FRESH

Hacker News

Kimi Linear: An Expressive, Efficient Attention Architecture (2025)

247 points by ronfriedhaber

by pooyamo

11 subcomments

Does any expert in the field know whether it is really the case that this intelligence we are seeing with frontier models is an "emerging" phenomena, only coming up when the architecture is scaled?
Like isn't it weird that the 1 million parameter model with the same architecture can't solve basic puzzles but suddenly the 1 trillion parameter can conjure up counter-examples for the Jacobian conjecture?
It's unintuitive since, to the best of my knowledge, one of the basic tenants of algorithm development was that you can't just brute-force your way towards a solution for some complex problems, e.g. naive sorting algorithms suddenly won't beat quicksort if you put more processing to them, but in the modern LLM scene it seems people are in a race to scaling up, experimenting empirically and hoping the same algorithm/architecture comes to a solution.

by senko

0 subcomment

Old but relevant: if you read the recently-released Kimi K3 paper[0], you'll see that it's heavily based on Kimi Linear discussed here, scaling it up and adding a bunch more things (like native vision and RL improvements).
[0] https://arxiv.org/abs/2607.24653

by bratao

1 subcomments

I started creating internal models using it, then the Gated Deltanet 2 came out( https://arxiv.org/abs/2605.22791), and it seems like an evolution of it in expressiveness. And in our tests it is really better than.

by oakpond

2 subcomments

>To support further research, we open-source the KDA kernel and vLLM implementations, and release the pre-trained and instruction-tuned model checkpoints.
This is just awesome.

by delichon

8 subcomments

If you want to believe that the success of Kimi is about distillation attacks, ignore this.

by imrozim

0 subcomment

Any one knows how this holds up on long context retrieval (needle in haystack , ruler) vs same size full attention model? efficiency gains look great but that usually where linear attention hybrids fall apart.

by Topology1

0 subcomment

by jasonjmcghee

3 subcomments