FRESH

Hacker News

Flash-MSA: Accelerating Million-Token Training with Sparse Attention Kernels

39 points by rawsh

by kamranjon

1 subcomments

I’ve actually been really interested in Minimax M3 - seems like it flew under the radar but size wise might actually be runnable for local inference with a footprint somewhere between Deepseek V4 flash and pro.
Has anyone used the new Minimax M3 model? I’m curious how it compares with Deepseek V4 and GLM 5.2 and other larger open weights models.

by throwa356262

0 subcomment

Speaking of minimax, has anyone used their video/music models? The demo page looks cool but I never heard of anyone actually using them in anything.

by villgax

1 subcomments

World’s first?
Such lazy, much farming
https://github.com/fla-org/native-sparse-attention?utm_sourc...