News for hackers. Stuff that matters.

A comment on Flash-MSA: Accelerating Million-Token Training with Sparse Attention Kernels.

Re:Flash-MSA: Accelerating Million-Token Training with Spars... by villgax on Sunday July 12, 2026 @10:55PM (#48887302)
World’s first?

Such lazy, much farming

https://github.com/fla-org/native-sparse-attention?utm_sourc...

[ Parent | on HN ]
Re:Flash-MSA: Accelerating Million-Token Training with Spars... by kamranjon on Monday July 13, 2026 @01:09AM (#48888162)
The Minimax paper was published in June 2026 coinciding with the Minimax M3 release - I’m not sure how the repo you posted here could have been an implementation of Minimax sparse attention when it was updated over a year ago?
[ Parent | on HN ]