• S
    detect tensorRT plugin fp16 in runtime (#27933) · b9e76a01
    Shang Zhizhou 提交于
    * remove -DSUPPORTS_CUDA_FP16 in cuda.cmake
    
    * comile with cuda9
    
    * add some unittest
    
    * notest;test=coverage
    
    * add unittest for trt plugin swish && split
    
    * update ernie unittest
    
    * fix some error message
    
    * remove repeated judgement of CUDA version in mbEltwiseLayerNormOpConverter
    
    * fix comile errror when CUDA_ARCH_NAME < Pascal"
    
    * fix comile error
    
    * update unittest timeout
    
    * compile with cuda9
    
    * update error msg
    
    * fix code style
    
    * add some comments
    
    * add define IF_CUDA_ARCH_SUPPORT_FP16
    
    * rename IF_CUDA_ARCH_SUPPORT_FP16 to CUDA_ARCH_FP16_SUPPORTED
    b9e76a01
float16.h 28.8 KB