Is it possible to use PyGAD's GPU acceleration to run a genetic algorithm as opposed to using numpy?

[Clev7]

I see the possibility of using GAs with torchGA to optimize neural networks using genetic algorithms, but is it possible to use Pytorch instead of numpy arrays to speed up the computation time of GAs?

[ahmedfgad]

Yes, it is possible but this is a major change.

Also, I am not sure if the GPU would help as the generic algorithm usually does not have complex time-consuming computations.