系统环境：

gcc版本：

预测库来源：
https://www.paddlepaddle.org.cn/documentation/docs/zh/1.5/advanced_usage/deploy/inference/build_and_install_lib_cn.html
从上面的链接里面下载的cpu_avx_mkl的1.5.1版本

预测库版本：

被编译的代码：

# include "paddle_inference_api.h"

int main() {
    // create a config and modify associated options
    paddle::NativeConfig config;
    config.model_dir = "xxx";
    config.use_gpu = false;
    config.fraction_of_gpu_memory = 0.15;
    config.device = 0;
    // create a native PaddlePredictor
    auto predictor = paddle::CreatePaddlePredictor<paddle::NativeConfig>(config);
    return 0;
}

编译和运行的命令（预测库解压到了~/fluid_inference/里面）

# !/bin/bash

set -x

# compile

g++ -I ~/fluid_inference/paddle/include/ simple.cpp -L ~/fluid_inference/paddle/lib/ -lpaddle_fluid -Wl,-rpath ~/fluid_inference/third_party/install/mklml/lib/ -Wl,-rpath ~/fluid_inference/third_party/install/mkldnn/lib/ -Wl,-rpath ~/fluid_inference/paddle/lib/

# prepare running libs

export LD_LIBRARY_PATH=~/fluid_inference/third_party/install/mklml/lib/:~/fluid_inference/third_party/install/mkldnn/lib/:~/fluid_inference/paddle/lib/

# run

./a.out

运行报错信息：