3d_parallelism_unit_tests.yaml

name: Run non-FA2-related unit tests

on:
  workflow_dispatch:
  push:
    branches: [ main ]
    # paths:
    #   - "src/**/*.py"
    #   - "examples/**/*.py"
    #   - "tests/**/*.py"

  pull_request:
    branches: [ main ]
    #paths:
    #  - "src/**/*.py"
    #  - "examples/**/*.py"
    #  - "tests/**/*.py"

jobs:
  tests:
    runs-on: [multi-gpu, nvidia-gpu, 8-t4, ci]
    container:
      # image: nvcr.io/nvidia/pytorch:23.03-py3
      image: runpod/pytorch:2.1.1-py3.10-cuda12.1.1-devel-ubuntu22.04
      ports:
        - 80
      options: --gpus all --shm-size "8G"
    steps:
    - uses: actions/checkout@v3
    # - name: Set up Python 3.10
    #   uses: actions/setup-python@v2
    #   with:
    #     python-version: '3.10'

    - name: Python environment
      run: |
        which python
        python --version

    - name: Check Pytorch version
      run: |
        nvidia-smi
        python -c "import torch; print('torch:', torch.__version__, torch)"
        python -c "import torch; print('CUDA available:', torch.cuda.is_available())"

    - name: Instal nanotron
      run: |
        python -m pip install --upgrade pip
        pip install packaging
        pip install wheel
        git clone https://github.com/huggingface/nanotron.git
        cd nanotron
        pip install -e .
        pip install -e .[dev]
        pip install -e .[test]

    - name: Install test dependencies
      run: |
        pip install pytest
        pip install pytest-cov

    - name: Show installed libraries and their versions
      run: pip freeze | tee installed.txt

    - name: Run tests
      # NOTE: -m "not fa2" will run all the unit tests that don't have the mark
      # "fa2" (these are FA2-related tests, we can't run it on T4)
      run: pytest -m "not fa2" --color=yes --durations=0 --verbose tests/