04:00
2026-10-05
arxiv.org
large-language-models
WakeKV: Reactive, Reversible KV Residency for Heads That Change Their Minds
WakeKV, a reactive KV-cache residency policy, improves miss rate over frozen head classification and destructive eviction at matched memory or budget, according to an arXiv paper (2610.02713v1). Acrosβ¦