xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-13 19:55:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix typo in logging (#17605)

Browse Source
This commit is contained in:
Eric Hartford 2025-05-02 21:04:40 -04:00 committed by GitHub
parent b90b0852e9
commit 9b103a1d76
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/layers/quantization/awq_marlin.py
View File

@ -140,7 +140,7 @@ class AWQMarlinConfig(QuantizationConfig):
from vllm.model_executor.layers.quantization.moe_wna16 import ( from vllm.model_executor.layers.quantization.moe_wna16 import (
MoeWNA16Config) MoeWNA16Config)
if not check_moe_marlin_supports_layer(layer, self.group_size): if not check_moe_marlin_supports_layer(layer, self.group_size):
logger.warning_one( logger.warning_once(
f"Layer '{prefix}' is not supported by AWQMoeMarlin. " f"Layer '{prefix}' is not supported by AWQMoeMarlin. "
"Falling back to Moe WNA16 kernels.") "Falling back to Moe WNA16 kernels.")
return MoeWNA16Config.from_config( return MoeWNA16Config.from_config(

2
vllm/model_executor/layers/quantization/gptq_marlin.py
View File

@ -157,7 +157,7 @@ class GPTQMarlinConfig(QuantizationConfig):
from vllm.model_executor.layers.quantization.moe_wna16 import ( from vllm.model_executor.layers.quantization.moe_wna16 import (
MoeWNA16Config) MoeWNA16Config)
if not check_moe_marlin_supports_layer(layer, self.group_size): if not check_moe_marlin_supports_layer(layer, self.group_size):
logger.warning_one( logger.warning_once(
f"Layer '{prefix}' is not supported by GPTQMoeMarlin. " f"Layer '{prefix}' is not supported by GPTQMoeMarlin. "
"Falling back to Moe WNA16 kernels.") "Falling back to Moe WNA16 kernels.")
return MoeWNA16Config.from_config( return MoeWNA16Config.from_config(