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:

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

permissions:
  contents: read
  issues: write

jobs:
  unit-tests:
    runs-on: [self-hosted, nvidia, a6000]
    container:
      image: nvcr.io/nvidia/pytorch:23.03-py3
      ports:
        - 80
      options: --gpus all --shm-size "8G"

    steps:
      - uses: actions/checkout@v3

      - 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 --depth=1 https://github.com/huggingface/transformers
          cd transformers
          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]
          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="2.0" --cuda_ver="12"
          python -m pytest --color=yes --durations=0 --verbose -rF -m 'inference_v2_ops' unit/ --torch_ver="2.0" --cuda_ver="12"
      - name: MII unit tests
        run: |
          git clone --depth=1 https://github.com/microsoft/DeepSpeed-MII.git
          cd DeepSpeed-MII
          pip install .[dev]
          cd tests
          python -m pytest --color=yes --durations=0 --verbose -rF ./