@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 2f3d36a8a1
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 17, 06:45 UTC

Fix logging so we actually get info level entries in the log. (#1494)

Adam Brusselback committed Oct 30, 2023 at 13:02 UTC 2f3d36a8a1485ae372071eb93f822ef9f592d957
1 file changed +5 -1
vllm/logger.py
+5 -1
@@ -48,4 +48,8 @@ _setup_logger()
48
49
50 def init_logger(name: str):
51 - return logging.getLogger(name)
51 + # Use the same settings as above for root logger
52 + logger = logging.getLogger(name)
53 + logger.setLevel(logging.DEBUG)
54 + logger.addHandler(_default_handler)
55 + return logger