Re:Show HN: I made a GPU VRAM calculator for transformer-bas...
by ttt3ts on Tuesday December 26, 2023 @08:33PM
(#38778097)
You have to pass the context between GPUs for large models that don't fit in VRAM. Often ends up slower. Also, tooling around AMD GPUs is still poor in comparison.
[ Parent
| on HN ]
There are no comments on this comment yet.