News for hackers. Stuff that matters.
Re:Bringing K/V context quantisation to Ollama by throwaway314155 on Thursday December 05, 2024 @11:04PM (#42336225)
I'm pretty satisfied with my linux nvidia gpu setup. I may not have as much memory on my card, but the speed is almost certainly competitive if not outright faster. Further there are lots of techniques that mitigate this issue like offloading/streaming layers in as needed, quantizing, etc.

It also handles actual training/finetuning better.

There are no comments on this comment yet.