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, 09:00 UTC
[Misc] fix this log format not space (#32112)
Signed-off-by: lengrongfu <lenronfu@gmail.com>
rongfu.leng committed
Jan 11, 2026 at 21:01 UTC
d70249e2e9b15655020efe08f3ef46fd908758aa
1 file changed
+1
-1
vllm/v1/engine/core_client.py
+1
-1
@@ -533,7 +533,7 @@ class MPClient(EngineCoreClient):
533
timeout=VLLM_ENGINE_READY_TIMEOUT_S * 1000 # convert to ms
534
):
535
raise TimeoutError(
536
- "Timed out waiting for engines to send"
536
+ "Timed out waiting for engines to send "
537
"initial message on input socket."
538
)
539
identity, _ = sync_input_socket.recv_multipart()