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 10, 06:30 UTC
[Misc] Change log level for batch queue log (#32192)
Signed-off-by: NickLucche <nlucches@redhat.com>
Nicolò Lucchesi committed
Jan 12, 2026 at 19:59 UTC
08e8e99ce78f370d2f430d28b802592bf816655a
1 file changed
+1
-1
vllm/v1/engine/core.py
+1
-1
@@ -183,7 +183,7 @@ class EngineCore:
183
deque[tuple[Future[ModelRunnerOutput], SchedulerOutput, Future[Any]]] | None
184
) = None
185
if self.batch_queue_size > 1:
186
- logger.info("Batch queue is enabled with size %d", self.batch_queue_size)
186
+ logger.debug("Batch queue is enabled with size %d", self.batch_queue_size)
187
self.batch_queue = deque(maxlen=self.batch_queue_size)
188
189
self.is_ec_producer = (