unit_test_gpu.yaml

name: unit test

on:
  push:
    branches: [ main ]
  pull_request:

jobs:
  unit_tests:
    runs-on: ${{ matrix.os }}
    strategy:
      matrix:
        os: [linux.p3.8xlarge.nvidia.gpu]
        python-version: [3.8]
        cuda-tag: ["cu11"]
    steps:
      - name: Check out repo
        uses: actions/checkout@v2
      - name: Setup conda env
        uses: conda-incubator/setup-miniconda@v2
        with:
          miniconda-version: "latest"
          activate-environment: test
          python-version: ${{ matrix.python-version }}
      - name: Clean up previous CUDA driver installations
        shell: bash
        run: |
          set -x
          yum list installed | grep nvidia || true
          yum list installed | grep cuda || true
          sudo yum remove -y cuda || true
          sudo yum remove -y cuda-drivers || true
          sudo yum remove -y "*nvidia*" || true
      - name: Install nvidia driver, nvidia-docker runtime, set GPU_FLAG
        uses: nick-fields/retry@71062288b76e2b6214ebde0e673ce0de1755740a
        with:
          timeout_minutes: 10
          max_attempts: 3
          command: |
            set -ex
            bash .github/scripts/install_nvidia_utils_linux.sh
            echo "GPU_FLAG=--gpus all" >> "${GITHUB_ENV}"
      - name: Display EC2 information
        shell: bash
        run: |
          set -euo pipefail
          function get_ec2_metadata() {
            # Pulled from instance metadata endpoint for EC2
            # see https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/instancedata-data-retrieval.html
            category=$1
            curl -fsSL "http://169.254.169.254/latest/meta-data/${category}"
          }
          echo "ami-id: $(get_ec2_metadata ami-id)"
          echo "instance-id: $(get_ec2_metadata instance-id)"
          echo "instance-type: $(get_ec2_metadata instance-type)"
      - name: Install dependencies
        shell: bash -l {0}
        run: |
          set -eux
          conda activate test
          pip install --pre torch -f https://download.pytorch.org/whl/nightly/cu113/torch_nightly.html
          pip install -r requirements.txt
          pip install -r dev-requirements.txt
          pip install --no-build-isolation -e ".[dev]"
      - name: Run unit tests with coverage
        shell: bash -l {0}
        run: |
          set -eux
          conda activate test
          pytest --cov=. --cov-report xml tests/gpu_tests -vv
      - name: Upload Coverage to Codecov
        uses: codecov/codecov-action@v2