Update _custom_ops.py

vllm/_custom_ops.py

@@ -906,9 +906,10 @@ def triton_scaled_mm(a: torch.Tensor,
                       scale_a: torch.Tensor,
                       scale_b: torch.Tensor,
                       out_dtype: torch.dtype,
-                      bias: Optional[torch.Tensor] = None) -> torch.Tensor:
+                      bias: Optional[torch.Tensor] = None,
+                      best_config:Optional[list] = None) -> torch.Tensor:
 
-    return quant_ops.triton_scaled_mm(a, b,scale_a,scale_b,out_dtype,bias)
+    return quant_ops.triton_scaled_mm(a, b,scale_a,scale_b,out_dtype,bias,best_config)
 
 def triton_int8_gemm_helper(m: int,
                              n: int,