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, 18:15 UTC
[BugFix] Fix "DP Coordinator receives unexpected..." messages (#37008)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Nick Hill committed
Mar 13, 2026 at 16:18 UTC
54a6db827ff618c4492f656fae82654def163f13
1 file changed
+2
-2
vllm/v1/engine/coordinator.py
+2
-2
@@ -248,9 +248,9 @@ class DPCoordinatorProc:
248
# Subscription message, on the other hand, is sent
249
# by each engine during initialization
250
publish_back.send(b"READY")
251
- else:
251
+ elif buffer != b"\x00":
252
logger.error(
253
- "DP Coordinator receives unexpected message from engines"
253
+ "DP Coordinator received unexpected message from engines"
254
)
255
256
if publish_front in events: