Does anybody know how to run this on Linux with an AMD GPU?

Also do I have to bother with their crappy driver module that doesn't support most GPUs?

llama.cpp doesn't need nor use GPU. You can run on Linux, but you gonna need a CPU with AVX2 support.

But if you have a GPU available, it can't use it? Why not?

It can not, that particular library is CPU-only.

If you want to run on GPU, use the official Python-based stack, which BTW takes about 10GB of runtime binaries on disk, and only supports nVidia GPUs because CUDA.

Do you have a link for that?

Source code: https://github.com/ggerganov/llama.cpp

My apologies @Const-me, are you referring to the module "convert-pth-to-ggml.py" in that repo? That appears to be the only Python in there.

The python + GPU one can be found on the official facebook repo: https://github.com/facebookresearch/llama (Presumably GP thought this was already known to everyone so they pasted the other link)