diff --git a/doc/fluid/advanced_usage/deploy/inference/build_and_install_lib_cn.rst b/doc/fluid/advanced_usage/deploy/inference/build_and_install_lib_cn.rst
index 4787e2c8ee8d71ead611efd2e33aed1ebca7f737..de43de186d5ccb4875bf570e5749ddbad8b19b7b 100644
--- a/doc/fluid/advanced_usage/deploy/inference/build_and_install_lib_cn.rst
+++ b/doc/fluid/advanced_usage/deploy/inference/build_and_install_lib_cn.rst
@@ -7,15 +7,16 @@
 -------------
 
 ..  csv-table:: c++预测库列表
-    :header: "版本说明", "预测库(1.4版本)", "预测库(develop版本)"
+    :header: "版本说明", "预测库(1.5版本)", "预测库(develop版本)"
     :widths: 1, 3, 3
 
-    "cpu_avx_mkl", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/1.4.0-cpu-avx-mkl/fluid_inference.tgz>`_", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/latest-cpu-avx-mkl/fluid_inference.tgz>`_"
-    "cpu_avx_openblas", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/1.4.0-cpu-avx-openblas/fluid_inference.tgz>`_", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/latest-cpu-avx-openblas/fluid_inference.tgz>`_"
-    "cpu_noavx_openblas","`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/1.4.0-cpu-noavx-openblas/fluid_inference.tgz>`_", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/latest-cpu-noavx-openblas/fluid_inference.tgz>`_"
-    "cuda8.0_cudnn5_avx_mkl", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/1.4.0-gpu-cuda8-cudnn5-avx-mkl/fluid_inference.tgz>`_", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/latest-gpu-cuda8-cudnn5-avx-mkl/fluid_inference.tgz>`_"
-    "cuda8.0_cudnn7_avx_mkl","`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/1.4.0-gpu-cuda8-cudnn7-avx-mkl/fluid_inference.tgz>`_", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/latest-gpu-cuda8-cudnn7-avx-mkl/fluid_inference.tgz>`_"
-    "cuda9.0_cudnn7_avx_mkl", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/1.4.0-gpu-cuda9-cudnn7-avx-mkl/fluid_inference.tgz>`_", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/latest-gpu-cuda9-cudnn7-avx-mkl/fluid_inference.tgz>`_"
+    "cpu_avx_mkl", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/1.5.0-cpu-avx-mkl/fluid_inference.tgz>`_", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/latest-cpu-avx-mkl/fluid_inference.tgz>`_"
+    "cpu_avx_openblas", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/1.5.0-cpu-avx-openblas/fluid_inference.tgz>`_", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/latest-cpu-avx-openblas/fluid_inference.tgz>`_"
+    "cpu_noavx_openblas", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/1.5.0-cpu-noavx-openblas/fluid_inference.tgz>`_", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/latest-cpu-noavx-openblas/fluid_inference.tgz>`_"
+    "cuda8.0_cudnn7_avx_openblas", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/1.5.0-gpu-cuda8-cudnn7-avx-openblas/fluid_inference.tgz>`_", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/latest-gpu-cuda8-cudnn7-avx-openblas/fluid_inference.tgz>`_"
+    "cuda8.0_cudnn7_avx_mkl", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/1.5.0-gpu-cuda8-cudnn7-avx-mkl/fluid_inference.tgz>`_", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/latest-gpu-cuda8-cudnn7-avx-mkl/fluid_inference.tgz>`_"
+    "cuda9.0_cudnn7_avx_mkl", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/1.5.0-gpu-cuda9-cudnn7-avx-mkl/fluid_inference.tgz>`_", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/latest-gpu-cuda9-cudnn7-avx-mkl/fluid_inference.tgz>`_"
+    "cuda10.0_cudnn7_avx_mkl", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/1.5.0-gpu-cuda10-cudnn7-avx-mkl/fluid_inference.tgz>`_", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/latest-gpu-cuda10-cudnn7-avx-mkl/fluid_inference.tgz>`_"
 
 
 从源码编译
@@ -99,4 +100,4 @@ version.txt 中记录了该预测库的版本信息，包括Git Commit ID、使
      WITH_MKLDNN: ON
      WITH_GPU: ON
      CUDA version: 8.0
-     CUDNN version: v5
+     CUDNN version: v7
diff --git a/doc/fluid/advanced_usage/deploy/inference/build_and_install_lib_en.rst b/doc/fluid/advanced_usage/deploy/inference/build_and_install_lib_en.rst
index d64e5b0fa6d649e539916aecee76dbd284936616..21d8c0cbe0219ff19fe8cd3ebebcbe067b13e1f7 100644
--- a/doc/fluid/advanced_usage/deploy/inference/build_and_install_lib_en.rst
+++ b/doc/fluid/advanced_usage/deploy/inference/build_and_install_lib_en.rst
@@ -7,15 +7,16 @@ Direct Download and Installation
 ---------------------------------
 
 ..  csv-table:: c++ inference library list
-    :header: "version description", "inference library(1.4 version)", "inference library(develop version)"
+    :header: "version description", "inference library(1.5 version)", "inference library(develop version)"
     :widths: 1, 3, 3
 
-    "cpu_avx_mkl", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/1.4.0-cpu-avx-mkl/fluid_inference.tgz>`_", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/latest-cpu-avx-mkl/fluid_inference.tgz>`_"
-    "cpu_avx_openblas", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/1.4.0-cpu-avx-openblas/fluid_inference.tgz>`_", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/latest-cpu-avx-openblas/fluid_inference.tgz>`_"
-    "cpu_noavx_openblas","`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/1.4.0-cpu-noavx-openblas/fluid_inference.tgz>`_", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/latest-cpu-noavx-openblas/fluid_inference.tgz>`_"
-    "cuda8.0_cudnn5_avx_mkl", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/1.4.0-gpu-cuda8-cudnn5-avx-mkl/fluid_inference.tgz>`_", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/latest-gpu-cuda8-cudnn5-avx-mkl/fluid_inference.tgz>`_"
-    "cuda8.0_cudnn7_avx_mkl","`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/1.4.0-gpu-cuda8-cudnn7-avx-mkl/fluid_inference.tgz>`_", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/latest-gpu-cuda8-cudnn7-avx-mkl/fluid_inference.tgz>`_"
-    "cuda9.0_cudnn7_avx_mkl", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/1.4.0-gpu-cuda9-cudnn7-avx-mkl/fluid_inference.tgz>`_", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/latest-gpu-cuda9-cudnn7-avx-mkl/fluid_inference.tgz>`_"
+    "cpu_avx_mkl", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/1.5.0-cpu-avx-mkl/fluid_inference.tgz>`_", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/latest-cpu-avx-mkl/fluid_inference.tgz>`_"
+    "cpu_avx_openblas", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/1.5.0-cpu-avx-openblas/fluid_inference.tgz>`_", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/latest-cpu-avx-openblas/fluid_inference.tgz>`_"
+    "cpu_noavx_openblas", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/1.5.0-cpu-noavx-openblas/fluid_inference.tgz>`_", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/latest-cpu-noavx-openblas/fluid_inference.tgz>`_"
+    "cuda8.0_cudnn7_avx_openblas", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/1.5.0-gpu-cuda8-cudnn7-avx-openblas/fluid_inference.tgz>`_", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/latest-gpu-cuda8-cudnn7-avx-openblas/fluid_inference.tgz>`_"
+    "cuda8.0_cudnn7_avx_mkl", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/1.5.0-gpu-cuda8-cudnn7-avx-mkl/fluid_inference.tgz>`_", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/latest-gpu-cuda8-cudnn7-avx-mkl/fluid_inference.tgz>`_"
+    "cuda9.0_cudnn7_avx_mkl", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/1.5.0-gpu-cuda9-cudnn7-avx-mkl/fluid_inference.tgz>`_", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/latest-gpu-cuda9-cudnn7-avx-mkl/fluid_inference.tgz>`_"
+    "cuda10.0_cudnn7_avx_mkl", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/1.5.0-gpu-cuda10-cudnn7-avx-mkl/fluid_inference.tgz>`_", "`fluid_inference.tgz <https://paddle-inference-lib.bj.bcebos.com/latest-gpu-cuda10-cudnn7-avx-mkl/fluid_inference.tgz>`_"
 
 
 Build from Source Code
@@ -102,4 +103,4 @@ The version information of the inference library is recorded in version.txt, inc
      WITH_MKLDNN: ON
      WITH_GPU: ON
      CUDA version: 8.0
-     CUDNN version: v5
+     CUDNN version: v7