News for hackers. Stuff that matters.

A comment on Llama.cpp: Full CUDA GPU Acceleration. Parent comment

Re:Llama.cpp: Full CUDA GPU Acceleration by numlock86 on Tuesday June 13, 2023 @12:36AM (#36305378)
> Absolutely a pity & a shame no one else has competed with this market dominance by Nvidia.

Well, at least you admit it's not Nvidia's fault. Apparently Apple, Intel and AMD don't think there's much money to grab here.

[ Parent | on HN ]
Re:Llama.cpp: Full CUDA GPU Acceleration by rapsey on Tuesday June 13, 2023 @01:11AM (#36305700)
I'm sure Intel and AMD heavily regret their neglect of OpenCL since the rise of LLMs and stable diffusion.
[ Parent | on HN ]