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, 23:45 UTC
[Misc] Reduce logs for model resolution (#21765)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Cyrus Leung committed
Jul 28, 2025 at 22:59 UTC
0e18a5d058260b5444dd1712152a942c78a991f7
1 file changed
+12
-6
vllm/config.py
+12
-6
@@ -949,9 +949,12 @@ class ModelConfig:
949
950
runner_type = self._get_default_runner_type(architectures)
951
952
- logger.info(
953
- "Resolved `--runner auto` to `--runner %s`. "
954
- "Pass the value explicitly to silence this message.", runner_type)
952
+ # Don't log the most common case
953
+ if runner_type != "generate":
954
+ logger.info(
955
+ "Resolved `--runner auto` to `--runner %s`. "
956
+ "Pass the value explicitly to silence this message.",
957
+ runner_type)
958
959
return runner_type
960
@@ -998,9 +1001,12 @@ class ModelConfig:
1001
convert_type = self._get_default_convert_type(architectures,
1002
runner_type)
1003
1001
- logger.info(
1002
- "Resolved `--convert auto` to `--convert %s`. "
1003
- "Pass the value explicitly to silence this message.", convert_type)
1004
+ # Don't log the most common case
1005
+ if convert_type != "none":
1006
+ logger.info(
1007
+ "Resolved `--convert auto` to `--convert %s`. "
1008
+ "Pass the value explicitly to silence this message.",
1009
+ convert_type)
1010
1011
return convert_type
1012