[Misc] add a flag max_batch_size_to_capture to reduce vllm's start up time #16231
Workflow file for this run
This file contains 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: clang-format | |
| on: | |
| # Trigger the workflow on push or pull request, | |
| # but only for the main branch | |
| push: | |
| branches: | |
| - main | |
| pull_request: | |
| branches: | |
| - main | |
| jobs: | |
| clang-format: | |
| runs-on: ubuntu-latest | |
| strategy: | |
| matrix: | |
| python-version: ["3.11"] | |
| steps: | |
| - uses: actions/checkout@eef61447b9ff4aafe5dcd4e0bbf5d482be7e7871 # v4.2.1 | |
| - name: Set up Python ${{ matrix.python-version }} | |
| uses: actions/setup-python@f677139bbe7f9c59b41e40162b753c062f5d49a3 # v5.2.0 | |
| with: | |
| python-version: ${{ matrix.python-version }} | |
| - name: Install dependencies | |
| run: | | |
| python -m pip install --upgrade pip | |
| pip install clang-format==18.1.5 | |
| - name: Running clang-format | |
| run: | | |
| EXCLUDES=( | |
| 'csrc/moe/topk_softmax_kernels.cu' | |
| 'csrc/quantization/gguf/ggml-common.h' | |
| 'csrc/quantization/gguf/dequantize.cuh' | |
| 'csrc/quantization/gguf/vecdotq.cuh' | |
| 'csrc/quantization/gguf/mmq.cuh' | |
| 'csrc/quantization/gguf/mmvq.cuh' | |
| ) | |
| find csrc/ \( -name '*.h' -o -name '*.cpp' -o -name '*.cu' -o -name '*.cuh' \) -print \ | |
| | grep -vFf <(printf "%s\n" "${EXCLUDES[@]}") \ | |
| | xargs clang-format --dry-run --Werror |