Summary: This commit adds support for QAT fusion for the [conv-transpose-bn] and [conv-transpose-bn-relu] patterns. Test Plan: python test/test_quantization.py ...

#include "paddle/phi/kernels/cpu/conv_util.h" #include "paddle/phi/kernels/funcs/math_function.h" #include "paddle/phi/kernels/gpu/depthwise_conv.h" #include "paddle ...