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 16, 15:45 UTC
[Bugfix] Fix print_warning_once's line info (#8867)
Tyler Michael Smith committed
Sep 26, 2024 at 19:18 UTC
e2f6f26e8636b8a23e5c0cda533a70c40ade01ec
1 file changed
+2
-1
vllm/utils.py
+2
-1
@@ -744,7 +744,8 @@ def create_kv_caches_with_random(
744
745
@lru_cache
746
def print_warning_once(msg: str) -> None:
747
- logger.warning(msg)
747
+ # Set the stacklevel to 2 to print the caller's line info
748
+ logger.warning(msg, stacklevel=2)
749
750
751
@lru_cache(maxsize=None)