fix doc for 0.6

976505b1 · TeslaZhao · f645baa6 · 976505b1 · 976505b1 · 976505b1
4 changed file
--- a/doc/COMPILE.md
+++ b/doc/COMPILE.md
@@ -16,7 +16,7 @@
 |         glibc-static         |               2.17                |
 |        openssl-devel         |              1.0.2k               |
 |         bzip2-devel          |          1.0.6 and later          |
-| python-devel / python3-devel | 2.7.5 and later / 3.6.8 and later |
+|        python3-devel         |         3.6.0 and later |
 |         sqlite-devel         |         3.7.17 and later          |
 |           patchelf           |                0.9                |
 |           libXext            |               1.3.3               |
@@ -123,6 +123,7 @@ If not in Docker environment, users can refer to the following execution methods
 export CUDA_PATH='/usr/local/cuda'
 export CUDNN_LIBRARY='/usr/local/cuda/lib64/'
 export CUDA_CUDART_LIBRARY="/usr/local/cuda/lib64/"
+
 export TENSORRT_LIBRARY_PATH="/usr/local/TensorRT6-cuda10.1-cudnn7/targets/x86_64-linux-gnu/"

 mkdir server-build-gpu && cd server-build-gpu

--- a/doc/LATEST_PACKAGES.md
+++ b/doc/LATEST_PACKAGES.md
@@ -4,41 +4,18 @@
 ### Python 3
 ```
 # Compile by gcc8.2
-https://paddle-serving.bj.bcebos.com/whl/paddle_serving_server-0.0.0-py3-none-any.whl
-```
-
-### Python 2
-```
-# Compile by gcc8.2
-https://paddle-serving.bj.bcebos.com/whl/paddle_serving_server-0.0.0-py2-none-any.whl
+https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server-0.0.0-py3-none-any.whl
 ```

 ## GPU server
 ### Python 3
 ```
-#cuda 9.0, Compile by gcc4.8
-https://paddle-serving.bj.bcebos.com/whl/paddle_serving_server_gpu-0.0.0.post9-py3-none-any.whl
-#cuda 10.0, Compile by gcc4.8
-https://paddle-serving.bj.bcebos.com/whl/paddle_serving_server_gpu-0.0.0.post10-py3-none-any.whl
-#cuda10.1 with TensorRT 6, Compile by gcc8.2
-https://paddle-serving.bj.bcebos.com/whl/paddle_serving_server_gpu-0.0.0.post101-py3-none-any.whl
-#cuda10.2 with TensorRT 7, Compile by gcc8.2
-https://paddle-serving.bj.bcebos.com/whl/paddle_serving_server_gpu-0.0.0.post102-py3-none-any.whl
-#cuda11.0 with TensorRT 7 (beta), Compile by gcc8.2
-https://paddle-serving.bj.bcebos.com/whl/paddle_serving_server_gpu-0.0.0.post11-py3-none-any.whl
-```
-### Python 2
-```
-#cuda 9.0, Compile by gcc4.8
-https://paddle-serving.bj.bcebos.com/whl/paddle_serving_server_gpu-0.0.0.post9-py2-none-any.whl
-#cuda 10.0, Compile by gcc4.8
-https://paddle-serving.bj.bcebos.com/whl/paddle_serving_server_gpu-0.0.0.post10-py2-none-any.whl
 #cuda10.1 with TensorRT 6, Compile by gcc8.2
-https://paddle-serving.bj.bcebos.com/whl/paddle_serving_server_gpu-0.0.0.post101-py2-none-any.whl
+https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server_gpu-0.0.0.post101-py3-none-any.whl
 #cuda10.2 with TensorRT 7, Compile by gcc8.2
-https://paddle-serving.bj.bcebos.com/whl/paddle_serving_server_gpu-0.0.0.post102-py2-none-any.whl
+https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server_gpu-0.0.0.post102-py3-none-any.whl
 #cuda11.0 with TensorRT 7 (beta), Compile by gcc8.2
-https://paddle-serving.bj.bcebos.com/whl/paddle_serving_server_gpu-0.0.0.post11-py2-none-any.whl
+https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server_gpu-0.0.0.post11-py3-none-any.whl
 ```
 **Tips:**  If you want to use CPU server and GPU server at the same time, you should check the gcc version,  only Cuda10.1/10.2/11 can run with CPU server owing to the same gcc version(8.2).

@@ -46,35 +23,21 @@ https://paddle-serving.bj.bcebos.com/whl/paddle_serving_server_gpu-0.0.0.post11-

 ### Python 3.6
 ```
-https://paddle-serving.bj.bcebos.com/whl/paddle_serving_client-0.0.0-cp36-none-any.whl
+https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_client-0.0.0-cp36-none-any.whl
 ```
 ### Python 3.8
 ```
-https://paddle-serving.bj.bcebos.com/whl/paddle_serving_client-0.0.0-cp38-none-any.whl
+https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_client-0.0.0-cp38-none-any.whl
 ```
 ### Python 3.7
 ```
-https://paddle-serving.bj.bcebos.com/whl/paddle_serving_client-0.0.0-cp37-none-any.whl
-```
-### Python 3.5
-```
-https://paddle-serving.bj.bcebos.com/whl/paddle_serving_client-0.0.0-cp35-none-any.whl
-```
-### Python 2.7
-```
-https://paddle-serving.bj.bcebos.com/whl/paddle_serving_client-0.0.0-cp27-none-any.whl
+https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_client-0.0.0-cp37-none-any.whl
 ```

-
 ## App
 ### Python 3
 ```
-https://paddle-serving.bj.bcebos.com/whl/paddle_serving_app-0.0.0-py3-none-any.whl
-```
-
-### Python 2
-```
-https://paddle-serving.bj.bcebos.com/whl/paddle_serving_app-0.0.0-py2-none-any.whl
+https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_app-0.0.0-py3-none-any.whl
 ```

 ## ARM user
@@ -98,26 +61,22 @@ for most users, we do not need to read this section. But if you deploy your Padd
 #### Bin links
 ```
 # CPU AVX MKL
-https://paddle-serving.bj.bcebos.com/bin/serving-cpu-avx-mkl-0.0.0.tar.gz
+https://paddle-serving.bj.bcebos.com/test-dev/bin/serving-cpu-avx-mkl-0.0.0.tar.gz
 # CPU AVX OPENBLAS
-https://paddle-serving.bj.bcebos.com/bin/serving-cpu-avx-openblas-0.0.0.tar.gz
+https://paddle-serving.bj.bcebos.com/test-dev/bin/serving-cpu-avx-openblas-0.0.0.tar.gz
 # CPU NOAVX OPENBLAS
-https://paddle-serving.bj.bcebos.com/bin/serving-cpu-noavx-openblas-0.0.0.tar.gz
-# Cuda 9
-https://paddle-serving.bj.bcebos.com/bin/serving-gpu-cuda9-0.0.0.tar.gz
-# Cuda 10
-https://paddle-serving.bj.bcebos.com/bin/serving-gpu-cuda10-0.0.0.tar.gz
+https://paddle-serving.bj.bcebos.com/test-dev/bin/serving-cpu-noavx-openblas-0.0.0.tar.gz
 # Cuda 10.1
-https://paddle-serving.bj.bcebos.com/bin/serving-gpu-101-0.0.0.tar.gz
+https://paddle-serving.bj.bcebos.com/test-dev/bin/serving-gpu-101-0.0.0.tar.gz
 # Cuda 10.2
-https://paddle-serving.bj.bcebos.com/bin/serving-gpu-102-0.0.0.tar.gz
+https://paddle-serving.bj.bcebos.com/test-dev/bin/serving-gpu-102-0.0.0.tar.gz
 # Cuda 11
-https://paddle-serving.bj.bcebos.com/bin/serving-gpu-cuda11-0.0.0.tar.gz
+https://paddle-serving.bj.bcebos.com/test-dev/bin/serving-gpu-cuda11-0.0.0.tar.gz
 ```

 #### How to setup SERVING_BIN offline?

 - download the serving server whl package and bin package, and make sure they are for the same environment
 - download the serving client whl and serving app whl, pay attention to the Python version.
- `pip install ` the serving and `tar xf ` the binary package, then `export SERVING_BIN=$PWD/serving-gpu-cuda10-0.0.0/serving` (take Cuda 10.0 as the example)
+- `pip install ` the serving and `tar xf ` the binary package, then `export SERVING_BIN=$PWD/serving-gpu-cuda11-0.0.0/serving` (take Cuda 11 as the example)

--- a/tools/dockerfiles/build_scripts/install_whl.sh
+++ b/tools/dockerfiles/build_scripts/install_whl.sh
@@ -24,41 +24,52 @@ app_release="paddle-serving-app==0.3.1"

 if [[ $PYTHON_VERSION == "3.6" ]];then
    CPYTHON="36"
+    CPYTHON_PADDLE="36m"
 elif [[ $PYTHON_VERSION == "3.7" ]];then
    CPYTHON="37"
+    CPYTHON_PADDLE="37m"
 elif [[ $PYTHON_VERSION == "3.8" ]];then
    CPYTHON="38"
+    CPYTHON_PADDLE="38"
 fi

 if [[ $SERVING_VERSION == "0.5.0" ]]; then
    if [[ "$RUN_ENV" == "cpu" ]];then
        server_release="paddle-serving-server==$SERVING_VERSION"
-        serving_bin="https://paddle-serving.bj.bcebos.com/bin/serving-cpu-noavx-openblas-${SERVING_VERSION}.tar.gz"
+        serving_bin="https://paddle-serving.bj.bcebos.com/bin/serving-cpu-avx-mkl-${SERVING_VERSION}.tar.gz"
+        paddle_whl="https://paddle-wheel.bj.bcebos.com/$PADDLE_VERSION-cpu-avx-mkl/paddlepaddle-$PADDLE_VERSION-cp$CPYTHON-cp$CPYTHON_PADDLE-linux_x86_64.whl"
    elif [[ "$RUN_ENV" == "cuda10.1" ]];then
        server_release="paddle-serving-server-gpu==$SERVING_VERSION.post101"
        serving_bin="https://paddle-serving.bj.bcebos.com/bin/serving-gpu-101-${SERVING_VERSION}.tar.gz"
+        paddle_whl="https://paddle-wheel.bj.bcebos.com/with-trt/$PADDLE_VERSION-gpu-cuda10.1-cudnn7-mkl-gcc8.2/paddlepaddle_gpu-$PADDLE_VERSION.post101-cp$CPYTHON-cp$CPYTHON_PADDLE-linux_x86_64.whl"
    elif [[ "$RUN_ENV" == "cuda10.2" ]];then
        server_release="paddle-serving-server-gpu==$SERVING_VERSION.post102"
        serving_bin="https://paddle-serving.bj.bcebos.com/bin/serving-gpu-102-${SERVING_VERSION}.tar.gz"
+        paddle_whl="https://paddle-wheel.bj.bcebos.com/with-trt/$PADDLE_VERSION-gpu-cuda10.2-cudnn8-mkl-gcc8.2/paddlepaddle_gpu-$PADDLE_VERSION-cp$CPYTHON-cp$CPYTHON_PADDLE-linux_x86_64.whl"
    elif [[ "$RUN_ENV" == "cuda11" ]];then
        server_release="paddle-serving-server-gpu==$SERVING_VERSION.post11"
        serving_bin="https://paddle-serving.bj.bcebos.com/bin/serving-gpu-cuda11-${SERVING_VERSION}.tar.gz"
+        paddle_whl="https://paddle-wheel.bj.bcebos.com/with-trt/$PADDLE_VERSION-gpu-cuda11.0-cudnn8-mkl-gcc8.2/paddlepaddle_gpu-$PADDLE_VERSION.post110-cp$CPYTHON-cp$CPYTHON_PADDLE-linux_x86_64.whl"
    fi
    client_release="paddle-serving-client==$SERVING_VERSION"
    app_release="paddle-serving-app==0.3.1"
 elif [[ $SERVING_VERSION == "0.6.0" ]]; then 
    if [[ "$RUN_ENV" == "cpu" ]];then
        server_release="https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server-$SERVING_VERSION-py3-none-any.whl"
-        serving_bin="https://paddle-serving.bj.bcebos.com/test-dev/bin/serving-cpu-noavx-openblas-$SERVING_VERSION.tar.gz"
+        serving_bin="https://paddle-serving.bj.bcebos.com/test-dev/bin/serving-cpu-avx-mkl-$SERVING_VERSION.tar.gz"
+        paddle_whl="https://paddle-wheel.bj.bcebos.com/$PADDLE_VERSION-cpu-avx-mkl/paddlepaddle-$PADDLE_VERSION-cp$CPYTHON-cp$CPYTHON_PADDLE-linux_x86_64.whl"
    elif [[ "$RUN_ENV" == "cuda10.1" ]];then
        server_release="https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server_gpu-$SERVING_VERSION.post101-py3-none-any.whl"
        serving_bin="https://paddle-serving.bj.bcebos.com/test-dev/bin/serving-gpu-101-$SERVING_VERSION.tar.gz"
+        paddle_whl="https://paddle-wheel.bj.bcebos.com/with-trt/$PADDLE_VERSION-gpu-cuda10.1-cudnn7-mkl-gcc8.2/paddlepaddle_gpu-$PADDLE_VERSION.post101-cp$CPYTHON-cp$CPYTHON_PADDLE-linux_x86_64.whl"
    elif [[ "$RUN_ENV" == "cuda10.2" ]];then
        server_release="https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server_gpu-$SERVING_VERSION.post102-py3-none-any.whl"
        serving_bin="https://paddle-serving.bj.bcebos.com/test-dev/bin/serving-gpu-102-$SERVING_VERSION.tar.gz"
+        paddle_whl="https://paddle-wheel.bj.bcebos.com/with-trt/$PADDLE_VERSION-gpu-cuda10.2-cudnn8-mkl-gcc8.2/paddlepaddle_gpu-$PADDLE_VERSION-cp$CPYTHON-cp$CPYTHON_PADDLE-linux_x86_64.whl"
    elif [[ "$RUN_ENV" == "cuda11" ]];then
        server_release="https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server_gpu-$SERVING_VERSION.post11-py3-none-any.whl"
        serving_bin="https://paddle-serving.bj.bcebos.com/test-dev/bin/serving-gpu-cuda11-$SERVING_VERSION.tar.gz"
+        paddle_whl="https://paddle-wheel.bj.bcebos.com/with-trt/$PADDLE_VERSION-gpu-cuda11.0-cudnn8-mkl-gcc8.2/paddlepaddle_gpu-$PADDLE_VERSION.post110-cp$CPYTHON-cp$CPYTHON_PADDLE-linux_x86_64.whl"
    fi
    client_release="https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_client-$SERVING_VERSION-cp$CPYTHON-none-any.whl"
    app_release="https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_app-$SERVING_VERSION-py3-none-any.whl"
@@ -66,7 +77,7 @@ fi

 if [[ "$RUN_ENV" == "cpu" ]];then
    python$PYTHON_VERSION -m pip install $client_release $app_release $server_release
-    python$PYTHON_VERSION -m pip install paddlepaddle==${PADDLE_VERSION}
+    python$PYTHON_VERSION -m pip install $paddle_whl
    cd /usr/local/
    wget $serving_bin 
    tar xf serving-cpu-noavx-openblas-${SERVING_VERSION}.tar.gz
@@ -76,7 +87,7 @@ if [[ "$RUN_ENV" == "cpu" ]];then
    cd -
 elif [[ "$RUN_ENV" == "cuda10.1" ]];then
    python$PYTHON_VERSION -m pip install $client_release $app_release $server_release
-    python$PYTHON_VERSION -m pip install paddlepaddle-gpu==${PADDLE_VERSION}
+    python$PYTHON_VERSION -m pip install $paddle_whl
    cd /usr/local/
    wget $serving_bin
    tar xf serving-gpu-101-${SERVING_VERSION}.tar.gz
@@ -86,7 +97,7 @@ elif [[ "$RUN_ENV" == "cuda10.1" ]];then
    cd -
 elif [[ "$RUN_ENV" == "cuda10.2" ]];then
    python$PYTHON_VERSION -m pip install $client_release $app_release $server_release
-    python$PYTHON_VERSION -m pip install paddlepaddle-gpu==${PADDLE_VERSION}
+    python$PYTHON_VERSION -m pip install $paddle_whl
    cd /usr/local/
    wget $serving_bin
    tar xf serving-gpu-102-${SERVING_VERSION}.tar.gz
@@ -96,7 +107,7 @@ elif [[ "$RUN_ENV" == "cuda10.2" ]];then
    cd -
 elif [[ "$RUN_ENV" == "cuda11" ]];then
    python$PYTHON_VERSION -m pip install $client_release $app_release $server_release
-    python$PYTHON_VERSION -m pip install paddlepaddle-gpu==${PADDLE_VERSION}
+    python$PYTHON_VERSION -m pip install $paddle_whl
    cd /usr/local/
    wget $serving_bin
    tar xf serving-gpu-cuda11-${SERVING_VERSION}.tar.gz

--- a/tools/dockerfiles/build_scripts/soft_link.sh
+++ b/tools/dockerfiles/build_scripts/soft_link.sh
@@ -6,14 +6,14 @@ if [[ "$RUN_ENV" == "cuda10.1" ]];then
    ln -sf /usr/lib/x86_64-linux-gnu/libcublas.so.10 /usr/lib/libcublas.so && \
    ln -sf /usr/lib/x86_64-linux-gnu/libcudnn.so.7 /usr/lib/libcudnn.so

-elif [[ "$RUN_ENV" == "cuda10.1" ]];then
+elif [[ "$RUN_ENV" == "cuda10.2" ]];then
    ln -sf /usr/local/cuda-10.2/targets/x86_64-linux/lib/libcudart.so.10.2 /usr/lib/libcudart.so && \
    ln -sf /usr/local/cuda-10.2/targets/x86_64-linux/lib/libcusolver.so.10 /usr/lib/libcusolver.so && \
    ln -sf /usr/lib/x86_64-linux-gnu/libcuda.so /usr/lib/libcuda.so && \
    ln -sf /usr/lib/x86_64-linux-gnu/libcublas.so.10 /usr/lib/libcublas.so && \
    ln -sf /usr/lib/x86_64-linux-gnu/libcudnn.so.8 /usr/lib/libcudnn.so

-elif [[ "$RUN_ENV" == "cuda10.1" ]];then
+elif [[ "$RUN_ENV" == "cuda11" ]];then
    ln -sf /usr/local/cuda-11.0/targets/x86_64-linux/lib/libcudart.so.11.0 /usr/lib/libcudart.so && \
    ln -sf /usr/local/cuda-11.0/targets/x86_64-linux/lib/libcusolver.so.10 /usr/lib/libcusolver.so && \
    ln -sf /usr/lib/x86_64-linux-gnu/libcuda.so /usr/lib/libcuda.so && \