AhaKV presents a KV cache eviction strategy that combines recent-window attention accumulation, an entropy-derived softmax temperature, and value-norm priors to reduce positional bias and improve long-context inference accuracy.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models
AhaKV presents a KV cache eviction strategy that combines recent-window attention accumulation, an entropy-derived softmax temperature, and value-norm priors to reduce positional bias and improve long-context inference accuracy.