[rollout,vllm] fix: Add LoRA Loading to Async vLLM #2641

Workflow file for this run

.github/workflows/e2e_ppo_trainer_megatron_vllm.yml at ed0f61c

	# # 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_ppo_trainer_megatron_vllm

	on:
	# Trigger the workflow on push or pull request,
	# but only for the main branch.
	# For push, for now only anti-patterns are specified so it is more conservative
	# and achieves higher coverage.
	push:
	branches:
	- main
	- v0.*
	paths:
	- "*/.py"
	# Other entrypoints
	- "!verl/trainer/fsdp_sft_trainer.py"
	# Recipes
	- "!recipe/**"
	# FSDP
	- "!verl/workers/*/dp_*.py"
	pull_request:
	branches:
	- main
	- v0.*
	paths:
	- "*/.py"
	# Other entrypoints
	- "!docker/**"
	# Docs
	- "!*/.md"
	- "!docs/**"
	- "!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_vllm.yml"
	- "examples/data_preprocess/gsm8k.py"
	- "examples/data_preprocess/geo3k.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:app-verl0.5-transformers4.55.4-vllm0.10.0-mcore0.13.0-te2.2"
	DYNAMIC_RUNNER_ENDPOINT: "https://sd10g3clalm04ug7alq90.apigateway-cn-beijing.volceapi.com/runner"
	TRANSFORMERS_VERSION: "4.56.2"

	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 }}"

	e2e_ppo_trainer_megatron-deepseek:
	needs: setup
	runs-on: ["${{ needs.setup.outputs.runner-label \|\| 'L20x8' }}"]
	timeout-minutes: 60 # Increase this timeout value as needed
	env:
	HTTP_PROXY: ${{ secrets.PROXY_HTTP }}
	HTTPS_PROXY: ${{ secrets.PROXY_HTTPS }}
	NO_PROXY: "localhost,127.0.0.1,hf-mirror.com"
	HF_ENDPOINT: "https://hf-mirror.com"
	HF_HUB_ENABLE_HF_TRANSFER: "0" # This is more stable
	steps:
	- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
	with:
	fetch-depth: 0
	- name: Install the current repository
	run: \|
	pip3 install --no-deps -e .[test]
	pip3 install math-verify transformers==$TRANSFORMERS_VERSION
	- name: Prepare GSM8K dataset
	run: \|
	python3 examples/data_preprocess/gsm8k.py --local_dataset_path ${HOME}/models/hf_data/gsm8k
	- name: Running GSM8K E2E training tests with 3D parallelism on 8 L20 GPUs with Megatron, use mbridge e2e to pre-load and save (Deepseek)
	run: \|
	ray stop --force
	ALL_OFFLOAD=True SAVE_FREQ=1 MODEL_ID=deepseek-ai/deepseek-coder-1.3b-instruct COMMON_PP=4 COMMON_VPP=null COMMON_CP=1 USE_MBRIDGE=True USE_DIST_CKPT=False \
	bash tests/special_e2e/run_ppo_trainer_megatron.sh
	- name: Running GSM8K E2E training tests with 3D parallelism on 8 L20 GPUs with Megatron, use mbridge e2e to pre-load and save (Deepseek)
	run: \|
	ray stop --force
	RESUME_MODE=auto MODEL_ID=deepseek-ai/deepseek-coder-1.3b-instruct TOTAL_TRAIN_STEPS=2 SAVE_FREQ=1 COMMON_PP=4 COMMON_VPP=null COMMON_CP=1 USE_MBRIDGE=True USE_DIST_CKPT=False \
	bash tests/special_e2e/run_ppo_trainer_megatron.sh
	- name: Running GSM8K E2E training tests with 3D parallelism on 8 L20 GPUs with Megatron (DeepSeek)
	run: \|
	ray stop --force
	export VLLM_USE_V1=1
	ray start --head
	MODE=async USE_FUSED_KERNELS=True MODEL_ID=deepseek-ai/deepseek-coder-1.3b-instruct TOTAL_TRAIN_STEPS=2 SAVE_FREQ=2 bash tests/special_e2e/run_ppo_trainer_megatron.sh
	- name: Test Megatron checkpoints merging function (DeepSeek Actor and Critic)
	run: \|
	exp_name="deepseek-coder-1.3b-instruct-megatron-gsm8k-minimal"
	python -m verl.model_merger test --backend megatron --local_dir checkpoints/verl-test/${exp_name}/global_step_2/actor --test_hf_dir checkpoints/verl-test/${exp_name}/global_step_2/actor/huggingface
	python -m verl.model_merger test --backend megatron --is-value-model --local_dir checkpoints/verl-test/${exp_name}/global_step_2/critic --test_hf_dir checkpoints/verl-test/${exp_name}/global_step_2/critic/huggingface
	- name: Test Megatron distributed checkpoints merging function (DeepSeek)
	run: \|
	exp_name="deepseek-coder-1.3b-instruct-megatron-gsm8k-minimal"
	torchrun --nproc_per_node 4 --nnodes 1 -m verl.model_merger merge --backend megatron --local_dir checkpoints/verl-test/${exp_name}/global_step_2/actor --target_dir checkpoints/verl-test/${exp_name}/global_step_2/actor/hf_model
	- name: Running GRPO GSM8K E2E training tests with 3D parallelism on 8 L20 GPUs with Megatron (Deepseek)
	run: \|
	ray stop --force
	ADV_ESTIMATOR=grpo USE_DYNAMIC_BSZ=False MODEL_ID=deepseek-ai/deepseek-coder-1.3b-instruct bash tests/special_e2e/run_ppo_trainer_megatron.sh
	- name: clean up
	run: \|
	rm -rf checkpoints
	e2e_ppo_trainer_megatron-qwen3:
	needs: setup
	runs-on: ["${{ needs.setup.outputs.runner-label \|\| 'L20x8' }}"]
	timeout-minutes: 60 # Increase this timeout value as needed
	env:
	HTTP_PROXY: ${{ secrets.PROXY_HTTP }}
	HTTPS_PROXY: ${{ secrets.PROXY_HTTPS }}
	NO_PROXY: "localhost,127.0.0.1,hf-mirror.com"
	HF_ENDPOINT: "https://hf-mirror.com"
	HF_HUB_ENABLE_HF_TRANSFER: "0" # This is more stable
	steps:
	- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
	with:
	fetch-depth: 0
	- name: Install the current repository
	run: \|
	pip3 install --no-deps -e .[test]
	pip3 install math-verify transformers==$TRANSFORMERS_VERSION
	- name: Prepare GSM8K dataset
	run: \|
	python3 examples/data_preprocess/gsm8k.py --local_dataset_path ${HOME}/models/hf_data/gsm8k
	- 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/special_e2e/run_ppo_trainer_megatron.sh
	- name: Running GSM8K E2E training tests with 3D parallelism on 8 L20 GPUs with Megatron (Qwen3) testing learning rate scheduler
	run: \|
	ray stop --force
	LR_WARMUP_STEPS=1 TOTAL_TRAIN_STEPS=2 MODEL_ID=Qwen/Qwen3-0.6B bash tests/special_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 -m verl.model_merger 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 -m verl.model_merger 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
	e2e_ppo_trainer_megatron-different-train-infer-tp-qwen-tie-embedding:
	needs: setup
	runs-on: ["${{ needs.setup.outputs.runner-label \|\| 'L20x8' }}"]
	timeout-minutes: 60 # Increase this timeout value as needed
	env:
	HTTP_PROXY: ${{ secrets.PROXY_HTTP }}
	HTTPS_PROXY: ${{ secrets.PROXY_HTTPS }}
	NO_PROXY: "localhost,127.0.0.1,hf-mirror.com"
	HF_ENDPOINT: "https://hf-mirror.com"
	HF_HUB_ENABLE_HF_TRANSFER: "0" # This is more stable
	steps:
	- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
	with:
	fetch-depth: 0
	- name: Install the current repository
	run: \|
	pip3 install --no-deps -e .[test]
	pip3 install math-verify transformers==$TRANSFORMERS_VERSION
	- name: Prepare GSM8K dataset
	run: \|
	python3 examples/data_preprocess/gsm8k.py --local_dataset_path ${HOME}/models/hf_data/gsm8k
	- name: Running GSM8K E2E training tests with 3D parallelism on 8 L20 GPUs with tie-embedding Megatron (Qwen) with train tp > infer tp
	run: \|
	ray stop --force
	VAL_BEFORE_TRAIN=True TEST_FREQ=1 SAVE_FREQ=1 TRAIN_TP=2 INFER_TP=1 MODEL_ID=Qwen/Qwen2.5-1.5B bash tests/special_e2e/run_ppo_trainer_megatron.sh
	- name: Running GSM8K E2E training tests with 3D parallelism on 8 L20 GPUs with Megatron (Qwen) with train tp < infer tp
	run: \|
	ray stop --force
	VAL_BEFORE_TRAIN=True TEST_FREQ=1 SAVE_FREQ=1 TRAIN_TP=1 INFER_TP=2 ALL_OFFLOAD=True MODEL_ID=Qwen/Qwen2.5-1.5B bash tests/special_e2e/run_ppo_trainer_megatron.sh
	- name: clean up
	run: \|
	rm -rf checkpoints
	e2e_ppo_trainer_megatron-qwen-override-transformer-config:
	needs: setup
	runs-on: ["${{ needs.setup.outputs.runner-label \|\| 'L20x8' }}"]
	timeout-minutes: 60 # Increase this timeout value as needed
	env:
	HTTP_PROXY: ${{ secrets.PROXY_HTTP }}
	HTTPS_PROXY: ${{ secrets.PROXY_HTTPS }}
	NO_PROXY: "localhost,127.0.0.1,hf-mirror.com"
	HF_ENDPOINT: "https://hf-mirror.com"
	HF_HUB_ENABLE_HF_TRANSFER: "0" # This is more stable
	steps:
	- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
	with:
	fetch-depth: 0
	- name: Install the current repository
	run: \|
	pip3 install --no-deps -e .[test]
	pip3 install math-verify transformers==$TRANSFORMERS_VERSION
	- name: Prepare GSM8K dataset
	run: \|
	python3 examples/data_preprocess/gsm8k.py --local_dataset_path ${HOME}/models/hf_data/gsm8k
	# - name: Download Model to Use
	# run: \|
	# huggingface-cli download Qwen/Qwen2.5-0.5B --local-dir ${HOME}/models/Qwen/Qwen2.5-0.5B
	# export HF_HUB_OFFLINE=1
	- 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 ${HOME}/models/Qwen/Qwen2.5-0.5B --output_path checkpoints/verl-test/qwen2.5-0.5b-megatron
	- name: Running GSM8K E2E training tests with 3D parallelism on 8 L20 GPUs with Megatron (Qwen)
	run: \|
	ray stop --force
	SAVE_FREQ=1 COMMON_PP=4 COMMON_VPP=null COMMON_CP=1 SKIP_SAVE_HF_MODEL=1 USE_DIST_CKPT=True DIST_CKPT_PATH=checkpoints/verl-test/qwen2.5-0.5b-megatron \
	bash tests/special_e2e/run_ppo_trainer_megatron.sh +actor_rollout_ref.actor.megatron.override_transformer_config.num_layers_in_first_pipeline_stage=8 +actor_rollout_ref.actor.megatron.override_transformer_config.num_layers_in_last_pipeline_stage=4
	cp -r checkpoints checkpoints-dut
	SAVE_FREQ=1 COMMON_PP=4 COMMON_VPP=null COMMON_CP=1 bash tests/special_e2e/run_ppo_trainer_megatron.sh
	- name: Test Megatron checkpoints merging function (Qwen Actor and Critic)
	run: \|
	exp_name="qwen2.5-0.5b-megatron-gsm8k-minimal"
	python -m verl.model_merger test --backend megatron --tie-word-embedding --local_dir checkpoints-dut/verl-test/${exp_name}/global_step_1/actor --test_hf_dir checkpoints/verl-test/${exp_name}/global_step_1/actor/huggingface
	python -m verl.model_merger test --backend megatron --is-value-model --local_dir checkpoints-dut/verl-test/${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

	cleanup:
	runs-on: ubuntu-latest
	needs:
	[
	setup,
	e2e_ppo_trainer_megatron-deepseek,
	e2e_ppo_trainer_megatron-qwen3,
	e2e_ppo_trainer_megatron-different-train-infer-tp-qwen-tie-embedding,
	e2e_ppo_trainer_megatron-qwen-override-transformer-config,
	]
	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 }}"

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

[rollout,vllm] fix: Add LoRA Loading to Async vLLM #2641

Workflow file

[rollout,vllm] fix: Add LoRA Loading to Async vLLM #2641

Uh oh!

Jobs

Run details

Workflow file for this run