A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 05:30 UTC
Fix incorrect docstring for stop_profile() method (#27101)
Signed-off-by: Yongtao Huang <yongtaoh2022@gmail.com>
Yongtao Huang committed
Oct 17, 2025 at 21:30 UTC
be429d0cfda9ad0c5e0df6bf1cd140c40073063d
1 file changed
+1
-1
vllm/engine/protocol.py
+1
-1
@@ -110,7 +110,7 @@ class EngineClient(ABC):
110
111
@abstractmethod
112
async def stop_profile(self) -> None:
113
- """Start profiling the engine"""
113
+ """Stop profiling the engine"""
114
...
115
116
@abstractmethod