• S
    TensorRT中ernie模型推理性能优化,支持变长输入 (#28367) · ea851796
    Shang Zhizhou 提交于
    * fp16 result ok
    
    * change -DWITH_NVINFER_PLUGIN toconfig.EnableTensorRtOSS
    
    * auto detect special slice op converter for ernie with trt oss
    
    * ernie oss only support fp16
    
    * fix special_slice_plugin serialize bug
    
    * matmul in tensorrt ok
    
    * ernie unittest ok
    
    * add matmul tensorrt unittest
    
    * remove demo code
    ea851796
analysis_predictor.cc 42.1 KB