News for hackers. Stuff that matters.

A comment on SEQUOIA: Exact Llama2-70B on an RTX4090 with half-second per-token latency. Parent comment

Re:SEQUOIA: Exact Llama2-70B on an RTX4090 with half-second ... by kaliqt on Sunday May 05, 2024 @12:50AM (#40262332)
They don't actually care about safety, that's a lie, so compute and business strategy is the only thing stopping them.

SoRA is the same. It's not ready and it's too slow.

[ Parent | on HN ]

There are no comments on this comment yet.