What’s new with MiMo-V2.5 series inference?
We just published a blog on our full pipeline inference optimizations for MiMo-V2.5 series, including how we pushed hybrid SWA efficiency to the limit.
Read the full blog here:
https://t.co/lYBEcgaVhU
attention — The mechanism that lets a model weigh which earlier words matter for the word it's currently processing — the core operation of a transformer.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
multimodal — A model that works with more than text — reading images, audio, or video, and sometimes generating them too.
open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
Why it matters
Hybrid sliding-window attentionThe mechanism that lets a model weigh which earlier words matter for the word it's currently processing — the core operation of a transformer.Full definition → is what makes long-context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → and multimodalA model that works with more than text — reading images, audio, or video, and sometimes generating them too.Full definition → serving affordable. The writeup traces where the wins come from at each pipeline stage, useful if you serve open weightsA model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.Full definition → models yourself.
postHeads up, agent users！ If you're using Xiaomi MiMo with thinking mode: When…
postMiMo-V2.5 and V2.5-Pro go open weights under MIT with day-zero SGLang and vLLM
postIntroducing MiMo-V2.5 Voice — our full-stack voice lineup for the Agent era. 🚀…
postFour hours, 672 tool calls: MiMo-V2.5-Pro's long-horizon run logs
