Inference Optimization for MiMo v2.5: Pushing Hybrid SWA Efficiency to the Limit

Discussion (6 Comments)Read Original on HackerNews

LaurensBER•about 2 hours ago

It's really cool and interesting to see the kind of engineering that goes into Xiaomi (and Deepseeks) inference optimizations. Z.ai has also published some interesting papers although I haven't had a chance to go through them yet.

It does inspire hope that the Chinese labs seem to be so open although the sceptic in me does wonder what their end game is.

Surely, from a purely economic perspective it would be wiser to keep this proprietary and benefit from the increased API traffic?

ignoramous•about 1 hour ago

> the kind of engineering that goes into Xiaomi (and Deepseeks) inference optimizations

At Xiaomi, MiMo is now led by Luo Fuli. She is a former Alibaba & DeepSeek employee: https://newsen.pku.edu.cn/news_events/news/people/15385.html (https://archive.vn/I8Pmu) / https://e.vnexpress.net/news/tech/personalities/who-is-luo-f... (https://archive.vn/sb3B6)

Don't know if it is due to Luo, but it is striking how similar performance & pricing of the models, DeepSeek v4 Pro & MiMo v2.5 Pro, is.

killingtime74•about 1 hour ago

Will they lower the price or is this documenting past work

limbicsystem•28 minutes ago

Their pricing is incredible on the token plan - something like 50b tokens for $60!

polski-g•16 minutes ago

No that's not right. It's 50b credits, not tokens. What is a credit? Nobody knows.

Someone did the math a few months ago and paying API prices was the same as the monthly subscription.

ricardobeat•about 1 hour ago

Such a well written article, refreshing to read in between all the slop.

I've used Mimo extensively in the past few months, can't wait to see what v3 will bring.

Inference Optimization for MiMo v2.5: Pushing Hybrid SWA Efficiency to the Limit

⚡ Community Insights

Discussion (6 Comments)Read Original on HackerNews