KV-Cache Oriented Query-Aware Sparse Attention Accelerator With Cross-Stage Precision-Configurable Digital CIM

IF 4.9 2区 工程技术 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC
Yang Zhang;Xilong Kang;Weixuan Wang;Yizhi Ding;Lizheng Ren;Yiran Zhang;Ruiqi Tan;Zhen Wang;Hao Cai;Bo Liu
{"title":"KV-Cache Oriented Query-Aware Sparse Attention Accelerator With Cross-Stage Precision-Configurable Digital CIM","authors":"Yang Zhang;Xilong Kang;Weixuan Wang;Yizhi Ding;Lizheng Ren;Yiran Zhang;Ruiqi Tan;Zhen Wang;Hao Cai;Bo Liu","doi":"10.1109/TCSII.2025.3580135","DOIUrl":null,"url":null,"abstract":"This brief proposes KV-CIM, a KV-Cache oriented Digital Compute-In-Memory (DCIM) sparse attention accelerator, to address computational and memory bottlenecks in autoregressive inference for large language models. Key innovations include: a) A query-aware pre-compute architecture, which dynamically selects and accesses KV-Cache for critical tokens at the pre-compute stage (Stage1) and deploys KV-Cache segmentally on memory-constrained edge devices while maintaining computational accuracy at the formal computation stage (Stage2); b) A cross-stage DCIM macro featuring precision-configurable adder trees, which works in approximate mode at Stage1 and changes to full precision mode at Stage2; c) A query-stationary dataflow that retains the current query tensors in q-CIM across stages to eliminate data movement. Under 28-nm CMOS technology, the proposed KV-CIM achieves 35.16 TOPS/W and 82% reduction of external memory access with negligible degradation in LLaMA2 expressiveness.","PeriodicalId":13101,"journal":{"name":"IEEE Transactions on Circuits and Systems II: Express Briefs","volume":"72 8","pages":"1073-1077"},"PeriodicalIF":4.9000,"publicationDate":"2025-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Circuits and Systems II: Express Briefs","FirstCategoryId":"5","ListUrlMain":"https://ieeexplore.ieee.org/document/11037450/","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0

Abstract

This brief proposes KV-CIM, a KV-Cache oriented Digital Compute-In-Memory (DCIM) sparse attention accelerator, to address computational and memory bottlenecks in autoregressive inference for large language models. Key innovations include: a) A query-aware pre-compute architecture, which dynamically selects and accesses KV-Cache for critical tokens at the pre-compute stage (Stage1) and deploys KV-Cache segmentally on memory-constrained edge devices while maintaining computational accuracy at the formal computation stage (Stage2); b) A cross-stage DCIM macro featuring precision-configurable adder trees, which works in approximate mode at Stage1 and changes to full precision mode at Stage2; c) A query-stationary dataflow that retains the current query tensors in q-CIM across stages to eliminate data movement. Under 28-nm CMOS technology, the proposed KV-CIM achieves 35.16 TOPS/W and 82% reduction of external memory access with negligible degradation in LLaMA2 expressiveness.
面向KV-Cache的查询感知稀疏注意力加速器与跨阶段精度可配置的数字CIM
本文提出了KV-CIM,一种面向KV-Cache的数字内存计算(DCIM)稀疏注意力加速器,用于解决大型语言模型自回归推理中的计算和内存瓶颈。关键创新包括:a)查询感知的预计算架构,它在预计算阶段(Stage1)动态选择和访问关键令牌的KV-Cache,并在内存受限的边缘设备上分段部署KV-Cache,同时在正式计算阶段(Stage2)保持计算精度;b)具有精度可配置加法器树的跨阶段DCIM宏,在Stage1工作在近似模式,在Stage2工作在全精度模式;c)一个查询平稳的数据流,在q-CIM中跨阶段保留当前的查询张量,以消除数据移动。在28纳米CMOS技术下,所提出的KV-CIM实现了35.16 TOPS/W和82%的外部存储器访问减少,LLaMA2表达能力的下降可以忽略。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
IEEE Transactions on Circuits and Systems II: Express Briefs
IEEE Transactions on Circuits and Systems II: Express Briefs 工程技术-工程:电子与电气
CiteScore
7.90
自引率
20.50%
发文量
883
审稿时长
3.0 months
期刊介绍: TCAS II publishes brief papers in the field specified by the theory, analysis, design, and practical implementations of circuits, and the application of circuit techniques to systems and to signal processing. Included is the whole spectrum from basic scientific theory to industrial applications. The field of interest covered includes: Circuits: Analog, Digital and Mixed Signal Circuits and Systems Nonlinear Circuits and Systems, Integrated Sensors, MEMS and Systems on Chip, Nanoscale Circuits and Systems, Optoelectronic Circuits and Systems, Power Electronics and Systems Software for Analog-and-Logic Circuits and Systems Control aspects of Circuits and Systems.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信