@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / e2f6f26e86
Fork 0

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)