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 6, 17:00 UTC
[Frontend][Misc] Remove unused log in `/is_sleeping` (#37093)
Signed-off-by: esmeetu <jasonailu87@gmail.com>
Roy Wang committed
Mar 16, 2026 at 17:46 UTC
0115e957d46002ca0c6823e66ef5856fbcef65be
1 file changed
-1
vllm/entrypoints/serve/sleep/api_router.py
-1
@@ -45,7 +45,6 @@ async def wake_up(raw_request: Request):
45
46
@router.get("/is_sleeping")
47
async def is_sleeping(raw_request: Request):
48
- logger.info("check whether the engine is sleeping")
48
is_sleeping = await engine_client(raw_request).is_sleeping()
49
return JSONResponse(content={"is_sleeping": is_sleeping})
50