PagedCache

Headlines · 1

1. 3d
   RossiLH demos a lightweight KIMI K3 serving module

   RossiLH presented a CPU-based interactive demonstration of parts of the KIMI K3 serving module across 14 tabs. It covers KDA speculative replay, replay-consistency checks, ReplaySSM ring buffering, unified paging for MLA and KDA storage, two-stage prefix-cache lookup, engine comparisons, and Fleet scheduling with consistent-hash routing and budget isolation. The author describes the components as reduced-scale versions or approximations and presents the project as part of his learning process.

   掘金 · 人工智能 · 🔥 0

Experience and discussion from the community

Share my PagedCache experienceAsk about PagedCache