diff --git a/doc/Serving_Configure_CN.md b/doc/Serving_Configure_CN.md
index 9b8fd1c5a5bdad3ffc73bf6ac2de655ec97e3de2..3a5b449d599f989a9b3e360e29d63560b838a277 100644
--- a/doc/Serving_Configure_CN.md
+++ b/doc/Serving_Configure_CN.md
@@ -399,7 +399,7 @@ op:
             #use_mkldnn
             #use_mkldnn: True
 
-            #ir_optim
+            #ir_optim, 开启TensorRT时，必须同时设置ir_optim=True，否则无效
             ir_optim: True
 ```
 
@@ -454,4 +454,4 @@ Python Pipeline支持低精度推理，CPU、GPU和TensoRT支持的精度类型
 #GPU 支持: "fp32"(default), "fp16(TensorRT)", "int8"；
 #CPU 支持: "fp32"(default), "fp16", "bf16"(mkldnn); 不支持: "int8"
 precision: "fp32"
-```
\ No newline at end of file
+```