Revert "[megatron] fix: BF16 mode should use PAO as well" (#4234) #6296
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # # 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: checkpoint_converter | |
| # latest version: Megatron-LM core_v0.14.0 https://github.com/NVIDIA/Megatron-LM/tree/core_v0.14.0 | |
| 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" | |
| # Other entrypoints | |
| - "!examples/**" | |
| - "!tests/**" | |
| - "!verl/trainer/main_*.py" | |
| - "!verl/trainer/fsdp_sft_trainer.py" | |
| # Recipes | |
| - "!recipe/**" | |
| # FSDP | |
| - "!verl/workers/**/*dp_*.py" | |
| # Entrypoints | |
| - ".github/workflows/checkpoint_converter.yml" | |
| - ".github/workflows/e2e_ppo_trainer_megatron.yml" | |
| - "examples/data_preprocess/gsm8k.py" | |
| - "tests/special_e2e/run_ppo_trainer_megatron.sh" | |
| - "verl/trainer/main_ppo.py" | |
| - "verl/trainer/config/ppo_megatron_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' }} | |
| # Declare permissions just read content. | |
| permissions: | |
| contents: read | |
| env: | |
| IMAGE: "verl-ci-cn-beijing.cr.volces.com/verlai/verl:sgl055.dev2" | |
| 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: "${{ env.IMAGE }}" | |
| checkpoint_converter: | |
| needs: setup | |
| runs-on: [ "${{ 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_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] | |
| # - name: Download Model to Use | |
| # run: | | |
| # huggingface-cli download Qwen/Qwen2.5-0.5B --local-dir ${HOME}/models/Qwen/Qwen2.5-0.5B | |
| # huggingface-cli download deepseek-ai/deepseek-coder-1.3b-instruct --local-dir ${HOME}/models/deepseek-ai/deepseek-coder-1.3b-instruct | |
| # export HF_HUB_OFFLINE=1 | |
| - name: Running Huggingface to Megatron dist_ckpt converter (Qwen/Qwen2.5-0.5B) | |
| run: | | |
| ray stop --force | |
| python scripts/converter_hf_to_mcore.py --hf_model_path=${HOME}/models/Qwen/Qwen2.5-0.5B --output_path checkpoints/Qwen/Qwen2.5-0.5B --test | |
| - name: Running Huggingface to Megatron dist_ckpt converter (deepseek-ai/deepseek-coder-1.3b-instruct) | |
| run: | | |
| ray stop --force | |
| python scripts/converter_hf_to_mcore.py --hf_model_path=${HOME}/models/deepseek-ai/deepseek-coder-1.3b-instruct --output_path checkpoints/deepseek-ai/deepseek-coder-1.3b-instruct --test | |
| - name: Clean up | |
| run: | | |
| rm -rf checkpoints | |
| checkpoint_converter_large_moe_models: | |
| needs: setup | |
| runs-on: [ "${{ needs.setup.outputs.runner-label || 'L20x8' }}" ] | |
| timeout-minutes: 30 # 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 | |
| HF_ENDPOINT: "https://hf-mirror.com" | |
| steps: | |
| - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2 | |
| with: | |
| fetch-depth: 0 | |
| - name: Install the current repository | |
| run: | | |
| pip3 install -e .[test] | |
| # - name: Download Model to Use | |
| # run: | | |
| # huggingface-cli download Qwen/Qwen1.5-MoE-A2.7B-Chat --local-dir ${HOME}/models/Qwen/Qwen1.5-MoE-A2.7B-Chat | |
| # export HF_HUB_OFFLINE=1 | |
| - name: Running Huggingface to Megatron dist_ckpt CPU converter (Qwen/Qwen1.5-MoE-A2.7B-Chat) | |
| run: | | |
| ray stop --force | |
| python scripts/converter_hf_to_mcore.py --hf_model_path=${HOME}/models/Qwen/Qwen1.5-MoE-A2.7B-Chat --output_path checkpoints/Qwen/Qwen1.5-MoE-A2.7B-Chat --use_cpu_initialization | |
| - name: Running distributed Huggingface to Megatron dist_ckpt CPU converter (Qwen/Qwen1.5-MoE-A2.7B-Chat) | |
| run: | | |
| ray stop --force | |
| torchrun --nproc_per_node 8 --nnodes 1 scripts/converter_hf_to_mcore.py --hf_model_path=${HOME}/models/Qwen/Qwen1.5-MoE-A2.7B-Chat --output_path checkpoints/Qwen/Qwen1.5-MoE-A2.7B-Chat_dist --use_cpu_initialization | |
| - name: clean up | |
| run: | | |
| rm -rf checkpoints | |
| cleanup: | |
| runs-on: ubuntu-latest | |
| needs: | |
| [ | |
| setup, | |
| checkpoint_converter, | |
| checkpoint_converter_large_moe_models | |
| ] | |
| if: always() | |
| steps: | |
| - id: destroy-runner | |
| uses: volcengine/vemlp-github-runner@v1 | |
| with: | |
| mode: "destroy" | |
| faas-url: "${{ env.DYNAMIC_RUNNER_ENDPOINT }}" | |
| mlp-task-id: "${{ needs.setup.outputs.mlp-task-id }}" |