Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

My understanding is that the GPU must still load its assigned layer from VRAM into registers and L2 cache for every token, because those aren’t large enough to hold a significant portion. So naively, for a 24GB layer, you‘d need to move up to 24GB for every token.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: