News for hackers. Stuff that matters.
Re:Llama.cpp: Full CUDA GPU Acceleration by vachina on Tuesday June 13, 2023 @08:41AM (#36309399)
You can “cd llama.cpp && make && ./main" because the developers made that happen.

A self contained zero dependency Python project is also literally “python app.py”

Re:Llama.cpp: Full CUDA GPU Acceleration by peatmoss on Tuesday June 13, 2023 @11:39AM (#36311859)
This is true, though in practice I so often find large, non-trivial examples of the former, but very seldom find examples of the latter.

The barriers to entry are lower with python, and so I think there tends to be a lower standard for deployment.