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

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>

vllm/model_executor/layers/quantization/auto_round.py

@@ -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)