Skip to content

[recipe] fix: Remove redundant parameters to resolve errors in the script caused by the latest Verl main branch. #3252

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Aug 29, 2025
Merged

[recipe] fix: Remove redundant parameters to resolve errors in the script caused by the latest Verl main branch. #3252

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 0 additions & 5 deletions recipe/dapo/run_dapo_qwen2.5_32b_npu.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,8 +56,6 @@ actor_ppo_max_token_len=$(((max_prompt_length + max_response_length) / sp_size))
infer_ppo_max_token_len=$(((max_prompt_length + max_response_length) / sp_size))
offload=True
gen_tp=4
gen_dp=1
gen_world_size=$((NNODES * 16)) # nnodes* npus_in_per_node
enable_chunked_prefill=True

ray job submit --no-wait --runtime-env="${RUNTIME_ENV}" \
Expand Down Expand Up @@ -111,8 +109,6 @@ ray job submit --no-wait --runtime-env="${RUNTIME_ENV}" \
actor_rollout_ref.actor.ulysses_sequence_parallel_size=${sp_size} \
actor_rollout_ref.rollout.gpu_memory_utilization=0.90 \
actor_rollout_ref.rollout.tensor_model_parallel_size=${gen_tp} \
+actor_rollout_ref.rollout.dp_model_parallel_size=${gen_dp} \
+actor_rollout_ref.rollout.rollout_world_size=${gen_world_size} \
actor_rollout_ref.rollout.enable_chunked_prefill=${enable_chunked_prefill} \
actor_rollout_ref.rollout.max_num_batched_tokens=$((max_prompt_length + max_response_length)) \
actor_rollout_ref.rollout.temperature=${temperature} \
Expand All @@ -126,7 +122,6 @@ ray job submit --no-wait --runtime-env="${RUNTIME_ENV}" \
actor_rollout_ref.ref.fsdp_config.param_offload=${offload} \
actor_rollout_ref.ref.ulysses_sequence_parallel_size=${sp_size} \
actor_rollout_ref.actor.fsdp_config.fsdp_size=-1 \
+actor_rollout_ref.rollout.enable_expert_parallel=False \
reward_model.reward_manager=dapo \
reward_model.overlong_buffer.enable=${enable_overlong_buffer} \
reward_model.overlong_buffer.len=${overlong_buffer_len} \
Expand Down
2 changes: 0 additions & 2 deletions recipe/dapo/run_dapo_qwen3_moe_30b_base_npu_fsdp.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,7 +58,6 @@ offload=True
recompute=True
max_num_seqs=128
gen_tp=2
gen_world_size=$((NNODES * NPUS_PER_NODE)) # nnodes* npus_in_per_node


ray job submit --no-wait --runtime-env="${RUNTIME_ENV}" \
Expand Down Expand Up @@ -111,7 +110,6 @@ ray job submit --no-wait --runtime-env="${RUNTIME_ENV}" \
actor_rollout_ref.actor.ulysses_sequence_parallel_size=${sp_size} \
actor_rollout_ref.rollout.gpu_memory_utilization=0.8 \
actor_rollout_ref.rollout.tensor_model_parallel_size=${gen_tp} \
+actor_rollout_ref.rollout.rollout_world_size=${gen_world_size} \
actor_rollout_ref.rollout.enable_chunked_prefill=True \
actor_rollout_ref.rollout.temperature=${temperature} \
actor_rollout_ref.rollout.top_p=${top_p} \
Expand Down