Merge 0c91dea4a2 into a3c7b01cc0

trainer/train_agent.py

@@ -476,7 +476,6 @@ if __name__ == "__main__":
     if args.use_compile == 1:
         model = torch.compile(model)
         Logger('torch.compile enabled')
-        rollout_engine.update_policy(model)
     if dist.is_initialized():
         model = DistributedDataParallel(model, device_ids=[local_rank])
     rollout_engine.update_policy(model)

trainer/train_grpo.py

@@ -311,7 +311,6 @@ if __name__ == "__main__":
     if args.use_compile == 1:
         model = torch.compile(model)
         Logger('torch.compile enabled')
-        rollout_engine.update_policy(model)
     if dist.is_initialized():
         model = DistributedDataParallel(model, device_ids=[local_rank])
     rollout_engine.update_policy(model)

trainer/train_ppo.py

@@ -427,7 +427,6 @@ if __name__ == "__main__":
     if args.use_compile == 1:
         actor_model = torch.compile(actor_model)
         Logger('torch.compile enabled')
-        rollout_engine.update_policy(actor_model)
     if dist.is_initialized():
         actor_model = DistributedDataParallel(actor_model, device_ids=[local_rank])
         critic_model = DistributedDataParallel(critic_model, device_ids=[local_rank])