cs.AI updates on arXiv.org 07月14日 12:08
Compactor: Calibrated Query-Agnostic KV Cache Compression with Approximate Leverage Scores
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文介绍了一种名为Compactor的参数自由、无查询依赖的KV压缩策略,通过近似利用分数确定词元重要性,在保留一半词元的同时,实现与竞品相当的性能,并显著降低内存负担。

arXiv:2507.08143v1 Announce Type: cross Abstract: Modern Large Language Models (LLMs) are increasingly trained to support very large context windows. Unfortunately the ability to use long contexts in generation is complicated by the large memory requirement of the KV cache, which scales linearly with the context length. This memory footprint is often the dominant resource bottleneck in real-world deployments, limiting throughput and increasing serving cost. One way to address this is by compressing the KV cache, which can be done either with knowledge of the question being asked (query-aware) or without knowledge of the query (query-agnostic). We present Compactor, a parameter-free, query-agnostic KV compression strategy that uses approximate leverage scores to determine token importance. We show that Compactor can achieve the same performance as competing methods while retaining 1/2 the tokens in both synthetic and real-world context tasks, with minimal computational overhead. We further introduce a procedure for context-calibrated compression, which allows one to infer the maximum compression ratio a given context can support. Using context-calibrated compression, we show that Compactor achieves full KV performance on Longbench while reducing the KV memory burden by 63%, on average. To demonstrate the efficacy and generalizability of our approach, we apply Compactor to 27 synthetic and real-world tasks from RULER and Longbench, with models from both the Qwen 2.5 and Llama 3.1 families.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

LLM 上下文压缩 Compactor
相关文章