It's the same *memory footprint* as inference. It's not that fast, and the paper... | Hacker News

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

		sp332 on June 6, 2023 \| parent \| context \| favorite \| on: GGML – AI at the Edge It's the same memory footprint as inference. It's not that fast, and the paper mentions some optimizations that could still be done.

nl on June 6, 2023 [–]

Yes you are right.

I completely misread that!

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