diff --git a/doc/FAQ.md b/doc/FAQ.md
index 4a20c25588dc1008b86fc52b298735464f0465d7..0d9e27a633a962b29a123e39a8b856ea9ad59eb0 100644
--- a/doc/FAQ.md
+++ b/doc/FAQ.md
@@ -186,7 +186,7 @@ wget https://paddle-serving.bj.bcebos.com/others/centos_ssl.tar && \
(2)Cuda和Cudnn动态库:文件名通常为 `libcudart.so.$CUDA_VERSION`,和 `libcudnn.so.$CUDNN_VERSION`。例如Cuda9就是 `libcudart.so.9.0`,Cudnn7就是 `libcudnn.so.7`。Cuda和Cudnn与Serving的版本匹配参见[Serving所有镜像列表](DOCKER_IMAGES_CN.md#%E9%99%84%E5%BD%95%E6%89%80%E6%9C%89%E9%95%9C%E5%83%8F%E5%88%97%E8%A1%A8).
- (3) Cuda10.1及更高版本需要TensorRT。安装TensorRT相关文件的脚本参考 [install_trt.sh](../tools/dockerfile/build_scripts/install_trt.sh).
+ (3) Cuda10.1及更高版本需要TensorRT。安装TensorRT相关文件的脚本参考 [install_trt.sh](../tools/dockerfiles/build_scripts/install_trt.sh).
## 部署问题
diff --git a/doc/PIPELINE_SERVING.md b/doc/PIPELINE_SERVING.md
index b8f39cf6c2695010fa2d542a6a7389e3d724b6ee..95d706e41eceef16b1f675ab0bf8db7bb7302ce3 100644
--- a/doc/PIPELINE_SERVING.md
+++ b/doc/PIPELINE_SERVING.md
@@ -15,7 +15,6 @@ The Server side is built based on RPC Service and graph execution engi
-
### 1. RPC Service
In order to meet the needs of different users, the RPC service starts one Web server and one RPC server at the same time, and can process 2 types of requests, RESTful API and gRPC.The gPRC gateway receives RESTful API requests and forwards requests to the gRPC server through the reverse proxy server; gRPC requests are received by the gRPC server, so the two types of requests are processed by the gRPC Service in a unified manner to ensure that the processing logic is consistent.
diff --git a/doc/deprecated/CLUSTERING.md b/doc/deprecated/CLUSTERING.md
index 7c372ac5657645c45c55e7189591739c95f1e166..b9da2e56165f17ee07116c46dbbdfefd806cb56f 100644
--- a/doc/deprecated/CLUSTERING.md
+++ b/doc/deprecated/CLUSTERING.md
@@ -1,6 +1,6 @@
# 搭建预测服务集群
-从[客户端配置](CLIENT_CONFIGURE.md)中我们已经知道,通过在客户端SDK的配置文件predictors.prototxt适当配置,可以搭建多副本和多Variant的预测集群。以下以图像分类任务为例,在单机上模拟搭建单Variant的多副本、和多Variant的预测集群
+从[客户端配置](../CLIENT_CONFIGURE.md)中我们已经知道,通过在客户端SDK的配置文件predictors.prototxt适当配置,可以搭建多副本和多Variant的预测集群。以下以图像分类任务为例,在单机上模拟搭建单Variant的多副本、和多Variant的预测集群
## 1. 单Variant多副本的预测集群
diff --git a/doc/deprecated/CREATING.md b/doc/deprecated/CREATING.md
index d057af4c38ef97c14b532cc563157a514745acec..2e77f3c12956000d688e6985afd59003820a7f30 100644
--- a/doc/deprecated/CREATING.md
+++ b/doc/deprecated/CREATING.md
@@ -75,7 +75,7 @@ service ImageClassifyService {
#### 2.2.2 示例配置
-关于Serving端的配置的详细信息,可以参考[Serving端配置](SERVING_CONFIGURE.md)
+关于Serving端的配置的详细信息,可以参考[Serving端配置](../SERVING_CONFIGURE.md)
以下配置文件将ReaderOP, ClassifyOP和WriteJsonOP串联成一个workflow (关于OP/workflow等概念,可参考[设计文档](DESIGN.md))
@@ -392,4 +392,4 @@ predictors {
}
}
```
-关于客户端的详细配置选项,可参考[CLIENT CONFIGURATION](CLIENT_CONFIGURE.md)
+关于客户端的详细配置选项,可参考[CLIENT CONFIGURATION](../CLIENT_CONFIGURE.md)
diff --git a/doc/deprecated/DESIGN_CN.md b/doc/deprecated/DESIGN_CN.md
index 846074b9144ea97bff4f70c2df7da86a639f15bd..42bc2b470195f5b60a80730db112dc41c39bdb2d 100644
--- a/doc/deprecated/DESIGN_CN.md
+++ b/doc/deprecated/DESIGN_CN.md
@@ -126,7 +126,7 @@ Paddle Serving实例可以同时加载多个模型,每个模型用一个Servic
![调用层级关系](../multi-variants.png)
一个Service对应一个预测模型,模型下有1个endpoint。模型的不同版本,通过endpoint下多个variant概念实现:
-同一个模型预测服务,可以配置多个variant,每个variant有自己的下游IP列表。客户端代码可以对各个variant配置相对权重,以达到调节流量比例的关系(参考[客户端配置](CLIENT_CONFIGURE.md)第3.2节中关于variant_weight_list的说明)。
+同一个模型预测服务,可以配置多个variant,每个variant有自己的下游IP列表。客户端代码可以对各个variant配置相对权重,以达到调节流量比例的关系(参考[客户端配置](../CLIENT_CONFIGURE.md)第3.2节中关于variant_weight_list的说明)。
![Client端proxy功能](../client-side-proxy.png)
@@ -143,7 +143,7 @@ Paddle Serving实例可以同时加载多个模型,每个模型用一个Servic
### 5.1 数据压缩方法
-Baidu-rpc内置了snappy, gzip, zlib等数据压缩方法,可在配置文件中配置(参考[客户端配置](CLIENT_CONFIGURE.md)第3.1节关于compress_type的介绍)
+Baidu-rpc内置了snappy, gzip, zlib等数据压缩方法,可在配置文件中配置(参考[客户端配置](../CLIENT_CONFIGURE.md)第3.1节关于compress_type的介绍)
### 5.2 C++ SDK API接口
diff --git a/python/setup.py.app.in b/python/setup.py.app.in
index cffa63cf8d98e542276ae8ef037b89a592c1947e..0d4763dfd448f12d23d26671a568f625d42ab7e7 100644
--- a/python/setup.py.app.in
+++ b/python/setup.py.app.in
@@ -44,7 +44,7 @@ REQUIRED_PACKAGES = [
'six >= 1.10.0',
'pillow',
'pyclipper', 'shapely',
- 'sentencepiece<=0.1.83; platform_machine != "aarch64"',
+ 'sentencepiece<=0.1.92; platform_machine != "aarch64"',
'sentencepiece; platform_machine == "aarch64"',
'opencv-python<=4.2.0.32; platform_machine != "aarch64"',
'opencv-python; platform_machine == "aarch64"',