diff --git a/.github/workflows/test_cuda.yml b/.github/workflows/test_cuda.yml index 4be035ba21..7b46563d11 100644 --- a/.github/workflows/test_cuda.yml +++ b/.github/workflows/test_cuda.yml @@ -18,30 +18,34 @@ jobs: name: Test Python and C++ on CUDA runs-on: nvidia # https://github.com/deepmodeling/deepmd-kit/pull/2884#issuecomment-1744216845 - container: - image: nvidia/cuda:12.9.1-cudnn-devel-ubuntu22.04 - options: --gpus all + # container: + # image: nvidia/cuda:12.9.1-cudnn-devel-ubuntu22.04 + # options: --gpus all if: github.repository_owner == 'deepmodeling' && (github.event_name == 'pull_request' && github.event.label && github.event.label.name == 'Test CUDA' || github.event_name == 'workflow_dispatch' || github.event_name == 'merge_group') steps: - - name: Make sudo and git work - run: apt-get update && apt-get install -y sudo git - uses: actions/checkout@v6 - uses: actions/setup-python@v6 with: python-version: "3.11" # cache: 'pip' - name: Install wget and unzip - run: apt-get update && apt-get install -y wget unzip + run: sudo apt-get update && sudo apt-get install -y wget unzip - uses: lukka/get-cmake@latest with: useLocalCache: true useCloudCache: false - run: | - wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-keyring_1.0-1_all.deb \ - && sudo dpkg -i cuda-keyring_1.0-1_all.deb \ + UBUNTU_VERSION=$(lsb_release -rs | tr -d '.') + OS_NAME="ubuntu${UBUNTU_VERSION}" + echo "Current OS: ${OS_NAME}" + + wget https://developer.download.nvidia.com/compute/cuda/repos/${OS_NAME}/x86_64/cuda-keyring_1.1-1_all.deb \ + && sudo dpkg -i cuda-keyring_1.1-1_all.deb \ && sudo apt-get update \ - && sudo apt-get -y install cuda-12-3 libcudnn8=8.9.5.*-1+cuda12.3 - if: false # skip as we use nvidia image + && sudo apt-get -y install cuda-toolkit-12-9 cudnn9-cuda-12 + echo "CUDA_PATH=/usr/local/cuda-12.9" >> $GITHUB_ENV + echo "/usr/local/cuda-12.9/bin" >> $GITHUB_PATH + # if: false # skip as we use nvidia image - run: python -m pip install -U uv - run: source/install/uv_with_retry.sh pip install --system --group pin_tensorflow_gpu --group pin_pytorch_gpu --group pin_jax_gpu - run: |