CacheLink: Functional KV Transport for Zero-Prefill Cross-Model Context Handoff
KV caches make long-context serving efficient by reusing past computation, but model switching breaks this reuse and forces the receiver to prefill the context again. We study \emph{zero-prefill cross-model context handoff}: translating a sender cache into a receiver-compatible state so that the receiver can continue d...
Hao-Miao Qiu, Yi-Ning Tang, Zi-Jia Song et al.
· 0 citations