# # Tests layout

# Each folder under tests/ corresponds to a test category for a sub-namespace in verl. For instance:
# - `tests/trainer` for testing functionality related to `verl/trainer`
# - `tests/models` for testing functionality related to `verl/models`
# - ...

# There are a few folders with `special_` prefix, created for special purposes:
# - `special_distributed`: unit tests that must run with multiple GPUs
# - `special_e2e`: end-to-end tests with training/generation scripts
# - `special_npu`: tests for NPUs
# - `special_sanity`: a suite of quick sanity tests
# - `special_standalone`: a set of test that are designed to run in dedicated environments

# Accelerators for tests 
# - By default tests are run with GPU available, except for the ones under `special_npu`, and any test script whose name ends with `on_cpu.py`.
# - For test scripts with `on_cpu.py` name suffix would be tested on CPU resources in linux environment.

# # Workflow layout

# All CI tests are configured by yaml files in `.github/workflows/`. Here's an overview of all test configs:
# 1. A list of always triggered CPU sanity tests: `check-pr-title.yml`, `secrets_scan.yml`, `check-pr-title,yml`, `pre-commit.yml`, `doc.yml`
# 2. Some heavy multi-GPU unit tests, such as `model.yml`, `vllm.yml`, `sgl.yml`
# 3. End-to-end tests: `e2e_*.yml`
# 4. Unit tests
#   - `cpu_unit_tests.yml`, run pytest on all scripts with file name pattern `tests/**/test_*_on_cpu.py`
#   - `gpu_unit_tests.yml`, run pytest on all scripts with file without the `on_cpu.py` suffix.
#   - Since cpu/gpu unit tests by default runs all tests under `tests`, please make sure tests are manually excluded in them when
#     - new workflow yaml is added to `.github/workflows`
#     - new tests are added to workflow mentioned in 2.


name: e2e_ascend

on:
  # Trigger the workflow on push or pull request,
  # but only for the main branch
  push:
    branches:
      - main
      - v0.*
  pull_request:
    branches:
      - main
    paths:
      - "**/*.py"
      - "requirements-npu.txt"
      # Other entrypoints
      - "!examples/**"
      - "!tests/**"
      - "!verl/trainer/main_*.py"
      - "!verl/trainer/fsdp_sft_trainer.py"
      # Recipes
      - "!recipe/**"
      # Entrypoints
      - ".github/workflows/e2e_ascend.yml"
      - "examples/data_preprocess/gsm8k.py"
      - "examples/data_preprocess/geo3k.py"
      - "tests/special_e2e/ppo_trainer"
      - "verl/trainer/main_ppo.py"
      - "verl/trainer/config/ppo_trainer.yaml"

# 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' }}

permissions:
  contents: read

jobs:
  test:
    name: verl Ascend test (self-host)
    runs-on: [self-hosted, npu-0]
    timeout-minutes: 40 # Increase this timeout value as needed
    container:
      image: crispig/verl_npu:cann8.1rc1-py3.10-torch2.5.1-vllm-ascend0.7.3.post1-250616
      volumes:
        - /usr/local/dcmi:/usr/local/dcmi
        - /usr/local/bin/npu-smi:/usr/local/bin/npu-smi
        - /usr/local/Ascend/driver/lib64/:/usr/local/Ascend/driver/lib64/
        - /usr/local/Ascend/driver/version.info:/usr/local/Ascend/driver/version.info
        - /etc/ascend_install.info:/etc/ascend_install.info
        # Use self-host cache speed up pip and model download
        # - /home/action/actions-runner/_work/cache:/github/home/.cache/
      options: >-
        --device /dev/davinci0
        --device /dev/davinci_manager
        --device /dev/devmm_svm
        --device /dev/hisi_hdc
        --network host
        --privileged
        --shm-size 16g
    env: 
      HTTP_PROXY: ${{ secrets.PROXY_HTTP }}
      HTTPS_PROXY: ${{ secrets.PROXY_HTTPS }}
      NO_PROXY: "localhost,127.0.0.1,hf-mirror.com"
      HF_ENDPOINT: "https://hf-mirror.com"
      HF_HUB_ENABLE_HF_TRANSFER: "0" # This is more stable
    steps:
      - name: Check npu and CANN info
        run: |
          cat /usr/local/Ascend/ascend-toolkit/latest/"$(uname -i)"-linux/ascend_toolkit_install.info
          npu-smi info
      - name: Checkout volcengine/verl repo
        uses: actions/checkout@v4
      - name: Install the current repository
        run: |
          pip3 install hf_transfer peft
          pip3 install -r requirements-npu.txt
          pip install -e .
      - name: Install torchviison
        run: |
          pip install torchvision==0.20.1+cpu --index-url https://download.pytorch.org/whl/cpu
      - name: Prepare gsm8k dataset
        run: |
          ray stop --force
          python3 examples/data_preprocess/gsm8k.py
      - name: Prepare geo3k dataset
        run: |
          ray stop --force
          python3 examples/data_preprocess/geo3k.py
      - name: Running gsm8k e2e training tests with peft sft on ASCEND NPU
        run: |
          ray stop --force
          bash tests/special_npu/run_qwen2_5_05b_sft_peft_sp2.sh
          rm -rf $HOME/ckpts
      - name: Running gsm8k e2e training tests with GRPO on ASCEND NPU
        run: |
          ray stop --force
          bash tests/special_npu/run_qwen2_5_05b_grpo.sh
          rm -rf $HOME/ckpts
      - name: Running geo3k e2e training tests with GRPO on ASCEND NPU
        run: |
          ray stop --force
          bash tests/special_npu/run_qwen2_5_vl_3b_npu.sh
          rm -rf $HOME/ckpts
      - name: Running gsm8k e2e training tests with DAPO on ASCEND NPU
        run: |
          ray stop --force
          bash tests/special_npu/run_qwen2_5_05b_dapo.sh
          rm -rf $HOME/ckpts