News for hackers. Stuff that matters.
Re:Llama.cpp: Full CUDA GPU Acceleration by emmender on Tuesday June 13, 2023 @10:26AM (#36310679)
In addition to the above:

1) function decorators etc have made the code unreadable

2) while code is succinct, a lot of abstraction is hidden in some C/C++ language binding somewhere, so, when there is a problem, it is hard to debug

3) Pytorch has become a monolithic monster with practically no-one understanding its functionality e-2-e

There are no comments on this comment yet.