Inference Optimization for MiMo v2.5: Pushing Hybrid SWA Efficiency to the Limit
mimo.xiaomi.com
May 30, 2026 中文版 › The V2.5 model family, including MiMo-V2.5 and MiMo-V2.5-Pro, combines several architectural design choices: Hybrid Sliding Window Attention (Hybrid SWA) compresses KVCache storage to roughly 1/7 that of Full Attention; sparse MoE activation cuts per-token compute … Read more