mirror of
https://github.com/volcengine/verl.git
synced 2025-10-20 13:43:50 +08:00
4de247fe4d
### Checklist Before Starting - [x] Search for similar PR(s). ### What does this PR do? - Unify the functionality of SGLangRollout and AsyncSGLangRollout, remove original SGLangRollout and rename AsyncSGLangRollout to SGLangRollout. - Make trivial changes due to modification in sglang==0.4.6.post5. ### High-Level Design > Demonstrate the high-level design if this PR is complex. ### Specific Changes > List the specific changes. ### API > Demonstrate how the API changes if any. ### Usage Example > Provide usage example(s) for easier usage. ```python # Add code snippet or script demonstrating how to use this ``` ### Test > For changes that can not be tested by CI (e.g., algorithm implementation, new model support), validate by experiment(s) and show results like training curve plots, evaluatuion results, etc. ### Additional Info. - **Issue Number**: Fixes issue # or discussion # if any. - **Training**: [Note which backend this PR will affect: FSDP, Megatron, both, or none] - **Inference**: [Note which backend this PR will affect: vLLM, SGLang, both, or none] ### Checklist Before Submitting - [ ] Read the [Contribute Guide](https://github.com/volcengine/verl?tab=readme-ov-file#contribution-guide). - [ ] Apply [pre-commit checks](https://github.com/volcengine/verl?tab=readme-ov-file#code-linting-and-formatting). - [ ] Add `[BREAKING]` to the PR title if it breaks any API. - [ ] Update the documentation about your changes in the [docs](https://github.com/volcengine/verl/tree/main/docs). - [ ] Add CI test(s) if necessary. --------- Co-authored-by: zyzshishui <@qq.com> Co-authored-by: Xiang Long <mindsculptor@yeah.net> Co-authored-by: ocss884 <ocss.lin@gmail.com> Co-authored-by: zhaochenyang20 <zhaochen20@outlook.com> Co-authored-by: H <linhaibin.eric@gmail.com>
234 lines
12 KiB
YAML
234 lines
12 KiB
YAML
name: e2e_ppo_trainer_megatron
|
|
# latest version: Megatron-LM core_r0.11.0 https://github.com/NVIDIA/Megatron-LM/tree/core_r0.11.0
|
|
|
|
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/e2e_ppo_trainer_megatron.yml"
|
|
- "examples/data_preprocess/gsm8k.py"
|
|
- "tests/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
|
|
|
|
jobs:
|
|
e2e_ppo_trainer_megatron-deepseek:
|
|
runs-on: [L20x8]
|
|
timeout-minutes: 60 # Increase this timeout value as needed
|
|
env:
|
|
HTTP_PROXY: ${{ secrets.PROXY_HTTP }}
|
|
HTTPS_PROXY: ${{ secrets.PROXY_HTTPS }}
|
|
NO_PROXY: "localhost,127.0.0.1,hf-mirror.com"
|
|
HF_ENDPOINT: "https://hf-mirror.com"
|
|
HF_HUB_ENABLE_HF_TRANSFER: "0" # This is more stable
|
|
container:
|
|
image: whatcanyousee/verl:ngc-cu124-vllm0.8.5-sglang0.4.6.post5-mcore0.12.0-te2.3
|
|
options: --gpus all --shm-size=10g
|
|
steps:
|
|
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
|
|
with:
|
|
fetch-depth: 0
|
|
- name: Install the current repository
|
|
run: |
|
|
pip3 install --no-deps -e .[test]
|
|
- name: Prepare GSM8K dataset
|
|
run: |
|
|
python3 examples/data_preprocess/gsm8k.py
|
|
- name: Running GSM8K E2E training tests with 3D parallelism on 8 L20 GPUs with Megatron (DeepSeek)
|
|
run: |
|
|
ray stop --force
|
|
ALL_OFFLOAD=True SAVE_FREQ=1 MODEL_ID=deepseek-ai/deepseek-coder-1.3b-instruct bash tests/e2e/run_ppo_trainer_megatron.sh
|
|
- name: Running GSM8K E2E training tests with 3D parallelism on 8 L20 GPUs with Megatron (DeepSeek)
|
|
run: |
|
|
ray stop --force
|
|
RESUME_MODE=auto MODEL_ID=deepseek-ai/deepseek-coder-1.3b-instruct TOTAL_TRAIN_STEPS=2 bash tests/e2e/run_ppo_trainer_megatron.sh
|
|
- name: Test Megatron checkpoints merging function (DeepSeek Actor and Critic)
|
|
run: |
|
|
exp_name="deepseek-coder-1.3b-instruct-megatron-gsm8k-minimal"
|
|
python scripts/model_merger.py test --backend megatron --local_dir checkpoints/verl-test/${exp_name}/global_step_1/actor --test_hf_dir checkpoints/verl-test/${exp_name}/global_step_1/actor/huggingface
|
|
python scripts/model_merger.py test --backend megatron --is-value-model --local_dir checkpoints/verl-test/${exp_name}/global_step_1/critic --test_hf_dir checkpoints/verl-test/${exp_name}/global_step_1/critic/huggingface
|
|
- name: Running GRPO GSM8K E2E training tests with 3D parallelism on 8 L20 GPUs with Megatron (Deepseek)
|
|
run: |
|
|
ray stop --force
|
|
ADV_ESTIMATOR=grpo USE_DYNAMIC_BSZ=False MODEL_ID=deepseek-ai/deepseek-coder-1.3b-instruct bash tests/e2e/run_ppo_trainer_megatron.sh
|
|
- name: clean up
|
|
run: |
|
|
rm -rf checkpoints
|
|
e2e_ppo_trainer_megatron-qwen3:
|
|
runs-on: [L20x8]
|
|
timeout-minutes: 60 # Increase this timeout value as needed
|
|
env:
|
|
HTTP_PROXY: ${{ secrets.PROXY_HTTP }}
|
|
HTTPS_PROXY: ${{ secrets.PROXY_HTTPS }}
|
|
NO_PROXY: "localhost,127.0.0.1,hf-mirror.com"
|
|
HF_ENDPOINT: "https://hf-mirror.com"
|
|
HF_HUB_ENABLE_HF_TRANSFER: "0" # This is more stable
|
|
container:
|
|
image: whatcanyousee/verl:ngc-cu124-vllm0.8.5-sglang0.4.6.post5-mcore0.12.0-te2.3
|
|
options: --gpus all --shm-size=10g
|
|
steps:
|
|
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
|
|
with:
|
|
fetch-depth: 0
|
|
- name: Install the current repository
|
|
run: |
|
|
pip3 install --no-deps -e .[test]
|
|
- name: Prepare GSM8K dataset
|
|
run: |
|
|
python3 examples/data_preprocess/gsm8k.py
|
|
- name: Running GSM8K E2E training tests with 3D parallelism on 8 L20 GPUs with Megatron (Qwen3) with validation and saving
|
|
run: |
|
|
ray stop --force
|
|
ALL_OFFLOAD=True VAL_BEFORE_TRAIN=True TEST_FREQ=1 SAVE_FREQ=1 MODEL_ID=Qwen/Qwen3-0.6B bash tests/e2e/run_ppo_trainer_megatron.sh
|
|
- name: Running GSM8K E2E training tests with 3D parallelism on 8 L20 GPUs with Megatron (Qwen3) after resuming
|
|
run: |
|
|
ray stop --force
|
|
RESUME_MODE=auto MODEL_ID=Qwen/Qwen3-0.6B bash tests/e2e/run_ppo_trainer_megatron.sh
|
|
- name: Test Megatron checkpoints merging function (Qwen3 Actor and Critic)
|
|
run: |
|
|
exp_name="qwen3-0.6b-megatron-gsm8k-minimal"
|
|
python scripts/model_merger.py test --backend megatron --tie-word-embedding --local_dir checkpoints/verl-test/${exp_name}/global_step_1/actor --test_hf_dir checkpoints/verl-test/${exp_name}/global_step_1/actor/huggingface
|
|
python scripts/model_merger.py test --backend megatron --is-value-model --local_dir checkpoints/verl-test/${exp_name}/global_step_1/critic --test_hf_dir checkpoints/verl-test/${exp_name}/global_step_1/critic/huggingface
|
|
- name: Running GRPO GSM8K E2E training tests with 3D parallelism on 8 L20 GPUs with Megatron (Qwen3)
|
|
run: |
|
|
ray stop --force
|
|
ADV_ESTIMATOR=grpo USE_DYNAMIC_BSZ=False MODEL_ID=Qwen/Qwen3-0.6B bash tests/e2e/run_ppo_trainer_megatron.sh
|
|
- name: clean up
|
|
run: |
|
|
rm -rf checkpoints
|
|
e2e_ppo_trainer_megatron-different-train-infer-tp-qwen-tie-embedding:
|
|
runs-on: [L20x8]
|
|
timeout-minutes: 60 # 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
|
|
container:
|
|
image: whatcanyousee/verl:ngc-cu124-vllm0.8.5-sglang0.4.6.post5-mcore0.12.0-te2.3
|
|
options: --gpus all --shm-size=10g
|
|
steps:
|
|
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
|
|
with:
|
|
fetch-depth: 0
|
|
- name: Install the current repository
|
|
run: |
|
|
pip3 install --no-deps -e .[test]
|
|
- name: Prepare GSM8K dataset
|
|
run: |
|
|
python3 examples/data_preprocess/gsm8k.py
|
|
- name: Running GSM8K E2E training tests with 3D parallelism on 8 L20 GPUs with tie-embedding Megatron (Qwen) with train tp > infer tp
|
|
run: |
|
|
ray stop --force
|
|
VAL_BEFORE_TRAIN=True TEST_FREQ=1 SAVE_FREQ=1 TRAIN_TP=2 INFER_TP=1 MODEL_ID=Qwen/Qwen2.5-1.5B bash tests/e2e/run_ppo_trainer_megatron.sh
|
|
- name: Running GSM8K E2E training tests with 3D parallelism on 8 L20 GPUs with Megatron (Qwen) with train tp < infer tp
|
|
run: |
|
|
ray stop --force
|
|
VAL_BEFORE_TRAIN=True TEST_FREQ=1 SAVE_FREQ=1 TRAIN_TP=1 INFER_TP=2 MODEL_ID=Qwen/Qwen2.5-1.5B bash tests/e2e/run_ppo_trainer_megatron.sh
|
|
- name: clean up
|
|
run: |
|
|
rm -rf checkpoints
|
|
e2e_ppo_trainer_megatron-qwen-override-transformer-config:
|
|
runs-on: [L20x8]
|
|
timeout-minutes: 60 # 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
|
|
container:
|
|
image: whatcanyousee/verl:ngc-cu124-vllm0.8.5-sglang0.4.6.post5-mcore0.12.0-te2.3
|
|
options: --gpus all --shm-size=10g
|
|
steps:
|
|
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
|
|
with:
|
|
fetch-depth: 0
|
|
- name: Install the current repository
|
|
run: |
|
|
pip3 install --no-deps -e .[test]
|
|
- name: Prepare GSM8K dataset
|
|
run: |
|
|
python3 examples/data_preprocess/gsm8k.py
|
|
- name: Prepare dist_ckpt of Qwen2.5-0.5B, uneven layer distribution only supports dist_ckpt
|
|
run: |
|
|
python3 scripts/converter_hf_to_mcore.py --hf_model_path ${HOME}/models/Qwen/Qwen2.5-0.5B --output_path checkpoints/verl-test/qwen2.5-0.5b-megatron
|
|
- name: Running GSM8K E2E training tests with 3D parallelism on 8 L20 GPUs with Megatron (Qwen)
|
|
run: |
|
|
ray stop --force
|
|
SAVE_FREQ=1 COMMON_PP=4 COMMON_VPP=null COMMON_CP=1 SKIP_SAVE_HF_MODEL=1 bash tests/e2e/run_ppo_trainer_megatron.sh +actor_rollout_ref.actor.megatron.override_transformer_config.num_layers_in_first_pipeline_stage=8 +actor_rollout_ref.actor.megatron.override_transformer_config.num_layers_in_last_pipeline_stage=4 actor_rollout_ref.actor.megatron.use_dist_checkpointing=true actor_rollout_ref.actor.megatron.dist_checkpointing_path=checkpoints/verl-test/qwen2.5-0.5b-megatron actor_rollout_ref.ref.megatron.use_dist_checkpointing=true actor_rollout_ref.ref.megatron.dist_checkpointing_path=checkpoints/verl-test/qwen2.5-0.5b-megatron critic.megatron.use_dist_checkpointing=true critic.megatron.dist_checkpointing_path=checkpoints/verl-test/qwen2.5-0.5b-megatron reward_model.megatron.use_dist_checkpointing=true reward_model.megatron.dist_checkpointing_path=checkpoints/verl-test/qwen2.5-0.5b-megatron
|
|
cp -r checkpoints checkpoints-dut
|
|
SAVE_FREQ=1 COMMON_PP=4 COMMON_VPP=null COMMON_CP=1 bash tests/e2e/run_ppo_trainer_megatron.sh
|
|
- name: Test Megatron checkpoints merging function (Qwen Actor and Critic)
|
|
run: |
|
|
exp_name="qwen2.5-0.5b-megatron-gsm8k-minimal"
|
|
python scripts/model_merger.py test --backend megatron --tie-word-embedding --local_dir checkpoints-dut/verl-test/${exp_name}/global_step_1/actor --test_hf_dir checkpoints/verl-test/${exp_name}/global_step_1/actor/huggingface
|
|
python scripts/model_merger.py test --backend megatron --is-value-model --local_dir checkpoints-dut/verl-test/${exp_name}/global_step_1/critic --test_hf_dir checkpoints/verl-test/${exp_name}/global_step_1/critic/huggingface
|
|
- name: clean up
|
|
run: |
|
|
rm -rf checkpoints
|
|
e2e_ppo_trainer_megatron-deepseek-override-transformer-config:
|
|
runs-on: [L20x8]
|
|
timeout-minutes: 60 # Increase this timeout value as needed
|
|
env:
|
|
HTTP_PROXY: ${{ secrets.PROXY_HTTP }}
|
|
HTTPS_PROXY: ${{ secrets.PROXY_HTTPS }}
|
|
NO_PROXY: "localhost,127.0.0.1,hf-mirror.com"
|
|
HF_ENDPOINT: "https://hf-mirror.com"
|
|
HF_HUB_ENABLE_HF_TRANSFER: "0" # This is more stable
|
|
container:
|
|
image: whatcanyousee/verl:ngc-cu124-vllm0.8.5-sglang0.4.6.post5-mcore0.12.0-te2.3
|
|
options: --gpus all --shm-size=10g
|
|
steps:
|
|
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
|
|
with:
|
|
fetch-depth: 0
|
|
- name: Install the current repository
|
|
run: |
|
|
pip3 install --no-deps -e .[test]
|
|
- name: Prepare GSM8K dataset
|
|
run: |
|
|
python3 examples/data_preprocess/gsm8k.py
|
|
- name: Running GSM8K E2E training tests with 3D parallelism on 8 L20 GPUs with Megatron (DeepSeek)
|
|
run: |
|
|
ray stop --force
|
|
SAVE_FREQ=1 MODEL_ID=deepseek-ai/deepseek-coder-1.3b-instruct COMMON_PP=2 COMMON_VPP=null bash tests/e2e/run_ppo_trainer_megatron.sh +actor_rollout_ref.actor.megatron.override_transformer_config.account_for_embedding_in_pipeline_split=true +actor_rollout_ref.actor.megatron.override_transformer_config.account_for_loss_in_pipeline_split=true
|
|
- name: Test Megatron checkpoints merging function (DeepSeek Actor and Critic)
|
|
run: |
|
|
exp_name="deepseek-coder-1.3b-instruct-megatron-gsm8k-minimal"
|
|
python scripts/model_merger.py test --backend megatron --local_dir checkpoints/verl-test/${exp_name}/global_step_1/actor --test_hf_dir checkpoints/verl-test/${exp_name}/global_step_1/actor/huggingface
|
|
python scripts/model_merger.py test --backend megatron --is-value-model --local_dir checkpoints/verl-test/${exp_name}/global_step_1/critic --test_hf_dir checkpoints/verl-test/${exp_name}/global_step_1/critic/huggingface
|
|
- name: clean up
|
|
run: |
|
|
rm -rf checkpoints
|
|
|