# Xiaomi shares lessons on long-context MiMo inference with SGLang

> Original title: 7 | @XiaomiMiMo

- Source: LMSYS Org
- Published: 2026-11-04T22:51:51.000Z
- Bad Influence: https://badinfluence.news/items/tsv4u7zti0tlsva50vl5wj0am
- Original: https://x.com/lmsysorg/status/2118114029365538930

## 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 presents these approaches as lessons from Xiaomi's MiMo deployments.

## Post

7 | @XiaomiMiMo 
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%2FHWUMZSwawAAWP7o.jpg&mode=thumb&exp=1794096000&sig=42fd009b41085f6e)