Bug: apply final_hidden_states*=self.routed_scaling_factor at MoE lay… (#8511)

Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>

python/sglang/srt/layers/moe/ep_moe/layer.py

@@ -304,7 +304,7 @@ class EPMoE(FusedMoE):
             m_max * self.start_expert_id,
             BLOCK_SIZE=512,
         )
-        return output
+        return output * self.routed_scaling_factor
 
 
 class DeepEPMoE(EPMoE):