Commits


Chen Fu authored and GitHub committed 34175f0b7cd
FP16 conv (#15062) ### Description Convolution for fp16 datatype. Use NHWC for computation. For NCHW input, it rearranges the input tensor to NHWC format before computing the result. Support two optional fusion: 1. Activation 2. Add (not yet implemented) ### Motivation and Context Accelerating fp16 inference