Article(id=1329419485678776776, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1329419378451394604, articleNumber=null, orderNo=null, doi=10.7544/issn1000-1239.202550461, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1749398400000, receivedDateStr=2025-06-09, revisedDate=1762963200000, revisedDateStr=2025-11-13, acceptedDate=1764259200000, acceptedDateStr=2025-11-28, onlineDate=1794887904805, onlineDateStr=2026-11-17, pubDate=1774972800000, pubDateStr=2026-04-01, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1794887904805, onlineIssueDateStr=2026-11-17, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1794887904805, creator=13701087609, updateTime=1794887904805, updator=13701087609, issue=Issue{id=1329419378451394604, tenantId=1146029695717560320, journalId=1324759914146529478, year='2026', volume='63', issue='4', pageStart='825', pageEnd='1093', issueExtLink='null', onlineDate='null', pubDate='1774972800000', pubDateStr='2026-04-01', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1794887879240, creator='13701087609', updateTime=1794887879240, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext=null, issueFiles=null, downloadFileDto=null}, startPage=1021, endPage=1038, ext={EN=ArticleExt(id=1329419485896880586, articleId=1329419485678776776, tenantId=1146029695717560320, journalId=1324759914146529478, language=EN, title=Survey on KV Cache Compression Methods for Large Language Model Inference, columnId=1325489901852041729, journalTitle=Journal of Computer Research and Development, columnName=Computer Architecture, runingTitle=null, highlight=null, articleAbstract=
Large language model (LLM) inference requires buffering and reusing intermediate data, namely KV cache. However, the rapid growth in the size of KV cache imposes significant storage pressure on systems. On one hand, the large-scale KV cache of ongoing inference requests leads to GPU memory bottlenecks, thereby limiting inference parallelism. On the other hand, the long-term memory capability enabled by LLM service providers results in large-scale KV cache being stored on persistent storage devices, incurring high storage costs and loading overhead. To alleviate the storage pressure caused by KV cache, existing research proposes various KV cache compression strategies to reduce its size. Nonetheless, it remains challenging to achieve high compression ratios while minimizing the impact on model response quality and keeping the additional computational overhead at an acceptable level. We present a systematic survey of recent advances in KV cache compression strategies. First, we analyze the scale of KV cache and its impact on inference efficiency and storage cost. Based on this, we identify three major challenges in designing KV cache compression strategies: preserving model response quality, minimizing computational overhead, and ensuring generalizability. We then categorize existing KV cache compression approaches into five types: merge-based, quantization-based, token eviction-based, sharing-based, and attention head pruning-based strategies. Each category is elaborated upon with representative examples, discussing their design principles and implementation techniques. Finally, we outline potential future research directions in KV cache compression.
, authors=Shipeng Hu, Guangyan Zhang*, Weimin Zheng, authorsList=Shipeng Hu, Guangyan Zhang, Weimin Zheng, authorCompany=null, correspAuthors=Guangyan Zhang, authorNote=
born in 1999. PhD candidate. His main research interests include storage systems and large language models
born in 1976. PhD, associate professor, PhD supervisor. Distinguished member of CCF. His main research interests include big data computing, storage systems, and distributed processing
born in 1946. Master, professor, PhD supervisor, academician of Chinese Academy of Engineering. Fellow of CCF. His main research interests include high performance computing, network storage, and parallel compiler
, correspAuthorsNote=null, copyrightStatement=Copyright © 2026 Journal of Computer Research and Development. All rights reserved., copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=null), CN=ArticleExt(id=1329419488426045930, articleId=1329419485678776776, tenantId=1146029695717560320, journalId=1324759914146529478, language=CN, title=大语言模型推理中的键值缓存压缩方法综述, columnId=1325489904427344387, journalTitle=计算机研究与发展, columnName=体系结构, runingTitle=null, highlight=null, articleAbstract=
大语言模型的部署推理需要针对中间数据,即键值缓存,进行存储复用。然而键值缓存的空间规模迅速增长,为系统带来显著的存储压力:一方面,当前推理请求的大规模键值缓存导致显存瓶颈问题,从而限制推理并行度。另一方面,长期记忆需求导致海量键值缓存长期存储在持久存储设备内,带来高昂的存储成本和加载开销。为了缓解键值缓存带来的存储压力,现有研究针对键值缓存进行压缩,从而削减其空间规模,然而如何在提升压缩率的同时减小对模型回答质量的影响并将压缩带来的计算开销控制在较低程度仍面临着诸多挑战。系统地综述了键值缓存压缩策略的研究进展,首先介绍键值缓存的规模及其对推理效率、存储成本的影响,并总结键值缓存压缩策略面临的三大挑战:模型回答质量、计算开销以及泛化性。然后对现有的键值缓存压缩策略进行分类:基于合并的、基于量化的、基于标记驱逐的、基于共享的以及基于注意力头削减的压缩策略。对每种压缩策略进行阐述,并分析其设计原理和软件技术。最后指出了键值缓存压缩策略的未来研究方向。
, authors=胡世鹏, 张广艳*, 郑纬民, authorsList=胡世鹏, 张广艳, 郑纬民, authorCompany=null, correspAuthors=张广艳, authorNote=
 |
1999年生。博士研究生。主要研究方向为存储系统、大语言模型 |
 |
1976年生。博士,副教授,博士生导师。CCF杰出会员。主要研究方向为大数据计算、存储系统、分布式处理 |
 |
1946年生。硕士,教授,博士生导师,中国工程院院士。CCF会士。主要研究方向为高性能计算、网络存储、并行编译 |
, correspAuthorsNote=
, copyrightStatement=版权所有 © 2026 计算机研究与发展编辑部, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=wOXVAwjkp328l07e6XNS3g==, magXml=mMZgX9YZs3+WpQTQ/625SQ==, pdfUrl=null, pdf=FlHOpG+M6yG3pEs6JxYTmw==, pdfFileSize=3934883, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=jIjvn/JQSzlXHWISrXS1qQ==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=RAP139VYN077n/HWzq3gvg==, mapNumber=null, fund=null)}, authors=[Author(id=1329419488728035824, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=hsp21@mails.tsinghua.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329419488824504819, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, authorId=1329419488728035824, language=EN, stringName=Shipeng Hu, firstName=Shipeng, middleName=null, lastName=Hu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Department of Computer Science and Technology, Tsinghua University, Beijing 100084, bio={"content":"
born in 1999. PhD candidate. His main research interests include storage systems and large language models
"}, bioImg=null, bioContent=
born in 1999. PhD candidate. His main research interests include storage systems and large language models
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329419488920973812, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, authorId=1329419488728035824, language=CN, stringName=胡世鹏, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=清华大学计算机科学与技术系 北京 100084, bio={"img":"OX1s4hYzg1zqPE7HywAd3w==","content":"
1999年生。博士研究生。主要研究方向为存储系统、大语言模型
"}, bioImg=OX1s4hYzg1zqPE7HywAd3w==, bioContent=
1999年生。博士研究生。主要研究方向为存储系统、大语言模型
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329419488631566828, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, xref=null, ext=[AuthorCompanyExt(id=1329419488639955437, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, companyId=1329419488631566828, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Department of Computer Science and Technology, Tsinghua University, Beijing 100084), AuthorCompanyExt(id=1329419488652538350, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, companyId=1329419488631566828, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=清华大学计算机科学与技术系 北京 100084)])]), Author(id=1329419488988082678, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=gyzh@tsinghua.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1329419489063580152, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, authorId=1329419488988082678, language=EN, stringName=Guangyan Zhang, firstName=Guangyan, middleName=null, lastName=Zhang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=*, address=Department of Computer Science and Technology, Tsinghua University, Beijing 100084, bio={"content":"
born in 1976. PhD, associate professor, PhD supervisor. Distinguished member of CCF. His main research interests include big data computing, storage systems, and distributed processing
"}, bioImg=null, bioContent=
born in 1976. PhD, associate professor, PhD supervisor. Distinguished member of CCF. His main research interests include big data computing, storage systems, and distributed processing
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329419489126494713, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, authorId=1329419488988082678, language=CN, stringName=张广艳, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=*, address=清华大学计算机科学与技术系 北京 100084, bio={"img":"Oc0gJH6hpk/1um0cgT5TnA==","content":"
1976年生。博士,副教授,博士生导师。CCF杰出会员。主要研究方向为大数据计算、存储系统、分布式处理
"}, bioImg=Oc0gJH6hpk/1um0cgT5TnA==, bioContent=
1976年生。博士,副教授,博士生导师。CCF杰出会员。主要研究方向为大数据计算、存储系统、分布式处理
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329419488631566828, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, xref=null, ext=[AuthorCompanyExt(id=1329419488639955437, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, companyId=1329419488631566828, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Department of Computer Science and Technology, Tsinghua University, Beijing 100084), AuthorCompanyExt(id=1329419488652538350, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, companyId=1329419488631566828, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=清华大学计算机科学与技术系 北京 100084)])]), Author(id=1329419489189409276, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329419489260712446, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, authorId=1329419489189409276, language=EN, stringName=Weimin Zheng, firstName=Weimin, middleName=null, lastName=Zheng, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Department of Computer Science and Technology, Tsinghua University, Beijing 100084, bio={"content":"
born in 1946. Master, professor, PhD supervisor, academician of Chinese Academy of Engineering. Fellow of CCF. His main research interests include high performance computing, network storage, and parallel compiler
"}, bioImg=null, bioContent=
born in 1946. Master, professor, PhD supervisor, academician of Chinese Academy of Engineering. Fellow of CCF. His main research interests include high performance computing, network storage, and parallel compiler
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329419489344598527, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, authorId=1329419489189409276, language=CN, stringName=郑纬民, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=清华大学计算机科学与技术系 北京 100084, bio={"img":"YFAz+95qDfCjyz6vDxcZvA==","content":"
1946年生。硕士,教授,博士生导师,中国工程院院士。CCF会士。主要研究方向为高性能计算、网络存储、并行编译
"}, bioImg=YFAz+95qDfCjyz6vDxcZvA==, bioContent=
1946年生。硕士,教授,博士生导师,中国工程院院士。CCF会士。主要研究方向为高性能计算、网络存储、并行编译
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329419488631566828, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, xref=null, ext=[AuthorCompanyExt(id=1329419488639955437, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, companyId=1329419488631566828, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Department of Computer Science and Technology, Tsinghua University, Beijing 100084), AuthorCompanyExt(id=1329419488652538350, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, companyId=1329419488631566828, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=清华大学计算机科学与技术系 北京 100084)])])], keywords=[Keyword(id=1329419489432678912, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, language=EN, orderNo=1, keyword=large language model), Keyword(id=1329419489541730818, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, language=EN, orderNo=2, keyword=inference service), Keyword(id=1329419489621422595, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, language=EN, orderNo=3, keyword=KV cache), Keyword(id=1329419489688531460, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, language=EN, orderNo=4, keyword=storage system), Keyword(id=1329419489759834629, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, language=EN, orderNo=5, keyword=data compression), Keyword(id=1329419489818554887, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, language=CN, orderNo=1, keyword=大语言模型), Keyword(id=1329419489877275144, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, language=CN, orderNo=2, keyword=推理服务), Keyword(id=1329419489935995401, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, language=CN, orderNo=3, keyword=键值缓存), Keyword(id=1329419490019881483, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, language=CN, orderNo=4, keyword=存储系统), Keyword(id=1329419490086990348, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, language=CN, orderNo=5, keyword=数据压缩)], refs=[Reference(id=1329419491940872745, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=1, rfOrder=0, authorNames=null, journalName=null, refType=null, unstructuredReference=Achiam J, Adler S, Agarwal S, et al. GPT-4 technical report[J]. arXiv preprint, arXiv: 2303.08774, 2023, articleTitle=null, refAbstract=null), Reference(id=1329419492012175914, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=1, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Aixin, Feng Bei, Xue Bing, et al. DeepSeek-V3 technical report[J]. arXiv preprint, arXiv: 2412.19437, 2024, articleTitle=null, refAbstract=null), Reference(id=1329419492070896172, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=2, authorNames=null, journalName=null, refType=null, unstructuredReference=Team G, Anil R, Borgeaud S, et al. Gemini: A family of highly capable multimodal models[J]. arXiv preprint, arXiv: 2312.11805, 2023, articleTitle=null, refAbstract=null), Reference(id=1329419492133810733, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=3, authorNames=null, journalName=null, refType=null, unstructuredReference=Touvron H, Lavril T, Izacard G, et al. LLaMA: Open and efficient foundation language models[J]. arXiv preprint, arXiv: 2302.13971, 2023, articleTitle=null, refAbstract=null), Reference(id=1329419492217696814, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=4, authorNames=null, journalName=null, refType=null, unstructuredReference=陈炫婷, 叶俊杰, 祖璨, 等. GPT系列大语言模型在自然语言处理任务中的鲁棒性[J]. 计算机研究与发展, 2024, 61(5): 1128−1142, articleTitle=null, refAbstract=null), Reference(id=1329419492280611375, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Xuanting, Ye Junjie, Zu Can, et al. Robustness of GPT large language models on natural language processing tasks[J]. Journal of Computer Research and Development, 2024, 61(5): 1128−1142 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1329419492351914544, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=林萌, 戴程威, 郭涛. 基于多模态大语言模型的攻击性模因解释生成方法[J]. 计算机研究与发展, 2024, 61(5): 1206−1217, articleTitle=null, refAbstract=null), Reference(id=1329419492419023410, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=Lin Meng, Dai Chengwei, Guo Tao. A method for generating explanations of offensive memes based on multimodal large language models[J]. Journal of Computer Research and Development, 2024, 61(5): 1206−1217 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1329419492477743667, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Yuhong, Huang Yingbing, Yang Bowen, et al. SnapKV: LLM knows what you are looking for before generation[C]//Proc of the 38th Conf on Advances in Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc, 2024: 22947−22970, articleTitle=null, refAbstract=null), Reference(id=1329419492544852532, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Minghan, Chen Xilun, Holtzman A, et al. Nearest neighbor speculative decoding for LLM generation and attribution[C]//Proc of the 38th Conf on Advances in Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc, 2024: 80987−81015, articleTitle=null, refAbstract=null), Reference(id=1329419492616155701, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=陈慧敏, 刘知远, 孙茂松. 大语言模型时代的社会机遇与挑战[J]. 计算机研究与发展, 2024, 61(5): 1094−1103, articleTitle=null, refAbstract=null), Reference(id=1329419492670681654, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Huimin, Liu Zhiyuan, Sun Maosong. The social opportunities and challenges in the era of large language models[J]. Journal of Computer Research and Development, 2024, 61(5): 1094−1103 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1329419492733596215, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Jinghan, Wang Xiting, Ren Weijieying, et al. RATT: A thought structure for coherent and correct LLM reasoning[C]//Proc of the 39th AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2025: 26733−26741, articleTitle=null, refAbstract=null), Reference(id=1329419492796510776, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=Xiao Ziyang, Zhang Dongxiang, Han Xiongwei, et al. Enhancing LLM reasoning via vision-augmented prompting[C]//Proc of the 38th Conf on Advances in Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc, 2024: 28772−28797, articleTitle=null, refAbstract=null), Reference(id=1329419492855231033, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Zhenyu, Fan Sunqi, Gu Yu, et al. FlexKBQA: A flexible LLM-powered framework for few-shot knowledge base question answering[C]//Proc of the 39th AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2024: 18608−18616, articleTitle=null, refAbstract=null), Reference(id=1329419492934922811, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=Keat K, Venkatesh R, Huang Yidi, et al. PGxQA: A resource for evaluating LLM performance for pharmacogenomic QA tasks[C]//Proc of the 30th Pacific Symp on Biocomputing. Singapore: World Scientific, 2024: 229−246, articleTitle=null, refAbstract=null), Reference(id=1329419493014614588, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=Gu Qiuhan. LLM-based code generation method for golang compiler testing[C]//Proc of the 31st ACM Joint European Software Engineering Conf and Symp on the Foundations of Software Engineering. New York: ACM, 2023: 2201−2203, articleTitle=null, refAbstract=null), Reference(id=1329419493085917757, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Jianxun, Chen Yixiang. A review on code generation with LLMs: Application and evaluation[C]//Proc of the 1st IEEE Int Conf on Medical Artificial Intelligence. Piscataway, NJ: IEEE, 2023: 284−289, articleTitle=null, refAbstract=null), Reference(id=1329419493161415230, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=Fakhoury S, Naik A, Sakkas G, et al. Exploring the effectiveness of LLM based test-driven interactive code generation: User study and empirical evaluation[C]//Proc of the 46th Int Conf on Software Engineering. New York: ACM, 2024: 390−391, articleTitle=null, refAbstract=null), Reference(id=1329419493220135487, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=Mu Fangwen, Shi Lin, Wang Song, et al. ClarifyGPT: A framework for enhancing LLM-based code generation via requirements clarification[J]. Proceedings of the ACM on Software Engineering, 2024, 1: 2332−2354, articleTitle=null, refAbstract=null), Reference(id=1329419493287244352, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=Stamper J, Xiao Ruiwei, Hou Xinying. Enhancing LLM-based feedback: Insights from intelligent tutoring systems and the learning sciences[C]//Proc of the 25th Int Conf on Artificial Intelligence in Education. Berlin: Springer, 2024: 32−43, articleTitle=null, refAbstract=null), Reference(id=1329419493362741826, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=Molina I V, Montalvo A, Ochoa B, et al. Leveraging LLM tutoring systems for non-native English speakers in introductory CS courses[J]. arXiv preprint, arXiv: 2411.02725, 2024, articleTitle=null, refAbstract=null), Reference(id=1329419493421462083, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]//Proc of the 31st Conf on Advances in Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc, 2017: 5998−6008, articleTitle=null, refAbstract=null), Reference(id=1329419493480182340, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=Gao Bin, He Zhuomin, Sharma P, et al. Cost-Efficient large language model serving for multi-turn conversations with CachedAttention[C]//Proc of the 30th USENIX Annual Technical Conf. Berkeley, CA: USENIX Association, 2024: 111−126, articleTitle=null, refAbstract=null), Reference(id=1329419493559874117, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=Kwon W, Li Zhuohan, Zhuang Siyuan, et al. Efficient memory management for large language model serving with PagedAttention[C]//Proc of the 29th Symp on Operating Systems Principles. New York: ACM, 2023: 611−626, articleTitle=null, refAbstract=null), Reference(id=1329419493618594374, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=Gao Shiwei, Chen Youmin, Shu Jiwu. Fast state restoration in LLM serving with HCache[C]//Proc of the 20th European Conf on Computer Systems. New York: ACM, 2025: 128−143, articleTitle=null, refAbstract=null), Reference(id=1329419493677314632, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=Hatalis K, Christou D, Myers J, et al. Memory matters: The need to improve long-term memory in LLM-agents[C]//Proc of AAAI Fall Symp Series. Palo Alto, CA: AAAI, 2023: 277−280, articleTitle=null, refAbstract=null), Reference(id=1329419493723451977, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Weizhi, Dong Li, Cheng Hao, et al. Augmenting language models with long-term memory[C]//Proc of the 37th Conf on Advances in Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc, 2023: 74530−74543, articleTitle=null, refAbstract=null), Reference(id=1329419493798949450, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=An Wei, Bi Xiao, Chen Guanting, et al. Fire-Flyer AI-HPC: A cost-effective software-hardware co-design for deep learning[C]//Proc of the 24th Int Conf for High Performance Computing, Networking, Storage and Analysis. Piscataway, NJ: IEEE, 2024: 1−23, articleTitle=null, refAbstract=null), Reference(id=1329419493878641227, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=Qin Ruoyu, Li Zheming, He Weiran, et al. Mooncake: Trading more storage for less computation—A KV cache-centric architecture for serving LLM Chatbot[C]//Proc of the 23rd USENIX Conf on File and Storage Technologies. Berkeley CA: USENIX Association, 2025: 155−170, articleTitle=null, refAbstract=null), Reference(id=1329419493945750092, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Zheng, Jin Boxiao, Yu Zhongzhi, et al. Model tells you where to merge: Adaptive KV cache merging for LLMs on long-context tasks[J]. arXiv preprint, arXiv: 2407.08454, 2024, articleTitle=null, refAbstract=null), Reference(id=1329419494050607693, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=Akide L, Liu Jing, Pan Zizheng, et al. MiniCache: KV cache compression in depth dimension for large language models[C]//Proc of the 38th Conf on Advances in Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc, 2024: 139997−140031, articleTitle=null, refAbstract=null), Reference(id=1329419494121910862, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=Hooper C, Kim S, Mohammadzadeh H, et al. KVQuant: Towards 10 million context length LLM inference with KV cache quantization[C]//Proc of the 38th Conf on Advances in Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc, 2024: 1270−1303, articleTitle=null, refAbstract=null), Reference(id=1329419494176436815, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Yuhan, Li Hanchen, Cheng Yihua, et al. CacheGen: KV cache compression and streaming for fast large language model serving[C]//Proc of the 38th Conf of the ACM Special Interest Group on Data Communication. New York: ACM, 2024: 38−56, articleTitle=null, refAbstract=null), Reference(id=1329419494230962768, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=32, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=Cheng Feng, Guo Cong, Wei Chiyue, et al. Ecco: Improving memory bandwidth and capacity for LLMs via entropy-aware cache compression[C]//Proc of the 52nd Annual Int Symp on Computer Architecture. New York: ACM, 2025: 793−807, articleTitle=null, refAbstract=null), Reference(id=1329419494461649489, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=33, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Zichang, Desai A, Liao Fangshuo, et al. Scissorhands: Exploiting the persistence of importance hypothesis for LLM KV cache compression at test time[C]//Proc of the 37th Conf on Advances in Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc, 2023: 52342−52364, articleTitle=null, refAbstract=null), Reference(id=1329419494520369747, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=34, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Weijian, He Shuibing, Qu Haoyang, et al. IMPRESS: An importance-informed multi-tier prefix KV storage system for large language model inference[C]//Proc of the 23rd USENIX Conf on File and Storage Technologies. Berkeley, CA: USENIX Association, 2025: 187−201, articleTitle=null, refAbstract=null), Reference(id=1329419494583284308, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=35, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Guangda, Li Chengwei, Zhao Jieru, et al. ClusterKV: Manipulating LLM KV cache in semantic space for recallable compression[C]//Proc of the 62nd ACM/IEEE Design Automation Conf. Piscataway, NJ: IEEE, 2025: 1−7, articleTitle=null, refAbstract=null), Reference(id=1329419494633615957, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=36, rfOrder=38, authorNames=null, journalName=null, refType=null, unstructuredReference=Yang Yifei, Cao Zouying, Chen Qiguang, et al. KVSharer: Efficient inference via layer-wise dissimilar KV cache sharing[J]. arXiv preprint, arXiv: 2410.18517, 2024, articleTitle=null, refAbstract=null), Reference(id=1329419494688141910, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=37, rfOrder=39, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Haoyi, Tu Kewei. Layer-condensed KV cache for efficient inference of large language models[C]//Proc of the 62nd Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA: ACL, 2024: 11175−11188, articleTitle=null, refAbstract=null), Reference(id=1329419494742667863, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=38, rfOrder=40, authorNames=null, journalName=null, refType=null, unstructuredReference=Shazeer N. Fast transformer decoding: One write-head is all you need[J]. arXiv preprint, arXiv: 1911.02150, 2019, articleTitle=null, refAbstract=null), Reference(id=1329419494809776728, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=39, rfOrder=41, authorNames=null, journalName=null, refType=null, unstructuredReference=Ainslie J, Lee-Thorp J, De Jong M, et al. GQA: Training generalized multi-query transformer models from multi-head checkpoints[J]. arXiv preprint, arXiv: 2305.13245, 2023, articleTitle=null, refAbstract=null), Reference(id=1329419494872691289, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=40, rfOrder=42, authorNames=null, journalName=null, refType=null, unstructuredReference=Ding Yiran, Zhang Li, Zhang Chengruidong, et al. LongRoPE: Extending LLM context window beyond 2 million tokens[J]. arXiv preprint, arXiv: 2402.13753, 2024, articleTitle=null, refAbstract=null), Reference(id=1329419494931411546, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=41, rfOrder=43, authorNames=null, journalName=null, refType=null, unstructuredReference=Ma Xuezhe, Yang Xiaomeng, Xiong Wenhan, et al. Megalodon: Efficient LLM pretraining and inference with unlimited context length[C]//Proc of the 38th Conf on Advances in Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc, 2024: 71831−71854, articleTitle=null, refAbstract=null), Reference(id=1329419494985937499, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=42, rfOrder=44, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhong Yinmin, Liu Shengyu, Chen Junda, et al. DistServe: Disaggregating prefill and decoding for goodput-optimized large language model serving[C]//Proc of the 18th USENIX Symp on Operating Systems Design and Implementation. Berkeley, CA: USENIX Association, 2024: 193−210, articleTitle=null, refAbstract=null), Reference(id=1329419495057240668, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=43, rfOrder=45, authorNames=null, journalName=null, refType=null, unstructuredReference=Jeong C. Generative AI service implementation using LLM application architecture based on RAG model and LangChain framework[J]. Journal of Intelligence and Information Systems, 2023, 29(4): 129−164, articleTitle=null, refAbstract=null), Reference(id=1329419495120155229, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=44, rfOrder=46, authorNames=null, journalName=null, refType=null, unstructuredReference=Qiu Jianing, Lam K, Li Guohao, et al. LLM-based agentic systems in medicine and healthcare[J]. Nature Machine Intelligence, 2024, 6(12): 1418−1420, articleTitle=null, refAbstract=null), Reference(id=1329419495174681182, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=45, rfOrder=47, authorNames=null, journalName=null, refType=null, unstructuredReference=Yu Yangyang, Yao Zhiyuan, Li Haohang, et al. Fincon: A synthesized LLM multi-agent system with conceptual verbal reinforcement for enhanced financial decision making[C]//Proc of the 38th Conf on Advances in Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc, 2024: 137010−137045, articleTitle=null, refAbstract=null), Reference(id=1329419495237595744, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=46, rfOrder=48, authorNames=null, journalName=null, refType=null, unstructuredReference=Singh K, Kaur S, Smiley C. FinQAPT: Empowering financial decisions with end-to-end LLM-driven question answering pipeline[C]//Proc of the 5th ACM Int Conf on AI in Finance. New York: ACM, 2024: 266−273, articleTitle=null, refAbstract=null), Reference(id=1329419495313093217, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=47, rfOrder=49, authorNames=null, journalName=null, refType=null, unstructuredReference=Gao Wei, Zhou Xinyu, Sun Peng, et al. Rethinking key-value cache compression techniques for large language model serving[J]. arXiv preprint, arXiv: 2503.24000, 2025, articleTitle=null, refAbstract=null), Reference(id=1329419495371813474, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=48, rfOrder=50, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Xiang, Tang Zhenheng, Chen Hong, et al. Can LLMs maintain fundamental abilities under KV cache compression?[J]. arXiv preprint, arXiv: 2502.01941, 2025, articleTitle=null, refAbstract=null), Reference(id=1329419495455699555, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=49, rfOrder=51, authorNames=null, journalName=null, refType=null, unstructuredReference=Cobbe K, Kosaraju V, Bavarian M, et al. Training verifiers to solve math word problems[J]. arXiv preprint, arXiv: 2110.14168, 2021, articleTitle=null, refAbstract=null), Reference(id=1329419495522808421, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=50, rfOrder=52, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Haotian, Li Chunyuan, Wu Qingyang, et al. Visual instruction tuning[C]//Proc of the 37th Conf on Advances in Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc, 2023: 34892−34916, articleTitle=null, refAbstract=null), Reference(id=1329419495585722982, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=51, rfOrder=53, authorNames=null, journalName=null, refType=null, unstructuredReference=Reddy S, Chen D, Manning C D. CoQA: A conversational question answering challenge[J]. Transactions of the Association for Computational Linguistics, 2019, 7: 249−266, articleTitle=null, refAbstract=null), Reference(id=1329419495640248935, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=52, rfOrder=54, authorNames=null, journalName=null, refType=null, unstructuredReference=Salimans T, Kingma D P. Weight normalization: A simple reparameterization to accelerate training of deep neural networks[C]//Proc of the 30th Conf on Advances in Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc, 2016: 901−909, articleTitle=null, refAbstract=null), Reference(id=1329419495703163497, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=53, rfOrder=55, authorNames=null, journalName=null, refType=null, unstructuredReference=Su Jianlin, Lu Yu, Pan Shengfeng et al. RoFormer: Enhanced transformer with rotary position embedding[J]. Neurocomputing, 2024, 568: 127063, articleTitle=null, refAbstract=null), Reference(id=1329419495766078058, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=54, rfOrder=56, authorNames=null, journalName=null, refType=null, unstructuredReference=Xiao Guangxuan, Tian Yuandong, Chen Beidi, et al. Efficient streaming language models with attention sinks[J]. arXiv preprint, arXiv: 2309.17453, 2023, articleTitle=null, refAbstract=null), Reference(id=1329419495828992619, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=55, rfOrder=57, authorNames=null, journalName=null, refType=null, unstructuredReference=Rissanen J, Langdon G G. Arithmetic coding[J]. IBM Journal of Research and Development, 1979, 23(2): 149−162, articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1329419488631566828, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, xref=null, ext=[AuthorCompanyExt(id=1329419488639955437, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, companyId=1329419488631566828, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Department of Computer Science and Technology, Tsinghua University, Beijing 100084), AuthorCompanyExt(id=1329419488652538350, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, companyId=1329419488631566828, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=清华大学计算机科学与技术系 北京 100084)])], figs=[ArticleFig(id=1329419490191847950, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, language=EN, label=Figure 1, caption=
The attention computing mechanism in LLM inference, figureFileSmall=cZ/PviZPEavxD1hvD8FuAA==, figureFileBig=jIjvn/JQSzlXHWISrXS1qQ==, tableContent=null), ArticleFig(id=1329419490271539728, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, language=CN, label=图1, caption=
大语言模型推理中的注意力计算机制, figureFileSmall=cZ/PviZPEavxD1hvD8FuAA==, figureFileBig=jIjvn/JQSzlXHWISrXS1qQ==, tableContent=null), ArticleFig(id=1329419490468672018, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, language=EN, label=Figure 2, caption=
The KV cache loading process when inference request arrives, figureFileSmall=2VynhgTWyTTVi8EMirl+Tg==, figureFileBig=x67hVR6hmFtkvyWbqJhvuA==, tableContent=null), ArticleFig(id=1329419490535780883, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, language=CN, label=图2, caption=
推理请求到来时的键值缓存加载过程, figureFileSmall=2VynhgTWyTTVi8EMirl+Tg==, figureFileBig=x67hVR6hmFtkvyWbqJhvuA==, tableContent=null), ArticleFig(id=1329419490594501140, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, language=EN, label=Figure 3, caption=
Merging objects selection method in KVMerger, figureFileSmall=CADF3jDgbp/0psZLQ/ESbw==, figureFileBig=sAxrb/ZEbVsCe7DVKmYCRQ==, tableContent=null), ArticleFig(id=1329419490669998614, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, language=CN, label=图3, caption=
KVMerger的合并对象选取方法, figureFileSmall=CADF3jDgbp/0psZLQ/ESbw==, figureFileBig=sAxrb/ZEbVsCe7DVKmYCRQ==, tableContent=null), ArticleFig(id=1329419490745496087, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, language=EN, label=Figure 4, caption=
KV cache merging method in MiniCache, figureFileSmall=xbH9AuAY40Xt04msQwhCmw==, figureFileBig=sj5WiNBO9Bf+Dexp2mFfpQ==, tableContent=null), ArticleFig(id=1329419490812604952, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, language=CN, label=图4, caption=
MiniCache的键值缓存合并方法, figureFileSmall=xbH9AuAY40Xt04msQwhCmw==, figureFileBig=sj5WiNBO9Bf+Dexp2mFfpQ==, tableContent=null), ArticleFig(id=1329419490883908122, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, language=EN, label=Figure 5, caption=
Compression method of CacheGen based on quantization of delta value, figureFileSmall=VbRZCz2uJKmHK/eUZbCVMg==, figureFileBig=IcDDcBDW5oCfuymP5+qPJg==, tableContent=null), ArticleFig(id=1329419490955211291, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, language=CN, label=图5, caption=
CacheGen中基于差值量化的压缩方法, figureFileSmall=VbRZCz2uJKmHK/eUZbCVMg==, figureFileBig=IcDDcBDW5oCfuymP5+qPJg==, tableContent=null), ArticleFig(id=1329419491026514460, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, language=EN, label=Figure 6, caption=
Mechanism of loading small-scale probe attention heads in Impress, figureFileSmall=4jAOhztbFeErunLcTBOd7g==, figureFileBig=s9yqNHyEvuEJd6kpT8aUSA==, tableContent=null), ArticleFig(id=1329419491085234717, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, language=CN, label=图6, caption=
Impress的小规模探测注意力头加载机制, figureFileSmall=4jAOhztbFeErunLcTBOd7g==, figureFileBig=s9yqNHyEvuEJd6kpT8aUSA==, tableContent=null), ArticleFig(id=1329419491148149278, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, language=EN, label=Figure 7, caption=
KV cache sharing mechanism among layers in KVSharer, figureFileSmall=97Xf6IkPNJycmovvhTrczA==, figureFileBig=YFF5UszrnxY6AsJcYicE6g==, tableContent=null), ArticleFig(id=1329419491211063839, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, language=CN, label=图7, caption=
KVSharer的层间键值缓存共享机制, figureFileSmall=97Xf6IkPNJycmovvhTrczA==, figureFileBig=YFF5UszrnxY6AsJcYicE6g==, tableContent=null), ArticleFig(id=1329419491265589792, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, language=EN, label=Figure 8, caption=
Sandwich architecture of KV cache sharing mechanism among layers in LCKV, figureFileSmall=i0SIQKBnCLPceJr6jl8Z0g==, figureFileBig=2ZdCPf+kdk0fwm5wmLhPvg==, tableContent=null), ArticleFig(id=1329419491328504353, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, language=CN, label=图8, caption=
LCKV层间键值缓存共享机制的三明治结构, figureFileSmall=i0SIQKBnCLPceJr6jl8Z0g==, figureFileBig=2ZdCPf+kdk0fwm5wmLhPvg==, tableContent=null), ArticleFig(id=1329419491445944866, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, language=EN, label=Figure 9, caption=
MQA mechanism reduces a large number of key value caches in the attention head dimension compared with the traditional MHA mechanism, figureFileSmall=9QkttniUIm36efo2wWv3Fw==, figureFileBig=QfV/lpc5mNNOu8OP9Jit1A==, tableContent=null), ArticleFig(id=1329419491517248035, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, language=CN, label=图9, caption=
MQA机制相比于传统MHA机制在注意力头维度削减大量的键值缓存, figureFileSmall=9QkttniUIm36efo2wWv3Fw==, figureFileBig=QfV/lpc5mNNOu8OP9Jit1A==, tableContent=null), ArticleFig(id=1329419491592745508, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, language=EN, label=Figure 10, caption=
GQA mechanism divides query attention heads into several groups and sharing KV cache within a group, figureFileSmall=KVF2L6eHeW9KK8iSpkn0Sg==, figureFileBig=nOt7KcBm/feMU7DA1MrYDA==, tableContent=null), ArticleFig(id=1329419491664048677, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, language=CN, label=图10, caption=
GQA机制针对查询注意力头进行分组并在组内进行键值缓存共享, figureFileSmall=KVF2L6eHeW9KK8iSpkn0Sg==, figureFileBig=nOt7KcBm/feMU7DA1MrYDA==, tableContent=null), ArticleFig(id=1329419491747934758, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, language=EN, label=Table 1, caption=
Classification of KV Cache Compression Methods for LLM Inference
, figureFileSmall=null, figureFileBig=null, tableContent=
| 压缩方法 | 年份 | 压缩方法类型 | 压缩维度 | 是否改变模型架构 | 额外计算操作 | 是否支持压缩率调节 | 压缩率调节方式 |
|---|
| KVMerger[28] | 2024 | 基于合并 | 标记维度 | 否 | 相似度计算/带权合并计算 | 是 | 调节注意力分数阈值 |
| MiniCache[29] | 2024 | 基于合并 | 层维度 | 否 | 重参数化合并计算 | 是 | 调节参与合并的层数 |
| KVQuant[30] | 2024 | 基于量化 | 数据位宽 | 否 | 缩放因子计算/量化计算 | 是 | 调节量化比特数 |
| CacheGen[31] | 2024 | 基于量化 | 数据位宽 | 否 | 差值计算/量化计算 | 是 | 调节量化比特数 |
| Ecco[32] | 2025 | 基于量化 | 数据位宽 | 否 | 缩放因子计算/量化计算 | 是 | 调节量化比特数 |
| Scissorhands[33] | 2023 | 基于标记弃用 | 标记维度 | 否 | 注意力分数计算 | 是 | 调节弃用触发阈值 |
| Impress[34] | 2025 | 基于标记弃用 | 标记维度 | 否 | 注意力分数计算 | 是 | 调节标记保留比例 |
| ClusterKV[35] | 2025 | 基于标记弃用 | 标记维度 | 否 | 注意力分数计算 | 是 | 调节标记保留比例 |
| KVSharer[36] | 2024 | 基于共享 | 层维度 | 否 | 距离计算/相似度计算 | 是 | 调节共享层数 |
| LCKV[37] | 2024 | 基于共享 | 层维度 | 是 | 模型重新训练 | 是 | 调节共享层数 |
| MQA[38] | 2019 | 基于注意力头削减 | 注意力头维度 | 是 | 模型重新训练 | 否 | |
| GQA[39] | 2023 | 基于注意力头削减 | 注意力头维度 | 是 | 模型重新训练 | 是 | 调节注意力头分组数目 |
), ArticleFig(id=1329419491836015144, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419485678776776, language=CN, label=表1, caption=
大语言模型推理中的键值缓存压缩方法分类
, figureFileSmall=null, figureFileBig=null, tableContent=
| 压缩方法 | 年份 | 压缩方法类型 | 压缩维度 | 是否改变模型架构 | 额外计算操作 | 是否支持压缩率调节 | 压缩率调节方式 |
|---|
| KVMerger[28] | 2024 | 基于合并 | 标记维度 | 否 | 相似度计算/带权合并计算 | 是 | 调节注意力分数阈值 |
| MiniCache[29] | 2024 | 基于合并 | 层维度 | 否 | 重参数化合并计算 | 是 | 调节参与合并的层数 |
| KVQuant[30] | 2024 | 基于量化 | 数据位宽 | 否 | 缩放因子计算/量化计算 | 是 | 调节量化比特数 |
| CacheGen[31] | 2024 | 基于量化 | 数据位宽 | 否 | 差值计算/量化计算 | 是 | 调节量化比特数 |
| Ecco[32] | 2025 | 基于量化 | 数据位宽 | 否 | 缩放因子计算/量化计算 | 是 | 调节量化比特数 |
| Scissorhands[33] | 2023 | 基于标记弃用 | 标记维度 | 否 | 注意力分数计算 | 是 | 调节弃用触发阈值 |
| Impress[34] | 2025 | 基于标记弃用 | 标记维度 | 否 | 注意力分数计算 | 是 | 调节标记保留比例 |
| ClusterKV[35] | 2025 | 基于标记弃用 | 标记维度 | 否 | 注意力分数计算 | 是 | 调节标记保留比例 |
| KVSharer[36] | 2024 | 基于共享 | 层维度 | 否 | 距离计算/相似度计算 | 是 | 调节共享层数 |
| LCKV[37] | 2024 | 基于共享 | 层维度 | 是 | 模型重新训练 | 是 | 调节共享层数 |
| MQA[38] | 2019 | 基于注意力头削减 | 注意力头维度 | 是 | 模型重新训练 | 否 | |
| GQA[39] | 2023 | 基于注意力头削减 | 注意力头维度 | 是 | 模型重新训练 | 是 | 调节注意力头分组数目 |
)], attaches=null, journal=Journal(id=1324759606947315908, delFlag=0, nameCn=计算机研究与发展, nameEn=Journal of Computer Research and Development, nameHistory1=null, nameHistory2=null, issn=1000-1239, eissn=null, cn=11-1777/TP, coden=null, periodic=0, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=k2l8zgqwstuxxevFX2qxVA==, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Computer Research and Development, journalRemark=null, publicationField=null, createdTime=1793776903141, updatedTime=1793850698612, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=J, firstLetterEn=J, subjectCode=Electronic Information, subjectName=null, subjectCodeEn=Electronic Information, subjectNameEn=null, picCn=k2l8zgqwstuxxevFX2qxVA==, picEn=r6k0Ry+RD+c/VXj5QarmDw==, jcr=null, cjcr=null, exts=[JournalExt(id=1325069127710286688, language=CN, name=计算机研究与发展, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1793850698640, updatedTime=1793850698640, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://crad.ict.ac.cn/journalx/authorLogOn.action, submissionEditorUrl=https://crad.ict.ac.cn/journalx/editorLogOn.action, submissionReviewUrl=https://crad.ict.ac.cn/journalx/expertLogOn.action, submissionCeEditorUrl=https://crad.ict.ac.cn/journalx/editorInChiefLogOn.action, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1325069127777395553, language=EN, name=Journal of Computer Research and Development, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1793850698656, updatedTime=1793850698656, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://crad.ict.ac.cn/journalx/authorLogOn.action, submissionEditorUrl=https://crad.ict.ac.cn/journalx/editorLogOn.action, submissionReviewUrl=https://crad.ict.ac.cn/journalx/expertLogOn.action, submissionCeEditorUrl=https://crad.ict.ac.cn/journalx/editorInChiefLogOn.action, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1324759914146529478, websiteList=[Website(id=1325070300139892771, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1324759914146529478, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN, language=CN, createTime=1793850978169, createBy=18614031015, updateTime=1793851040259, updateBy=18614031015, name=计算机研究与发展-中文, tplId=1146099689490845704, title=计算机研究与发展, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1325070893751349360, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=articleTextType, value=kx, createTime=1793851119697, updateTime=1793851119697, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893730377837, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=banner, value=null, createTime=1793851119692, updateTime=1793851119692, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893772320883, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=grayFlag, value=0, createTime=1793851119702, updateTime=1793851119702, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893721989228, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=logo, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/file/pic?fileId=U27tDsy717YF7XSPA+Vwdw==, createTime=1793851119690, updateTime=1793851119690, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893784903797, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=minRunFlag, value=0, createTime=1793851119705, updateTime=1793851119705, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893742960751, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/file/pic, createTime=1793851119695, updateTime=1793851119695, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893780709492, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=silenceFlag, value=0, createTime=1793851119704, updateTime=1793851119704, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893738766446, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1793851119694, updateTime=1793851119694, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893755543665, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=themeColor, value=null, createTime=1793851119698, updateTime=1793851119698, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893763932274, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=themeStyle, value=null, createTime=1793851119700, updateTime=1793851119700, creator=18614031015, updator=18614031015)]), Website(id=1325070300580294698, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1324759914146529478, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN, language=EN, createTime=1793850978274, createBy=18614031015, updateTime=1793851036638, updateBy=18614031015, name=计算机研究与发展-英文, tplId=1146101810881728533, title=Journal of Computer Research and Development, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1325070925288321148, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=articleTextType, value=kx, createTime=1793851127216, updateTime=1793851127216, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925263155321, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=banner, value=null, createTime=1793851127210, updateTime=1793851127210, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925309292671, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=grayFlag, value=0, createTime=1793851127221, updateTime=1793851127221, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925254766712, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=logo, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/file/pic?fileId=U27tDsy717YF7XSPA+Vwdw==, createTime=1793851127208, updateTime=1793851127208, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925326069889, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=minRunFlag, value=0, createTime=1793851127225, updateTime=1793851127225, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925279932539, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/file/pic, createTime=1793851127214, updateTime=1793851127214, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925317681280, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=silenceFlag, value=0, createTime=1793851127223, updateTime=1793851127223, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925271543930, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1793851127212, updateTime=1793851127212, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925292515453, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=themeColor, value=null, createTime=1793851127217, updateTime=1793851127217, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925300904062, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=themeStyle, value=null, createTime=1793851127219, updateTime=1793851127219, creator=18614031015, updator=18614031015)])], journalTitle=计算机研究与发展, weixinUrl=null, journalUrl=https://crad.ict.ac.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Computer Research and Development, journalPhotoCn=k2l8zgqwstuxxevFX2qxVA==, journalPhotoEn=r6k0Ry+RD+c/VXj5QarmDw==, journalFirstLetter=J, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/10.7544/issn1000-1239.202550461, detailUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202550461, pdfUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/PDF/10.7544/issn1000-1239.202550461, pdfUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/PDF/10.7544/issn1000-1239.202550461, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1774972800000, fullTextJson=null, articleText=null, reference=null)