From b00b090149a23dc04e7d98afae15691790481894 Mon Sep 17 00:00:00 2001
From: Lingfeng Wang <62014693+wlf-darkmatter@users.noreply.github.com>
Date: Sat, 13 Sep 2025 19:08:23 +0800
Subject: [PATCH] [megatron,recipe] feat: support Qwen3-30B (MoE) DAPO training
on ASCEND NPU (#3203)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
### What does this PR do?
Fix of megatron config, and example shell of Qwen3-30B-Dapo with
megatron.
### Checklist Before Starting
- [x] Search for similar PRs. Paste at least one query link here: ...
- [x] Format the PR title as `[{modules}] {type}: {description}` (This
will be checked by the CI)
- `{modules}` include `fsdp`, `megatron`, `sglang`, `vllm`, `rollout`,
`trainer`, `ci`, `training_utils`, `recipe`, `hardware`, `deployment`,
`ray`, `worker`, `single_controller`, `misc`, `perf`, `model`, `algo`,
`env`, `tool`, `ckpt`, `doc`, `data`
- If this PR involves multiple modules, separate them with `,` like
`[megatron, fsdp, doc]`
- `{type}` is in `feat`, `fix`, `refactor`, `chore`, `test`
- If this PR breaks any API (CLI arguments, config, function signature,
etc.), add `[BREAKING]` to the beginning of the title.
- Example: `[BREAKING][fsdp, megatron] feat: dynamic batching`
### Test
critic/reward/mean:
response_length/mean:
### Checklist Before Submitting
> [!IMPORTANT]
> Please check all the following items before requesting a review,
otherwise the reviewer might deprioritize this PR for review.
- [x] Read the [Contribute
Guide](https://github.com/volcengine/verl/blob/main/CONTRIBUTING.md).
- [x] Apply [pre-commit
checks](https://github.com/volcengine/verl/blob/main/CONTRIBUTING.md#code-linting-and-formatting):
`pre-commit install && pre-commit run --all-files --show-diff-on-failure
--color=always`
- [x] Add / Update [the
documentation](https://github.com/volcengine/verl/tree/main/docs).
- [x] Add unit or end-to-end test(s) to [the CI
workflow](https://github.com/volcengine/verl/tree/main/.github/workflows)
to cover all the code. If not feasible, explain why: ...
- [ ] Once your PR is ready for CI, send a message in [the `ci-request`
channel](https://verl-project.slack.com/archives/C091TCESWB1) in [the
`verl` Slack
workspace](https://join.slack.com/t/verl-project/shared_invite/zt-3855yhg8g-CTkqXu~hKojPCmo7k_yXTQ).
(If not accessible, please try [the Feishu group
(飞书群)](https://applink.larkoffice.com/client/chat/chatter/add_by_link?link_token=772jd4f1-cd91-441e-a820-498c6614126a).)
---
recipe/dapo/config/dapo_megatron_trainer.yaml | 28 +++
...> run_dapo_qwen3_moe_30b_base_fsdp_npu.sh} | 0
.../run_dapo_qwen3_moe_30b_megatron_npu.sh | 169 ++++++++++++++++++
.../_generated_ppo_megatron_trainer.yaml | 1 +
verl/trainer/config/ppo_megatron_trainer.yaml | 3 +
verl/utils/reward_score/__init__.py | 2 +-
6 files changed, 202 insertions(+), 1 deletion(-)
create mode 100644 recipe/dapo/config/dapo_megatron_trainer.yaml
rename recipe/dapo/{run_dapo_qwen3_moe_30b_base_npu_fsdp.sh => run_dapo_qwen3_moe_30b_base_fsdp_npu.sh} (100%)
create mode 100644 recipe/dapo/run_dapo_qwen3_moe_30b_megatron_npu.sh
diff --git a/recipe/dapo/config/dapo_megatron_trainer.yaml b/recipe/dapo/config/dapo_megatron_trainer.yaml
new file mode 100644
index 000000000..b846eaeb7
--- /dev/null
+++ b/recipe/dapo/config/dapo_megatron_trainer.yaml
@@ -0,0 +1,28 @@
+hydra:
+ searchpath:
+ - file://verl/trainer/config
+
+defaults:
+ - ppo_megatron_trainer
+ - _self_
+
+data:
+ gen_batch_size: ${data.train_batch_size}
+
+reward_model:
+ reward_manager: dapo
+ overlong_buffer:
+ enable: False # We try to avoid forgetting to set enable
+ len: 0
+ penalty_factor: 0.0
+ log: False
+
+algorithm:
+ filter_groups:
+ _target_: verl.trainer.config.FilterGroupsConfig
+ enable: False # We try to avoid forgetting to set enable
+ metric: null # acc / score / seq_reward / seq_final_reward / ...
+ max_num_gen_batches: 0 # Non-positive values mean no upper limit
+
+trainer:
+ project_name: verl-dapo
diff --git a/recipe/dapo/run_dapo_qwen3_moe_30b_base_npu_fsdp.sh b/recipe/dapo/run_dapo_qwen3_moe_30b_base_fsdp_npu.sh
similarity index 100%
rename from recipe/dapo/run_dapo_qwen3_moe_30b_base_npu_fsdp.sh
rename to recipe/dapo/run_dapo_qwen3_moe_30b_base_fsdp_npu.sh
diff --git a/recipe/dapo/run_dapo_qwen3_moe_30b_megatron_npu.sh b/recipe/dapo/run_dapo_qwen3_moe_30b_megatron_npu.sh
new file mode 100644
index 000000000..81d5b1505
--- /dev/null
+++ b/recipe/dapo/run_dapo_qwen3_moe_30b_megatron_npu.sh
@@ -0,0 +1,169 @@
+#!/bin/bash
+
+project_name='DAPO'
+exp_name='DAPO-Qwen3-30B-megatron'
+
+adv_estimator=grpo
+
+use_kl_in_reward=False
+kl_coef=0.0
+use_kl_loss=False
+kl_loss_coef=0.0
+
+clip_ratio_low=0.2
+clip_ratio_high=0.28
+
+max_prompt_length=$((1024 * 2))
+max_response_length=$((1024 * 20))
+enable_overlong_buffer=True
+overlong_buffer_len=$((1024 * 4))
+overlong_penalty_factor=1.0
+
+loss_agg_mode="token-mean"
+
+enable_filter_groups=True
+filter_groups_metric=acc
+max_num_gen_batches=10
+train_prompt_bsz=16
+gen_prompt_bsz=$((train_prompt_bsz * 2))
+n_resp_per_prompt=16
+train_prompt_mini_bsz=2
+
+# Ray
+RAY_ADDRESS=${RAY_ADDRESS:-"http://localhost:8265"}
+WORKING_DIR=${WORKING_DIR:-"${PWD}"}
+RUNTIME_ENV=${RUNTIME_ENV:-"${WORKING_DIR}/verl/trainer/runtime_env.yaml"}
+NNODES=${NNODES:-1}
+# Paths
+RAY_DATA_HOME=${RAY_DATA_HOME:-"${HOME}/verl"}
+MODEL_PATH=${MODEL_PATH:-"${RAY_DATA_HOME}/models/Qwen3-30B-A3B"}
+# MCORE_MODEL_PATH points to the converted checkpoint.
+# To avoid loading these weights, set actor_rollout_ref.actor.megatron.use_dist_checkpointing=False.
+MCORE_MODEL_PATH=${MCORE_MODEL_PATH:-"${RAY_DATA_HOME}/models/Qwen3-30B-A3B-dist_ckpt"}
+CKPTS_DIR=${CKPTS_DIR:-"${RAY_DATA_HOME}/ckpts/${project_name}/${exp_name}"}
+TRAIN_FILE=${TRAIN_FILE:-"${RAY_DATA_HOME}/data/dapo-math-17k.parquet"}
+TEST_FILE=${TEST_FILE:-"${RAY_DATA_HOME}/data/aime-2024.parquet"}
+
+# Algorithm
+temperature=1.0
+top_p=1.0
+top_k=-1 # 0 for HF rollout, -1 for vLLM rollout
+
+# Performance Related Parameter
+sp_size=8
+use_dynamic_bsz=True
+actor_ppo_max_token_len=$(((max_prompt_length + max_response_length)))
+infer_ppo_max_token_len=$(((max_prompt_length + max_response_length)))
+offload=True
+
+max_num_batched_tokens=$((max_prompt_length + max_response_length))
+
+# Megatron backen
+train_tp=4
+train_ep=2
+train_pp=2
+train_cp=1
+
+ray job submit --no-wait --runtime-env="${RUNTIME_ENV}" \
+ --address "${RAY_ADDRESS}" \
+ -- python3 -m recipe.dapo.main_dapo \
+ --config-name="dapo_megatron_trainer" \
+ data.filter_overlong_prompts=False \
+ data.train_files="${TRAIN_FILE}" \
+ data.val_files="${TEST_FILE}" \
+ data.shuffle=False \
+ data.prompt_key=prompt \
+ data.truncation='left' \
+ data.max_prompt_length=${max_prompt_length} \
+ data.max_response_length=${max_response_length} \
+ data.gen_batch_size=${gen_prompt_bsz} \
+ data.train_batch_size=${train_prompt_bsz} \
+ algorithm.adv_estimator=${adv_estimator} \
+ algorithm.use_kl_in_reward=${use_kl_in_reward} \
+ algorithm.kl_ctrl.kl_coef=${kl_coef} \
+ actor_rollout_ref.rollout.n=${n_resp_per_prompt} \
+ actor_rollout_ref.rollout.name=vllm \
+ actor_rollout_ref.actor.use_kl_loss=${use_kl_loss} \
+ actor_rollout_ref.actor.kl_loss_coef=${kl_loss_coef} \
+ actor_rollout_ref.actor.clip_ratio_low=${clip_ratio_low} \
+ actor_rollout_ref.actor.clip_ratio_high=${clip_ratio_high} \
+ actor_rollout_ref.actor.clip_ratio_c=10.0 \
+ actor_rollout_ref.actor.ppo_epochs=1 \
+ algorithm.filter_groups.enable=${enable_filter_groups} \
+ algorithm.filter_groups.max_num_gen_batches=${max_num_gen_batches} \
+ algorithm.filter_groups.metric=${filter_groups_metric} \
+ actor_rollout_ref.model.use_remove_padding=True \
+ actor_rollout_ref.actor.use_dynamic_bsz=${use_dynamic_bsz} \
+ actor_rollout_ref.actor.ppo_micro_batch_size_per_gpu=1 \
+ actor_rollout_ref.ref.log_prob_micro_batch_size_per_gpu=1 \
+ actor_rollout_ref.rollout.log_prob_micro_batch_size_per_gpu=1 \
+ actor_rollout_ref.ref.log_prob_use_dynamic_bsz=${use_dynamic_bsz} \
+ actor_rollout_ref.rollout.log_prob_use_dynamic_bsz=${use_dynamic_bsz} \
+ actor_rollout_ref.actor.ppo_max_token_len_per_gpu=${actor_ppo_max_token_len} \
+ actor_rollout_ref.ref.log_prob_max_token_len_per_gpu=${infer_ppo_max_token_len} \
+ actor_rollout_ref.rollout.log_prob_max_token_len_per_gpu=${infer_ppo_max_token_len} \
+ actor_rollout_ref.model.path="${MODEL_PATH}" \
+ +actor_rollout_ref.model.override_config.attention_dropout=0. \
+ +actor_rollout_ref.model.override_config.embd_pdrop=0. \
+ +actor_rollout_ref.model.override_config.resid_pdrop=0. \
+ actor_rollout_ref.actor.optim.lr=1e-6 \
+ +actor_rollout_ref.critic.optim.lr=5e-8 \
+ actor_rollout_ref.actor.optim.lr_warmup_steps=10 \
+ actor_rollout_ref.actor.ppo_mini_batch_size=${train_prompt_mini_bsz} \
+ actor_rollout_ref.actor.megatron.param_offload=${offload} \
+ actor_rollout_ref.actor.megatron.optimizer_offload=${offload} \
+ actor_rollout_ref.actor.megatron.grad_offload=${offload} \
+ actor_rollout_ref.actor.megatron.pipeline_model_parallel_size=${train_pp} \
+ actor_rollout_ref.actor.megatron.tensor_model_parallel_size=${train_tp} \
+ actor_rollout_ref.actor.megatron.expert_model_parallel_size=${train_ep} \
+ actor_rollout_ref.actor.megatron.context_parallel_size=${train_cp} \
+ actor_rollout_ref.actor.megatron.dist_checkpointing_path=${MCORE_MODEL_PATH} \
+ actor_rollout_ref.actor.megatron.use_dist_checkpointing=True \
+ actor_rollout_ref.ref.megatron.pipeline_model_parallel_size=${train_pp} \
+ actor_rollout_ref.ref.megatron.tensor_model_parallel_size=${train_tp} \
+ actor_rollout_ref.ref.megatron.expert_model_parallel_size=${train_ep} \
+ actor_rollout_ref.ref.megatron.context_parallel_size=${train_cp} \
+ actor_rollout_ref.ref.megatron.param_offload=${offload} \
+ actor_rollout_ref.ref.megatron.dist_checkpointing_path=${MCORE_MODEL_PATH} \
+ actor_rollout_ref.actor.entropy_coeff=0 \
+ actor_rollout_ref.actor.loss_agg_mode=${loss_agg_mode} \
+ actor_rollout_ref.rollout.gpu_memory_utilization=0.7 \
+ actor_rollout_ref.rollout.tensor_model_parallel_size=${gen_tp} \
+ actor_rollout_ref.rollout.enable_chunked_prefill=True \
+ actor_rollout_ref.rollout.enable_prefix_caching=False \
+ actor_rollout_ref.rollout.max_num_batched_tokens=${max_num_batched_tokens} \
+ actor_rollout_ref.rollout.max_model_len=$((max_prompt_length + max_response_length)) \
+ actor_rollout_ref.rollout.temperature=${temperature} \
+ actor_rollout_ref.rollout.top_p=${top_p} \
+ actor_rollout_ref.rollout.top_k=${top_k} \
+ actor_rollout_ref.rollout.val_kwargs.temperature=${temperature} \
+ actor_rollout_ref.rollout.val_kwargs.top_p=${top_p} \
+ actor_rollout_ref.rollout.val_kwargs.top_k=${top_k} \
+ actor_rollout_ref.rollout.val_kwargs.do_sample=True \
+ actor_rollout_ref.rollout.val_kwargs.n=1 \
+ actor_rollout_ref.rollout.enforce_eager=True \
+ actor_rollout_ref.rollout.free_cache_engine=True \
+ actor_rollout_ref.ref.megatron.use_dist_checkpointing=True \
+ reward_model.reward_manager=dapo \
+ reward_model.overlong_buffer.enable=${enable_overlong_buffer} \
+ reward_model.overlong_buffer.len=${overlong_buffer_len} \
+ reward_model.overlong_buffer.penalty_factor=${overlong_penalty_factor} \
+ trainer.logger=['console'] \
+ trainer.project_name="${project_name}" \
+ trainer.experiment_name="${exp_name}" \
+ trainer.n_gpus_per_node=16 \
+ trainer.nnodes="${NNODES}" \
+ trainer.val_before_train=False \
+ trainer.test_freq=-1 \
+ trainer.save_freq=-1 \
+ trainer.total_epochs=1 \
+ trainer.default_local_dir="${CKPTS_DIR}" \
+ trainer.device="npu" \
+ actor_rollout_ref.nccl_timeout=14400 \
+ actor_rollout_ref.actor.use_torch_compile=False \
+ actor_rollout_ref.ref.use_torch_compile=False \
+ +actor_rollout_ref.actor.megatron.override_transformer_config.use_flash_attn=True \
+ +actor_rollout_ref.actor.megatron.override_transformer_config.recompute_method=uniform \
+ +actor_rollout_ref.actor.megatron.override_transformer_config.recompute_granularity=full \
+ +actor_rollout_ref.actor.megatron.override_transformer_config.recompute_num_layers=1
+
diff --git a/verl/trainer/config/_generated_ppo_megatron_trainer.yaml b/verl/trainer/config/_generated_ppo_megatron_trainer.yaml
index dba8ee89d..4c81aaf2c 100644
--- a/verl/trainer/config/_generated_ppo_megatron_trainer.yaml
+++ b/verl/trainer/config/_generated_ppo_megatron_trainer.yaml
@@ -264,6 +264,7 @@ actor_rollout_ref:
freeze_moe_router: false
use_fused_kernels: false
trust_remote_code: false
+ use_remove_padding: false
data:
tokenizer: null
use_shm: false
diff --git a/verl/trainer/config/ppo_megatron_trainer.yaml b/verl/trainer/config/ppo_megatron_trainer.yaml
index a9bfb2fba..478582ea3 100644
--- a/verl/trainer/config/ppo_megatron_trainer.yaml
+++ b/verl/trainer/config/ppo_megatron_trainer.yaml
@@ -43,6 +43,9 @@ actor_rollout_ref:
trust_remote_code: False
+ # Whether to remove padding tokens in inputs during training
+ use_remove_padding: false
+
rollout:
# may get higher throughput when set to True. When activated, Please increase max_num_batched_tokens or decrease max_model_len.
enable_chunked_prefill: False
diff --git a/verl/utils/reward_score/__init__.py b/verl/utils/reward_score/__init__.py
index 44b68aba7..6a3c3cb0f 100644
--- a/verl/utils/reward_score/__init__.py
+++ b/verl/utils/reward_score/__init__.py
@@ -55,7 +55,7 @@ def default_compute_score(
# from . import math_verify
# res = math_verify.compute_score(solution_str, ground_truth)
- elif data_source == "math_dapo" or data_source.startswith("aime"):
+ elif data_source in ["math_dapo", "math", "math_dapo_reasoning"] or data_source.startswith("aime"):
from . import math_dapo
res = math_dapo.compute_score(solution_str, ground_truth)