Revert "chore: upgrade flashinfer 0.2.11 (#9036)" (#9057) #80
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: PR Test (sgl-kernel) | |
| on: | |
| push: | |
| branches: [main] | |
| paths: | |
| - "sgl-kernel/**" | |
| pull_request: | |
| branches: [main] | |
| paths: | |
| - "sgl-kernel/**" | |
| workflow_dispatch: | |
| concurrency: | |
| group: pr-test-sgl-kernel-${{ github.ref }} | |
| cancel-in-progress: true | |
| jobs: | |
| lint: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - name: Checkout code | |
| uses: actions/checkout@v4 | |
| - name: Check clang-format | |
| uses: DoozyX/clang-format-lint-action@v0.18.1 | |
| with: | |
| source: sgl-kernel | |
| extensions: h,c,cpp,hpp,cu,cuh,cc | |
| clangFormatVersion: 18 | |
| style: file | |
| build-wheels: | |
| if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request' | |
| runs-on: sgl-kernel-build-node | |
| strategy: | |
| matrix: | |
| include: | |
| - python-version: "3.10" | |
| cuda-version: "12.4" | |
| - python-version: "3.10" | |
| cuda-version: "12.9" | |
| name: Build Wheel (CUDA ${{ matrix.cuda-version }}) | |
| steps: | |
| - name: Cleanup | |
| run: | | |
| sudo rm -rf $GITHUB_WORKSPACE/* || true | |
| - 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 wheel for Python ${{ matrix.python-version }} and CUDA ${{ matrix.cuda-version }} | |
| if: github.event_name != 'push' || (matrix.cuda-version != '11.8' && matrix.cuda-version != '12.9') | |
| run: | | |
| cd sgl-kernel | |
| chmod +x ./build.sh | |
| ./build.sh "${{ matrix.python-version }}" "${{ matrix.cuda-version }}" | |
| - name: Upload artifacts | |
| uses: actions/upload-artifact@v4 | |
| with: | |
| name: wheel-python${{ matrix.python-version }}-cuda${{ matrix.cuda-version }} | |
| path: sgl-kernel/dist/* | |
| unit-test: | |
| if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request' | |
| needs: build-wheels | |
| runs-on: 1-gpu-runner | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - name: Download artifacts | |
| uses: actions/download-artifact@v4 | |
| with: | |
| path: sgl-kernel/dist/ | |
| merge-multiple: true | |
| pattern: wheel-python3.10-cuda12.4 | |
| - name: Install | |
| run: | | |
| bash scripts/ci/ci_install_dependency.sh | |
| pip3 install torch==2.8.0 torchvision torchaudio --index-url https://download.pytorch.org/whl/test/cu126 && pip3 install pytest | |
| pip3 uninstall sgl-kernel -y || true | |
| pip3 install sgl-kernel/dist/*whl --force-reinstall --no-deps | |
| pip3 list | grep sgl-kernel | |
| - name: Run test | |
| timeout-minutes: 30 | |
| run: | | |
| cd sgl-kernel | |
| pytest tests/ | |
| - name: Uninstall dependencies | |
| run: | | |
| pip3 uninstall sgl-kernel -y | |
| mla-test: | |
| if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request' | |
| needs: build-wheels | |
| runs-on: 1-gpu-runner | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - name: Download artifacts | |
| uses: actions/download-artifact@v4 | |
| with: | |
| path: sgl-kernel/dist/ | |
| merge-multiple: true | |
| pattern: wheel-python3.10-cuda12.4 | |
| - name: Install | |
| run: | | |
| bash scripts/ci/ci_install_dependency.sh | |
| pip3 install torch==2.8.0 torchvision torchaudio --index-url https://download.pytorch.org/whl/test/cu126 | |
| pip3 uninstall sgl-kernel -y || true | |
| pip3 install sgl-kernel/dist/*whl --force-reinstall --no-deps | |
| pip3 list | grep sgl-kernel | |
| - name: Run test | |
| timeout-minutes: 30 | |
| run: | | |
| cd test/srt | |
| python3 test_mla_deepseek_v3.py | |
| - name: Uninstall dependencies | |
| run: | | |
| pip3 uninstall sgl-kernel -y | |
| finish: | |
| needs: [unit-test, mla-test, lint, build-wheels] | |
| runs-on: ubuntu-latest | |
| steps: | |
| - name: Check all dependent job statuses | |
| run: | | |
| results=(${{ join(needs.*.result, ' ') }}) | |
| for result in "${results[@]}"; do | |
| if [ "$result" = "failure" ] || [ "$result" = "cancelled" ]; then | |
| echo "Job failed with result: $result" | |
| exit 1 | |
| fi | |
| done | |
| echo "All jobs completed successfully" | |
| exit 0 |