mirror of
https://github.com/vllm-project/vllm.git
synced 2025-10-20 14:53:52 +08:00
@ -325,7 +325,6 @@ class AsyncLLM(EngineClient):
|
||||
# Note: drain queue without await if possible (avoids
|
||||
# task switching under load which helps performance).
|
||||
out = q.get_nowait() or await q.get()
|
||||
|
||||
|
||||
# Note: both OutputProcessor and EngineCore handle their
|
||||
# own request cleanup based on finished.
|
||||
|
Reference in New Issue
Block a user