Skip to content

[bugfix] fix vllm sleep&wake_up produces meaningless output #5143

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 2 commits into from
Jul 29, 2025
Merged

[bugfix] fix vllm sleep&wake_up produces meaningless output #5143

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f0e5d78
fix vllm meaningless output
hjh0119 Jul 29, 2025
38b510d
add comments
hjh0119 Jul 29, 2025
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
1 change: 1 addition & 0 deletions swift/trainers/rlhf_trainer/grpo_trainer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -894,6 +894,7 @@ def _fast_infer(self, inputs: InputsType) -> Tuple[InputsType, OutputsType]:
outputs = self._infer_single_or_multi_turn(inputs, self.request_config)

if self.vllm_mode == 'colocate' and self.args.sleep_level > 0:
self.engine.engine.reset_prefix_cache()
self.engine.engine.sleep(level=self.args.sleep_level)
empty_cache()

Expand Down
Loading