Skip to content

[BREAKING][megatron] chore: set ETP default to null #4119

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
wuxibin89 merged 1 commit into from
Nov 14, 2025
Merged

[BREAKING][megatron] chore: set ETP default to null #4119

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
8 changes: 4 additions & 4 deletions verl/trainer/config/_generated_ppo_megatron_trainer.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,7 +33,7 @@ actor_rollout_ref:
optimizer_offload: false
tensor_model_parallel_size: 1
expert_model_parallel_size: 1
expert_tensor_parallel_size: 1
expert_tensor_parallel_size: null
pipeline_model_parallel_size: 1
virtual_pipeline_model_parallel_size: null
context_parallel_size: 1
Expand Down Expand Up @@ -157,7 +157,7 @@ actor_rollout_ref:
optimizer_offload: false
tensor_model_parallel_size: 1
expert_model_parallel_size: 1
expert_tensor_parallel_size: 1
expert_tensor_parallel_size: null
pipeline_model_parallel_size: 1
virtual_pipeline_model_parallel_size: null
context_parallel_size: 1
Expand Down Expand Up @@ -348,7 +348,7 @@ critic:
optimizer_offload: false
tensor_model_parallel_size: 1
expert_model_parallel_size: 1
expert_tensor_parallel_size: 1
expert_tensor_parallel_size: null
pipeline_model_parallel_size: 1
virtual_pipeline_model_parallel_size: null
context_parallel_size: 1
Expand Down Expand Up @@ -465,7 +465,7 @@ reward_model:
param_offload: false
tensor_model_parallel_size: 1
expert_model_parallel_size: 1
expert_tensor_parallel_size: 1
expert_tensor_parallel_size: null
pipeline_model_parallel_size: 1
virtual_pipeline_model_parallel_size: null
context_parallel_size: 1
Expand Down
4 changes: 2 additions & 2 deletions verl/trainer/config/engine/megatron.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,8 +16,8 @@ tensor_model_parallel_size: 1
# expert model parallel size
expert_model_parallel_size: 1

# expert tensor parallel size
expert_tensor_parallel_size: 1
# expert tensor parallel size (null to be same as TP)
expert_tensor_parallel_size: null

# pipeline model parallel size
pipeline_model_parallel_size: 1
Expand Down
4 changes: 2 additions & 2 deletions verl/trainer/config/reward_model/megatron_reward_model.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,8 +28,8 @@ megatron:
# Number of GPUs in expert model parallel group
expert_model_parallel_size: 1

# Expert tensor parallel size
expert_tensor_parallel_size: 1
# Expert tensor parallel size (null to be same as TP)
expert_tensor_parallel_size: null

# Number of pipeline model parallel stages
pipeline_model_parallel_size: 1
Expand Down
Loading