Xiaomi Previews HySparse2 for MiMo-V3: KV Cache Cut to ~1/4.5 at 1M Context
智东西 · wechat · 2026-09-24
Xiaomi MiMo lead Luo Fuli pre-announced HySparse2, a core architectural component of the upcoming MiMo-V3, with a paper published just two days after the MiMo-V2.6 release.
HySparse2 targets three pain points of long-horizon agent inference: heavy Prefill compute, large KV cache, and long-context retrieval. Its two-level KV sharing (KV Bridging + KV Reuse) lets Prefill exit after running only the first half of the model — a 49-layer model needs just 25 layers on prefill nodes, nearly halving weights — while switching from block-level to token-level sparse selection for precise cross-context retrieval.
At 1M-token context, versus HybridSWA, Prefill compute drops to 1/5 and KV cache to 1/4.5 (2.69GB vs 12.09GB); RULER-v2 improves by 18.65 points after post-training, with lower AgentPPL and LongPPL. General capabilities remain roughly on par.
More from Infra
- Omarchy 4.6 lets you share local AI models across your tailnet, says DHH — alexcovo_eth · 2026-11-12
- Eric Schmidt's foundation funds French NGO fighting against data centers — StephanSturges · 2026-11-12
- Epoch: Open-Weight GLM 5.3 Hacks Six Firefox Versions for ~$1,000 Each; Claude Fable 5.2 Sets ECI Record — Epoch AI · 2026-11-12
- Polymarket prices 28% odds of a state data center moratorium; Torus raises $500M — Polymarket · 2026-11-12
- AWS-wrapper cloud startup shuts down just one month after seed round — thedealdirector · 2026-11-12
- Utah startup Torus raises $500M for shipping container-sized AI data centers deployable in 4 months — Polymarket · 2026-11-12