Xiaomi discloses MiMo-V3 plans to adopt HySparse2 architecture, stating that prefill computation for million tokens can be reduced by approximately 80%
Xiaomi's MiMo team publicly stated that the next generation MiMo-V3 will adopt the HySparse2 architecture to reduce long-context Agent prefill computation and KV Cache usage. Tests in the article state that with a million-token input, prefill compute is reduced to approximately the original 1/5。