name: Release SGLang Kernels on: push: branches: - main paths: - sgl-kernel/python/sgl_kernel/version.py workflow_dispatch: inputs: tag_name: type: string required: false concurrency: group: release-sglang-kernels-${{ github.ref }} cancel-in-progress: true jobs: build-cu129-matrix: if: github.repository == 'sgl-project/sglang' strategy: matrix: python-version: ["3.10"] cuda-version: ["12.9"] arch: [x86_64, aarch64] include: - arch: x86_64 runner: x64-kernel-build-node - arch: aarch64 runner: arm-kernel-build-node runs-on: ${{ matrix.runner }} steps: - uses: actions/checkout@v4 with: submodules: "recursive" - name: Set up Python ${{ matrix.python-version }} uses: actions/setup-python@v5 with: python-version: ${{ matrix.python-version }} - name: Build wheels run: | cd sgl-kernel chmod +x ./build.sh ./build.sh "${{ matrix.python-version }}" "${{ matrix.cuda-version }}" ${{ matrix.arch == 'aarch64' && 'aarch64' || '' }} - name: Upload to PyPI working-directory: sgl-kernel run: | pip install twine python3 -m twine upload --skip-existing dist/* -u __token__ -p ${{ secrets.PYPI_TOKEN }} - name: Upload artifacts uses: actions/upload-artifact@v4 with: name: wheel-python${{ matrix.python-version }}-cuda${{ matrix.cuda-version }}${{ matrix.arch == 'aarch64' && '-aarch64' || '' }} path: sgl-kernel/dist/* release-cu129: needs: build-cu129-matrix runs-on: ubuntu-latest steps: - uses: actions/checkout@v4 - name: Download artifacts uses: actions/download-artifact@v4 with: path: sgl-kernel/dist/ merge-multiple: true pattern: wheel-* - name: Set tag name id: set_tag_name run: | if [ -z "${{ inputs.tag_name }}" ]; then TAG_NAME="v$(cat sgl-kernel/python/sgl_kernel/version.py | cut -d'"' -f2)" echo "tag_name=$TAG_NAME" >> $GITHUB_OUTPUT else echo "tag_name=${{ inputs.tag_name }}" >> $GITHUB_OUTPUT fi - name: Release uses: softprops/action-gh-release@v2 with: tag_name: ${{ steps.set_tag_name.outputs.tag_name }} repository: sgl-project/whl token: ${{ secrets.WHL_TOKEN }} files: | sgl-kernel/dist/* - name: Clone wheel index run: git clone https://oauth2:${WHL_TOKEN}@github.com/sgl-project/whl.git sgl-whl env: WHL_TOKEN: ${{ secrets.WHL_TOKEN }} - name: Update wheel index run: python3 scripts/update_kernel_whl_index.py --cuda 129 - name: Push wheel index run: | cd sgl-whl git config --local user.name "sglang-bot" git config --local user.email "sglangbot@gmail.com" git add -A git commit -m "update whl index" git push # for now we do not release CUDA 13.0 wheels to pypi build-cu130-matrix: if: github.repository == 'sgl-project/sglang' strategy: matrix: python-version: ["3.10"] cuda-version: ["13.0"] arch: [x86_64, aarch64] include: - arch: x86_64 runner: x64-kernel-build-node - arch: aarch64 runner: arm-kernel-build-node runs-on: ${{ matrix.runner }} steps: - uses: actions/checkout@v4 with: submodules: "recursive" - name: Set up Python ${{ matrix.python-version }} uses: actions/setup-python@v5 with: python-version: ${{ matrix.python-version }} - name: Build wheels run: | cd sgl-kernel chmod +x ./build.sh ./build.sh "${{ matrix.python-version }}" "${{ matrix.cuda-version }}" ${{ matrix.arch == 'aarch64' && 'aarch64' || '' }} - name: Upload artifacts uses: actions/upload-artifact@v4 with: name: wheel-python${{ matrix.python-version }}-cuda${{ matrix.cuda-version }}${{ matrix.arch == 'aarch64' && '-aarch64' || '' }} path: sgl-kernel/dist/* release-cu130: needs: build-cu130-matrix runs-on: ubuntu-latest steps: - uses: actions/checkout@v4 - name: Download artifacts uses: actions/download-artifact@v4 with: path: sgl-kernel/dist/ merge-multiple: true pattern: wheel-* - name: Set tag name id: set_tag_name run: | if [ -z "${{ inputs.tag_name }}" ]; then TAG_NAME="v$(cat sgl-kernel/python/sgl_kernel/version.py | cut -d'"' -f2)" echo "tag_name=$TAG_NAME" >> $GITHUB_OUTPUT else echo "tag_name=${{ inputs.tag_name }}" >> $GITHUB_OUTPUT fi - name: Release uses: softprops/action-gh-release@v2 with: tag_name: ${{ steps.set_tag_name.outputs.tag_name }} repository: sgl-project/whl token: ${{ secrets.WHL_TOKEN }} files: | sgl-kernel/dist/* - name: Clone wheel index run: git clone https://oauth2:${WHL_TOKEN}@github.com/sgl-project/whl.git sgl-whl env: WHL_TOKEN: ${{ secrets.WHL_TOKEN }} - name: Update wheel index run: python3 scripts/update_kernel_whl_index.py --cuda 130 - name: Push wheel index run: | cd sgl-whl git config --local user.name "sglang-bot" git config --local user.email "sglangbot@gmail.com" git add -A git commit -m "update whl index" git push