hao-ai-lab-FastVideo/.github/workflows/sta-publish.yml

name: Publish Sliding Tile Attention Kernel to PyPI on Version Change

on:
  push:
    branches:
      - main
    paths:
      - "csrc/attn/setup_sta.py"
  workflow_dispatch:

jobs:
  check-version-change:
    runs-on: ubuntu-latest
    outputs:
      version-changed: ${{ steps.check-version.outputs.changed }}
      new-version: ${{ steps.check-version.outputs.new-version }}
    steps:
      - name: Checkout code
        uses: actions/checkout@v4
        with:
          fetch-depth: 2

      - name: Check if version changed
        id: check-version
        run: |
          cd csrc/attn
          # Get current commit's version
          NEW_VERSION=$(grep -oP 'VERSION\s*=\s*"\K[^"]+' setup_sta.py)
          echo "New version: $NEW_VERSION"
          
          # Get previous version from git history
          OLD_VERSION=$(git show HEAD~1:./setup_sta.py | grep -oP 'VERSION\s*=\s*"\K[^"]+' || echo "0.0.0")
          echo "Old version: $OLD_VERSION"
          
          if [ "$NEW_VERSION" != "$OLD_VERSION" ]; then
            echo "Version changed from $OLD_VERSION to $NEW_VERSION"
            echo "changed=true" >> $GITHUB_OUTPUT
            echo "new-version=$NEW_VERSION" >> $GITHUB_OUTPUT
          else
            echo "Version did not change"
            echo "changed=false" >> $GITHUB_OUTPUT
          fi

  build_wheels:
    name: Build Wheel
    needs: check-version-change
    if: ${{ needs.check-version-change.outputs.version-changed == 'true' || github.event_name == 'workflow_dispatch' }}
    runs-on: ${{ matrix.os }}

    strategy:
      fail-fast: false
      matrix:
          # Using ubuntu-20.04 instead of 22.04 for more compatibility (glibc). Ideally we'd use the
          # manylinux docker image, but I haven't figured out how to install CUDA on manylinux.
          os: [ubuntu-22.04]
          python-version: ['3.10', '3.11', '3.12', '3.13']
          torch-version: ['2.5.1', '2.6.0']
          cuda-version: ['12.4.1', '12.5.1', '12.6.3']

    steps:
      - name: Free up disk space
        run: |
          echo "Initial disk space:"
          df -h
          
          # Remove large directories
          sudo rm -rf /usr/share/dotnet
          sudo rm -rf /usr/local/lib/android
          sudo rm -rf /opt/ghc
          sudo rm -rf /usr/local/share/boost
          sudo rm -rf /usr/share/swift
          sudo rm -rf /usr/local/lib/node_modules
          sudo rm -rf /usr/local/share/powershell
          sudo rm -rf /usr/share/rust
          sudo rm -rf /usr/local/.ghcup
          
          # Remove cached files
          sudo rm -rf /var/lib/apt/lists/*
          sudo rm -rf /var/cache/apt/archives/*
          
          echo "Disk space after cleanup:"
          df -h

      - name: Checkout
        uses: actions/checkout@v4

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

      - name: Install CUDA ${{ matrix.cuda-version }}
        uses: Jimver/cuda-toolkit@v0.2.21
        id: cuda-toolkit
        with:
          cuda: ${{ matrix.cuda-version }}
          linux-local-args: '["--toolkit"]'
          method: 'network'

      - name: Install dependencies (GCC, Clang, CUDA Paths, Git)
        run: |
          sudo apt update
          sudo apt install -y git patchelf gcc-11 g++-11 clang-11
          sudo update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-11 100 --slave /usr/bin/g++ g++ /usr/bin/g++-11

          # Allow Git to Access Safe Directory
          git config --global --add safe.directory /__w/FastVideo/FastVideo

          # Set CUDA environment variables
          export CUDA_HOME=/usr/local/cuda-${{ matrix.cuda-version }}
          export PATH=${CUDA_HOME}/bin:${PATH}
          export LD_LIBRARY_PATH=${CUDA_HOME}/lib64:$LD_LIBRARY_PATH
          
          # Verify installation
          gcc --version
          g++ --version
          clang-11 --version
          nvcc --version

      - name: Install PyTorch ${{ matrix.torch-version }}+cu${{ matrix.cuda-version }}
        run: |
          pip install --upgrade pip
          # With python 3.13 and torch 2.5.1, unless we update typing-extensions, we get error
          # AttributeError: attribute '__default__' of 'typing.ParamSpec' objects is not writable
          pip install typing-extensions==4.12.2
          # We want to figure out the CUDA version to download pytorch
          # e.g. we can have system CUDA version being 11.7 but if torch==1.12 then we need to download the wheel from cu116
          # see https://github.com/pytorch/pytorch/blob/main/RELEASE.md#release-compatibility-matrix
          export TORCH_CUDA_VERSION=124
          pip install --no-cache-dir torch==${{ matrix.torch-version }} --index-url https://download.pytorch.org/whl/cu${TORCH_CUDA_VERSION}
          nvcc --version
          python --version
          python -c "import torch; print('PyTorch:', torch.__version__)"
          python -c "import torch; print('CUDA:', torch.version.cuda)"
          python -c "from torch.utils import cpp_extension; print (cpp_extension.CUDA_HOME)"

      - name: Build wheel
        run: |
          export PYTHONPATH=$GITHUB_WORKSPACE:$PYTHONPATH
          
          # We want setuptools >= 49.6.0 otherwise we can't compile the extension if system CUDA version is 11.7 and pytorch cuda version is 11.6
          # https://github.com/pytorch/pytorch/blob/664058fa83f1d8eede5d66418abff6e20bd76ca8/torch/utils/cpp_extension.py#L810
          # However this still fails so I'm using a newer version of setuptools
          pip install setuptools
          pip install ninja packaging wheel

          cd csrc/attn  # Move into the correct folder
          git submodule update --init --recursive # Ensure ThunderKittens submodule is initialized
          python setup_sta.py bdist_wheel --dist-dir=dist

      - name: Rename wheel file
        run: |
          cd csrc/attn

          CUDA_SHORT_VERSION=$(echo ${{ matrix.cuda-version }} | cut -d. -f1,2 | sed 's/\.//g')
          TORCH_SHORT_VERSION=$(echo ${{ matrix.torch-version }} | cut -d. -f1,2)
          # Get the correct version format
          tmpname=cu${CUDA_SHORT_VERSION}torch${TORCH_SHORT_VERSION}
          wheel_name=$(ls dist/*whl | xargs -n 1 basename | sed "s/-/+$tmpname-/2")
          # Rename with version information
          ls dist/*whl |xargs -I {} mv {} dist/${wheel_name}
          echo "wheel_name=${wheel_name}" >> $GITHUB_ENV

      - name: Upload wheel artifact
        uses: actions/upload-artifact@v4
        with:
          name: ${{ env.wheel_name }}
          path: csrc/attn/dist/*.whl
          retention-days: 90

  publish_package:
    name: Publish package
    needs: [build_wheels, check-version-change]
    if: ${{ needs.check-version-change.outputs.version-changed == 'true' || github.event_name == 'workflow_dispatch' }}
    runs-on: ubuntu-22.04
    permissions:
      id-token: write  # Needed for OIDC Trusted Publishing

    steps:
      - uses: actions/checkout@v4

      - uses: actions/setup-python@v5
        with:
          python-version: '3.10'
      
      - name: Install CUDA 12.4.1
        uses: Jimver/cuda-toolkit@v0.2.21
        id: cuda-toolkit
        with:
          cuda: 12.4.1
          linux-local-args: '["--toolkit"]'
          method: 'network'
          sub-packages: '["nvcc"]'

      - name: Install dependencies (GCC, Clang, CUDA Paths, Git)
        run: |
          sudo apt update
          sudo apt install -y git patchelf gcc-11 g++-11 clang-11
          sudo update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-11 100 --slave /usr/bin/g++ g++ /usr/bin/g++-11

          # Allow Git to Access Safe Directory
          git config --global --add safe.directory /__w/FastVideo/FastVideo

          # Set CUDA environment variables
          export CUDA_HOME=/usr/local/cuda-12.4.1
          export PATH=${CUDA_HOME}/bin:${PATH}
          export LD_LIBRARY_PATH=${CUDA_HOME}/lib64:$LD_LIBRARY_PATH
          
          # Verify installation
          gcc --version
          g++ --version
          clang-11 --version
          nvcc --version

      - name: Install PyTorch 2.5.1+cu12.4.1
        run: |
          pip install --upgrade pip
          # With python 3.13 and torch 2.5.1, unless we update typing-extensions, we get error
          # AttributeError: attribute '__default__' of 'typing.ParamSpec' objects is not writable
          pip install typing-extensions==4.12.2
          # We want to figure out the CUDA version to download pytorch
          # e.g. we can have system CUDA version being 11.7 but if torch==1.12 then we need to download the wheel from cu116
          # see https://github.com/pytorch/pytorch/blob/main/RELEASE.md#release-compatibility-matrix
          export TORCH_CUDA_VERSION=124
          pip install --no-cache-dir torch==2.5.1 --index-url https://download.pytorch.org/whl/cu${TORCH_CUDA_VERSION}
          nvcc --version
          python --version
          python -c "import torch; print('PyTorch:', torch.__version__)"
          python -c "import torch; print('CUDA:', torch.version.cuda)"
          python -c "from torch.utils import cpp_extension; print (cpp_extension.CUDA_HOME)"

      - name: Build source distribution
        run: |
          export PYTHONPATH=$GITHUB_WORKSPACE:$PYTHONPATH
          
          # We want setuptools >= 49.6.0 otherwise we can't compile the extension if system CUDA version is 11.7 and pytorch cuda version is 11.6
          # https://github.com/pytorch/pytorch/blob/664058fa83f1d8eede5d66418abff6e20bd76ca8/torch/utils/cpp_extension.py#L810
          # However this still fails so I'm using a newer version of setuptools
          pip install setuptools
          pip install ninja packaging wheel

          cd csrc/attn  # Move into the correct folder
          git submodule update --init --recursive # Ensure ThunderKittens submodule is initialized
          python setup_sta.py sdist --dist-dir=dist

      - name: Publish release distributions to PyPI
        uses: pypa/gh-action-pypi-publish@release/v1
        with:
          packages-dir: csrc/attn/dist/