name: model_rmpad

on:
  # Trigger the workflow on push or pull request,
  # but only for the main branch
  pull_request:
    branches:
      - main
      - v0.3.x
    paths:
      - "verl/**/*.py"
      - "tests/**/*.sh"
      - "tests/model/*"
      - .github/workflows/model.yml
      - "!recipe/**"

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

jobs:
  model_rmpad:
    runs-on: [L20x8]
    timeout-minutes: 20 # 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 and upgrade to latest transformers/flash_attn
        run: |
          pip3 install -e .[test]
          pip3 install --upgrade transformers
      - name: Running rmpad model tests on 8 L20 GPUs + flash_attn 2.5.8
        run: |
          pytest -s tests/model/test_transformer.py
      - name: Running rmpad model tests on 8 L20 GPUs + latest flash_attn
        run: |
          pip3 install --upgrade flash_attn --no-build-isolation
          pytest -s tests/model/test_transformer.py
      - name: Running FSDP rmpad model tests on 8 L20 GPUs + latest flash_attn
        run: |
          torchrun --nproc_per_node=8 tests/checkpoint/test_fsdp_ckpt.py
      - name: Running transformers ulysses tests on 8 L20 GPUs + latest transformers
        run: |
          torchrun --nproc_per_node=8 -m pytest tests/model/test_transformers_ulysses.py
      - name: Running transformers ulysses tests on 8 L20 GPUs + transformers 4.49.0
        run: |
          pip3 install transformers==4.49.0
          torchrun --nproc_per_node=8 -m pytest tests/model/test_transformers_ulysses.py
      - name: Running transformers ulysses tests on 8 L20 GPUs + transformers 4.48.0
        run: |
          pip3 install transformers==4.48.0
          torchrun --nproc_per_node=8 -m pytest tests/model/test_transformers_ulysses.py
      - name: Running transformers ulysses tests on 8 L20 GPUs + transformers 4.47.0
        run: |
          pip3 install transformers==4.47.0
          torchrun --nproc_per_node=8 -m pytest tests/model/test_transformers_ulysses.py
      - name: Running transformers ulysses tests on 8 L20 GPUs + transformers 4.46.0
        run: |
          pip3 install transformers==4.46.0
          torchrun --nproc_per_node=8 -m pytest tests/model/test_transformers_ulysses.py
      - name: Running transformers ulysses tests on 8 L20 GPUs + transformers 4.45.0
        run: |
          pip3 install transformers==4.45.0
          torchrun --nproc_per_node=8 -m pytest tests/model/test_transformers_ulysses.py
      - name: Run distributed test
        run: |
          bash tests/distributed/run_all.sh