Skip to content

Explicitly clean up allocated memory on LLM deletion #3116

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

Closed
wants to merge 2 commits into from
Closed

Explicitly clean up allocated memory on LLM deletion #3116

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
57061a9
Explicitly clean up allocated memory on LLM deletion
mgoin Feb 29, 2024
6c8b5f7
Update llm.py
mgoin Feb 29, 2024
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
6 changes: 6 additions & 0 deletions vllm/entrypoints/llm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -218,3 +218,9 @@ def _run_engine(self, use_tqdm: bool) -> List[RequestOutput]:
# its previous requests.
outputs = sorted(outputs, key=lambda x: int(x.request_id))
return outputs

def __del__(self):
del self.llm_engine.driver_worker.model_runner
del self.llm_engine.driver_worker
Copy link
Collaborator

@robertgshaw2-redhat robertgshaw2-redhat Feb 29, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We will also have to handle the case where there are multiple gpus.

In this case llm_engine will also have a workers list

import gc
gc.collect()