Enable Qwen models familly #236
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: GPU Enabled Integration Test on PRs | |
| on: | |
| pull_request: | |
| branches: | |
| - main | |
| push: | |
| branches: | |
| - ci-* | |
| concurrency: | |
| group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }} | |
| cancel-in-progress: true | |
| env: | |
| OPTIMUM_NVIDIA_IS_CI: ON | |
| HF_HUB_ENABLE_HF_TRANSFER: ON | |
| jobs: | |
| run_gpu_tests: | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| config: | |
| - name: Optimum-Nvidia Test Suite | |
| image: nvidia/cuda:12.6.3-devel-ubuntu24.04 | |
| gpu_target: ["aws-g6-12xlarge-cache", "aws-g5-12xlarge-cache"] | |
| name: ${{ matrix.config.name }} | |
| runs-on: | |
| group: "${{matrix.gpu_target}}" | |
| container: | |
| image: ${{ matrix.config.image }} | |
| options: --mount type=tmpfs,destination=/tmp --privileged --shm-size 64gb --gpus all --ipc host -v /mnt/hf_cache:/mnt/cache/ | |
| env: | |
| HF_TOKEN: ${{ secrets.OPTIMUM_NVIDIA_HUB_READ_TOKEN }} | |
| defaults: | |
| run: | |
| shell: bash | |
| steps: | |
| - name: Change ownership of /github/home | |
| run: chown -R $(whoami) /github/home | |
| - uses: actions/setup-python@v5 | |
| with: | |
| python-version: '3.10' | |
| - name: Checkout optimum-nvidia | |
| uses: actions/checkout@v4 | |
| with: | |
| fetch-depth: 1 | |
| - name: Install dependencies | |
| run: | | |
| apt update && apt install -y libmpich-dev libopenmpi-dev openmpi-bin git | |
| python3 -m pip install --upgrade -e .[quality,tests] --extra-index-url https://pypi.nvidia.com | |
| - name: Run nvidia-smi | |
| run: | | |
| nvidia-smi | |
| - name: Print TensorRT-LLM version | |
| run: | | |
| python -c "from tensorrt_llm import __version__; print(__version__)" | |
| - name: Run optimum-nvidia test-suite | |
| run: | | |
| pytest -s -v -p no:warnings -o log_cli=true --ignore=tests/cli tests/ | |
| run_optimum_cli_tests: | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| config: | |
| - name: Optimum-Nvidia CLI Test Suite | |
| image: nvidia/cuda:12.6.3-devel-ubuntu24.04 | |
| gpu_target: ["aws-g6-12xlarge-cache", "aws-g5-12xlarge-cache"] | |
| name: ${{ matrix.config.name }} | |
| runs-on: | |
| group: "${{matrix.gpu_target}}" | |
| container: | |
| image: ${{ matrix.config.image }} | |
| options: --mount type=tmpfs,destination=/tmp --privileged --shm-size 64gb --gpus all --ipc host -v /mnt/hf_cache:/mnt/cache/ | |
| env: | |
| HF_TOKEN: ${{ secrets.OPTIMUM_NVIDIA_HUB_READ_TOKEN }} | |
| defaults: | |
| run: | |
| shell: bash | |
| steps: | |
| - name: Change ownership of /github/home | |
| run: chown -R $(whoami) /github/home | |
| - uses: actions/setup-python@v5 | |
| with: | |
| python-version: '3.10' | |
| - name: Checkout optimum-nvidia | |
| uses: actions/checkout@v4 | |
| with: | |
| fetch-depth: 1 | |
| - name: Install dependencies | |
| run: | | |
| apt update && apt install -y openmpi-bin libopenmpi-dev git | |
| python3 -m pip install --upgrade -e .[quality,tests] --extra-index-url https://pypi.nvidia.com | |
| - name: Run nvidia-smi | |
| run: | | |
| nvidia-smi | |
| - name: Print TensorRT-LLM version | |
| run: | | |
| python -c "from tensorrt_llm import __version__; print(__version__)" | |
| - name: Run optimum-nvidia cli test-suite | |
| run: | | |
| pytest -rx -s -p no:warnings tests/cli | |
| - name: Tailscale Wait | |
| if: ${{ failure() || runner.debug == '1' }} | |
| uses: huggingface/tailscale-action@main | |
| with: | |
| waitForSSH: true | |
| authkey: ${{ secrets.TAILSCALE_SSH_AUTHKEY }} | |
| slackChannel: ${{ secrets.SLACK_CIFEEDBACK_CHANNEL }} | |
| slackToken: ${{ secrets.SLACK_CIFEEDBACK_BOT_TOKEN }} |