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 7, 06:30 UTC
[UX] Remove NoOpOffloader log (#35678)
Signed-off-by: Robert Shaw <robshaw@redhat.com> Co-authored-by: Robert Shaw <robshaw@redhat.com>
Robert Shaw committed
Mar 4, 2026 at 15:13 UTC
b7d59ffce2f951e0ec8d1dc3a2f1e3d27f779906
1 file changed
+6
-1
vllm/model_executor/offloader/base.py
+6
-1
@@ -103,7 +103,12 @@ def set_offloader(instance: BaseOffloader) -> None:
103
"""Set the global offloader instance."""
104
global _instance
105
_instance = instance
106
- logger.info("Offloader set to %s", type(instance).__name__)
106
+ if isinstance(instance, NoopOffloader):
107
+ logger.debug_once(
108
+ "Offloader set to NoopOffloader (no offloading).", scope="local"
109
+ )
110
+ else:
111
+ logger.info_once("Offloader set to %s", type(instance).__name__, scope="local")
112
113
114
def create_offloader(offload_config: "OffloadConfig") -> BaseOffloader: