diff --git a/paddle/fluid/inference/api/high_level_api.md b/paddle/fluid/inference/api/high_level_api.md
index eb92885052a453d8c837bbf6f6e984efb509332a..8b8b6916d7e2b1a2f9fd09e9dfd2fe5a332461f5 100644
--- a/paddle/fluid/inference/api/high_level_api.md
+++ b/paddle/fluid/inference/api/high_level_api.md
@@ -57,4 +57,4 @@ By specifying the engine kind and config, one can get a specific implementation.
 ## Reference
 
 - [paddle_inference_api.h](./paddle_inference_api.h)
-- [some demos](./demo)
+- [some demos](./demo_ci)
diff --git a/paddle/fluid/inference/api/high_level_api_cn.md b/paddle/fluid/inference/api/high_level_api_cn.md
index a57f015a4e44d43ee4e475cf606faa6f05e095fa..2fb914592cbcb1b0c3f2ef33ff9cf4c295e427b6 100644
--- a/paddle/fluid/inference/api/high_level_api_cn.md
+++ b/paddle/fluid/inference/api/high_level_api_cn.md
@@ -83,5 +83,5 @@ CHECK(predictor->Run(slots, &outputs));
 
 ## 详细代码参考
 
-- [inference demos](./demo)
-- [复杂单线程/多线程例子](https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/contrib/inference/test_paddle_inference_api_impl.cc)
+- [inference demos](./demo_ci)
+- [复杂单线程/多线程例子](https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/fluid/inference/api/test_api_impl.cc)