[dTal]

You don't need to compile it yourself though? Unless you want CUDA support on Linux I guess, dunno why you'd need such a silly thing though:

https://github.com/ggml-org/llama.cpp/releases

[flux3125]

> dunno why you'd need such a silly thing though

I'm not sure I follow, what alternative to CUDA on Linux offers similar performance?

[dTal]

Ah, 'twas a mere jest, a sarcastic jab that of all the manifold builds provided, the most useful is missing - doubtless for good and practical reasons.

Nevertheless, worth looking at the Vulkan builds. They work on all GPUs!