Xiaomi MiMo company blog
Inference Optimization for MiMo v2.5: Pushing Hybrid SWA Efficiency to the Limit
An end-to-end engineering practice for the MiMo-V2.5 series inference system, covering KVCache management, tiered caching, SWA-aware prefix cache trees, scheduling, Prefill/Decode pipelines, and multimodal optimizations.
- Points
- 116
- HN comments
- 49
- Submissions
- 1
- Cited by
- 0 commenters
AI & Machine LearningSystems & Performance2026
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Jul 7, 2026 | Inference Optimization for MiMo v2.5: Pushing Hybrid SWA Efficiency to the Limit by theanonymousone | 116 | 49 |
