diff --git a/vllm_ascend/torchair/quantization/torchair_w8a8_dynamic.py b/vllm_ascend/torchair/quantization/torchair_w8a8_dynamic.py
index 6517127..b933db6 100644
--- a/vllm_ascend/torchair/quantization/torchair_w8a8_dynamic.py
+++ b/vllm_ascend/torchair/quantization/torchair_w8a8_dynamic.py
@@ -1052,6 +1052,7 @@ class TorchairAscendW8A8DynamicFusedMoEMethod:
             layer.w2_weight.data = layer.w2_weight.data.transpose(
                 1, 2).contiguous()
         if is_enable_nz():
+            torch_npu.npu_format_cast_(layer.w13_weight, ACL_FORMAT_FRACTAL_NZ)
             torch_npu.npu_format_cast_(layer.w2_weight, ACL_FORMAT_FRACTAL_NZ)
         layer.w13_weight_scale.data = layer.w13_weight_scale.data.view(
             layer.w13_weight_scale.data.shape[0], -1)