arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2607.08057cs.LGcs.AIcs.CL
收藏

迈向高效大语言模型服务:关于系统感知键值缓存优化的综述

Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization

School of Computing and Information Systems, The University of Melbourne(墨尔本大学计算与信息系统学院);School of Computer Science and Technology, Huazhong University of Science and Technology(华中科技大学计算机科学与技术学院)

Jiantong Jiang, Peiyu Yang, Rui Zhang, Feng Liu

AI总结:

该综述聚焦大语言模型服务中系统感知的键值缓存优化,从执行与调度、放置与迁移、表示与保留三个维度回顾相关工作,分析跨行为协同设计及行为与目标联系,为理解和创新键值缓存设计提供基础。

摘要:

尽管大语言模型(LLMs)发展迅速,但LLM服务系统仍内存密集且成本高昂。键值(KV)缓存在自回归解码期间存储KV张量,对实现低延迟、高吞吐量的LLM推理服务至关重要。在本综述中,我们关注用于服务LLMs的系统感知KV基础设施(简称为sKis)。我们从系统行为角度回顾近期工作,将现有成果分为执行与调度(时间)、放置与迁移(空间)、表示与保留(结构)三个维度。此外,我们分析跨行为协同设计的关联性和行为与目标的联系,突出未来机遇。我们的工作使这个快速发展的领域系统化,为理解和创新现代LLM服务基础设施中的KV缓存设计奠定基础。

英文摘要:

Despite the rapid advancements of large language models (LLMs), LLM serving systems remain memory-intensive and costly. The key-value (KV) cache, which stores KV tensors during autoregressive decoding, is crucial for enabling low-latency, high-throughput LLM inference serving. In this survey, we focus on system-aware KV infrastructure for serving LLMs (abbreviated as sKis). We revisit recent work from a system behavior perspective, organizing existing efforts into three dimensions: execution and scheduling (temporal), placement and migration (spatial), and representation and retention (structural). Furthermore, we analyze cross-behavior co-design affinity and behavior-objective links, highlighting future opportunities. Our work systematizes a rapidly evolving area, providing a foundation for understanding and innovating KV cache designs in modern LLM serving infrastructure.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑