github
/
minimind
mirror of https://github.com/jingyaogong/minimind.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

[refactor] remove redundant rollout update_policy after torch.compile

pull/821/head
TOPSAIL\78190 2026-08-24 12:43:50 +08:00
parent d65ef2c00e
commit 0c91dea4a2
3 changed files with 0 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
trainer/train_agent.py
View File

@ -470,7 +470,6 @@ if __name__ == "__main__":
if args.use_compile == 1: if args.use_compile == 1:
model = torch.compile(model) model = torch.compile(model)
Logger('torch.compile enabled') Logger('torch.compile enabled')
rollout_engine.update_policy(model)
if dist.is_initialized(): if dist.is_initialized():
model = DistributedDataParallel(model, device_ids=[local_rank]) model = DistributedDataParallel(model, device_ids=[local_rank])
rollout_engine.update_policy(model) rollout_engine.update_policy(model)

1
trainer/train_grpo.py
View File

@ -310,7 +310,6 @@ if __name__ == "__main__":
if args.use_compile == 1: if args.use_compile == 1:
model = torch.compile(model) model = torch.compile(model)
Logger('torch.compile enabled') Logger('torch.compile enabled')
rollout_engine.update_policy(model)
if dist.is_initialized(): if dist.is_initialized():
model = DistributedDataParallel(model, device_ids=[local_rank]) model = DistributedDataParallel(model, device_ids=[local_rank])
rollout_engine.update_policy(model) rollout_engine.update_policy(model)

1
trainer/train_ppo.py
View File

@ -426,7 +426,6 @@ if __name__ == "__main__":
if args.use_compile == 1: if args.use_compile == 1:
actor_model = torch.compile(actor_model) actor_model = torch.compile(actor_model)
Logger('torch.compile enabled') Logger('torch.compile enabled')
rollout_engine.update_policy(actor_model)
if dist.is_initialized(): if dist.is_initialized():
actor_model = DistributedDataParallel(actor_model, device_ids=[local_rank]) actor_model = DistributedDataParallel(actor_model, device_ids=[local_rank])
critic_model = DistributedDataParallel(critic_model, device_ids=[local_rank]) critic_model = DistributedDataParallel(critic_model, device_ids=[local_rank])