diff --git a/ktransformers/optimize/optimize_rules/DeepSeek-V3-Chat-multi-gpu-fp8-linear-ggml-experts.yaml b/ktransformers/optimize/optimize_rules/DeepSeek-V3-Chat-multi-gpu-fp8-linear-ggml-experts.yaml
index fa8c03d..849439c 100644
--- a/ktransformers/optimize/optimize_rules/DeepSeek-V3-Chat-multi-gpu-fp8-linear-ggml-experts.yaml
+++ b/ktransformers/optimize/optimize_rules/DeepSeek-V3-Chat-multi-gpu-fp8-linear-ggml-experts.yaml
@@ -66,7 +66,7 @@
     name: "^model\\.layers\\.(0|[1-9]|[12][0-9])\\.mlp\\.gate$"
     class: ktransformers.models.modeling_deepseek_v3.MoEGate
   replace:
-    class: ktransformers.operators.gate.KMoEGate
+    class: ktransformers.operators.gate.KMoEGateDeepSeekV3
     kwargs:
       generate_device: "cuda:0"
       prefill_device: "cuda:0"
@@ -74,7 +74,7 @@
     name: "^model\\.layers\\.([3456][0-9])\\.mlp\\.gate$"
     class: ktransformers.models.modeling_deepseek_v3.MoEGate
   replace:
-    class: ktransformers.operators.gate.KMoEGate     # mlp module with custom forward function
+    class: ktransformers.operators.gate.KMoEGateDeepSeekV3     # mlp module with custom forward function
     kwargs:
       generate_device: "cuda:1"
       prefill_device: "cuda:1"