name: e2e_sppo

on:
  # Trigger the workflow on push or pull request,
  # but only for the main branch
  push:
    branches:
      - main
      - v0.*
    paths:
      - "**/*.py"
      # Other entrypoints
      - "!examples/**"
      - "!tests/**"
      - "!verl/trainer/main_*.py"
      - "!verl/trainer/fsdp_sft_trainer.py"
      # Other recipes
      - "!recipe/**"
      # Megatron
      - "!verl/workers/**/megatron_*.py"
      # Home
      - "recipe/sppo"
      # Entrypoints
      - ".github/workflows/e2e_sppo.yml"
      - "examples/data_preprocess/gsm8k.py"
      - "tests/special_e2e/run_sppo.sh"
  pull_request:
    branches:
      - main
      - v0.*
    paths:
      - "**/*.py"
      # Other entrypoints
      - "!examples/**"
      - "!tests/**"
      - "!verl/trainer/main_*.py"
      - "!verl/trainer/fsdp_sft_trainer.py"
      # Other recipes
      - "!recipe/**"
      # Megatron
      - "!verl/workers/**/megatron_*.py"
      # Home
      - "recipe/sppo"
      # Entrypoints
      - ".github/workflows/e2e_sppo.yml"
      - "examples/data_preprocess/gsm8k.py"
      - "tests/special_e2e/run_sppo.sh"

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

# 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' }}

env:
  IMAGE: "verl-ci-cn-beijing.cr.volces.com/verlai/verl:app-verl0.6-transformers4.56.1-sglang0.5.2-mcore0.13.0-te2.2"
  DYNAMIC_RUNNER_ENDPOINT: "https://sd10g3clalm04ug7alq90.apigateway-cn-beijing.volceapi.com/runner"
  TRANSFORMERS_VERSION: "4.56.2"

jobs:
  setup:
    if: github.repository_owner == 'volcengine'
    runs-on: ubuntu-latest
    outputs:
      runner-label: ${{ steps.create-runner.outputs.runner-label }}
      mlp-task-id: ${{ steps.create-runner.outputs.mlp-task-id }}
    steps:
      - uses: actions/checkout@v4
      - id: create-runner
        uses: volcengine/vemlp-github-runner@v1
        with:
          mode: "create"
          faas-url: "${{ env.DYNAMIC_RUNNER_ENDPOINT }}"
          mlp-image: "${{ env.IMAGE }}"

  e2e_sppo:
    needs: setup
    runs-on: [ "${{ needs.setup.outputs.runner-label || 'L20x8' }}" ]
    timeout-minutes: 40 # 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-mirror.com"
      HF_ENDPOINT: "https://hf-mirror.com"
      HF_HUB_ENABLE_HF_TRANSFER: "0" # This is more stable
    steps:
      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
        with:
          fetch-depth: 0
      - name: Install the current repository
        run: |
          pip3 install -e .[test,gpu,sglang]
      - name: Prepare MATH dataset
        run: |
          python3 examples/data_preprocess/math_dataset.py --local_dataset_path $HOME/models/hf_data/DigitalLearningGmbH/MATH-lighteval
      - name: Running the E2E test with the SPPO algorithm
        run: |
          ray stop --force
          bash tests/special_e2e/run_sppo.sh

  cleanup:
    runs-on: ubuntu-latest
    needs:
      [
        setup,
        e2e_sppo
      ]
    if: always()
    steps:
      - id: destroy-runner
        uses: volcengine/vemlp-github-runner@v1
        with:
          mode: "destroy"
          faas-url: "${{ env.DYNAMIC_RUNNER_ENDPOINT }}"
          mlp-task-id: "${{ needs.setup.outputs.mlp-task-id }}"