reference/code/SpecForge/.github/workflows/test.yaml

name: PR Test

on:
  pull_request:
    branches: [ main ]
  workflow_dispatch:

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

permissions:
  contents: read

jobs:
  unit-test:
    if: (github.repository == 'sgl-project/SpecForge' || github.event_name == 'pull_request') &&
        github.event.pull_request.draft == false
    runs-on: [self-hosted]
    container:
      image: lmsysorg/sglang:v0.5.14-cu130 # we lock to this version to avoid repeated docker pull
      options: --gpus all --shm-size=2g --rm -v /dev/shm --privileged --pid=host
    steps:
      - name: Checkout code
        uses: actions/checkout@v4

      - name: Restore cache
        run: |
          if [ -d /github/home/cache ] && [ ! -z "$(ls -A /github/home/cache/)" ]; then
            cp -p -r /github/home/cache ./
          fi

          if [ -d /github/home/sf ] && [ ! -z "$(ls -A /github/home/sf/)" ]; then
            cp -p -r /github/home/sf ./
          fi

      - name: Remove flashinfer # this is needed to avoid flashinfer jit compilation makes the program hang
        run: |
          rm -rf /github/home/.cache/flashinfer

      - name: Install dependencies
        shell: bash
        run: |
          # if sf venv does not exist, create it
          if [ ! -d sf ]; then
            uv venv sf -p 3.11
          fi
          source sf/bin/activate
          uv pip install wheel setuptools psutil packaging ninja
          uv pip install torch==2.11.0 --index-url https://download.pytorch.org/whl/cu130
          MAX_JOBS=8  uv pip install -v flash-attn --no-build-isolation
          uv pip install -v . --prerelease=allow

      - name: Run test
        timeout-minutes: 45
        shell: bash
        run: |
          source sf/bin/activate
          export PYTHONPATH=$PWD
          python -m unittest discover -s ./tests -p "test_*.py" -v

      - name: Save cache
        run: |
          cp -p -r sf /github/home/
          cp -p -r cache /github/home/