gpu_e2e_ci_fully_async.yaml

name: SkyRL-GPU-E2E-CI-Fully-Async

on:
  schedule:
    - cron: '5 8 * * *'   # Every day at 08:05 UTC (~00:05 PST / ~01:05 PDT)
  workflow_dispatch:

permissions:
  checks: write   # for status checks to appear
  contents: read

jobs:
  
  skyrl_gpu_e2e_test_fully_async:
    runs-on: ubuntu-latest
    defaults:
      run:
        shell: bash
        working-directory: .

    steps:
      - uses: actions/checkout@v4
      - name: Set up Python
        # This is the version of the action for setting up Python, not the Python version.
        uses: actions/setup-python@v5
        with:
          # Semantic version range syntax or exact version of a Python version
          python-version: '3.12'
          cache: 'pip'
      - name: Install the latest version of uv
        uses: astral-sh/setup-uv@v6
        with:
          activate-environment: true
      - name: Install basic dependencies
        run: uv pip install anyscale==0.26.103 typer==0.9.0
      - name: Install envsubst
        run: sudo apt-get update && sudo apt-get install -y gettext-base
      - name: Basic convergence test
        env:
          ANYSCALE_CLI_TOKEN: ${{ secrets.ANYSCALE_CLI_TOKEN }}
          ANYSCALE_HOST: https://console.anyscale.com
          WANDB_API_KEY: ${{ secrets.WANDB_API_KEY }}
        run: |
          envsubst < ci/anyscale_gpu_e2e_test_fully_async.yaml > ci/anyscale_gpu_e2e_test_fully_async_envsubst.yaml
          COMMIT_SHA="${{ github.event.pull_request.head.sha || github.sha }}"
          JOB_NAME="skyrl-train-gpu-e2e-test-fully-async-${COMMIT_SHA:0:7}-${{ github.run_id }}"
          anyscale job submit -f ci/anyscale_gpu_e2e_test_fully_async_envsubst.yaml --name "$JOB_NAME" --timeout 5000
          anyscale job wait --cloud sky-anyscale-aws-us-east-1 --name "$JOB_NAME" --timeout 5000
          rm -f ci/anyscale_gpu_e2e_test_fully_async_envsubst.yaml