diff --git a/README.md b/README.md
index e2f2b8b..ab5344a 100755
--- a/README.md
+++ b/README.md
@@ -63,6 +63,7 @@
 #### 🚩2022-10-01 udpate:
 - 修复python部分下一些较小bugs
 - merge来自[AutumnSun1996](https://github.com/AutumnSun1996)的[OCRWeb实现的多语言部署](https://github.com/RapidAI/RapidOCR/pull/46)demo，详情参见：[ocrweb_mutli-README](./ocrweb_multi/README.md)
+- 添加onnxruntime-gpu推理速度较慢于CPU的问题说明，详情参见：[onnxruntime-gpu版相关说明](./python/README.md#onnxruntime-gpu版相关说明)
 
 #### 🛴2022-09-01 update:
 - 由于openvino发布了2022.2.0.dev20220829版本，该版本解决了`cls`部分模型推理的问题。至此，基于openvino的rapidocr完成了统一，全部由openvino推理引擎完成。
diff --git a/docs/README_en.md b/docs/README_en.md
index 0896d51..abf1af7 100644
--- a/docs/README_en.md
+++ b/docs/README_en.md
@@ -65,6 +65,7 @@
 #### 🚩2022-10-01 udpate:
 - Fix some minor bugs under python section.
 - Merge the [OCRWeb Implementation of Multilingual Deployment](https://github.com/RapidAI/RapidOCR/pull/46) demo from [AutumnSun1996](https://github.com/AutumnSun1996), see for details: [ocrweb_mutli-README](./ocrweb_multi/README.md)
+- Add a description of the problem that onnxruntime-gpu inference speed is slower than CPU. For details, please refer to: [onnxruntime-gpu version related instructions](../python/README.md#onnxruntime-gpu版相关说明)
 
 #### 🛴2022-09-01 update:
 - Since openvino released version 2022.2.0.dev20220829, this version solves the problem of `cls` partial model inference. So far, the openvino-based rapidocr has been unified, and it is all completed by the openvino inference engine.
diff --git a/docs/change_log.md b/docs/change_log.md
index b9b4ef5..234fba6 100644
--- a/docs/change_log.md
+++ b/docs/change_log.md
@@ -1,6 +1,7 @@
 #### 🚩2022-10-01 udpate:
 - 修复python部分下一些较小bugs
 - merge来自[AutumnSun1996](https://github.com/AutumnSun1996)的[OCRWeb实现的多语言部署](https://github.com/RapidAI/RapidOCR/pull/46)demo，详情参见：[ocrweb_mutli-README](../ocrweb_multi/README.md)
+- 添加onnxruntime-gpu推理速度较慢于CPU的问题说明，详情参见：[onnxruntime-gpu版相关说明](../python/README.md#onnxruntime-gpu版相关说明)
 
 #### 🛴2022-09-01 update:
 - 由于openvino发布了2022.2.0.dev20220829版本，该版本解决了`cls`部分模型推理的问题。至此，基于openvino的rapidocr完成了统一，全部由openvino推理引擎完成。
diff --git a/docs/change_log_en.md b/docs/change_log_en.md
index 7a1900b..ab20be1 100644
--- a/docs/change_log_en.md
+++ b/docs/change_log_en.md
@@ -1,6 +1,7 @@
 #### 🚩2022-10-01 udpate:
 - Fix some minor bugs under python section.
 - Merge the [OCRWeb Implementation of Multilingual Deployment](https://github.com/RapidAI/RapidOCR/pull/46) demo from [AutumnSun1996](https://github.com/AutumnSun1996), see for details: [ocrweb_mutli-README](../ocrweb_multi/README.md)
+- Add a description of the problem that onnxruntime-gpu inference speed is slower than CPU. For details, please refer to: [onnxruntime-gpu version related instructions](../python/README.md#onnxruntime-gpu版相关说明)
 
 #### 🛴2022-09-01 update:
 - Since openvino released version 2022.2.0.dev20220829, this version solves the problem of `cls` partial model inference. So far, the openvino-based rapidocr has been unified, and it is all completed by the openvino inference engine.
diff --git a/python/README.md b/python/README.md
index ade848f..66444ba 100755
--- a/python/README.md
+++ b/python/README.md
@@ -12,6 +12,7 @@
   - [pip安装快速使用](#pip安装快速使用)
   - [源码使用步骤](#源码使用步骤)
   - [`config.yaml`中常用参数介绍](#configyaml中常用参数介绍)
+  - [onnxruntime-gpu版相关说明](#onnxruntime-gpu版相关说明)
   - [onnxruntime-gpu版推理配置](#onnxruntime-gpu版推理配置)
   - [OpenVINO GPU推理配置](#openvino-gpu推理配置)
 </details>
@@ -240,8 +241,11 @@ print(rec_res)
     |`rec_img_shape`| - |`[3, 48, 320]`| 输入文本识别模型的图像Shape（CHW） |
     |`rec_batch_num`| - | 6 | 批次推理的batch大小，一般采用默认值即可，太大并没有明显提速，效果还可能会差 |
 
-### onnxruntime-gpu版推理配置
+### onnxruntime-gpu版相关说明
+- 目前已知在onnxruntime-gpu上测试过的小伙伴，反映都是GPU推理速度比在CPU上慢很多。经过探索，初步确定原因为onnxruntime在推理动态图输入时，速度就会慢很多。关于该问题，已经提了相关issue,具体可参见[onnxruntime issue#13198](https://github.com/microsoft/onnxruntime/issues/13198)
+- 为了便于比较onnxruntime上推理的基准比较，简单整理了一个[AI Studio: TestOrtInfer](https://aistudio.baidu.com/aistudio/projectdetail/4634684?contributionType=1&sUid=57084&shared=1&ts=1664700017761)项目，小伙伴想要测试的，可以直接Fork来运行查看。
 
+### onnxruntime-gpu版推理配置
 1. **onnxruntime-gpu**需要严格按照与CUDA、cuDNN版本对应来安装，具体参考[文档](https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html#requirements)，**这一步关乎后面是否可以成功调用GPU**。
    - 以下是安装示例：
         - 所用机器环境情况：