diff --git a/vllm/v1/engine/async_llm.py b/vllm/v1/engine/async_llm.py index 6736ed7273458..6395d2c1875b7 100644 --- a/vllm/v1/engine/async_llm.py +++ b/vllm/v1/engine/async_llm.py @@ -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.