Re:GPT-4
by bitL on Tuesday March 14, 2023 @10:35PM
(#35163023)
It's not, it uses locality-sensitive hashing to reduce attention complexity from O(n^2) to O(nlogn) while maintaining the same performance in 16GB as a best model that could fit into 100GB but nobody scaled it up to 1000 GPUs as its purpose was the opposite.
[ Parent
| on HN ]
There are no comments on this comment yet.