News for hackers. Stuff that matters.
Re:Mamba-3 by esquire_900 on Saturday March 21, 2026 @02:24AM (#47464477)
This is sort of what their first sentence states? Except your line implies that they are fast in training and inference, they imply they are focusing on inference and are dropping training speed for it.

It's a nice opening as it is imo

Re:Mamba-3 by cubefox on Saturday March 21, 2026 @04:38AM (#47465210)
They don't say anything about dropping training speed.
Re:Mamba-3 by estearum on Saturday March 21, 2026 @07:12AM (#47465987)
> a departure from Mamba-2, which optimized for training speed.

?

Re:Mamba-3 by cubefox on Saturday March 21, 2026 @09:43AM (#47466964)
Yes? Mamba-2 optimized for training speed compared to Mamba-1. Mamba-3 adds optimization for inference. These are pretty much version numbers.