Re:MK-1
by Lindon4290 on Sunday August 06, 2023 @11:00AM
(#37022695)
Looks their performance is better than llama.cpp - https://news.ycombinator.com/item?id=37018989 - and scales to batches of prompts.
[ Parent
| on HN ]
Re:MK-1
by polishgladiator on Sunday August 06, 2023 @01:33PM
(#37024483)
Actually no -- that post shows they are not performing measurements and comparisons correctly.
These are not serious people.