Llama.cpp Now Part of the Nvidia RTX AI Toolkit

[alanzhuly]

https://developer.nvidia.com/blog/accelerating-llms-with-llama-cpp-on-nvidia-rtx-systems/

[stuaxo]

I don't want nvidia to pull in projects.

I don't want ROCM to be the only way to use HIP.

Just upstream stuff, I don't want some special proprietary package.