name: amd on: push: branches: - 'master' - 'staging**' paths-ignore: - 'docs/**' pull_request: paths-ignore: - 'docs/**' concurrency: group: ${{ github.workflow }}-${{ github.ref }} cancel-in-progress: true jobs: unit-tests: # The type of runner that the job will run on runs-on: [self-hosted, amd] # Steps represent a sequence of tasks that will be executed as part of the job steps: # Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it - uses: actions/checkout@v2 # Runs a single command using the runners shell - name: environment run: | echo "JobID: $AISC_NODE_INSTANCE_ID" rocm-smi --showhw which python python --version which hipcc hipcc --version pip install --upgrade pip pip uninstall --yes torch torchvision triton pip install torch torchvision --extra-index-url https://download.pytorch.org/whl/rocm5.1.1 python -c "import torch; print('torch:', torch.__version__, torch)" python -c "import torch; print('CUDA available:', torch.cuda.is_available())" sudo apt-get update sudo apt-get install -y libaio-dev - name: Python environment run: | pip list - name: Install transformers run: | git clone https://github.com/huggingface/transformers cd transformers # if needed switch to the last known good SHA until transformers@master is fixed # git checkout 1cc453d33 git rev-parse --short HEAD pip install . # Runs a set of commands using the runners shell - name: Install deepspeed run: | pip install .[dev,1bit,autotuning] #python -c "from deepspeed.env_report import cli_main; cli_main()" ds_report # Runs a set of commands using the runners shell - name: Unit tests run: | if [[ -d ./torch-extensions ]]; then rm -rf ./torch-extensions; fi cd tests TORCH_EXTENSIONS_DIR=./torch-extensions pytest --color=yes --durations=0 --forked -n 4 --verbose unit/ TORCH_EXTENSIONS_DIR=./torch-extensions pytest --color=yes --durations=0 --forked --verbose -m 'sequential' unit/