LLaMA-Factory/.github/workflows/tests_cuda.yml

name: tests_cuda

on:
  workflow_dispatch:
  push:
    branches:
      - "main"
    paths:
      - "**/*.py"
      - "pyproject.toml"
      - "Makefile"
      - ".github/workflows/*.yml"
  pull_request:
    branches:
      - "main"
    paths:
      - "**/*.py"
      - "pyproject.toml"
      - "Makefile"
      - ".github/workflows/*.yml"

jobs:
  tests:
    strategy:
      fail-fast: false
      matrix:
        python:
          - "3.11"
        os:
          - "linux-x86_64-gpu-2"

    runs-on: ${{ matrix.os }}

    concurrency:
      group: ${{ github.workflow }}-${{ github.ref }}-${{ matrix.os }}-${{ matrix.python }}
      cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}

    steps:
      - name: Checkout
        uses: actions/checkout@v4

      - name: Install uv
        uses: astral-sh/setup-uv@v7
        with:
          python-version: ${{ matrix.python }}
          github-token: ${{ github.token }}
          enable-cache: false

      - name: Check GPU Status
        run: nvidia-smi

      - name: Install dependencies
        run: |
          uv venv
          uv pip install -e ".[dev]"

      - name: Cache HuggingFace models
        id: hf-hub-cache
        uses: actions/cache@v4
        with:
          path: ${{ runner.temp }}/huggingface
          key: hf-cache-${{ runner.os }}-${{ hashFiles('tests/version.txt') }}

      - name: Check quality
        run: |
          make style && make quality
        env:
          UV_NO_SYNC: 1

      - name: Check license
        run: |
          make license
        env:
          UV_NO_SYNC: 1

      - name: Check build
        run: |
          make build
        env:
          UV_NO_SYNC: 1

      - name: Test with pytest
        run: |
          make test
        env:
          UV_NO_SYNC: 1
          HF_HOME: ${{ runner.temp }}/huggingface
          HF_HUB_OFFLINE: "${{ steps.hf-hub-cache.outputs.cache-hit == 'true' && '1' || '0' }}"