simplify the control logic for using shared experts fusion (#5504)

python/sglang/srt/layers/quantization/w8a8_fp8.py

@@ -294,6 +294,7 @@ class W8A8FP8MoEMethod:
         activation: str = "silu",
         inplace: bool = True,
         no_combine: bool = False,
+        routed_scaling_factor: Optional[float] = None,
     ) -> torch.Tensor:
         from sglang.srt.layers.moe.fused_moe_triton.fused_moe import fused_experts
         from sglang.srt.layers.moe.topk import select_experts
@@ -309,6 +310,7 @@ class W8A8FP8MoEMethod:
             num_expert_group=num_expert_group,
             custom_routing_function=custom_routing_function,
             correction_bias=correction_bias,
+            routed_scaling_factor=routed_scaling_factor,
         )
 
         return fused_experts(