update inference lib to 1.7.1 && support py3

cmake/paddlepaddle.cmake

@@ -31,7 +31,7 @@ message( "WITH_GPU = ${WITH_GPU}")
 # Paddle Version should be one of:
 # latest: latest develop build
 # version number like 1.5.2
-SET(PADDLE_VERSION "1.6.3")
+SET(PADDLE_VERSION "1.7.1")
 
 if (WITH_GPU)
     SET(PADDLE_LIB_VERSION "${PADDLE_VERSION}-gpu-cuda${CUDA_VERSION_MAJOR}-cudnn7-avx-mkl")

core/general-client/CMakeLists.txt

@@ -2,4 +2,6 @@ if(CLIENT_ONLY)
 add_subdirectory(pybind11)
 pybind11_add_module(serving_client src/general_model.cpp src/pybind_general_model.cpp)
 target_link_libraries(serving_client PRIVATE -Wl,--whole-archive utils sdk-cpp pybind python -Wl,--no-whole-archive -lpthread -lcrypto -lm -lrt -lssl -ldl -lz)
+file(GLOB so ${PADDLE_SERVING_BINARY_DIR}/core/general-client/serving_client.*)
+file(RENAME ${so} ${PADDLE_SERVING_BINARY_DIR}/core/general-client/serving_client.so)
 endif()

python/paddle_serving_server/__init__.py

@@ -19,7 +19,7 @@ import google.protobuf.text_format
 import tarfile
 import socket
 import paddle_serving_server as paddle_serving_server
-from version import serving_server_version
+from .version import serving_server_version
 from contextlib import closing
 
 

python/paddle_serving_server_gpu/__init__.py

@@ -20,7 +20,7 @@ import google.protobuf.text_format
 import tarfile
 import socket
 import paddle_serving_server_gpu as paddle_serving_server
-from version import serving_server_version
+from .version import serving_server_version
 from contextlib import closing
 import argparse