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] remove unused try-except in pooling config check (#21618)
Signed-off-by: reidliu41 <reid201711@gmail.com>
Reid committed
Jul 26, 2025 at 20:20 UTC
05c1126f292ccaf6c57f46cc2c4f5df37db21543
1 file changed
+5
-7
vllm/transformers_utils/config.py
+5
-7
@@ -574,13 +574,11 @@ def get_pooling_config_name(pooling_name: str) -> Union[str, None]:
574
supported_pooling_types = ['LAST', 'ALL', 'CLS', 'STEP', 'MEAN']
575
pooling_type_name = pooling_name.upper()
576
577
- try:
578
- if pooling_type_name in supported_pooling_types:
579
- return pooling_type_name
580
- except NotImplementedError as e:
581
- logger.debug("Pooling type not supported", e)
582
- return None
583
- return None
577
+ if pooling_type_name in supported_pooling_types:
578
+ return pooling_type_name
579
+
580
+ raise NotImplementedError(
581
+ f"Pooling type {pooling_type_name} not supported")
582
583
584
@cache