• Fenglei's avatar
    nvgpu softmax cuda version (#2014) · be9f031e
    Fenglei authored
    * add softmax cuda support
    
    * optimize block size
    
    * remove debug info
    
    * remove debug
    
    * style
    
    * remove unused
    
    * remove cudnn softmax
    
    * format
    
    * using nullptr
    
    * move helper, add test
    
    * fix style
    
    * using all_close_f
    
    * using kahansum
    
    * style
    
    * remove commentted out code
    be9f031e
backend_test.in.cpp 228 KB