name: ray

on:
  # Trigger the workflow on push or pull request,
  # but only for the main branch
  push:
    branches:
      - main
      - v0.2.x
    paths:
      - "verl/single_controller/*.py"
      - .github/workflows/ray_test.yml
  pull_request:
    branches:
      - main
      - v0.2.x
    paths:
      - "verl/single_controller/*.py"
      - .github/workflows/ray_test.yml
      - "!recipe/**"

# Cancel jobs on the same ref if a new one is triggered
concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}

# Declare permissions just read content.
permissions: 
  contents: read

jobs:
  ray:
    runs-on: [L20x8]
    timeout-minutes: 10 # Increase this timeout value as needed
    env:
      HTTP_PROXY: ${{ secrets.PROXY_HTTP }}
      HTTPS_PROXY: ${{ secrets.PROXY_HTTPS }}
      NO_PROXY: "localhost,127.0.0.1"
      HF_HUB_ENABLE_HF_TRANSFER: "0" # This is more stable
    container:
      image: whatcanyousee/verl:ngc-th2.6.0-cu124-vllm0.8.2-mcore0.11.0-te2.0
      options: --gpus all --shm-size=10g
    steps:
      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
        with:
            fetch-depth: 0
      - name: Install the current repository
        run: |
          pip install -e .[test]
          pip install --upgrade "ray>=2.40.0"
      - name: Running ray tests that need 8 GPUs
        run: |
          cd tests/ray
          pytest -s -x --ignore=test_check_worker_alive.py --ignore=test_rvdz.py .