OVAL:面向输出感知的局部页面基用于KV缓存压缩
OVAL: Output-Aware Local Page Bases for KV Cache Compression
Ashkan Shahbazi, Chayne Thrash, Soheil Kolouri
AI 速读 基于摘要
OVAL 将每个KV页面存储为一对输出感知的低秩基(键基与PCA值基),同时充当检索索引与存储,从而在丢弃精确页面的同时不增加额外缓存开销。
cs.LG
查看原文摘要
Long-context decoding, whether over long reasoning traces, long videos, or robot episodes, is increasingly limited by the memory of the key-value (KV) cache. Page-retrieval sparse attention makes each decoding step cheaper by attending only to the top-scoring KV pages. However, it still stores every page exactly, and adds a small digest per page for scoring, so the cache ends up slightly \emph{larger} than the full cache. We propose OVAL, which stores each page as a pair of output-aware low-rank bases that act as both the retrieval index and the storage. A key basis scores the page and rebuilds its keys when the page is selected, and a PCA basis rebuilds its values. The exact pages can then be dropped, and nothing extra is added to the cache. The key idea is that the key basis should be output-aware. A low-rank error in the keys perturbs the attention output at first order, but perturbs the page mass that retrieval ranks only at second order in expectation. OVAL therefore builds the key basis from a mix of key geometry (key PCA) and the attention-output error, with a per-head mixing weight set in closed form. At the same attended budget, OVAL is best or tied-best in eight of nine long-reasoning settings. It matches FullKV on MATH500 with 66\% of its memory, is 1.25 points above the best baseline on AIME24 with 56\%, and is on par with FullKV on LongBench~v2. On \mbox{Video-MME} and LVBench, it is within 0.32 points of exact-page retrieval at the same read, while storing 53\% of the full cache instead of 103\%. Its savings also stack with quantization and token pruning: with 4-bit bases, it is within 0.25 points of FullKV at 41\% of its memory.