fix(quant): add layer_type parameter to torchair w8a8 dynamic

Signed-off-by: Anionex <[email protected]>

Author: Anionex

vllm_ascend/torchair/quantization/torchair_w8a8_dynamic.py

@@ -778,7 +778,8 @@ def get_perchannel_param(
         return params_dict
 
     def get_pergroup_param(self, input_size: int, output_size: int,
-                           params_dtype: torch.dtype) -> Dict[str, Any]:
+                           params_dtype: torch.dtype, 
+                           layer_type: Optional[str] = None) -> Dict[str, Any]:
         return {}
 
     @staticmethod