[DRAFT] Set vllm version limit to avoid upstream API incompatibility #950
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: API CUDA Tests | |
| on: | |
| workflow_dispatch: | |
| push: | |
| branches: | |
| - main | |
| pull_request: | |
| branches: | |
| - main | |
| types: | |
| - opened | |
| - reopened | |
| - synchronize | |
| - labeled | |
| - unlabeled | |
| concurrency: | |
| cancel-in-progress: true | |
| group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }} | |
| jobs: | |
| run_api_cuda_tests: | |
| if: ${{ | |
| (github.event_name == 'push') || | |
| (github.event_name == 'workflow_dispatch') || | |
| contains( github.event.pull_request.labels.*.name, 'api') || | |
| contains( github.event.pull_request.labels.*.name, 'cuda') || | |
| contains( github.event.pull_request.labels.*.name, 'api_cuda') | |
| }} | |
| runs-on: [single-gpu, nvidia-gpu, a10, ci] | |
| container: | |
| image: ghcr.io/huggingface/optimum-benchmark:latest-cuda | |
| options: --ipc host --gpus all | |
| steps: | |
| - name: Checkout | |
| uses: actions/checkout@v4 | |
| - name: Install dependencies | |
| run: | | |
| pip install -e .[testing,timm,diffusers,codecarbon] | |
| - name: Run tests | |
| env: | |
| HF_TOKEN: ${{ secrets.HF_TOKEN }} | |
| PUSH_REPO_ID: optimum-benchmark/cuda | |
| run: | | |
| pytest tests/test_api.py -x -s -k "api and cuda" |