Determine version bump type | ||
| VERSION_TYPE="${{ github.event.inputs.version_type }}" | ||
| if [ -z "$VERSION_TYPE" ]; then | ||
| VERSION_TYPE="minor" # Default for scheduled releases | ||
| fi | ||
| # Parse version | ||
| IFS='.' read -r major minor patch <<< "$CURRENT_VERSION" | ||
| # Bump version based on type | ||
| case $VERSION_TYPE in | ||
| major) | ||
| major=$((major + 1)) | ||
| minor=0 | ||
| patch=0 | ||
| ;; | ||
| minor) | ||
| minor=$((minor + 1)) | ||
| patch=0 | ||
| ;; | ||
| patch) | ||
| patch=$((patch + 1)) | ||
| ;; | ||
| esac | ||
| NEW_VERSION="${major}.${minor}.${patch}" | ||
| RELEASE_TAG="v${NEW_VERSION}" | ||
| echo "New version: $NEW_VERSION" | ||
| echo "Release tag: $RELEASE_TAG" | ||
| # Update pyproject.toml | ||
| sed -i "s/version = \"$CURRENT_VERSION\"/version = \"$NEW_VERSION\"/" mooncake-wheel/pyproject.toml | ||
| # Output for next jobs | ||
| echo "new_version=$NEW_VERSION" >> $GITHUB_OUTPUT | ||
| echo "release_tag=$RELEASE_TAG" >> $GITHUB_OUTPUT | ||
| - name: Configure Git | ||
| run: | | ||
| git config user.name "github-actions[bot]" | ||
| git config user.email "github-actions[bot]@users.noreply.github.com" | ||
| - name: Commit version bump | ||
| run: | | ||
| git add mooncake-wheel/pyproject.toml | ||
| git commit -m "Release ${{ steps.bump_version.outputs.new_version }} | ||
| Generated with [Claude Code](https://claude.ai/code) | ||
| via [Happy](https://happy.engineering) | ||
| Co-Authored-By: Claude <noreply@anthropic.com> | ||
| Co-Authored-By: Happy <yesreply@happy.engineering>" | ||
| git push origin main | ||
| - name: Create and push tag | ||
| run: | | ||
| git tag ${{ steps.bump_version.outputs.release_tag }} | ||
| git push origin ${{ steps.bump_version.outputs.release_tag }} | ||
| build-cuda: | ||
| needs: prepare-release | ||
| runs-on: ubuntu-22.04 | ||
| permissions: | ||
| contents: write | ||
| strategy: | ||
| matrix: | ||
| python-version: ['3.10', '3.11', '3.12', '3.13'] | ||
| env: | ||
| BUILD_WITH_EP: "1" | ||
| EP_TORCH_VERSIONS: "2.9.0;2.9.1;2.10.0" | ||
| TORCH_CUDA_ARCH_LIST: "8.0;9.0" | ||
| steps: | ||
| - name: Checkout source | ||
| uses: actions/checkout@v4 | ||
| with: | ||
| ref: ${{ needs.prepare-release.outputs.release_tag }} | ||
| - name: Set up Python ${{ matrix.python-version }} | ||
| uses: actions/setup-python@v5 | ||
| with: | ||
| python-version: ${{ matrix.python-version }} | ||
| - name: Free up disk space | ||
| run: | | ||
| sudo rm -rf /usr/share/dotnet | ||
| sudo rm -rf /opt/ghc | ||
| sudo rm -rf /opt/hostedtoolcache/CodeQL | ||
| sudo rm -rf /usr/local/lib/android | ||
| df -h | ||
| - name: Install CUDA Toolkit | ||
| uses: Jimver/cuda-toolkit@v0.2.24 | ||
| with: | ||
| cuda: '12.8.1' | ||
| linux-local-args: '["--toolkit"]' | ||
| method: 'network' | ||
| sub-packages: '["nvcc", "nvrtc-dev"]' | ||
| non-cuda-sub-packages: '["libcusparse-dev", "libcublas-dev", "libcusolver-dev"]' | ||
| - name: Run sccache-cache | ||
| uses: mozilla-actions/sccache-action@v0.0.9 | ||
| - name: Configure sccache | ||
| uses: actions/github-script@v7 | ||
| with: | ||
| script: | | ||
| core.exportVariable('ACTIONS_RESULTS_URL', process.env.ACTIONS_RESULTS_URL || ''); | ||
| core.exportVariable('ACTIONS_RUNTIME_TOKEN', process.env.ACTIONS_RUNTIME_TOKEN || ''); | ||
| - name: Run sccache stat for check | ||
| shell: bash | ||
| run: ${SCCACHE_PATH} --show-stats | ||
| - name: Configure project | ||
| run: | | ||
| sudo apt update -y | ||
| sudo bash -x dependencies.sh -y | ||
| mkdir build | ||
| cd build | ||
| cmake .. -DBUILD_UNIT_TESTS=OFF -DUSE_HTTP=ON -DUSE_ETCD=ON -DUSE_CUDA=ON -DWITH_EP=ON -DSTORE_USE_ETCD=ON -DENABLE_SCCACHE=ON -DCMAKE_BUILD_TYPE=Release | ||
| shell: bash | ||
| - name: Build project | ||
| run: | | ||
| export LIBRARY_PATH=/usr/local/cuda/lib64/stubs:LIBRARY_PATH | ||
| cd build | ||
| make -j | ||
| sudo make install | ||
| shell: bash | ||
| - name: Build nvlink_allocator.so | ||
| run: | | ||
| export PATH=/usr/local/nvidia/bin:/usr/local/nvidia/lib64:$PATH | ||
| export LD_LIBRARY_PATH=/usr/local/cuda/lib64/stubs:$LD_LIBRARY_PATH | ||
| export LIBRARY_PATH=/usr/local/cuda/lib64/stubs:$LIBRARY_PATH | ||
| mkdir -p build/mooncake-transfer-engine/nvlink-allocator | ||
| cd mooncake-transfer-engine/nvlink-allocator | ||
| bash build.sh ../../build/mooncake-transfer-engine/nvlink-allocator/ | ||
| shell: bash | ||
| - name: Generate Python version tag | ||
| id: generate_tag_release | ||
| run: | | ||
| echo "python_version_tag=$(echo ${{ matrix.python-version }} | tr -d '.')" >> $GITHUB_OUTPUT | ||
| shell: bash | ||
| - name: Build Python wheel | ||
| run: | | ||
| export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/lib | ||
| PYTHON_VERSION=${{ matrix.python-version }} OUTPUT_DIR=dist-py${{ steps.generate_tag_release.outputs.python_version_tag }} ./scripts/build_wheel.sh | ||
| - name: Upload Python wheel artifact | ||
| uses: actions/upload-artifact@v4 | ||
| with: | ||
| name: mooncake-wheel-cuda-py${{ steps.generate_tag_release.outputs.python_version_tag }} | ||
| path: mooncake-wheel/dist-py${{ steps.generate_tag_release.outputs.python_version_tag }}/*.whl | ||
| build-non-cuda: | ||
| needs: prepare-release | ||
| runs-on: ubuntu-22.04 | ||
| permissions: | ||
| contents: write | ||
| strategy: | ||
| matrix: | ||
| python-version: ['3.10', '3.11', '3.12', '3.13'] | ||
| env: | ||
| BUILD_WITH_EP: "0" | ||
| NON_CUDA_BUILD: "1" | ||
| steps: | ||
| - name: Checkout source | ||
| uses: actions/checkout@v4 | ||
| with: | ||
| ref: ${{ needs.prepare-release.outputs.release_tag }} | ||
| - name: Set up Python ${{ matrix.python-version }} | ||
| uses: actions/setup-python@v5 | ||
| with: | ||
| python-version: ${{ matrix.python-version }} | ||
| - name: Free up disk space | ||
| run: | | ||
| sudo rm -rf /usr/share/dotnet | ||
| sudo rm -rf /opt/ghc | ||
| sudo rm -rf /opt/hostedtoolcache/CodeQL | ||
| - name: Run sccache-cache | ||
| uses: mozilla-actions/sccache-action@v0.0.9 | ||
| - name: Configure sccache | ||
| uses: actions/github-script@v7 | ||
| with: | ||
| script: | | ||
| core.exportVariable('ACTIONS_RESULTS_URL', process.env.ACTIONS_RESULTS_URL || ''); | ||
| core.exportVariable('ACTIONS_RUNTIME_TOKEN', process.env.ACTIONS_RUNTIME_TOKEN || ''); | ||
| - name: Run sccache stat for check | ||
| shell: bash | ||
| run: ${SCCACHE_PATH} --show-stats | ||
| - name: Configure project | ||
| run: | | ||
| sudo apt update -y | ||
| sudo bash -x dependencies.sh -y | ||
| mkdir build | ||
| cd build | ||
| cmake .. -DUSE_HTTP=ON -DUSE_ETCD=ON -DUSE_CUDA=OFF -DWITH_EP=OFF -DSTORE_USE_ETCD=ON -DENABLE_SCCACHE=ON -DCMAKE_BUILD_TYPE=Release | ||
| shell: bash | ||
| - name: Build project | ||
| run: | | ||
| cd build | ||
| make -j | ||
| sudo make install | ||
| shell: bash | ||
| - name: Generate Python version tag | ||
| id: generate_tag_release | ||
| run: | | ||
| echo "python_version_tag=$(echo ${{ matrix.python-version }} | tr -d '.')" >> $GITHUB_OUTPUT | ||
| shell: bash | ||
| - name: Build Python wheel | ||
| run: | | ||
| export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/lib | ||
| PYTHON_VERSION=${{ matrix.python-version }} OUTPUT_DIR=dist-py${{ steps.generate_tag_release.outputs.python_version_tag }} ./scripts/build_wheel.sh | ||
| - name: Upload Python wheel artifact | ||
| uses: actions/upload-artifact@v4 | ||
| with: | ||
| name: mooncake-wheel-non-cuda-py${{ steps.generate_tag_release.outputs.python_version_tag }} | ||
| path: mooncake-wheel/dist-py${{ steps.generate_tag_release.outputs.python_version_tag }}/*.whl | ||
| publish-release: | ||
| needs: [prepare-release, build-cuda, build-non-cuda] | ||
| runs-on: ubuntu-22.04 | ||
| permissions: | ||
| contents: write | ||
| id-token: write | ||
| steps: | ||
| - name: Checkout source | ||
| uses: actions/checkout@v4 | ||
| with: | ||
| ref: ${{ needs.prepare-release.outputs.release_tag }} | ||
| - name: Download all wheel artifacts | ||
| uses: actions/download-artifact@v4 | ||
| with: | ||
| path: mooncake-wheel/dist-all | ||
| - name: Prepare wheels for release | ||
| run: | | ||
| mkdir -p mooncake-wheel/dist-release | ||
| find mooncake-wheel/dist-all -name "*.whl" -exec cp {} mooncake-wheel/dist-release/ \; | ||
| echo "Collected wheels for release:" | ||
| ls -la mooncake-wheel/dist-release/ | ||
| - name: Generate release notes | ||
| id: release_notes | ||
| run: | | ||
| cat > release_notes.md << 'EOF' | ||
| # Mooncake ${{ needs.prepare-release.outputs.new_version }} | ||
| This is an automated monthly release of Mooncake Transfer Engine. | ||
| ## What's Included | ||
| - **CUDA builds**: Full-featured builds with CUDA 12.8 support and Expert Parallelism | ||
| - **Non-CUDA builds**: CPU-only builds for environments without GPU support | ||
| ## Python Support | ||
| - Python 3.10, 3.11, 3.12, 3.13 | ||
| ## Installation | ||
| ### CUDA version (default): | ||
| ```bash | ||
| pip install mooncake-transfer-engine | ||
| ``` | ||
| ### Non-CUDA version: | ||
| ```bash | ||
| pip install mooncake-transfer-engine-non-cuda | ||
| ``` | ||
| ## Documentation | ||
| - [GitHub Repository](https://github.com/kvcache-ai/Mooncake) | ||
| - [Documentation](https://kvcache-ai.github.io/Mooncake/) | ||
| --- | ||
| *This release was automatically generated on $(date -u +"%Y-%m-%d")* | ||
| EOF | ||
| - name: Create GitHub Release | ||
| uses: softprops/action-gh-release@v1 | ||
| with: | ||
| tag_name: ${{ needs.prepare-release.outputs.release_tag }} | ||
| name: Release ${{ needs.prepare-release.outputs.new_version }} | ||
| body_path: release_notes.md | ||
| files: mooncake-wheel/dist-release/*.whl | ||
| draft: false | ||
| prerelease: false | ||
| - name: Publish package to PyPI | ||
| if: github.repository == 'kvcache-ai/Mooncake' | ||
| uses: pypa/gh-action-pypi-publish@release/v1 | ||
| with: | ||
| packages-dir: mooncake-wheel/dist-release/ | ||
| password: ${{ secrets.PYPI_API_TOKEN }} | ||
