name: nv-megatron

on:
  push:
    branches:
      - 'staging**'
    paths-ignore:
      - 'docs/**'
  pull_request:
    paths-ignore:
      - 'docs/**'
  schedule:
    - cron: "0 0 * * *"

concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: true

jobs:
  unit-tests:
    runs-on: [self-hosted, nvidia, cu116, v100]

    steps:
      - uses: actions/checkout@v2

      - id: setup-venv
        uses: ./.github/workflows/setup-venv

      - name: Install pytorch
        run: |
          pip install torch==1.13.1 torchvision --extra-index-url https://download.pytorch.org/whl/cu116
          python -c "import torch; print('torch:', torch.__version__, torch)"
          python -c "import torch; print('CUDA available:', torch.cuda.is_available())"

      - name: Install deepspeed
        run: |
          pip install .[dev]
          ds_report

      - name: Install apex
        run: |
          pip install -v --disable-pip-version-check --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" git+https://github.com/NVIDIA/apex.git

      - name: Python environment
        run: |
          pip list

      - name: Megatron unit tests
        run: |
          git clone https://github.com/microsoft/Megatron-DeepSpeed.git
          cd Megatron-DeepSpeed
          pip install .
          unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
          if [[ -d ./torch-extensions ]]; then rm -rf ./torch-extensions; fi
          cd tests
          MEGATRON_CKPT_DIR=/blob/megatron_ckpt/ TORCH_EXTENSIONS_DIR=./torch-extensions pytest --color=yes --durations=0 --verbose ./