LookaheadKV: Fast and Accurate KV Cache Eviction by Glimpsing into the Future without Generation
Transformer-based large language models (LLMs) rely on key-value (KV) caching to avoid redundant computation during autoregressive inference. While this mechanism greatly improves efficiency, the cache size grows linearly with the input sequence length, quickly becoming a bottleneck for long-context tasks. Existing solutions mitigate this problem by evicting prompt KV that are deemed unimportant, guided by estimated importance scores. Notably, a recent line of work proposes to improve eviction quality by "glimpsing into the future", in which a draft generator produces a surrogate future response approximating the target model's true response, and this surrogate is subsequently used to est...
| Authors | Jinwoo Ahn, Ingyu Seong, Akhil Kedia et al. |
|---|---|
| Primary category | cs.LG |
| Published | 11 March 2026 |
| Last updated at source | 11 March 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.