[perf, data] feat: DP workload balance #202

Workflow file for this run

.github/workflows/e2e_ppo_trainer_megatron_vllm_2.yml at 090a58b

	# # 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_2

	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-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: ${{ secrets.PROXY_HTTPS }}
	NO_PROXY: "localhost,127.0.0.1,hf-mirror.com"
	HF_ENDPOINT: "https://hf-mirror.com"
	HF_HUB_ENABLE_HF_TRANSFER: "0" # This is more stable
	steps:
	- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
	with:
	fetch-depth: 0
	- name: Install the current repository
	run: \|
	pip3 install --no-deps -e .[test]
	pip3 install transformers==$TRANSFORMERS_VERSION
	- name: Prepare GSM8K dataset
	run: \|
	python3 examples/data_preprocess/gsm8k.py --local_dataset_path ${HOME}/models/hf_data/gsm8k
	- name: Running GSM8K E2E training tests with 3D parallelism on 8 L20 GPUs with Megatron (DeepSeek)
	run: \|
	ray stop --force
	SAVE_FREQ=1 MODEL_ID=deepseek-ai/deepseek-coder-1.3b-instruct COMMON_PP=2 COMMON_VPP=null bash tests/special_e2e/run_ppo_trainer_megatron.sh +actor_rollout_ref.actor.megatron.override_transformer_config.account_for_embedding_in_pipeline_split=true +actor_rollout_ref.actor.megatron.override_transformer_config.account_for_loss_in_pipeline_split=true
	- name: Test Megatron checkpoints merging function (DeepSeek Actor and Critic)
	run: \|
	exp_name="deepseek-coder-1.3b-instruct-megatron-gsm8k-minimal"
	python -m verl.model_merger test --backend megatron --local_dir checkpoints/verl-test/${exp_name}/global_step_1/actor --test_hf_dir checkpoints/verl-test/${exp_name}/global_step_1/actor/huggingface
	python -m verl.model_merger test --backend megatron --is-value-model --local_dir checkpoints/verl-test/${exp_name}/global_step_1/critic --test_hf_dir checkpoints/verl-test/${exp_name}/global_step_1/critic/huggingface
	- name: clean up
	run: \|
	rm -rf checkpoints
	e2e_ppo_trainer_megatron-moe-expert-parallel:
	needs: setup
	runs-on: ["${{ needs.setup.outputs.runner-label \|\| 'L20x8' }}"]
	timeout-minutes: 60 # Increase this timeout value as needed
	env:
	HTTP_PROXY: ${{ secrets.PROXY_HTTP }}
	HTTPS_PROXY: ${{ secrets.PROXY_HTTPS }}
	NO_PROXY: "localhost,127.0.0.1,hf-mirror.com"
	HF_ENDPOINT: "https://hf-mirror.com"
	HF_HUB_ENABLE_HF_TRANSFER: "0" # This is more stable
	steps:
	- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
	with:
	fetch-depth: 0
	- name: Install the current repository
	run: \|
	pip3 install --no-deps -e .[test]
	pip3 install mbridge
	pip3 install transformers==$TRANSFORMERS_VERSION
	- name: Prepare GSM8K dataset
	run: \|
	python3 examples/data_preprocess/gsm8k.py --local_dataset_path ${HOME}/models/hf_data/gsm8k
	- name: Running GSM8K E2E training tests with 3D parallelism on 8 L20 GPUs with Megatron (DeepSeek)
	run: \|
	ray stop --force
	ADV_ESTIMATOR=grpo USE_DUMMY_MODEL=True DUMMY_MODEL_CONFIG_PATH=tests/special_e2e/ppo_trainer/expert_parallel/qwen2moe_minimal.json \
	PPO_MAX_TOKEN_LEN=512 FWD_MAX_TOKEN_LEN=512 \
	MAX_PROMPT_LENGTH=256 MAX_RESPONSE_LENGTH=256 \
	MODEL_ID=Qwen/Qwen1.5-MoE-A2.7B-Chat USE_MBRIDGE=True \
	COMMON_PP=2 COMMON_VPP=null COMMON_CP=1 COMMON_TP=4 COMMON_EP=4 COMMON_ETP=1 INFER_TP=8 \
	USE_DIST_CKPT=True ALL_OFFLOAD=True SKIP_SAVE_HF_MODEL=1 bash tests/special_e2e/run_ppo_trainer_megatron.sh
	- name: clean up
	run: \|
	rm -rf checkpoints
	e2e_ppo_trainer_megatron-qwen2_5vl-3b:
	needs: setup
	runs-on: ["${{ needs.setup.outputs.runner-label \|\| 'L20x8' }}"]
	timeout-minutes: 60 # Increase this timeout value as needed
	env:
	HTTP_PROXY: ${{ secrets.PROXY_HTTP }}
	HTTPS_PROXY: ${{ secrets.PROXY_HTTPS }}
	NO_PROXY: "localhost,127.0.0.1,hf-mirror.com"
	HF_ENDPOINT: "https://hf-mirror.com"
	HF_HUB_ENABLE_HF_TRANSFER: "0" # This is more stable
	steps:
	- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
	with:
	fetch-depth: 0
	- name: Install the current repository
	run: \|
	pip3 install --no-deps -e .[test]
	pip3 install transformers==$TRANSFORMERS_VERSION
	- name: Prepare Geo3k dataset
	run: \|
	python3 examples/data_preprocess/geo3k.py --local_dataset_path ${HOME}/models/hf_data/hiyouga/geometry3k/
	- name: Prepare dist_ckpt of Qwen2.5-VL-3B, only supports dist_ckpt
	run: \|
	python3 scripts/converter_hf_to_mcore.py --hf_model_path ${HOME}/models/Qwen/Qwen2.5-VL-3B-Instruct --output_path checkpoints/verl-test/qwen2.5-vl-3b-megatron
	- name: Running Geo3k E2E training tests with 3D parallelism on 8 L20 GPUs with Megatron (Qwen)
	run: \|
	ray stop --force
	TRAIN_FILES=${HOME}/data/geo3k/train.parquet VAL_FILES=${HOME}/data/geo3k/test.parquet \
	MAX_PROMPT_LENGTH=1024 MAX_RESPONSE_LENGTH=2048 MODEL_ID=Qwen/Qwen2.5-VL-3B-Instruct ADV_ESTIMATOR=grpo \
	USE_DYNAMIC_BSZ=False USE_FUSED_KERNELS=True SKIP_SAVE_HF_MODEL=1 \
	COMMON_PP=4 COMMON_VPP=null COMMON_CP=1 COMMON_TP=2 USE_DIST_CKPT=true \
	DIST_CKPT_PATH=checkpoints/verl-test/qwen2.5-vl-3b-megatron bash tests/special_e2e/run_ppo_trainer_megatron.sh
	- name: clean up
	run: \|
	rm -rf checkpoints
	e2e_ppo_trainer_vllm:
	needs: setup
	runs-on: [ "${{ needs.setup.outputs.runner-label \|\| 'L20x8' }}" ]
	timeout-minutes: 60 # Increase this timeout value as needed
	env:
	HTTP_PROXY: ${{ secrets.PROXY_HTTP }}
	HTTPS_PROXY: ${{ secrets.PROXY_HTTPS }}
	NO_PROXY: "localhost,127.0.0.1,hf-mirror.com"
	HF_ENDPOINT: "https://hf-mirror.com"
	HF_HUB_ENABLE_HF_TRANSFER: "0" # This is more stable
	steps:
	- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
	with:
	fetch-depth: 0
	- name: Install the current repository
	run: \|
	pip3 install --no-deps -e .[test,vllm]
	pip3 install transformers==$TRANSFORMERS_VERSION
	- name: Prepare GSM8K dataset
	run: \|
	ray stop --force
	python3 examples/data_preprocess/gsm8k.py --local_dataset_path ${HOME}/models/hf_data/gsm8k
	# HF sanity
	# - name: Running GSM8K E2E training tests on 1 L20 GPU with hf for sanity
	# run: \|
	# ray stop --force
	# bash tests/special_e2e/ppo_trainer/run_single_gpu.sh
	# # HF sanity
	# - name: Running GSM8K E2E training tests on 1 L20 GPU with engine interface for sanity.
	# run: \|
	# ray stop --force
	# bash tests/special_e2e/ppo_trainer/run_single_gpu_with_engine.sh
	# Function RM
	- name: Running GSM8K E2E training tests on 8 L20 GPUs with rmpad using function rm with validation and saving (FSDP_SIZE=8)
	run: \|
	ray stop --force
	VAL_BEFORE_TRAIN=True TEST_FREQ=1 SAVE_FREQ=1 SAVE_HF_MODEL=True VERL_EXP_NAME="qwen2.5-0.5b-function-reward-minimal-fsdp-size8" bash tests/special_e2e/ppo_trainer/run_function_reward.sh
	- name: Running GSM8K E2E training tests on 8 L20 GPUs with rmpad using function rm after resuming
	run: \|
	ray stop --force
	RESUME_MODE=auto VERL_EXP_NAME="qwen2.5-0.5b-function-reward-minimal-fsdp-size8" bash tests/special_e2e/ppo_trainer/run_function_reward.sh
	- name: Test merging FSDP checkpoints (Qwen Actor)
	run: \|
	exp_name="qwen2.5-0.5b-function-reward-minimal-fsdp-size8"
	python -m verl.model_merger test --backend fsdp --local_dir checkpoints/verl-test/${exp_name}/global_step_1/actor --test_hf_dir checkpoints/verl-test/${exp_name}/global_step_1/actor/huggingface
	- name: Running GSM8K E2E training tests on 8 L20 GPUs with rmpad using function rm with validation and saving (DDP_SIZE=2, FSDP_SIZE=4)
	run: \|
	ray stop --force
	VAL_BEFORE_TRAIN=True TEST_FREQ=1 SAVE_FREQ=1 SAVE_HF_MODEL=True FSDP_SIZE=4 VERL_EXP_NAME="qwen2.5-0.5b-function-reward-minimal-ddp-size2-fsdp-size4" bash tests/special_e2e/ppo_trainer/run_function_reward.sh
	- name: Test merging DDP+FSDP checkpoints (Qwen Actor)
	run: \|
	exp_name="qwen2.5-0.5b-function-reward-minimal-ddp-size2-fsdp-size4"
	python -m verl.model_merger test --backend fsdp --local_dir checkpoints/verl-test/${exp_name}/global_step_1/actor --test_hf_dir checkpoints/verl-test/${exp_name}/global_step_1/actor/huggingface
	- name: Running GSM8K E2E training tests on 8 L20 GPUs with rmpad using function rm with validation and saving (FSDP2)
	run: \|
	ray stop --force
	VAL_BEFORE_TRAIN=True TEST_FREQ=1 SAVE_FREQ=1 SAVE_HF_MODEL=True VERL_EXP_NAME="qwen2.5-0.5b-function-reward-minimal-fsdp2-size8" STRATEGY=fsdp2 bash tests/special_e2e/ppo_trainer/run_function_reward.sh
	- name: Test merging FSDP2 checkpoints (Qwen Actor)
	run: \|
	exp_name="qwen2.5-0.5b-function-reward-minimal-fsdp2-size8"
	python -m verl.model_merger test --backend fsdp --local_dir checkpoints/verl-test/${exp_name}/global_step_1/actor --test_hf_dir checkpoints/verl-test/${exp_name}/global_step_1/actor/huggingface
	- name: Running GSM8K E2E without rmpad using function rm
	run: \|
	ray stop --force
	RM_PAD=False bash tests/special_e2e/ppo_trainer/run_function_reward.sh
	- name: Running GSM8K E2E training tests on 8 L20 GPUs with rmpad using function rm (GRPO)
	run: \|
	ray stop --force
	ADV_ESTIMATOR=grpo USE_KL=True bash tests/special_e2e/ppo_trainer/run_function_reward.sh
	- name: Running GSM8K E2E training tests on 8 L20 GPUs with rmpad using function rm (ReMax)
	run: \|
	ray stop --force
	ADV_ESTIMATOR=remax USE_KL=True bash tests/special_e2e/ppo_trainer/run_function_reward.sh
	- name: Running GSM8K E2E training tests on 8 L20 GPUs with rmpad using customized reward function
	run: \|
	ray stop --force
	CUSTOM_REWARD_FN=True bash tests/special_e2e/ppo_trainer/run_function_reward.sh
	- name: Running GSM8K E2E training tests on 8 L20 GPUs with rmpad using function rm with in-reward kl and kl loss
	run: \|
	ray stop --force
	USE_KL=True bash tests/special_e2e/ppo_trainer/run_function_reward.sh
	# LoRA tests
	- name: Running GSM8K E2E training tests on 8 L20 GPUs with grpo lora using function rm with use_shm
	run: \|
	ray stop --force
	ADV_ESTIMATOR=grpo USE_SHM=True LORA_RANK=32 LOAD_FORMAT=safetensors bash tests/special_e2e/ppo_trainer/run_function_reward.sh
	- name: Running GSM8K E2E training tests on 8 L20 GPUs with grpo lora using function rm with use_shm and layered_summon
	run: \|
	ray stop --force
	ADV_ESTIMATOR=grpo USE_SHM=True LORA_RANK=32 LOAD_FORMAT=safetensors LAYERED_SUMMON=True TOTAL_TRAIN_STEPS=1 SAVE_FREQ=1 FSDP_SIZE=4 VERL_EXP_NAME="qwen2.5-0.5b-function-reward-minimal" bash tests/special_e2e/ppo_trainer/run_function_reward.sh
	- name: Test GRPO LoRA checkpoints merging function
	run: \|
	export EXP_NAME="qwen2.5-0.5b-function-reward-minimal"
	ls checkpoints/verl-test/${EXP_NAME}/global_step_1/actor
	cat checkpoints/verl-test/${EXP_NAME}/global_step_1/actor/huggingface/config.json
	python3 -m verl.model_merger merge --backend fsdp --local_dir checkpoints/verl-test/${EXP_NAME}/global_step_1/actor/ --target_dir checkpoints/verl-test/${EXP_NAME}/global_step_1/actor/huggingface
	- name: Running GSM8K E2E training tests on 8 L20 GPUs with grpo lora using function rm with use_shm and layered_summon with fsdp2
	run: \|
	ray stop --force
	ADV_ESTIMATOR=grpo USE_SHM=True LORA_RANK=32 LOAD_FORMAT=safetensors LAYERED_SUMMON=True STRATEGY=fsdp2 bash tests/special_e2e/ppo_trainer/run_function_reward.sh
	# Model RM
	- name: Running GRPO GSM8K E2E training tests with FSDP on 8 L20 GPUs (DeepSeek)
	run: \|
	ray stop --force
	MODEL_ID=deepseek-ai/deepseek-coder-1.3b-instruct bash tests/special_e2e/ppo_trainer/run_function_reward.sh
	- name: Running GSM8K E2E with rmpad using model rm
	run: \|
	ray stop --force
	bash tests/special_e2e/ppo_trainer/run_model_reward.sh
	- name: Running GSM8K E2E without rmpad using model rm
	run: \|
	ray stop --force
	RM_PAD=False bash tests/special_e2e/ppo_trainer/run_model_reward.sh
	- name: Running GSM8K E2E with rmpad using model rm and ulysses sp=2
	run: \|
	ray stop --force
	SP_SIZE=2 bash tests/special_e2e/ppo_trainer/run_model_reward.sh
	- name: Running GSM8K E2E with rmpad using model rm and dynamic batch size
	run: \|
	ray stop --force
	SEQ_BALANCE=True bash tests/special_e2e/ppo_trainer/run_model_reward.sh
	- name: Running GSM8K E2E with rmpad using model rm with Liger Kernel enabled
	run: \|
	ray stop --force
	LIGER=True bash tests/special_e2e/ppo_trainer/run_model_reward.sh
	- name: Running GSM8K E2E with rmpad using model rm with Fused Kernel enabled
	run: \|
	ray stop --force
	FUSED_KERNELS=True bash tests/special_e2e/ppo_trainer/run_model_reward.sh
	- name: Running GSM8K E2E with rmpad using model rm with Fused Kernel enabled
	run: \|
	ray stop --force
	FUSED_KERNEL=True FUSED_KERNEL_BACKEND=triton bash tests/special_e2e/ppo_trainer/run_model_reward.sh
	- name: Running GSM8K E2E training tests on vllm async
	run: \|
	ray stop --force
	export VLLM_USE_V1=1
	ray start --head
	TOTAL_TRAIN_STEPS=2 ENGINE=vllm ROLLOUT_MODE=async bash tests/special_e2e/ppo_trainer/run_function_reward.sh

	e2e_ppo_trainer_vllm_vlm:
	needs: setup
	runs-on: [ "${{ needs.setup.outputs.runner-label \|\| 'L20x8' }}" ]
	timeout-minutes: 40 # Increase this timeout value as needed
	env:
	HTTP_PROXY: ${{ secrets.PROXY_HTTP }}
	HTTPS_PROXY: ${{ secrets.PROXY_HTTPS }}
	NO_PROXY: "localhost,127.0.0.1,hf-mirror.com"
	HF_ENDPOINT: "https://hf-mirror.com"
	HF_HUB_ENABLE_HF_TRANSFER: "0" # This is more stable
	steps:
	- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
	with:
	fetch-depth: 0
	- name: Install the current repository
	run: \|
	pip3 install --no-deps -e .[test,gpu,vllm,geo,trl]
	pip3 install transformers==$TRANSFORMERS_VERSION
	# Geo3k
	- name: Prepare GEO3K dataset
	run: \|
	python3 examples/data_preprocess/geo3k.py --local_dataset_path ${HOME}/models/hf_data/hiyouga/geometry3k/
	- name: Running GEO3K VLM GRPO E2E training tests on 8 L20 GPUs with rmpad using function rm
	run: \|
	ray stop --force
	TRAIN_FILES=$HOME/data/geo3k/train.parquet VAL_FILES=$HOME/data/geo3k/test.parquet \
	MAX_PROMPT_LEN=1536 MAX_RESPONSE_LEN=1536 \
	MODEL_ID=Qwen/Qwen2-VL-2B-Instruct \
	ADV_ESTIMATOR=grpo RM_PAD=True USE_KL=True ENABLE_CHUNKED_PREFILL=False \
	SP_SIZE=2 \
	bash tests/special_e2e/ppo_trainer/run_function_reward.sh

	- name: Running GEO3K VLM PPO E2E training tests on 8 L20 GPUs with rmpad using function rm
	run: \|
	ray stop --force
	TRAIN_FILES=$HOME/data/geo3k/train.parquet VAL_FILES=$HOME/data/geo3k/test.parquet \
	MAX_PROMPT_LEN=1536 MAX_RESPONSE_LEN=1536 \
	MODEL_ID=Qwen/Qwen2-VL-2B-Instruct \
	ADV_ESTIMATOR=gae RM_PAD=True USE_KL=True ENABLE_CHUNKED_PREFILL=False \
	SP_SIZE=2 \
	bash tests/special_e2e/ppo_trainer/run_function_reward.sh
	- name: Running GEO3K VLM GRPO E2E lora training tests on 8 L20 GPUs with rmpad using function rm
	run: \|
	ray stop --force
	TRAIN_FILES=$HOME/data/geo3k/train.parquet VAL_FILES=$HOME/data/geo3k/test.parquet \
	MAX_PROMPT_LEN=1536 MAX_RESPONSE_LEN=1536 \
	MODEL_ID=Qwen/Qwen2-VL-2B-Instruct \
	ADV_ESTIMATOR=grpo RM_PAD=True USE_KL=True ENABLE_CHUNKED_PREFILL=False \
	SP_SIZE=2 \
	LORA_RANK=32 LORA_EXCLUDE=".visual." \
	bash tests/special_e2e/ppo_trainer/run_function_reward.sh

	cleanup:
	runs-on: ubuntu-latest
	needs:
	[
	setup,
	e2e_ppo_trainer_megatron-deepseek-override-transformer-config,
	e2e_ppo_trainer_megatron-moe-expert-parallel,
	e2e_ppo_trainer_megatron-qwen2_5vl-3b,
	e2e_ppo_trainer_vllm,
	e2e_ppo_trainer_vllm_vlm
	]
	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!

[perf, data] feat: DP workload balance #202

Workflow file

[perf, data] feat: DP workload balance #202

Uh oh!

Jobs

Run details

Workflow file for this run