#artificial intelligence
Jun 2026
Fractional Decay KV-Cache: Ownership-Aware Memory Management for Improved Inference Relevancy in Dialog Systems
Fractional Decay KV-Cache is proposed, a novel algorithm that maintains a dual-channel scoring mechanism for each cached KV pair: a cumulative attention channel that tracks aggregate importance (akin to H2O), and a recency-weighted relevance channel governed by temporal decay and reinforcement-inspired updates.
Sukanta Ganguly
· SIGDIAL Conferences · 0 citations