1.在lightseq-master/lightseq/csrc/kernels/cuda/cuda_util.cu文件中
添加头文件#include <thrust/transform_reduce.h>
2.把所有c++14改成c++17
成功运行!
Compare the results of custom and baseline...
Test passed. Time of custom/baseline (ms): 0.461 / 2.943, speedup: 6.389