KAN-benchmarking
KAN-benchmarking copied to clipboard
Jerry-Master
Benchmark for efficiency in memory and time of different KAN implementations.
The results of the benchmark are not including the apple metal performance.
Is there any plan to provide a comparison of model performance besides efficiency?
I benchmarked my implementation of ChebyKAN written in CUDA. The code runs slower than pure pytorch version and uses more VRAM, probably because the cuda code is not optimized. -...
Metadata
Owner
Metadata
Benchmark for efficiency in memory and time of different KAN implementations.