sglang/.github/workflows/release-whl-kernel.yml

name: Release SGLang Kernels

on:
  push:
    branches:
      - main
    paths:
      - sgl-kernel/python/sgl_kernel/version.py
  workflow_dispatch:
    inputs:
      target:
        type: choice
        description: 'Build target'
        required: false
        default: 'all'
        options:
          - 'all'
          - 'cu129'
          - 'cu130'
          - 'rocm700'
          - 'rocm720'
          - 'musa43'
      tag_name:
        description: "Version number, must be in the form of vX.Y.Z (e.g. v0.4.0)"
        type: string
        required: false
      pr_number:
        description: "PR number to build from (e.g. 12345)"
        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' &&
      (github.event_name == 'push' || github.event.inputs.target == 'all' || github.event.inputs.target == 'cu129')
    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"
          ref: ${{ inputs.pr_number && format('refs/pull/{0}/head', inputs.pr_number) || '' }}

      - 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' || '' }}
        env:
          BUILD_JOBS: 64
          NVCC_THREADS: 8

      - 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_SGLANG_KERNEL }}

      - 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
        with:
          ref: ${{ inputs.pr_number && format('refs/pull/{0}/head', inputs.pr_number) || '' }}

      - 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.GH_PAT_FOR_WHL_RELEASE }}
          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.GH_PAT_FOR_WHL_RELEASE }}

      - 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' &&
      (github.event_name == 'push' || github.event.inputs.target == 'all' || github.event.inputs.target == 'cu130')
    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"
          ref: ${{ inputs.pr_number && format('refs/pull/{0}/head', inputs.pr_number) || '' }}

      - 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' || '' }}
        env:
          BUILD_JOBS: 64
          NVCC_THREADS: 8

      - 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
        with:
          ref: ${{ inputs.pr_number && format('refs/pull/{0}/head', inputs.pr_number) || '' }}

      - 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.GH_PAT_FOR_WHL_RELEASE }}
          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.GH_PAT_FOR_WHL_RELEASE }}

      - 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

  build-rocm-matrix:
    if: |
      github.repository == 'sgl-project/sglang' &&
      (github.event_name == 'push' || github.event.inputs.target == 'all' || github.event.inputs.target == 'rocm700' || github.event.inputs.target == 'rocm720')
    runs-on: amd-docker-scale
    strategy:
      matrix:
        python-version: ["3.10"]
        rocm-version: ["700", "720"]
    steps:
      - uses: actions/checkout@v4
        with:
          submodules: "recursive"
          ref: ${{ inputs.pr_number && format('refs/pull/{0}/head', inputs.pr_number) || '' }}

      - name: Set up Python ${{ matrix.python-version }}
        uses: actions/setup-python@v5
        with:
          python-version: ${{ matrix.python-version }}

      - name: Build wheels
        run: |
          cp 3rdparty/amd/wheel/sgl-kernel/* sgl-kernel/
          cd sgl-kernel
          chmod +x ./build_rocm.sh
          ./build_rocm.sh "${{ matrix.rocm-version }}"

      - name: Upload artifacts
        uses: actions/upload-artifact@v4
        with:
          name: wheel-python${{ matrix.python-version }}-rocm${{ matrix.rocm-version }}
          path: sgl-kernel/dist/*

  release-rocm700:
    needs: build-rocm-matrix
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
        with:
          ref: ${{ inputs.pr_number && format('refs/pull/{0}/head', inputs.pr_number) || '' }}

      - name: Download artifacts
        uses: actions/download-artifact@v4
        with:
          path: sgl-kernel/dist/
          merge-multiple: true
          pattern: wheel-*-rocm700

      - 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.GH_PAT_FOR_WHL_RELEASE }}
          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.GH_PAT_FOR_WHL_RELEASE }}

      - name: Update wheel index
        run: python3 scripts/update_kernel_whl_index.py --rocm 700

      - 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

  release-rocm720:
    needs: build-rocm-matrix
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
        with:
          ref: ${{ inputs.pr_number && format('refs/pull/{0}/head', inputs.pr_number) || '' }}

      - name: Download artifacts
        uses: actions/download-artifact@v4
        with:
          path: sgl-kernel/dist/
          merge-multiple: true
          pattern: wheel-*-rocm720

      - 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.GH_PAT_FOR_WHL_RELEASE }}
          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.GH_PAT_FOR_WHL_RELEASE }}

      - name: Update wheel index
        run: python3 scripts/update_kernel_whl_index.py --rocm 720

      - 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

  build-musa43:
    if: |
      github.repository == 'sgl-project/sglang' &&
      (github.event_name == 'push' || github.event.inputs.target == 'all' || github.event.inputs.target == 'musa43')
    runs-on: kernel-build-node-musa
    strategy:
      matrix:
        python-version: ["3.10"]
        musa-version: ["43"]
    steps:
      - uses: actions/checkout@v4
        with:
          submodules: "recursive"

      - name: Build wheels
        run: |
          cd sgl-kernel
          mv pyproject_musa.toml pyproject.toml
          python setup_musa.py sdist bdist_wheel

      - name: Rename MUSA wheels
        run: |
          bash scripts/ci/musa/rename_wheels_musa.sh ${{ matrix.musa-version }} sgl-kernel/dist

      - name: Upload artifacts
        uses: actions/upload-artifact@v4
        with:
          name: wheel-python${{ matrix.python-version }}-musa${{ matrix.musa-version }}
          path: sgl-kernel/dist/*

  release-musa43:
    needs: build-musa43
    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.GH_PAT_FOR_WHL_RELEASE }}
          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.GH_PAT_FOR_WHL_RELEASE }}

      - name: Update wheel index
        run: python3 scripts/update_kernel_whl_index.py --musa 43

      - 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