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
[UX] Remove AsyncLLM torch profiler disabled log (#24609)
Signed-off-by: mgoin <mgoin64@gmail.com>
Michael Goin committed
Sep 12, 2025 at 13:08 UTC
9d2a44606d6b95b4e6aa7b6c75ae3a87f0560ede
1 file changed
-3
vllm/v1/engine/async_llm.py
-3
@@ -177,9 +177,6 @@ class AsyncLLM(EngineClient):
177
worker_name=worker_name,
178
use_gzip=True))
179
else:
180
- logger.info(
181
- "Torch profiler disabled. AsyncLLM CPU traces will not be collected." # noqa: E501
182
- )
180
self.profiler = None
181
182
@classmethod