# Xiaomi explains long-context inference serving for MiMo with SGLang

> Original title: 7 | Xiaomi

- Source: LMSYS Org
- Published: 2026-11-04T22:36:25.000Z
- Bad Influence: https://badinfluence.news/items/fbafj7zjy2nc5mpan0l6sepwb
- Original: https://x.com/lmsysorg/status/2118110141765886219

## Summary

Xiaomi engineers Chen Zhang and Yingchun Lai describe how the company handles KV caches, disaggregated serving, and scheduling for long-context MiMo workloads using SGLang. The post shares lessons from Xiaomi's production inference setup without listing benchmark figures.

## Post

7 | Xiaomi
Efficient Long-Context Inference with SGLang: Lessons from Xiaomi MiMo

Chen Zhang & Yingchun Lai share how Xiaomi handles KV caches, disaggregated serving, and scheduling for long-context MiMo workloads.

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWUCs33a0AAXFYq.jpg&mode=thumb&exp=1794096000&sig=ca3dacfdfd9d6951)