name: nv-a6000 on: pull_request: paths: - 'accelerator/cuda_accelerator.py' - 'deepspeed/inference/v2/**' - 'tests/unit/inference/v2/**' - '.github/workflows/nv-a6000.yml' workflow_dispatch: inputs: mii_branch: description: 'DeepSpeed-MII Branch' required: false default: 'main' type: string concurrency: group: ${{ github.workflow }}-${{ github.ref }} cancel-in-progress: true jobs: unit-tests: name: nv-a6000 / inference and MII tests runs-on: [self-hosted, nvidia, a6000] container: image: nvcr.io/nvidia/pytorch:25.01-py3 ports: - 80 options: --gpus all --shm-size "8G" steps: - uses: actions/checkout@v4 - name: Check container state run: | ldd --version nvcc --version nvidia-smi python -c "import torch; print('torch:', torch.__version__, torch)" python -c "import torch; print('CUDA available:', torch.cuda.is_available())" - name: Install transformers run: | git clone https://github.com/huggingface/transformers cd transformers # if you need to use an older transformers version temporarily in case of breakage # git checkout 981c276 git rev-parse --short HEAD python -m pip install . - name: Install deepspeed run: | python -m pip install docutils==0.18.1 jinja2==3.0 urllib3==1.26.11 ninja python -m pip install .[dev,1bit,autotuning,inf] ds_report - name: Python environment run: | python -m pip list - name: Unit tests run: | unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch cd tests python -m pytest --color=yes --durations=0 --verbose -rF -m 'inference_v2' unit/ --torch_ver="2.6" --cuda_ver="12" python -m pytest --color=yes --durations=0 --verbose -rF -m 'inference_v2_ops' unit/ --torch_ver="2.6" --cuda_ver="12" - name: MII unit tests run: | BRANCH="main" if [[ ! -z "${{ github.event.inputs.mii_branch }}" ]]; then BRANCH="${{ github.event.inputs.mii_branch }}" fi echo "Cloning DeepSpeed-MII branch: $BRANCH" git clone -b $BRANCH --depth=1 https://github.com/deepspeedai/DeepSpeed-MII.git cd DeepSpeed-MII pip install .[dev] cd tests python -m pytest --color=yes --durations=0 --verbose -rF ./