File tree Expand file tree Collapse file tree 1 file changed +2
-2
lines changed
vllm/model_executor/layers/quantization Expand file tree Collapse file tree 1 file changed +2
-2
lines changed Original file line number Diff line number Diff line change @@ -236,7 +236,7 @@ def get_quant_method(
236236 if "vision_tower" in prefix or "vision_model" in prefix :
237237 return UnquantizedLinearMethod ()
238238 return ModelOptFp8LinearMethod (self )
239- elif isinstance (layer , Attention ) or isinstance ( layer , MLAAttention ):
239+ elif isinstance (layer , ( Attention , MLAAttention ) ):
240240 return ModelOptFp8KVCacheMethod (self )
241241 elif isinstance (layer , FusedMoE ):
242242 return ModelOptFp8MoEMethod (self , layer )
@@ -921,7 +921,7 @@ def get_quant_method(
921921 if "vision_tower" in prefix or "vision_model" in prefix :
922922 return UnquantizedLinearMethod ()
923923 return ModelOptNvFp4LinearMethod (self )
924- elif isinstance (layer , Attention ) or isinstance ( layer , MLAAttention ):
924+ elif isinstance (layer , ( Attention , MLAAttention ) ):
925925 return ModelOptFp8KVCacheMethod (self )
926926 elif isinstance (layer , FusedMoE ):
927927 if skip_layer :
You can’t perform that action at this time.
0 commit comments