Nahs / .github /workflows /cpu_unit_tests.yml

Add files using upload-large-folder tool

7a52ba3 verified about 1 month ago

4.64 kB

# # 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: cpu_unit_tests

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

# 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

env:
  IMAGE: "verl-ci-cn-beijing.cr.volces.com/verlai/verl:vllm012.latest"
  DYNAMIC_RUNNER_ENDPOINT: "https://sd10g3clalm04ug7alq90.apigateway-cn-beijing.volceapi.com/runner"

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 }}"

  cpu_unit_tests:
    needs: setup
    runs-on: ["${{ needs.setup.outputs.runner-label || '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-mirror.com"
      HF_ENDPOINT: "https://hf-mirror.com"
      HF_HUB_ENABLE_HF_TRANSFER: "0" # This is more stable
      TORCH_COMPILE_DISABLE: 1
      TORCHINDUCTOR_DISABLE: 1
    steps:
      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
        with:
          fetch-depth: 0
      - name: Install the current repository
        run: |
          pip3 install -r requirements-test.txt
          pip3 install --no-deps -e .
          pip3 install --upgrade transformers
      - name: Download datasets
        run: |
          python3 examples/data_preprocess/gsm8k.py --local_dataset_path ${HOME}/models/hf_data/gsm8k
          python3 examples/data_preprocess/geo3k.py --local_dataset_path ${HOME}/models/hf_data/hiyouga/geometry3k
      - name: Running CPU unit tests
        run: |
          echo '[pytest]' > pytest.ini
          echo 'python_files = *_on_cpu.py' >> pytest.ini
          pytest -s -x --asyncio-mode=auto tests/
  cleanup:
    runs-on: ubuntu-latest
    needs: [setup, cpu_unit_tests]
    if: always()
    steps:
      - id: destroy-runner
        uses: volcengine/vemlp-github-runner@v1
        with:
          mode: "destroy"
          faas-url: "${{ env.DYNAMIC_RUNNER_ENDPOINT }}"
          mlp-task-id: "${{ needs.setup.outputs.mlp-task-id }}"

	# # 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: cpu_unit_tests

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

	# 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

	env:
	IMAGE: "verl-ci-cn-beijing.cr.volces.com/verlai/verl:vllm012.latest"
	DYNAMIC_RUNNER_ENDPOINT: "https://sd10g3clalm04ug7alq90.apigateway-cn-beijing.volceapi.com/runner"

	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 }}"

	cpu_unit_tests:
	needs: setup
	runs-on: ["${{ needs.setup.outputs.runner-label \|\| '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-mirror.com"
	HF_ENDPOINT: "https://hf-mirror.com"
	HF_HUB_ENABLE_HF_TRANSFER: "0" # This is more stable
	TORCH_COMPILE_DISABLE: 1
	TORCHINDUCTOR_DISABLE: 1
	steps:
	- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
	with:
	fetch-depth: 0
	- name: Install the current repository
	run: \|
	pip3 install -r requirements-test.txt
	pip3 install --no-deps -e .
	pip3 install --upgrade transformers
	- name: Download datasets
	run: \|
	python3 examples/data_preprocess/gsm8k.py --local_dataset_path ${HOME}/models/hf_data/gsm8k
	python3 examples/data_preprocess/geo3k.py --local_dataset_path ${HOME}/models/hf_data/hiyouga/geometry3k
	- name: Running CPU unit tests
	run: \|
	echo '[pytest]' > pytest.ini
	echo 'python_files = *_on_cpu.py' >> pytest.ini
	pytest -s -x --asyncio-mode=auto tests/
	cleanup:
	runs-on: ubuntu-latest
	needs: [setup, cpu_unit_tests]
	if: always()
	steps:
	- id: destroy-runner
	uses: volcengine/vemlp-github-runner@v1
	with:
	mode: "destroy"
	faas-url: "${{ env.DYNAMIC_RUNNER_ENDPOINT }}"
	mlp-task-id: "${{ needs.setup.outputs.mlp-task-id }}"