Skip to content
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

[Minor] Add warning on CUDA graph memory usage #2182

Merged
merged 1 commit into from
Dec 19, 2023
Merged

[Minor] Add warning on CUDA graph memory usage #2182

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
Add warning on CUDA graph memory usage
  • Loading branch information
@WoosukKwon
WoosukKwon committed Dec 18, 2023
commit a5f079143c128395617ece85db95093cbbd972ff
3 changes: 3 additions & 0 deletions vllm/worker/model_runner.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -395,6 +395,9 @@ def capture_model(self, kv_caches: List[KVCache]) -> None:
"unexpected consequences if the model is not static. To "
"run the model in eager mode, set 'enforce_eager=True' or "
"use '--enforce-eager' in the CLI.")
logger.info("CUDA graphs can take additional 1~3 GiB memory per GPU. "
"If you are running out of memory, consider decreasing "
"`gpu_memory_utilization` or enforcing eager mode.")
start_time = time.perf_counter()

# Prepare dummy inputs. These will be reused for all batch sizes.
Expand Down
Loading