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
Lower sevarity of log when model info cache misses due to exception (#26917)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Harry Mellor committed
Oct 15, 2025 at 17:01 UTC
d3cbaa08dc94a75edc129df42966ccbeb4b15f5d
1 file changed
+1
-1
vllm/model_executor/models/registry.py
+1
-1
@@ -581,7 +581,7 @@ class _LazyRegisteredModel(_BaseRegisteredModel):
581
# file not changed, use cached _ModelInfo properties
582
return _ModelInfo(**mi_dict["modelinfo"])
583
except Exception:
584
- logger.exception(
584
+ logger.debug(
585
("Cached model info for class %s.%s error. "),
586
self.module_name,
587
self.class_name,