build(deps): bump flash-attn from 2.6.3 to 2.8.2 #1056
Workflow file for this run
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: Tests | |
| on: | |
| push: | |
| branches: [main] | |
| pull_request: | |
| merge_group: | |
| workflow_dispatch: | |
| schedule: | |
| - cron: "20 4 * * 2" # once a week | |
| env: | |
| FORCE_COLOR: "1" | |
| # facilitate testing by building vLLM for CPU when needed | |
| VLLM_CPU_DISABLE_AVX512: "true" | |
| VLLM_TARGET_DEVICE: "cpu" | |
| VLLM_CPU_ONLY: "1" | |
| CMAKE_ARGS: "-DVLLM_CPU_ONLY=ON" | |
| # prefer index for torch cpu version | |
| UV_EXTRA_INDEX_URL: "https://download.pytorch.org/whl/cpu" | |
| # have uv match pip's behaviour for extra index operations | |
| UV_INDEX_STRATEGY: "unsafe-best-match" | |
| VLLM_ALLOW_LONG_MAX_MODEL_LEN: 1 | |
| concurrency: | |
| group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }} | |
| cancel-in-progress: true | |
| jobs: | |
| tests: | |
| timeout-minutes: 30 | |
| runs-on: ${{ matrix.os }} | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| os: [ubuntu-latest] | |
| pyv: ["3.12"] | |
| vllm_version: | |
| # - "" # skip the pypi version as it will not work on CPU | |
| - "git+https://github.com/vllm-project/[email protected]" | |
| - "git+https://github.com/vllm-project/vllm@main" | |
| steps: | |
| - name: Check out the repository | |
| uses: actions/checkout@v4 | |
| with: | |
| fetch-depth: 0 | |
| - name: Free Disk Space | |
| uses: jlumbroso/[email protected] | |
| with: | |
| tool-cache: false | |
| large-packages: false | |
| docker-images: false | |
| - name: Install vLLM build deps | |
| run: | | |
| sudo apt update | |
| sudo apt install --no-install-recommends -y \ | |
| ccache \ | |
| libnuma-dev libdnnl-dev opencl-dev | |
| - name: Install the latest version of uv | |
| uses: astral-sh/setup-uv@v5 | |
| with: | |
| version: "latest" | |
| python-version: ${{ matrix.pyv }} | |
| enable-cache: true | |
| cache-dependency-glob: | | |
| pyproject.toml | |
| cache-suffix: ${{matrix.vllm_version}} | |
| - name: Install nox | |
| run: | | |
| uv pip install nox | |
| - name: nox envs cache | |
| id: cache | |
| uses: actions/cache@v4 | |
| with: | |
| path: /home/runner/.nox | |
| key: ${{ runner.os }}-python-${{matrix.pyv}}-${{ hashFiles('noxfile.py') }}-${{matrix.vllm_version}} | |
| - name: hf hub cache | |
| id: hf-cache | |
| uses: actions/cache@v4 | |
| with: | |
| path: ~/.cache/huggingface/hub | |
| key: ${{ runner.os }} | |
| - name: Lint code and check dependencies | |
| run: nox --envdir ~/.nox --reuse-venv=yes -v -s lint-${{ matrix.pyv }} | |
| env: | |
| RUFF_OUTPUT_FORMAT: github | |
| - name: Cache ccache cache directory | |
| id: cache-ccache | |
| uses: actions/cache@v4 | |
| with: | |
| path: /home/runner/.cache/ccache | |
| key: ${{ runner.os }} | |
| - name: build vllm | |
| run: nox --envdir ~/.nox --reuse-venv=yes -v -s build_vllm-${{ matrix.pyv }} | |
| env: | |
| VLLM_VERSION_OVERRIDE: ${{ matrix.vllm_version }} | |
| - name: Run tests | |
| run: nox --envdir ~/.nox --reuse-venv=yes -v -s tests-${{ matrix.pyv }} -- --cov-report=xml | |
| env: | |
| VLLM_VERSION_OVERRIDE: ${{ matrix.vllm_version }} | |
| - name: Upload coverage report | |
| uses: codecov/codecov-action@v5 | |
| if: github.actor != 'dependabot[bot]' | |
| with: | |
| fail_ci_if_error: true | |
| env: | |
| CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }} | |
| - name: Build package | |
| run: nox --envdir ~/.nox --reuse-venv=yes -s build-${{ matrix.pyv }} |