[Bug] R1 Accuracy: Fix routed_scaling_factor Double Mul Issue (vllm-project#24119)

Signed-off-by: yewentao256 <[email protected]>

Author: yewentao256

vllm/model_executor/models/deepseek_v2.py

@@ -160,7 +160,8 @@ def __init__(
             topk_group=config.topk_group,
             prefix=f"{prefix}.experts",
             scoring_func=config.scoring_func,
-            routed_scaling_factor=self.routed_scaling_factor,
+            # we do scaling outside, set factor to 1.0 to avoid double mul
+            routed_scaling_factor=1.0,
             e_score_correction_bias=self.gate.e_score_correction_bias,
             enable_eplb=self.enable_eplb,
             num_redundant_experts=self.n_redundant_experts)