xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-25 10:16:32 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix: Correct FusedMoE layer reference in auto_round quantization (#24818)

Browse Source 
Signed-off-by: David-Wen <18927700430@163.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
This commit is contained in:
David-Wen 2025-09-20 04:44:24 +08:00 committed by yewentao256
parent d0a1364188
commit 9da51c77a9
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/model_executor/layers/quantization/auto_round.py
View File

@ -241,7 +241,7 @@ class AutoRoundConfig(QuantizationConfig):
if isinstance(layer, FusedMoE):
if use_marlin:
return AWQMoEMethod(quant_args_marlin, layer.moe)
return AWQMoEMethod(quant_args_marlin, layer.moe_config)
from vllm.model_executor.layers.quantization.moe_wna16 import (
MoeWNA16Config)
@ -327,7 +327,7 @@ class AutoRoundConfig(QuantizationConfig):
if isinstance(layer, FusedMoE):
if use_marlin:
return GPTQMarlinMoEMethod(quant_args_marlin, layer.moe)
return GPTQMarlinMoEMethod(quant_args_marlin, layer.moe_config)
else:
from vllm.model_executor.layers.quantization.moe_wna16 import (
MoeWNA16Config)