ECOKV: Geometry-Aware KV Cache Eviction via Complementary Diversity Metrics
Although multimodal Large Language Models (MLLMs) excel in diverse tasks, their scalability remains limited by the memory and computational overhead of KV cache storage. Recent KV cache eviction approaches incorporate a cosine similarity-based diversity metric with importance metrics to selectively retain critical key-...
Chin-Ting Hsu, Yu-Syuan Xu, Ling Zou et al.
· 0 citations