RESEARCHInvestigateNEXT 12 MONTHS
Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse
arXiv cs.LG — Machine Learning
Factual evidence
What the source reports
Researchers propose a closed-form linear mapping to transfer KV caches between different-sized models in the same family, bypassing prefill.
Open source