Llama.cpp Now Part of the Nvidia RTX AI Toolkit Posted by alanzhuly on Thursday October 03, 2024 @02:31PM from the developer.nvidia.com dept. https://developer.nvidia.com/blog/accelerating-llms-with-llama-cpp-on-nvidia-rtx-systems/ ( 1 comment | 5 points | on HN )
I don't want ROCM to be the only way to use HIP.
Just upstream stuff, I don't want some special proprietary package.