I wonder how to accurately count floating point operations per second of RAFT model. The open interface basically only counts the convolution , for those special operations in the model, are there any good statistical methods? In other words, how do you do that?
I wonder how to accurately count floating point operations per second of RAFT model. The open interface basically only counts the convolution , for those special operations in the model, are there any good statistical methods? In other words, how do you do that?