News for hackers. Stuff that matters.
Re:How to make LLMs go fast by nickpsecurity on Friday December 22, 2023 @06:01PM (#38739628)
I didn’t know those alternatives had those weaknesses. I did have a whole list of alternatives to check out. Having already looked at some, do you know any transformer alternatives that don’t forget things but were still sub-quadratic? What rabbit holes are worth digging deeper into?
Re:How to make LLMs go fast by deepnotderp on Friday December 22, 2023 @06:29PM (#38739920)
Doesn't sub-quadratic attention fundamentally imply forgetting things?